System and method for vehicle navigation

Abstract

Systems and methods for vehicle navigation are provided. The systems and methods can detect traffic lights. For example, one or more traffic lights can be detected using a detection redundant camera arrangement based on contrast enhancement of night-time images and based on low resolution traffic light candidate identification followed by high resolution candidate analysis using fusion of information from traffic light emitters and one or more cameras. Additionally, the systems and methods can navigate based on worst-case red-to-red time estimates.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to U.S. Provisional Application No. 62 / 854191 (filed May 29, 2019) and U.S. Provisional Application No. 62 / 880208 (filed July 30, 2019). Both applications are incorporated herein by reference in their entirety. Technical Field

[0003] This disclosure generally pertains to autonomous vehicle navigation. Background Technology

[0004] With continuous technological advancements, the goal of fully autonomous vehicles capable of navigating highways is nearing realization. Autonomous vehicles will need to consider a multitude of factors and make appropriate decisions based on those factors to safely and accurately reach their intended destination. For example, autonomous vehicles may need to process and interpret visual information (such as information captured by cameras) and may also utilize information from other sources (such as GPS devices, speed sensors, accelerometers, suspension sensors, etc.). Simultaneously, to navigate to their destination, autonomous vehicles may need to identify their position within a specific highway (e.g., a specific lane on a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, observe traffic light signals and signs, and navigate from one road to another at appropriate intersections or overpasses. Utilizing and interpreting the vast amounts of information collected by autonomous vehicles as they travel to their destination presents numerous design challenges. The large amounts of data that autonomous vehicles may need to analyze, access, and / or store (e.g., captured image data, map data, GPS data, sensor data, etc.) create challenges that can effectively limit or even adversely affect autonomous navigation. Furthermore, if autonomous vehicles rely on traditional mapping techniques for navigation, the vast amounts of data required for storing and updating maps pose significant challenges. Summary of the Invention

[0005] Systems and methods for autonomous vehicle navigation are provided according to embodiments of this disclosure. The disclosed embodiments may use photographic devices to provide autonomous vehicle navigation features. For example, according to the disclosed embodiments, the system may include one, two, or more photographic devices that monitor the vehicle's environment. The disclosed system may provide a navigation response based, for example, on the analysis of one or more images captured by the photographic devices.

[0006] In an embodiment, the vehicle's navigation system may include at least one processor. The at least one processor may be programmed to receive a first image captured from the vehicle's environment from a first camera device of the vehicle, and a second image captured from the vehicle's environment from a second camera device of the vehicle. The at least one processor may also be programmed to analyze the first image to generate a first detection result. The first detection result may include an identifier of a traffic light and its status. The at least one processor may be further configured to analyze the second image to generate a second detection result. The second detection result may include an identifier of a traffic light and its status. The at least one processor may also be configured to compare the first detection result and the second detection result to determine a third detection result. The third detection result may include a confirmed status of the traffic light. The at least one processor may be further configured to determine a navigation action for the vehicle based on the confirmed status of the traffic light. The at least one processor may also be configured to cause the vehicle to perform a navigation action.

[0007] In an embodiment, a method for navigating a vehicle may include receiving a first image captured from the vehicle's environment from a first camera device of the vehicle. The method may further include receiving a second image captured from the vehicle's environment from a second camera device of the vehicle. The method may further include analyzing the first image to generate a first detection result. The first detection result may include an identifier of a traffic light and its status. The method may further include analyzing the second image to generate a second detection result. The second detection result may include an identifier of a traffic light and its status. The method may further include comparing the first detection result and the second detection result to determine a third detection result. The third detection result may include a confirmed status of the traffic light. The method may further include determining a navigation action for the vehicle based on the confirmed status of the traffic light. The method may further include causing the vehicle to perform a navigation action.

[0008] In an embodiment, the vehicle's navigation system may include at least one processor. The at least one processor may be programmed to receive images captured from the vehicle's environment. The images may have a first resolution. The at least one processor may also be programmed to analyze a modified version of the captured image to determine at least one traffic light candidate region associated with the modified version of the captured image. The modified version of the captured image may have a second resolution lower than the first resolution of the captured image. The at least one processor may be further programmed to determine a portion of the captured image to be analyzed based on the at least one traffic light candidate region of the modified version of the captured image. The at least one processor may also be programmed to analyze the determined portion of the captured image to confirm that a representation of a traffic light exists within the determined portion of the captured image.

[0009] In an embodiment, the method for detecting traffic lights may include: receiving an image captured from the environment of a vehicle, wherein the image has a first resolution; analyzing a modified version of the captured image to determine at least one traffic light candidate region associated with the modified version of the captured image, wherein the modified version of the captured image has a second resolution lower than the first resolution of the captured image; determining a portion of the captured image to be analyzed based on the at least one traffic light candidate region of the modified version of the captured image; and analyzing the determined portion of the captured image to confirm that a representation of a traffic light exists in the determined portion of the captured image.

[0010] In an embodiment, the vehicle's navigation system may include at least one processor. The at least one processor may be programmed to receive images captured from the vehicle's environment via a camera device. The at least one processor may also be programmed to determine candidate traffic light regions in the captured images based on information indicating the location of the captured images and also based on map information storing locations associated with at least one traffic light in the vehicle's environment. The at least one processor may be further programmed to determine a portion of the captured images to be analyzed based on the traffic light candidate regions. The at least one processor may also be programmed to analyze said portion of the image to identify representations of at least one traffic light in the captured images. The at least one processor may be further programmed to determine at least one navigation action of the vehicle based on the at least one traffic light. The at least one processor may also be programmed to cause the vehicle to perform at least one navigation action.

[0011] In an embodiment, the vehicle's navigation system may include at least one processor. The at least one processor may be programmed to receive at least one image captured from the vehicle's environment by a camera. The at least one processor may also be programmed to analyze the at least one image to identify a representation of a traffic light in the at least one image. The traffic light may be associated with an intersection. The at least one processor may be further programmed to determine the state of the traffic light based on the analysis of the at least one image, and to determine a planned navigation action for the vehicle based on the determined state of the traffic light. After determining that the traffic light is green, and in cases where the time when the traffic light turns green is not known, if the vehicle is expected to arrive at the traffic light or intersection within a predetermined time interval before turning red, the at least one processor may be programmed to cause the vehicle to perform the planned navigation action. If the vehicle is not expected to arrive at the traffic light or intersection within a predetermined time interval before turning red, the at least one processor may be further programmed to cause the vehicle to perform a second navigation action different from the planned navigation action.

[0012] In an embodiment, a method for navigating a vehicle may include receiving at least one image captured from the vehicle's environment by a photographic device. The method may further include analyzing the at least one image to identify a representation of a traffic light in the at least one image. The traffic light may be associated with an intersection. The method may further include determining the state of the traffic light based on the analysis of the at least one image, and determining a planned navigation action for the vehicle based on the determined state of the traffic light. The method may further include: after determining that the traffic light is in a green state, and when the time when the traffic light turns green is not known, if the vehicle is expected to arrive at the traffic light or intersection within a predetermined time interval before turning red, then causing the vehicle to perform the planned navigation action. The method may further include: if the vehicle is not expected to arrive at the traffic light or intersection within the predetermined time interval before turning red, then causing the vehicle to perform a second navigation action different from the planned navigation action.

[0013] According to other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that are executed by at least one processing device and perform any of the methods described herein.

[0014] The above general description and the following detailed description are merely illustrative and not intended to limit the scope of the claims. Attached Figure Description

[0015] The accompanying drawings, which are incorporated in and form a part of this disclosure, illustrate various disclosed embodiments. The drawings include:

[0016] Figure 1 This is a schematic representation of an exemplary system according to the disclosed embodiments.

[0017] Figure 2A It is a schematic side view representation of an exemplary vehicle including the system according to the disclosed embodiments.

[0018] Figure 2B This is a top view illustration of the vehicle and system according to the disclosed embodiments.

[0019] Figure 2C This is a top-view illustration of another embodiment of a vehicle that includes the system according to the disclosed embodiments.

[0020] Figure 2D This is a top-view illustration of yet another embodiment of a vehicle including the system according to the disclosed embodiments.

[0021] Figure 2E This is a top-view illustration of yet another embodiment of a vehicle including the system according to the disclosed embodiments.

[0022] Figure 2FThis is a schematic representation of an exemplary vehicle control system according to the disclosed embodiments.

[0023] Figure 3A It is a schematic representation of the interior of a vehicle, including a rearview mirror and a user interface for a vehicle imaging system, according to the disclosed embodiments.

[0024] Figure 3B This is an illustration of an example of a camera mount configured behind a rearview mirror and positioned against the vehicle's windshield, according to the disclosed embodiment.

[0025] Figure 3C This is according to the disclosed embodiments, from different angles. Figure 3B The diagram shows the support frame for the photographic device.

[0026] Figure 3D This is an illustration of an example of a camera mount configured behind a rearview mirror and positioned against the vehicle's windshield, according to the disclosed embodiment.

[0027] Figure 4 This is an exemplary block diagram of a memory configured to store instructions for performing one or more operations, according to the disclosed embodiments.

[0028] Figure 5A This is a flowchart illustrating an exemplary process of inducing one or more navigation responses based on monocular image analysis according to the disclosed embodiments.

[0029] Figure 5B This is a flowchart illustrating an exemplary process of detecting one or more vehicles and / or pedestrians in a set of images according to the disclosed embodiments.

[0030] Figure 5C This is a flowchart illustrating an exemplary process for detecting road markings and / or lane geometry information in an image set according to the disclosed embodiments.

[0031] Figure 5D This is a flowchart illustrating an exemplary process of detecting traffic lights in a set of images according to the disclosed embodiments.

[0032] Figure 5E This is a flowchart illustrating an exemplary process of inducing one or more navigation responses based on vehicle path, according to the disclosed embodiments.

[0033] Figure 5F This is a flowchart illustrating a demonstration process for determining whether a leading vehicle is changing lanes, according to the disclosed embodiment.

[0034] Figure 6 This is a flowchart illustrating an exemplary process of evoking one or more navigation responses based on stereoscopic image analysis according to the disclosed embodiments.

[0035] Figure 7 This is a flowchart illustrating an exemplary process of evoking one or more navigation responses based on the analysis of three sets of images, according to the disclosed embodiment.

[0036] Figure 8 This illustrates a sparse map for providing autonomous vehicle navigation according to a disclosed embodiment.

[0037] Figure 9A A polynomial representation of a portion of a road segment according to the disclosed embodiment is shown.

[0038] Figure 9B A curve in three-dimensional space according to the disclosed embodiment is shown, which represents the target trajectory of a vehicle on a specific road segment contained in a sparse map.

[0039] Figure 10 Example road signs that can be included in a sparse map according to the disclosed embodiments are shown.

[0040] Figure 11A A polynomial representation of the trajectory according to the disclosed embodiments is shown.

[0041] Figure 11B and Figure 11C The target trajectory along a multi-lane road is shown according to the disclosed embodiment.

[0042] Figure 11D An example road signature profile according to the disclosed embodiment is shown.

[0043] Figure 12 This is a schematic diagram of a system according to a disclosed embodiment, which uses crowdsourcing data received from multiple vehicles for autonomous vehicle navigation.

[0044] Figure 13 An example autonomous vehicle road navigation model is shown, represented by multiple three-dimensional splines according to the disclosed embodiments.

[0045] Figure 14 This illustrates a map skeleton generated from a combination of location information from the secondary driver, according to the disclosed embodiment.

[0046] Figure 15 An example is shown where, according to the disclosed embodiment, two driving maneuvers are aligned longitudinally with an example sign serving as a road sign.

[0047] Figure 16 An example is shown, aligning longitudinally with an example sign used as a road sign, following the disclosed embodiment and multiple driving maneuvers.

[0048] Figure 17This is a schematic diagram of a system for generating driving data using a camera device, a vehicle, and a server, according to the disclosed embodiments.

[0049] Figure 18 This is a schematic diagram of a system for crowdsourced sparse maps according to the disclosed embodiments.

[0050] Figure 19 This is a flowchart illustrating an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment, according to the disclosed embodiments.

[0051] Figure 20 A block diagram of a server according to a disclosed embodiment is shown.

[0052] Figure 21 A block diagram of a memory according to a disclosed embodiment is shown.

[0053] Figure 22 This illustrates the process of clustering vehicle trajectories associated with vehicles according to the disclosed embodiments.

[0054] Figure 23 A navigation system for a vehicle according to a disclosed embodiment is shown, which can be used for autonomous navigation.

[0055] Figure 24A , Figure 24B , Figure 24C and Figure 24D The diagram shows a demonstrative lane marking that can be detected according to the disclosed embodiments.

[0056] Figure 24E An example of a mapped lane marking is shown according to the disclosed embodiment.

[0057] Figure 24F This illustrates a demonstrative anomaly associated with lane markings in accordance with the disclosed embodiments.

[0058] Figure 25A The image shows an example of the vehicle's surroundings in accordance with the disclosed embodiments of navigation based on mapped lane markings.

[0059] Figure 25B This illustrates the lateral positioning correction of a vehicle in a road navigation model based on mapped lane markings, according to the disclosed embodiment.

[0060] Figure 26A This is a flowchart illustrating an exemplary process of mapping lane markings for use in autonomous vehicle navigation, according to the disclosed embodiments.

[0061] Figure 26B This is a flowchart illustrating a demonstration process of autonomously navigating a master vehicle along a road segment using mapped lane markings, according to the disclosed embodiments.

[0062] Figure 27A The diagram shows exemplary directional arrows that can be detected according to the disclosed embodiments.

[0063] Figure 27B An example image processing of the detected directional arrow is shown according to the disclosed embodiment.

[0064] Figure 27C The image shows an example of the environment surrounding a vehicle that can be used to detect directional arrows according to the disclosed embodiments.

[0065] Figure 28A A plan view showing a demonstration autonomous navigation maneuver performed by a vehicle on a straight road segment according to the disclosed embodiment.

[0066] Figure 28B A plan view showing a demonstration autonomous navigation maneuver performed by a vehicle from a turning lane according to the disclosed embodiment.

[0067] Figure 28C A plan view showing a demonstration autonomous navigation maneuver performed by a vehicle entering a turning lane according to the disclosed embodiment.

[0068] Figure 28D A plan view showing a demonstration autonomous navigation maneuver performed by a vehicle based on a directional arrow outside the current lane, according to the disclosed embodiment.

[0069] Figure 28E This illustrates a demonstration of autonomous navigation actions performed by a vehicle based on mapped directional arrows, according to the disclosed embodiments.

[0070] Figure 29A This is a flowchart illustrating an exemplary process for use in autonomous vehicle navigation, according to the disclosed embodiments, by mapping directional arrows.

[0071] Figure 29B This is a flowchart illustrating a demonstration process of autonomously navigating a master vehicle along a road segment based on detected directional arrows, according to the disclosed embodiments.

[0072] Figure 29C This is a flowchart illustrating a demonstration process of autonomous navigation of a master vehicle along a road segment based on mapped directional arrows, according to the disclosed embodiments.

[0073] Figure 30A , Figure 30B , Figure 30C and Figure 30D The images shown are exemplary images related to various failure conditions according to the disclosed embodiments.

[0074] Figure 31 An exemplary image showing the environment of a vehicle according to a disclosed embodiment.

[0075] Figure 32This is a flowchart illustrating an exemplary process of transmitting navigation information according to the disclosed embodiments.

[0076] Figure 33 This is a schematic diagram of a system for mapping road segment free space and / or for autonomous navigation of master vehicles along road segments, according to the disclosed embodiments.

[0077] Figure 34 This is a flowchart illustrating a demonstration process of mapping the free space of a road segment according to the disclosed embodiments.

[0078] Figure 35 This is a flowchart illustrating a demonstration process of autonomous navigation of a master vehicle along a road segment according to the disclosed embodiments.

[0079] Figure 36A This is a schematic diagram of a highway including an intersection, according to the disclosed embodiment.

[0080] Figure 36B This is a schematic diagram of a triangulation technique for determining the position of a vehicle relative to a traffic light, according to a disclosed embodiment.

[0081] Figure 37A and Figure 37B This is an explanatory chart showing the time-related variables for determining vehicle navigation according to the disclosed embodiments.

[0082] Figure 38 This describes the process of updating the autonomous vehicle road navigation model according to the disclosed embodiments.

[0083] Figure 39 This describes the process of selecting and implementing navigation actions according to the disclosed embodiments.

[0084] Figure 40 This is an illustrative diagram of the time-related traffic light status according to the disclosed embodiment.

[0085] Figure 41 This describes the process of selecting and implementing navigation actions for a vehicle according to the disclosed embodiments.

[0086] Figure 42 This is a schematic representation of an exemplary system according to the disclosed embodiments.

[0087] Figure 43A and Figure 43B An exemplary image showing the environment surrounding a vehicle according to a disclosed embodiment is shown.

[0088] Figure 44 This is a flowchart illustrating a demonstration process of a navigation vehicle according to the disclosed embodiments.

[0089] Figure 45 This is a schematic representation of an exemplary system according to the disclosed embodiments.

[0090] Figure 46A and Figure 46B An exemplary image showing the environment surrounding a vehicle according to a disclosed embodiment is shown.

[0091] Figure 47 This is a flowchart illustrating a demonstration process of a navigation vehicle according to the disclosed embodiments.

[0092] Figure 48 This is a flowchart illustrating a demonstration process of a navigation vehicle according to the disclosed embodiments.

[0093] Figure 49 This is a schematic representation of an exemplary system according to the disclosed embodiments.

[0094] Figure 50 The image shows an example of the environment surrounding the vehicle according to the disclosed embodiment.

[0095] Figures 51-55 This is a table illustrating an exemplary scenario of the worst-case red-end time timing according to the disclosed embodiment.

[0096] Figure 56 This is a flowchart illustrating a demonstration process of a navigation vehicle according to the disclosed embodiments. Detailed Implementation

[0097] The following detailed description refers to the accompanying drawings. Where possible, the same reference numerals are used in the drawings and the following description to denote the same or similar parts. Although several illustrative embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, components shown in the drawings may be substituted, added, or modified, and the illustrative methods described herein may be modified by substituted, reordered, removed, or added steps in the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. The appropriate scope is defined instead by the appended claims.

[0098] Overview of Autonomous Vehicles

[0099] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle capable of making at least one navigation change without driver input. "Navigation change" refers to one or more changes in the vehicle's steering, braking, or acceleration. To be autonomous, a vehicle need not be fully automatic (e.g., fully operational without a driver or driver input). Autonomous vehicles include those capable of operating under driver control during certain time periods and without driver control during other time periods. Autonomous vehicles may also include vehicles that control only some aspects of vehicle navigation, such as steering (e.g., to keep the vehicle's path within lane constraints), while leaving other aspects to the driver (e.g., braking). In some cases, an autonomous vehicle may control some or all aspects of the vehicle's braking, speed control, and / or steering.

[0100] Since human drivers typically rely on visual cues and observation to control vehicles, transportation infrastructure is accordingly constructed, with lane markings, traffic signs, and traffic lights all designed to provide visual information to the driver. Given these design characteristics of transportation infrastructure, autonomous vehicles may include photographic devices and processing units that analyze visual information captured from the vehicle's environment. Visual information may include, for example, components of the transportation infrastructure observable to the driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, autonomous vehicles may use stored information, such as information providing a model of the vehicle's environment during navigation. For example, a vehicle may use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data while driving to provide information relevant to its environment, and the vehicle (and other vehicles) can use this information to locate itself on the model.

[0101] In some embodiments of this disclosure, the autonomous vehicle may use information obtained during navigation (e.g., from a camera, GPS device, accelerometer, speed sensor, suspension sensor, etc.). In other embodiments, the autonomous vehicle may use information obtained from previous navigation by the vehicle (or other vehicles) while navigating. In still other embodiments, the autonomous vehicle may use a combination of information obtained during navigation and information obtained from previous navigation. The following sections provide an overview of the disclosed embodiments, followed by an overview of the forward imaging system and method according to the system. The following sections disclose systems and methods for constructing, using, and updating sparse maps for autonomous vehicle navigation.

[0102] System Overview

[0103] Figure 1This is a block diagram representation of system 100 according to the disclosed exemplary embodiment. System 100 may include various components depending on the requirements of a particular implementation. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140 and 150, a map database 160, a user interface 170, and a wireless transceiver 172. Processing unit 110 may include one or more processing means. In some embodiments, processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing means. Similarly, image acquisition unit 120 may include any number of image acquisition means and components depending on the requirements of a particular application. In some embodiments, image acquisition unit 120 may include one or more image capture means (e.g., photographic means), such as image capture means 122, image capture means 124, and image capture means 126. System 100 may also include a data interface 128 that communicatively connects processing unit 110 to image acquisition means 120. For example, data interface 128 may include one or more wired and / or wireless links for transmitting image data acquired by image acquisition device 120 to processing unit 110.

[0104] Wireless transceiver 172 may include one or more means configured to exchange transmissions to one or more networks (e.g., cellular, Internet, etc.) via an air interface using radio frequency, infrared frequency, magnetic field, or electric field. Wireless transceiver 172 may use any known standard to transmit and / or receive data (e.g., Wi-Fi, Bluetooth®, BluetoothSmart, 802.15.4, ZigBee, etc.). Such transmissions can include communication from a host vehicle to one or more remote location servers. Such transmissions may also include communication (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to facilitate coordination of the host vehicle's navigation taking into account or in conjunction with target vehicles in the host vehicle's environment) or even broadcast transmissions to unspecified receivers near the transmitting vehicle.

[0105] Both application processor 180 and graphics processor 190 may include various types of processing devices. For example, either or both of application processor 180 and graphics processor 190 may include a microprocessor, a preprocessor (e.g., an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), supporting circuitry, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for running applications and suitable for image processing and analysis. In some embodiments, application processor 180 and / or graphics processor 190 may include any type of single-core or multi-core processor, mobile device microcontroller, CPU, etc. Various processing devices may be used, including processors available from manufacturers such as Intel®, AMD®, etc., or GPUs available from manufacturers such as NVIDIA®, ATI®, etc., and may include various architectures (e.g., x86 processors, ARM®, etc.).

[0106] In some embodiments, application processor 180 and / or image processor 190 may include any of the EyeQ family of processor chips available from Mobileye®. These processor designs each include multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors and may also include video output capabilities. In one example, the EyeQ2® uses 90 nm microtechnology operating at 332 MHz. The EyeQ2® architecture includes two floating-point hyper-threaded 32-bit RISC CPUs (MIPS32® 34K® cores), five Visual Computing Engines (VCEs), three Vector Microcode Processors (VMPs®), a Denali 64-bit mobile DDR controller, a 128-bit internal Sonics interconnect, dual 16-bit video input and 18-bit video output controllers, a 16-channel DMA, and several peripherals. The MIPS34K CPU manages the five VCEs, three VMPs™ and DMA, a second MIPS34K CPU and multi-channel DMA, and other peripherals. Five VCEs, three VMP®, and a MIPS34K CPU enable the intensive vision computing required for versatile bundled applications. In another example, the EyeQ3®, a third-generation processor six times more powerful than the EyeQ2®, can be used in the disclosed embodiments. In other examples, the EyeQ4® and / or EyeQ5® can be used in the disclosed embodiments. Of course, any newer or future EyeQ processing devices may also be used in conjunction with the disclosed embodiments.

[0107] Any of the processing devices disclosed herein can be configured to perform certain functions. Configuring a processing device (such as the EyeQ processor or any other controller or microprocessor) to perform certain functions may include programming computer-executable instructions and making those instructions available for execution by the processing device during operation. In some embodiments, configuring the processing device may include programming the processing device directly using architectural instructions. For example, one or more hardware description languages ​​(HDLs) may be used to configure the processing device (e.g., field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc.).

[0108] In other embodiments, the configuration processing means may include storing executable instructions on a memory accessible to the processing means during operation. For example, the processing means may access the memory during operation to retrieve and execute the stored instructions. In any case, a processing means configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system for controlling multiple hardware-based components of a master vehicle.

[0109] Although Figure 1 Two independent processing devices are shown within processing unit 110, but more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to perform the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by more than two processing devices. Furthermore, in some embodiments, system 100 may include one or more of processing unit 110 without including other components (such as image acquisition unit 120).

[0110] Processing unit 110 may include various types of devices. For example, processing unit 110 may include various devices such as controllers, image processors, central processing units (CPUs), graphics processing units (GPUs), support circuitry, digital signal processors, integrated circuits, memory, or any other type of device for image processing and analysis. Image preprocessors may include video processors for capturing, digitizing, and processing images from image sensors. CPUs may include any number of microcontrollers or microprocessors. GPUs may also include any number of microcontrollers or microprocessors. Support circuitry may be any number of circuits generally known in the art, including caches, power supply devices, clocks, and input / output circuitry. Memory may store software that controls the operation of the system when executed by the processor. Memory may include databases and image processing software. Memory may include any number of random access memories, read-only memories, flash memory, disk drives, optical storage devices, magnetic tape storage devices, removable storage devices, and other types of storage devices. In one instance, memory may be separate from processing unit 110. In another instance, memory may be integrated into processing unit 110.

[0111] Each memory unit 140, 150 may include software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), can control the operation of various aspects of system 100. These memory units may include various databases and image processing software, as well as trained systems (e.g., neural networks or deep neural networks). Memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage devices, magnetic tape storage devices, removable storage devices, and / or other types of storage devices. In some embodiments, memory units 140, 150 may be decoupled from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

[0112] The position sensor 130 may include any type of device suitable for determining the location associated with at least one component of the system 100. In some embodiments, the position sensor 130 may include a GPS receiver. Such a receiver is capable of determining the user's location and speed by processing signals broadcast by Global Positioning System satellites. The location information from the position sensor 130 may be available to the application processor 180 and / or the image processor 190.

[0113] In some embodiments, system 100 may include components such as a speed sensor (e.g., tachometer, speedometer) for measuring the speed of vehicle 200 and / or an accelerometer (single-axis or multi-axis) for measuring the acceleration of vehicle 200.

[0114] User interface 170 may include any means suitable for providing information to or receiving input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including, for example, a touchscreen, microphone, keyboard, pointer device, trackwheel, camera device, knob, button, etc. With such input devices, users can provide information input or commands to system 100 by typing instructions or information, providing voice commands, selecting menu options on the screen using buttons, pointers or eye-tracking capabilities, or by any other suitable technology for conveying information to system 100.

[0115] User interface 170 may be equipped with one or more processing devices configured to provide / receive information to / from a user and process that information for use by, for example, application processor 180. In some embodiments, such processing devices may execute instructions for recognizing and tracking eye movements, receiving and interpreting voice commands, recognizing and interpreting touch and / or gestures performed on a touchscreen, responding to keyboard input or menu selections, etc. In some embodiments, user interface 170 may include a display, speakers, haptic devices, and / or any other means for providing output information to the user.

[0116] Map database 160 may include any type of database for storing map data useful to system 100. In some embodiments, map database 160 may include data on various items (including roads, water features, geographic features, business areas, points of interest, restaurants, gas stations, etc.) associated with locations in a reference coordinate system. Map database 160 may store not only the locations of such items but also descriptors associated with those items, including, for example, names associated with any of the stored features. In some embodiments, map database 160 may be physically located along with other components of system 100. Alternatively or supplementally, map database 160, or a portion thereof, may be remotely located relative to other components of system 100 (e.g., processing unit 110). In such embodiments, information from map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via cellular networks and / or the Internet, etc.). In some cases, map database 160 may store a sparse data model containing a polynomial representation of certain road features (e.g., lane markings) or target trajectories of the primary vehicle. (Refer to below) Figure 8-19 This paper discusses the systems and methods for generating such maps.

[0117] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from the environment. Furthermore, any number of image capture devices can be used to acquire images for input to an image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four or more image capture devices. Reference will be made below. Figure 2B-2E The image capture devices 122, 124 and 126 are further described.

[0118] System 100 or its various components can be integrated into various different platforms. In some embodiments, system 100 may be included on vehicle 200, such as... Figure 2A As shown. For example, vehicle 200 may be equipped with processing unit 110 and any of the other components of system 100, as described above relative to... Figure 1 As described above. While in some embodiments, the vehicle 200 may be equipped with only a single image capture device (e.g., a camera), in embodiments such as combining... Figure 2B-2E In other embodiments, such as the described embodiments, multiple image capture devices may be used. For example, such as Figure 2A As shown, either of the image capture devices 122 and 124 of the vehicle 200 can be a component of an ADAS (Advanced Driver Assistance System) imaging suite.

[0119] The image capture device, included as part of the image acquisition unit 120 on the vehicle 200, can be positioned at any suitable location. In some embodiments, such as Figures 2A-2E and Figures 3A-3C As shown, the image capture device 122 can be located near the rearview mirror. This location provides a similar line of sight to that of the driver of vehicle 200, which helps determine what is visible and invisible to the driver. The image capture device 122 can be positioned anywhere near the rearview mirror, but placing the image capture device 122 on the driver's side of the rearview mirror further helps to obtain an image representing the driver's field of vision and / or line of sight.

[0120] Other locations for the image capturing device of image capturing unit 120 may also be used. For example, image capturing device 124 may be located on or in the bumper of vehicle 200. This location is particularly suitable for image capturing devices with a wide field of view. The line of sight of the bumper-positioned image capturing device may differ from that of the driver, and therefore the bumper image capturing device and the driver may not necessarily see the same object. Image capturing devices (e.g., image capturing devices 122, 124, and 126) may also be located in other locations. For example, the image capturing device may be located on or in the middle of one or both of the side mirrors of vehicle 200, on the roof of vehicle 200, on the hood of vehicle 200, on the trunk of vehicle 200, on the side of vehicle 200, mounted on any of the windows of vehicle 200, positioned behind or in front of them, and mounted in or near the front and / or rear of vehicle 200.

[0121] In addition to the image capture device, vehicle 200 may also include various other components of system 100. For example, processing unit 110 may be included on vehicle 200, integrated with or separate from the vehicle's engine control unit (ECU). Vehicle 200 may also be equipped with position sensor 130 (e.g., GPS receiver) and may also include map database 160 and memory units 140 and 150.

[0122] As previously described, the wireless transceiver 172 can and / or receive data via one or more networks (e.g., cellular networks, the Internet, etc.). For example, the wireless transceiver 172 can upload data collected by the system 100 to one or more servers and download data from one or more servers. Via the wireless transceiver 172, the system 100 can receive periodic or on-demand updates to data stored in the map database 160, memory 140, and / or memory 150. Similarly, the wireless transceiver 172 can upload any data (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, vehicle control system, etc.) and / or any data processed by the processing unit 110 from the system 100 to one or more servers.

[0123] System 100 can upload data to a server (e.g., to the cloud) based on privacy level settings. For example, system 100 can implement privacy level settings to adjust or limit the types of data (including metadata) sent to the server, which can uniquely identify a vehicle and / or its driver / owner. Such settings can be configured by a user via, for example, a wireless transceiver 172, either through factory default settings or by data received by the wireless transceiver 172.

[0124] In some embodiments, system 100 may upload data at a “high” privacy level, and under certain settings, system 100 may transmit data (e.g., route-related location information, captured images, etc.) without any details relating to a specific vehicle and / or driver / owner. For example, when uploading data at a “high” privacy setting, system 100 may exclude the vehicle identification number (VIN) or the name of the vehicle’s driver or owner, and instead transmit data such as captured images and / or limited route-related location information.

[0125] Consider other privacy levels. For example, system 100 may transmit data to the server at an "intermediate" privacy level and include additional information not included at the "high" privacy level, such as the vehicle's brand and / or model and / or vehicle type (e.g., passenger car, SUV, truck, etc.). In some embodiments, system 100 may upload data at a "low" privacy level. At the "low" privacy level setting, system 100 may upload data and include information sufficient to uniquely identify a particular vehicle, owner / driver, and / or part or all of the route traveled by the vehicle. Such "low" privacy level data may include one or more of the following: for example, VIN, driver / owner name, vehicle's origin before departure, vehicle's intended destination, vehicle's brand and / or model, vehicle type, etc.

[0126] Figure 2A This is a schematic side view representation of an exemplary vehicle imaging system according to the disclosed embodiment. Figure 2B yes Figure 2A The illustrated top view of the embodiment is shown. Figure 2B As shown, the disclosed embodiments may include a vehicle 200, which includes a system 100 in the vehicle body, having a first image capture device 122 positioned near a rearview mirror and / or near the driver of the vehicle 200, a second image capture device 124 positioned on or in a bumper area (e.g., one of the bumper areas 210) of the vehicle 200, and a processing unit 110.

[0127] like Figure 2C As shown, both image capture devices 122 and 124 can be positioned near the rearview mirror and / or near the driver of vehicle 200. Additionally, although in Figure 2B and Figure 2C Two image capture devices 122 and 124 are shown, but it should be understood that other embodiments may include more than two image capture devices. For example, in Figure 2D and Figure 2E In the illustrated embodiment, the first, second, and third image capture devices 122, 124, and 126 are included in the system 100 of the vehicle 200.

[0128] like Figure 2D As shown, image capture device 122 can be positioned near the rearview mirror and / or near the driver of vehicle 200, and image capture devices 124 and 126 can be positioned above or in the bumper area of ​​vehicle 200 (e.g., one of bumper areas 210). Figure 2E As shown, image capture devices 122, 124, and 126 may be positioned near the rearview mirror and / or near the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices may be positioned at any suitable location within and / or above vehicle 200.

[0129] It should be understood that the disclosed embodiments are not limited to vehicles, but may be applied to other contexts. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200, but can be applied to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0130] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024 WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280 × 960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included, for example, to provide a desired focal length and field of view for the image capture device. In some embodiments, the image capture device 122 may be associated with a 6mm lens or a 12mm lens. In some embodiments, the image capture device 122 may be configured to capture an image with a desired field of view (FOV) 202, such as... Figure 2DAs shown. For example, the image capture device 122 may be configured to have a conventional FOV, for example, in the range of 40 to 56 degrees, including 46-degree FOV, 50-degree FOV, 52-degree FOV, or above. Alternatively, the image capture device 122 may be configured to have a narrow FOV in the range of 23 to 40 degrees, such as 28-degree FOV or 36-degree FOV. Additionally, the image capture device 122 may be configured to have a wide FOV in the range of 100 to 180 degrees. In some embodiments, the image capture device 122 may include a wide-angle bumper camera or a camera with a FOV up to 180 degrees. In some embodiments, the image capture device 122 may be a 7.2-megapixel image capture device with an aspect ratio of approximately 2:1 (e.g., H×V = 3800×1900 pixels), having a horizontal FOV of approximately 100 degrees. Such an image capture device can be used instead of a three-image capture device configuration. Due to significant lens distortion, in implementations of image capture devices using radially symmetrical lenses, the vertical field of view (FOV) of such devices can be significantly less than 50 degrees. For example, such lenses may not be radially symmetrical, which allows for a vertical FOV greater than 50 degrees, including a horizontal FOV of 100 degrees.

[0131] The first image capturing device 122 can acquire multiple first images relative to a scene associated with the vehicle 200. Each of the multiple first images can be acquired as a series of image scan lines, which can be captured using a rolling shutter. Each scan line may include multiple pixels.

[0132] The first image capturing device 122 may have a scan rate associated with the acquisition of each of a first series of image scan lines. The scan rate may represent the rate at which the image sensor is able to acquire image data associated with each pixel contained in a particular scan line.

[0133] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, such as CCD sensors or CMOS sensors. In one embodiment, a CMOS image sensor may be used in conjunction with a rolling shutter, such that each pixel in a row is read one at a time, and the rows are scanned line by line until an entire image frame has been captured. In some embodiments, rows may be captured sequentially from top to bottom relative to the frame.

[0134] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124 and 126) may constitute a high-resolution imager and may have a resolution greater than 5M pixels, 7M pixels, 10M pixels or more.

[0135] The use of a rolling shutter allows pixels in different rows to be exposed and captured at different times, which can cause skew and other image artifacts in the captured image frame. On the other hand, when the image capture device 122 is configured to operate in conjunction with a global or synchronous shutter, all pixels can be exposed for the same amount of time during a common exposure cycle. Therefore, the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (e.g., FOV 202) at a specific time. In contrast, in a rolling shutter application, each row in the frame is exposed, and the data is captured at different times. Therefore, in an image capture device with a rolling shutter, moving objects may be distorted. This phenomenon will be described in more detail below.

[0136] The second image capture device 124 and the third image capture device 126 can be any type of image capture device. Similar to the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses of the associated image capture devices 124 and 126 may provide the same or narrower FOV (e.g., FOV 204 and 206) compared to the FOV (e.g., FOV 202) of the associated image capture device 122. For example, the image capture devices 124 and 126 may have FOVs of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0137] Image capture devices 124 and 126 can acquire multiple second and third images relative to a scene associated with vehicle 200. Each of the multiple second and third images can be acquired as a second and third series of image scan lines, which can be captured using a rolling shutter. Each scan line or row can have multiple pixels. Image capture devices 124 and 126 can have second and third scan rates associated with the acquisition of each of the image scan lines included in the second and third series.

[0138] Each image capture device 122, 124, and 126 may be positioned relative to the vehicle 200 in any suitable location and orientation. The relative positioning of the image capture devices 122, 124, and 126 may be selected to facilitate the fusion of information acquired from the image capture devices. For example, in some embodiments, the field of view (FOV) of associated image capture device 124 (e.g., FOV 204) may partially or completely overlap with the FOV of associated image capture device 122 (e.g., FOV 202) and the FOV of associated image capture device 126 (e.g., FOV 206).

[0139] Image capture devices 122, 124, and 126 can be located at any suitable relative height on vehicle 200. In one example, a height difference may exist between image capture devices 122, 124, and 126, which can provide sufficient parallax information for stereoscopic analysis. For example, as Figure 2A As shown, the two image capture devices 122 and 124 are at different heights. A lateral displacement difference may also exist between image capture devices 122, 124, and 126, thereby providing, for example, additional parallax information for the processing unit 110 to perform stereoscopic analysis. The difference in lateral displacement can be expressed by d... x Indicates, such as Figure 2C and Figure 2D As shown. In some embodiments, forward or backward displacement (e.g., range displacement) may exist between image capture devices 122, 124, and 126. For example, image capture device 122 may be located 0.5 to 2 meters or more behind image capture devices 124 and / or 126. This type of displacement allows one of the image capture devices to cover potential blind spots of the other(s) image capture devices(s).

[0140] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with an image sensor), and the resolution of image sensors associated with image capture devices 122 may be higher, lower, or the same as the resolution of image sensors(s) associated with image capture devices 124 and 126. In some embodiments, image sensors(s) associated with image capture devices 122 and / or image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0141] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for an image frame before continuing to capture pixel data associated with the next image frame) can be controllable. The frame rate of associated image capture device 122 can be higher, lower, or the same as the frame rates of associated image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 can depend on a variety of factors that can affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 may include a selectable pixel delay period applied before or after acquiring image data associated with one or more pixels of the image sensors in image capture devices 122, 124, and / or 126. Generally, image data corresponding to each pixel can be acquired according to the device's clock rate (e.g., one pixel per clock cycle). Additionally, in embodiments including a rolling shutter, one or more of the image capture devices 122, 124, and 126 may include a selectable horizontal blanking period applied before or after acquiring image data associated with a row of pixels of the image sensor in the image capture devices 122, 124, and / or 126. Furthermore, one or more of the image capture devices 122, 124, and 126 may include a selectable vertical blanking period applied before or after acquiring image data associated with image frames of the image capture devices 122, 124, and / or 126.

[0142] These timing controls enable synchronization of frame rates associated with image capture devices 122, 124, and 126, even when the line scan rates of each are different. Furthermore, as will be discussed in more detail below, these selectable timing controls, along with other factors such as image sensor resolution, maximum line scan rate, etc., enable synchronization of image capture in areas where the field of view (FOV) of image capture device 122 overlaps with one or more FOVs of image capture devices 124 and 126, even when the field of view of image capture device 122 differs from the FOVs of image capture devices 124 and 126.

[0143] The frame rate timing in the image capture devices 122, 124, and 126 can depend on the resolution of the associated image sensor. For example, assuming similar line scan rates for the two devices, if one device includes an image sensor with a resolution of 640×480 while the other device includes an image sensor with a resolution of 1280×960, more time will be required to acquire image data frames from the sensor with the higher resolution.

[0144] Another factor that can affect the timing of image data acquisition in image capture devices 122, 124, and 126 is the maximum line scan rate. For example, acquiring one line of image data from the image sensors included in image capture devices 122, 124, and 126 will require a certain minimum amount of time. Assuming no increase in pixel delay period, this minimum amount of time for acquiring one line of image data will be related to the maximum line scan rate of the particular device. Devices providing a higher maximum line scan rate have the potential to provide a higher frame rate compared to devices with a lower maximum line scan rate. In some embodiments, one or more of image capture devices 124 and 126 may have a higher maximum line scan rate than the maximum line scan rate of the associated image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more of the maximum line scan rate of image capture device 122.

[0145] In another embodiment, image capture devices 122, 124, and 126 may have the same maximum line scan rate, but image capture device 122 may operate at a scan rate less than or equal to its maximum scan rate. The system may be configured such that one or more of image capture devices 124 and 126 operate at a line scan rate equal to the line scan rate of image capture device 122. In other instances, the system may be configured such that the line scan rate of image capture device 124 and / or image capture device 126 may be 1.25, 1.5, 1.75, or 2 times or more of the line scan rate of image capture device 122.

[0146] In some embodiments, image capturing devices 122, 124, and 126 may be asymmetrical. That is, they may include photographic devices with different fields of view (FOV) and focal lengths. The fields of view of image capturing devices 122, 124, and 126 may include, for example, any desired area relative to the environment of vehicle 200. In some embodiments, one or more of image capturing devices 122, 124, and 126 may be configured to acquire image data from the environment of the front of vehicle 200, the rear of vehicle 200, the side of vehicle 200, or a combination thereof.

[0147] Furthermore, the focal length associated with each image capturing device 122, 124, and / or 126 can be selectable (e.g., by including appropriate lenses, etc.) so that each device acquires images of objects at a desired distance range relative to the vehicle 200. For example, in some embodiments, image capturing devices 122, 124, and 126 can acquire images of close-up objects within a few meters of the vehicle. Image capturing devices 122, 124, and 126 can also be configured to acquire images of objects at a greater distance range from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or more). Additionally, the focal length of image capturing devices 122, 124, and 126 can be selected such that one image capturing device (e.g., image capturing device 122) can acquire images of objects relatively close to the vehicle (e.g., within 10 m or 20 m), while other image capturing devices (e.g., image capturing devices 124 and 126) can acquire images of objects further away from the vehicle 200 (e.g., greater than 20 m, 50 m, 100 m, 150 m, etc.).

[0148] According to some embodiments, the field of view (FOV) of one or more image capture devices 122, 124, and 126 may have a wide angle. For example, an FOV of 140 degrees may be advantageous, especially for image capture devices 122, 124, and 126 that can be used to capture images of an area near vehicle 200. For example, image capture device 122 can be used to capture images of an area to the right or left of vehicle 200, and in such embodiments, it is desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0149] The field of view associated with each of the image capturing devices 122, 124, and 126 may depend on the corresponding focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0150] Image capture devices 122, 124, and 126 can be configured to have any suitable field of view. In one particular example, image capture device 122 may have a horizontal FOV of 46 degrees, image capture device 124 may have a horizontal FOV of 23 degrees, and image capture device 126 may have a horizontal FOV between 23 and 46 degrees. In another example, image capture device 122 may have a horizontal FOV of 52 degrees, image capture device 124 may have a horizontal FOV of 26 degrees, and image capture device 126 may have a horizontal FOV between 26 and 52 degrees. In some embodiments, the ratio of the FOV of image capture device 122 to the FOV of image capture device 124 and / or image capture device 126 may vary from 1.5 to 2.0. In other embodiments, this ratio may vary between 1.25 and 2.25.

[0151] System 100 may be configured such that the field of view of image capture device 122 at least partially or completely overlaps with the field of view of image capture devices 124 and / or 126. In some embodiments, system 100 may be configured such that the field of view of image capture devices 124 and 126, for example, falls within (e.g., narrower) the field of view of image capture device 122 and shares a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs or may have partial overlap in their FOVs. In some embodiments, the field of view of image capture devices 122, 124, and 126 may be aligned such that the center of the narrower FOV image capture device 124 and / or 126 may be located in the lower half of the field of view of the wider FOV device 122.

[0152] Figure 2F This is a schematic representation of an exemplary vehicle control system according to the disclosed embodiments. For example... Figure 2F As shown, vehicle 200 may include a throttle system 220, a braking system 230, and a steering system 240. System 100 may provide inputs (e.g., control signals) to one or more of the throttle system 220, braking system 230, and steering system 240 via one or more data links (e.g., one or more wired and / or wireless links for transmitting data). For example, based on analysis of images acquired by image capture devices 122, 124, and / or 126, system 100 may provide control signals to one or more of the throttle system 220, braking system 230, and steering system 240 to navigate vehicle 200 (e.g., by inducing acceleration, turning, lane changes, etc.). Furthermore, system 100 may receive inputs from one or more of the throttle system 220, braking system 230, and steering system 240 indicating operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.). The following is in conjunction with... Figure 4-7 Further details are provided.

[0153] like Figure 3AAs shown, vehicle 200 may also include a user interface 170 for interacting with the driver or passengers of vehicle 200. For example, user interface 170 in a vehicle application may include a touchscreen 320, a knob 330, a button 340, and a microphone 350. The driver or passengers of vehicle 200 may also interact with system 100 using handles (e.g., located on or near the steering column of vehicle 200, including, for example, a turn signal handle), buttons (e.g., located on the steering wheel of vehicle 200), etc. In some embodiments, microphone 350 may be positioned adjacent to rearview mirror 310. Similarly, in some embodiments, image capture device 122 may be located near rearview mirror 310. In some embodiments, user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, system 100 may provide various notifications (e.g., alarms) via speaker 360.

[0154] Figure 3B-3D This is an illustration of an exemplary photographic device bracket 370 according to the disclosed embodiment, which is configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) against the vehicle's windshield. Figure 3B As shown, the camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be positioned behind a glare shield 380, which may be flush with the vehicle windshield and includes components of a film and / or anti-reflective material. For example, the glare shield 380 may be positioned such that it is aligned with a vehicle windshield having a matching bevel. In some embodiments, each of the image capture devices 122, 124, and 126 may be positioned behind the glare shield 380, as... Figure 3D As shown. The disclosed embodiments are not limited to any particular configuration of the image capture devices 122, 124 and 126, the camera device bracket 370 and the light shield 380. Figure 3C It's from the front angle. Figure 3B The diagram shows the camera device support 370.

[0155] As will be appreciated by those skilled in the art who benefit from this disclosure, many changes and / or modifications can be made to the embodiments disclosed above. For example, not all components are essential to the operation of system 100. Furthermore, any component may be located in any suitable part of system 100, and components may be rearranged in a variety of configurations while providing the functionality of the disclosed embodiments. Thus, the above configuration is exemplary, and regardless of the configuration described above, system 100 is capable of providing a wide range of functionality to analyze the surrounding environment of vehicle 200 and navigate vehicle 200 in response to that analysis.

[0156] As discussed in more detail below and according to the various disclosed embodiments, system 100 may provide a variety of features related to autonomous driving and / or driver assistance technologies. For example, system 100 may analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 may collect data for analysis from, for example, image acquisition unit 120, position sensor 130, and other sensors. Furthermore, system 100 may analyze the collected data to determine whether vehicle 200 should take a certain action, and then automatically take the determined action without human intervention. For example, when vehicle 200 is navigating without human intervention, system 100 may automatically control the braking, acceleration, and / or steering of vehicle 200 (e.g., by sending control signals to one or more of throttle system 220, braking system 230, and steering system 240). In addition, system 100 may analyze the collected data and issue warnings and / or alerts to vehicle occupants based on the analysis of the collected data. Additional details relating to the various embodiments provided with system 100 are provided below.

[0157] Forward Multi-Imaging System

[0158] As described above, system 100 can provide driver assistance functionality using a multi-camera system. The multi-camera system may use one or more cameras facing forward of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side or rear of the vehicle. In one embodiment, for example, system 100 may use a dual-camera imaging system, wherein a first camera and a second camera (e.g., image capture devices 122 and 124) may be positioned at the front and / or side of the vehicle (e.g., vehicle 200). The first camera may have a field of view larger than, smaller than, or partially overlapping with that of the second camera. Additionally, the first camera may be connected to a first image processor to perform monocular image analysis of images provided by the first camera, and the second camera may be connected to a second image processor to perform monocular image analysis of images provided by the second camera. The outputs of the first and second image processors (e.g., processed information) may be combined. In some embodiments, the second image processor may receive images from the first and second cameras to perform stereo analysis. In another embodiment, system 100 may use a three-camera imaging system, where each camera has a different field of view. Therefore, such a system can make decisions based on information derived from objects located at varying distances in front of and to the sides of the vehicle. The term monocular image analysis can refer to an instance of performing image analysis based on an image captured from a single viewpoint (e.g., from a single camera). Stereo image analysis can refer to an instance of performing image analysis based on two or more images captured using one or more variations of image capture parameters. For example, captured images suitable for performing stereo image analysis may include images captured from two or more different positions, from different fields of view, using different focal lengths, along with parallax information, etc.

[0159] For example, in one embodiment, system 100 may use image capture devices 122, 124, and 126 to implement a three-camera configuration. In this configuration, image capture device 122 provides a narrow field of view (e.g., 34 degrees, or other values ​​selected from the range of approximately 20 to 45 degrees), image capture device 124 provides a wide field of view (e.g., 150 degrees, or other values ​​selected from the range of approximately 100 to approximately 180 degrees), and image capture device 126 provides an intermediate field of view (e.g., 46 degrees, or other values ​​selected from the range of approximately 35 to approximately 60 degrees). In some embodiments, image capture device 126 may act as a primary or master camera. Image capture devices 122, 124, and 126 may be positioned behind rearview mirror 310 and substantially side-by-side (e.g., 6 cm apart). Furthermore, in some embodiments, as described above, one or more of image capture devices 122, 124, and 126 may be mounted behind a sun visor 380, which is flush with the windshield of vehicle 200. This shielding works to minimize the impact of any reflections from inside the vehicle on the image capture devices 122, 124, and 126.

[0160] In another embodiment, as described above Figure 3B and Figure 3C The wide field-of-view camera (e.g., image capture device 124 in the example above) can be mounted below the narrow and main field-of-view cameras (e.g., image devices 122 and 126 in the example above). This configuration provides free line of sight from the wide field-of-view camera. To reduce reflections, the camera can be mounted close to the windshield of the vehicle 200 and may include a polarizer on the camera to dampen reflected light.

[0161] A three-camera system can provide certain performance characteristics. For example, some embodiments may include verifying the ability of one camera to detect an object based on detection results from another camera. In the three-camera configuration described above, the processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as described above), wherein each processing device is dedicated to processing one or more images captured by the image capture devices 122, 124, and 126.

[0162] In a three-camera system, a first processing unit receives images from the main camera and the narrow field-of-view camera, and performs visual processing on the narrow field-of-view camera, such as detecting other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Furthermore, the first processing unit calculates pixel differences between the images from the main camera and the narrow field-of-view camera, and creates a 3D reconstruction of the vehicle 200's environment. The first processing unit can then combine the 3D reconstruction with 3D map data or with 3D information calculated based on information from the other camera.

[0163] The second processing unit can receive images from the main imaging unit and perform visual processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the second processing unit can calculate the displacement of the imaging unit and, based on that displacement, calculate the pixel differences between consecutive images, and create a 3D reconstruction of the scene (e.g., from moving structures). The second processing unit can send the structure from the motion-based 3D reconstruction to the first processing unit for combination with the stereoscopic 3D image.

[0164] The third processing unit can receive images from the wide field-of-view (FOV) camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing unit can further execute additional processing instructions to analyze the images in order to identify moving objects in the images, such as vehicles changing lanes or pedestrians.

[0165] In some embodiments, allowing the stream of image-based information to be captured and processed separately can provide an opportunity to provide redundancy in the system. This redundancy may include, for example, using a first image capture device and images processed from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0166] In some embodiments, system 100 may use two image capture devices (e.g., image capture devices 122 and 124) to provide navigation assistance to vehicle 200, and use a third image capture device (e.g., image capture device 126) to provide redundancy and verify the analysis of data received from the other two image capture devices. For example, in this configuration, image capture devices 122 and 124 may provide images for system 100 to perform stereo analysis for navigating vehicle 200, while image capture device 126 may provide images for system 100 to perform monocular analysis to provide redundancy and verification based on information obtained from images captured by image capture devices 122 and / or 124. That is, image capture device 126 (and corresponding processing device) may be considered to provide a redundant subsystem for providing checks on the analysis obtained from image capture devices 122 and 124 (e.g., providing an automatic emergency braking (AEB) system). Furthermore, in some embodiments, the redundancy and verification of the received data may be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside the vehicle, etc.).

[0167] Those skilled in the art will recognize that the above-described camera configurations, camera placements, number of cameras, camera positions, etc., are merely examples. These components, as well as other components described with respect to the entire system, can be assembled and used in a variety of different configurations without departing from the scope of the disclosed embodiments. Further details relating to the use of the multi-camera system to provide driver assistance and / or autonomous vehicle functionality are as follows.

[0168] Figure 4 This is an exemplary functional block diagram of a memory 140 and / or 150, which is capable of storing / programming instructions for performing one or more operations, according to the disclosed embodiments. Although reference is made to memory 140 below, those skilled in the art will appreciate that instructions may be stored in memory 140 and / or 150.

[0169] like Figure 4 As shown, memory 140 may store monocular image analysis module 402, stereo image analysis module 404, velocity and acceleration module 406, and navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of the modules 402, 404, 406, and 408 contained in memory 140. Those skilled in the art will understand that the reference to processing unit 110 in the following discussion may individually or collectively refer to application processor 180 and image processor 190. Accordingly, steps of any of the following processes may be performed by one or more processing devices.

[0170] In one embodiment, the monocular image analysis module 402 may store instructions (e.g., computer vision software) that, when executed by the processing unit 110, perform monocular image analysis on a set of images acquired by one of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the image set with additional sensing information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. (See the following for further details.) Figures 5A-5D The monocular image analysis module 402 may include instructions for detecting a set of features within the image set (e.g., lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other features associated with the vehicle's environment). Based on this analysis, the system 100 (e.g., via processing unit 110) may induce one or more navigation responses in the vehicle 200, such as turning, lane changing, changes in acceleration, etc., as described below in conjunction with the navigation response module 408.

[0171] In one embodiment, the stereo image analysis module 404 may store instructions (e.g., computer vision software) that, when executed by the processing unit 110, perform stereo image analysis on first and second sets of images acquired from a combination of image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first and second sets of images with additional sensing information (e.g., information from radar) to perform stereo image analysis. For example, the stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. (The following is a continuation of the previous paragraph.) Figure 6 The stereo image analysis module 404 may include instructions for detecting feature sets (e.g., lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, etc.) within the first and second sets of images. Based on this analysis, the processing unit 110 may induce one or more navigation responses in the vehicle 200, such as turning, lane changing, changes in acceleration, etc., as described below in conjunction with the navigation response module 408. Furthermore, in some embodiments, the stereo image analysis module 404 may implement techniques associated with a trained system (e.g., a neural network or deep neural network) or an untrained system (e.g., a system configured to use computer vision algorithms to detect and / or label objects in an environment from which sensed information is captured and processed). In one embodiment, the stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0172] In one embodiment, the speed and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in the vehicle 200, the devices being configured to cause changes in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 may execute instructions associated with the speed and acceleration module 406 to calculate a target speed of the vehicle 200 based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, speed and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, and position information of the vehicle 200 relative to lane markings on the road. Additionally, the processing unit 110 may calculate the target speed of the vehicle 200 based on sensing inputs (e.g., information from radar) and inputs from other systems of the vehicle 200 (e.g., the vehicle 200's throttle system 220, braking system 230, and / or steering system 240). Based on the calculated target speed, the processing unit 110 may transmit electronic signals to the throttle system 220, braking system 230 and / or steering system 240 of the vehicle 200 to trigger changes in speed and / or acceleration by, for example, physically pressing down the brakes or releasing the accelerator of the vehicle 200.

[0173] In one embodiment, the navigation response module 408 may store software executable by the processing unit 110 to determine the expected navigation response based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. This data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, target position information of the vehicle 200, etc. Additionally, in some embodiments, the navigation response may be (partially or entirely) based on map data, the predetermined position of the vehicle 200, and / or the relative velocity or relative acceleration between the vehicle 200 and one or more objects detected from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine the expected navigation response based on sensor inputs (e.g., information from radar) and inputs from other systems of the vehicle 200 (e.g., the vehicle 200's throttle system 220, braking system 230, and steering system 240). Based on the anticipated navigation response, the processing unit 110 may transmit electronic signals to the throttle system 220, braking system 230, and steering system 240 of the vehicle 200 to trigger the anticipated navigation response by, for example, rotating the steering wheel of the vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the anticipated navigation response) as input to the execution of the speed and acceleration module 406 for calculating changes in the speed of the vehicle 200.

[0174] Furthermore, any of the modules disclosed herein (e.g., modules 402, 404, and 406) can implement techniques associated with trained systems (e.g., neural networks or deep neural networks) or untrained systems.

[0175] Figure 5A This is a flowchart illustrating an exemplary process 500A for inducing one or more navigation responses based on monocular image analysis according to the disclosed embodiment. In step 510, processing unit 110 may receive multiple images via data interface 128 between processing unit 110 and image acquisition unit 120. For example, a photographic device included in image acquisition unit 120 (e.g., image capture device 122 with field of view 202) may capture multiple images of an area in front of vehicle 200 (or, for example, the side or rear of the vehicle) and transmit them to processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). Processing unit 110 may execute monocular image analysis module 402 in step 520 to analyze the multiple images, as described below. Figures 5B-5D More detailed description. By performing analysis, the processing unit 110 can detect a set of features within the image set, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0176] Processing unit 110 may also execute monocular image analysis module 402 in step 520 to detect various road hazards, such as parts of truck tires, fallen road signs, loose cargo, small animals, etc. Road hazards can vary in structure, shape, size, and color, making their detection more challenging. In some embodiments, processing unit 110 may execute monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road hazards. For example, processing unit 110 may estimate camera movement between consecutive image frames and calculate pixel differences between frames to construct a 3D map of the road. Processing unit 110 can then use the 3D map to detect road surfaces and hazards present above them.

[0177] In step 530, processing unit 110 may execute navigation response module 408 to perform the analysis performed in step 520 and the above combination. Figure 4The described technique induces one or more navigation responses in vehicle 200. Navigation responses may include, for example, turning, lane changing, changes in acceleration, etc. In some embodiments, processing unit 110 may induce one or more navigation responses using data derived from the execution of speed and acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, processing unit 110 may induce vehicle 200 to change lanes and then accelerate by, for example, sequentially transmitting control signals to steering system 240 and throttle system 220 of vehicle 200. Alternatively, processing unit 110 may induce vehicle 200 to brake and change lanes by, for example, simultaneously transmitting control signals to braking system 230 and steering system 240 of vehicle 200.

[0178] Figure 5B This is a flowchart illustrating an exemplary process 500B for detecting one or more vehicles and / or pedestrians in a set of images according to a disclosed embodiment. Processing unit 110 may execute monocular image analysis module 402 to implement process 500B. In step 540, processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 may scan one or more images, compare the images to one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or portions thereof). The predetermined patterns may be designed to achieve a high false hit rate and a low false miss rate. For example, processing unit 110 may use a low threshold of similarity to the predetermined pattern to identify candidate objects as possible vehicles or pedestrians. Doing so allows processing unit 110 to reduce the probability of missing (e.g., not identifying) candidate objects representing vehicles or pedestrians.

[0179] In step 542, processing unit 110 may filter the candidate object set based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria may be derived from various properties associated with object types stored in a database (e.g., a database stored in memory 140). Properties may include object shape, size, texture, location (e.g., relative to vehicle 200), etc. Therefore, processing unit 110 may use one or more sets of criteria to exclude false candidates from the candidate object set.

[0180] In step 544, processing unit 110 may analyze multiple frames of the image to determine whether an object in the candidate object set represents a vehicle and / or a pedestrian. For example, processing unit 110 may track detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected object (e.g., size, position relative to vehicle 200, etc.). Additionally, processing unit 110 may estimate parameters of the detected object and compare the object's frame-by-frame position data with its predicted position.

[0181] In step 546, processing unit 110 may construct a set of measurements of the detected objects. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to vehicle 200) associated with the detected objects. In some embodiments, processing unit 110 may construct measurements based on available modeling data using a range of time-based observation estimation techniques (e.g., Kalman filters or linear quadratic estimation (LQE)) and / or based on different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). Kalman filters may be based on object scaling measurements, where the scaling measurement is proportional to the collision time (e.g., the amount of time it takes for vehicle 200 to arrive at the object). Therefore, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the captured image set and derive information associated with the vehicles and pedestrians (e.g., position, velocity, size). Based on the identification and the derived information, processing unit 110 may induce one or more navigation responses in vehicle 200, as described above. Figure 5A As stated above.

[0182] In step 548, processing unit 110 may perform optical flow analysis on one or more images to reduce the probability of detecting false positives and false negatives representing candidate objects representing vehicles or pedestrians. Optical flow analysis may involve, for example, analyzing motion patterns relative to vehicle 200 in one or more images associated with other vehicles and pedestrians, where the motion patterns differ from road surface motion. Processing unit 110 can calculate the motion of candidate objects by observing different positions of the objects across multiple image frames captured at different times. Processing unit 110 can use position and time values ​​as input to a mathematical model to calculate the motion of candidate objects. Therefore, optical flow analysis can provide another method for detecting vehicles and pedestrians near vehicle 200. Processing unit 110 may combine steps 540-546 to perform optical flow analysis to provide redundancy in vehicle and pedestrian detection and increase the reliability of system 100.

[0183] Figure 5C This is a flowchart illustrating an exemplary process 500C for detecting road markings and / or lane geometry information in a set of images according to the disclosed embodiments. Processing unit 110 can execute monocular image analysis module 402 to implement process 500C. In step 550, processing unit 110 can detect a set of objects by scanning one or more images. To detect lane marking segments, lane geometry information, and other relevant road markings, processing unit 110 can filter the set of objects to exclude those determined to be irrelevant (e.g., potholes, small rocks, etc.). In step 552, processing unit 110 can group together segments belonging to the same road marking or lane marking detected in step 550. Based on the grouping, processing unit 110 can develop a model, such as a mathematical model, representing the detected segments.

[0184] In step 554, processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, processing unit 110 may create a projection of the detected segment from an image plane to a real-world plane. The projection may be characterized using a cubic polynomial with coefficients corresponding to physical properties such as the location, slope, curvature, and derivative of curvature of the detected road. In generating the projection, processing unit 110 may consider variations in the road surface and the tilt and roll rates associated with vehicle 200. Additionally, processing unit 110 may model the road elevation by analyzing positional and motion cues present on the road surface. Furthermore, processing unit 110 may estimate the tilt and roll rates associated with vehicle 200 by tracking a set of feature points in one or more images.

[0185] In step 556, processing unit 110 may perform multi-frame analysis, for example, by tracking the detected segment across consecutive image frames and accumulating frame-by-frame data associated with the detected segment. As processing unit 110 performs multi-frame analysis, the measurement set constructed in step 554 becomes more reliable and associated with increasingly higher confidence levels. Therefore, by performing steps 550, 552, 554, and 556, processing unit 110 can identify road markings appearing within the captured image set and derive lane geometry information. Based on the identification and derived information, processing unit 110 may induce one or more navigation responses in vehicle 200, as described above. Figure 5A As stated above.

[0186] In step 558, processing unit 110 may consider additional information sources to further develop a safety model of vehicle 200 within the context of the surrounding environment. Processing unit 110 may use the safety model to define the context in which system 100 can safely perform autonomous control of vehicle 200. To develop the safety model, in some embodiments, processing unit 110 may consider the positions and movements of other vehicles, detected road edges and barriers, and / or general road shape descriptions extracted from map data (e.g., data from map database 160). By considering additional information sources, processing unit 110 can provide redundancy in detecting road markings and lane geometry, and increase the reliability of system 100.

[0187] Figure 5DThis is a flowchart illustrating an exemplary process 500D for detecting traffic lights in a set of images according to a disclosed embodiment. Processing unit 110 may execute monocular image analysis module 402 to implement process 500D. In step 560, processing unit 110 may scan the set of images and identify objects appearing in the images at locations where traffic lights may be present. For example, processing unit 110 may filter the identified objects to form a candidate object set, thereby excluding those objects that could not possibly correspond to traffic lights. Filtering may be based on various properties associated with traffic lights, such as shape, size, texture, location (e.g., relative to vehicle 200), etc. Such properties may be based on multiple examples of traffic lights and traffic control signals and are stored in a database. In some embodiments, processing unit 110 may perform multi-frame analysis on the candidate object set reflecting possible traffic lights. For example, processing unit 110 may track candidate objects across consecutive image frames, estimate the real-world location of the candidate objects, and filter out those objects that are moving (and therefore unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects and identify the relative position of the detected color appearing within possible traffic lights.

[0188] In step 562, processing unit 110 may analyze the geometry of the intersection. The analysis may be based on any combination of the following: (i) the number of lanes detected on either side of vehicle 200, (ii) markings detected on the road (e.g., arrow markings), and (iii) a description of the intersection extracted from map data (e.g., data from map database 160). Processing unit 110 may use information derived from the execution of monocular analysis module 402 for the analysis. Additionally, processing unit 110 may determine the correspondence between the traffic lights detected in step 560 and the lanes appearing near vehicle 200.

[0189] As vehicle 200 approaches the intersection, in step 564, processing unit 110 may update the confidence level associated with the analyzed intersection geometry and the detected traffic lights. For example, the estimated number of traffic lights present at the intersection may affect the confidence level compared to the actual number present at the intersection. Therefore, based on the confidence level, processing unit 110 may delegate control to the driver of vehicle 200 to improve safety conditions. By performing steps 560, 562, and 564, processing unit 110 may identify traffic lights appearing within the captured image set and analyze intersection geometry information. Based on the identification and analysis, processing unit 110 may induce one or more navigation responses in vehicle 200, as described above. Figure 5A As stated above.

[0190] Figure 5EThis is a flowchart illustrating an exemplary process 500E of inducing a navigation response in one or more vehicles 200 based on a vehicle path, according to a disclosed embodiment. In step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path can be represented using a set of points expressed in coordinates (x, z), and the distance d between two points in the set of points... i The distance can fall within a range of 1 to 5 meters. In one embodiment, processing unit 110 can use two polynomials (e.g., left and right road polynomials) to construct an initial vehicle path. Processing unit 110 can calculate the geometric midpoint between the two polynomials and, if present, offset each point contained in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset) (zero offset may correspond to driving in the middle of the lane). The offset may be along a direction perpendicular to the segment between any two points in the vehicle path. In another embodiment, processing unit 110 can use a polynomial and an estimated lane width to offset each point in the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0191] In step 572, processing unit 110 may update the vehicle path constructed in step 570. Processing unit 110 may use a higher resolution to reconstruct the vehicle path constructed in step 570, such that the distance d between two points in the set of points representing the vehicle path... k less than the above distance d i For example, distance d k It can fall within a range of 0.1 to 0.3 meters. The processing unit 110 can use a parabolic spline algorithm to reconstruct the vehicle path, which can generate a cumulative distance vector S (i.e., based on the set of points representing the vehicle path) corresponding to the total length of the vehicle path.

[0192] In step 574, processing unit 110 can determine the forward viewpoint (expressed in coordinates as (x...) based on the updated vehicle path constructed in step 572. l , z l Processing unit 110 can extract a forward-looking point from the accumulated distance vector S, and the forward-looking point can be associated with a forward-looking distance and a forward-looking time. The forward-looking distance can have a lower limit ranging from 10 to 20 meters and can be calculated as the product of the vehicle 200's speed and the forward-looking time. For example, as the speed of the vehicle 200 decreases, the forward-looking distance can also decrease (e.g., until it reaches the lower limit). The forward-looking time can range from 0.5 to 1.5 seconds and can be inversely proportional to the gain of one or more control loops (e.g., a heading error tracking control loop) that cause the navigation response in the vehicle 200. For example, the gain of the heading error tracking control loop can depend on the bandwidth of the yaw rate loop, the steering actuator loop, the vehicle's lateral dynamics, etc. Therefore, the higher the gain of the heading error tracking control loop, the shorter the forward-looking time.

[0193] In step 576, processing unit 110 can determine the heading error and yaw rate commands based on the foresight point determined in step 574. Processing unit 110 can do this by calculating the arctangent of the foresight point (e.g., arctan(x)). l / z l The yaw rate command is determined by the product of the heading error and the advanced control gain. The advanced control gain can be equal to (2 / look-ahead time) if the look-ahead distance is not at the lower limit. Otherwise, the advanced control gain can be equal to (2 × vehicle speed 200 / look-ahead distance).

[0194] Figure 5F This is a flowchart illustrating an exemplary process 500F for determining whether a preceding vehicle is changing lanes, according to the disclosed embodiment. In step 580, processing unit 110 may determine navigation information associated with the preceding vehicle (e.g., a vehicle traveling in front of vehicle 200). For example, processing unit 110 may use the above-described combination... Figure 5A and Figure 5B The described technology determines the position, speed (e.g., direction and velocity), and / or acceleration of a moving vehicle. Processing unit 110 may also utilize the above combinations. Figure 5E The technique is used to determine one or more road polynomials, forward look-ahead points (associated with vehicle 200), and / or snail trails (e.g., a set of points describing the path taken by the preceding vehicle).

[0195] In step 582, processing unit 110 may analyze the navigation information determined in step 580. In one embodiment, processing unit 110 may calculate the distance between the snail trail and the road polynomial (e.g., along the trail). If the variation of this distance along the trail exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a road with sharp bends), processing unit 110 may determine that the preceding vehicle may be changing lanes. In the case of multiple vehicles detected traveling in front of vehicle 200, processing unit 110 may compare the snail trail associated with each vehicle. Based on this comparison, processing unit 110 may determine that vehicles whose snail trails do not match those of other vehicles may be changing lanes. Processing unit 110 may also compare the curvature of the snail trail (associated with the preceding vehicle) with the expected curvature of the road segment the preceding vehicle is traveling on. The predicted curvature can be extracted from map data (e.g., data from map database 160), from road polynomials, from snail trails of other vehicles, from prior knowledge related to the road, etc. If the difference between the curvature of the snail trail and the predicted curvature of the road segment exceeds a predetermined threshold, the processing unit 110 can determine that the preceding vehicle may be changing lanes.

[0196] In another embodiment, processing unit 110 may compare the instantaneous position of the preceding vehicle with a forward viewpoint (associated with vehicle 200) over a specific time period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the preceding vehicle and the forward viewpoint changes during the specific time period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a road with sharp bends), processing unit 110 may determine that the preceding vehicle may be changing lanes. In another embodiment, processing unit 110 may analyze the geometry of a snail trail by comparing the lateral distance traveled along the trail with the expected curvature of the snail trail. The expected radius of curvature may be determined by the following calculation: (δ... z 2 + δ x 2 ) / 2 / (δ x ), where δ x This represents the lateral distance traveled, and δ. z This represents the longitudinal distance traveled. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 can determine that the preceding vehicle may be changing lanes. In another embodiment, the processing unit 110 can analyze the position of the preceding vehicle. If the position of the preceding vehicle obscures the road polynomial (e.g., the preceding vehicle is overlaid on the road polynomial), the processing unit 110 can determine that the preceding vehicle may be changing lanes. If the position of the preceding vehicle is such that another vehicle is detected in front of the preceding vehicle and the snail trails of the two vehicles are not parallel, the processing unit 110 can determine that the (closer) preceding vehicle may be changing lanes.

[0197] In step 584, processing unit 110 may determine whether the preceding vehicle 200 is changing lanes based on the analysis performed in step 582. For example, processing unit 110 may make this determination based on a weighted average of the individual analyses performed in step 582. In this approach, for example, a determination by processing unit 110 based on a particular type of analysis that the preceding vehicle may be changing lanes may be assigned a value "1" (while "0" indicates that the preceding vehicle is unlikely to change lanes). Different analyses performed in step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0198] Figure 6This is a flowchart illustrating an exemplary process 600 that induces one or more navigation responses based on stereoscopic image analysis according to the disclosed embodiment. In step 610, processing unit 110 may receive first and second plurality of images via data interface 128. For example, a photographic device included in image acquisition unit 120 (e.g., image capture devices 122 and 124 having fields of view 202 and 204) may capture first and second plurality of images of an area in front of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive first and second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0199] In step 620, processing unit 110 may execute stereo image analysis module 404 to perform stereo image analysis on the first and second plurality of images in order to create a 3D map of the road in front of the vehicle and detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. Stereo image analysis may be performed in conjunction with the above. Figures 5A-5D The steps are performed in a similar manner. For example, processing unit 110 may execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road markings, traffic lights, road hazards, etc.) in first and second plurality of images, filter out subsets of candidate objects based on various criteria, perform multi-frame analysis, construct measurements, and determine the confidence level of the remaining candidate objects. In performing the above steps, processing unit 110 may consider information from the first and second plurality of images rather than information from a single set of images. For example, processing unit 110 may analyze differences in pixel-level data (or other subsets of data from the two captured image streams) of candidate objects appearing in the first and second plurality of images. As another example, processing unit 110 may estimate the position and / or velocity (e.g., relative to vehicle 200) of a candidate object by observing that the object appears in one image of the plurality of images rather than another, or relative to other differences (which may exist relative to objects appearing in both image streams). For example, the position, velocity, and / or acceleration relative to vehicle 200 may be determined based on the trajectory, position, movement characteristics, etc., of features associated with objects appearing in one or both image streams.

[0200] In step 630, processing unit 110 may execute navigation response module 408 to perform the analysis performed in step 620 and the above combination. Figure 4The described technique induces one or more navigation responses in vehicle 200. Navigation responses may include, for example, turning, lane changing, changes in acceleration, changes in speed, braking, etc. In some embodiments, processing unit 110 may use data derived from the execution of speed and acceleration module 406 to induce one or more navigation responses. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0201] Figure 7 This is a flowchart illustrating an exemplary process 700 that induces one or more navigation responses based on the analysis of three sets of images, according to the disclosed embodiment. In step 710, processing unit 110 may receive first, second, and third plurality of images via data interface 128. For example, photographic devices included in image acquisition unit 120 (e.g., image capture devices 122, 124, and 126 having fields of view 202, 204, and 206) may capture first, second, and third plurality of images of areas in front of and / or to the sides of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive first, second, and third plurality of images via three or more data interfaces. For example, each of image capture devices 122, 124, and 126 may have an associated data interface for transmitting data to processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0202] In step 720, processing unit 110 can analyze the first, second, and third images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road hazards. The analysis can be performed in conjunction with the above. Figures 5A-5D and Figure 6 The steps are performed in a similar manner. For example, processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., via execution by monocular image analysis module 402 and based on the above combination). Figures 5A-5D The steps described above). Alternatively, the processing unit 110 may perform stereoscopic image analysis on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images (e.g., via execution by the stereoscopic image analysis module 404 and based on the above combination). Figure 6(The steps described above). Processed information corresponding to the analysis of the first, second, and / or third plurality of images can be combined. In some embodiments, processing unit 110 may perform a combination of monocular and stereoscopic image analysis. For example, processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via execution by monocular image analysis module 402) and perform stereoscopic image analysis on the second and third plurality of images (e.g., via execution by stereoscopic image analysis module 404). The configuration of image capture devices 122, 124, and 126—including their respective positions and fields of view 202, 204, and 206—may affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a specific configuration of image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0203] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed in steps 710 and 720. Such tests may provide an indication of the overall performance of system 100 against certain configurations of image capture devices 122, 124, and 126. For example, processing unit 110 may determine the ratio of "false hits" (e.g., situations where system 100 incorrectly determines the presence of vehicles or pedestrians) to "misses".

[0204] In step 730, processing unit 110 may induce one or more navigation responses in vehicle 200 based on information derived from two of the first, second, and third plurality of images. The selection of two of the first, second, and third plurality of images may depend on various factors, such as the number, type, and size of objects detected in each of the plurality of images. Processing unit 110 may also make selections based on image quality and resolution, the effective field of view reflected in the image, the number of captured frames, and the degree to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which the object appears, the proportion of objects appearing in each such frame, etc.).

[0205] In some embodiments, processing unit 110 can select two pieces of information derived from a first, second, and third plurality of images by determining the degree of consistency between information derived from one image source and information derived from other image sources. For example, processing unit 110 can combine processed information derived from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination of both) and determine that the images captured across each of image capture devices 122, 124, and 126 are consistent visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.). Processing unit 110 can also exclude inconsistent information across the captured images (e.g., vehicles changing lanes, lane model indicating vehicles too close to vehicle 200, etc.). Therefore, processing unit 110 can select two pieces of information derived from the first, second, and third plurality of images based on the determination of consistent and inconsistent information.

[0206] Navigation responses may include, for example, turning, lane changes, and changes in acceleration. Processing unit 110 may base its responses on the analysis performed in step 720 and, as described above. Figure 4 The aforementioned techniques are used to induce one or more navigation responses. Processing unit 110 may also use data derived from the execution of velocity and acceleration module 406 to induce one or more navigation responses. In some embodiments, processing unit 110 may induce one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration between vehicle 200 and objects detected within any of the first, second, and third plurality of images. The plurality of navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0207] Sparse road model for autonomous vehicle navigation

[0208] In some embodiments, the disclosed systems and methods may use sparse maps for autonomous vehicle navigation. In particular, sparse maps can be used for autonomous vehicle navigation along road segments. For example, sparse maps can provide sufficient information for navigating autonomous vehicles without requiring the storage and / or updating of large amounts of data. As discussed in more detail below, autonomous vehicles may use sparse maps to navigate one or more roads based on one or more stored trajectories.

[0209] Sparse maps for autonomous vehicle navigation

[0210] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, sparse maps can provide sufficient information for navigation without requiring excessive data storage or data transfer rates. As described in more detail below, a vehicle (which may be an autonomous vehicle) can use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map may include data related to roads and potentially road signs along those roads, which may be sufficient for vehicle navigation but also present a small data footprint. For example, sparse data maps, as described in detail below, may require significantly less storage space and data transfer bandwidth compared to digital maps that include detailed map information, such as image data collected along roads.

[0211] For example, instead of storing detailed representations of road segments, sparse data maps can store three-dimensional polynomial representations of preferred vehicle routes along roads. These routes can require minimal data storage space. Additionally, in such sparse data maps, road signs can be identified and included in the sparse map road model to aid navigation. These road signs can be positioned at any spacing suitable for vehicle navigation, but in some cases, such road signs do not need to be identified and included in the model with high density and short spacing. Instead, in some cases, navigation based on road signs spaced at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart may be possible. As will be discussed in more detail elsewhere, sparse maps can be generated based on data collected or measured by vehicles equipped with various sensors and devices (e.g., image capture devices, GPS sensors, motion sensors, etc.) while traveling along a highway. In some cases, sparse maps can be generated based on data collected during multiple trips of one or more vehicles along a particular highway. Generating sparse maps using multiple trips of one or more vehicles can be called “crowdsourced” sparse maps.

[0212] According to the disclosed embodiments, autonomous vehicle systems can use sparse maps for navigation. For example, the disclosed systems and methods can distribute sparse maps to generate road navigation models for autonomous vehicles, and the sparse maps and / or the generated road navigation models can be used to navigate autonomous vehicles along road segments. The sparse maps according to this disclosure may include one or more three-dimensional contours that represent predetermined trajectories that an autonomous vehicle can traverse as it moves along associated road segments.

[0213] The sparse map according to this disclosure may also include data representing one or more road features. Such road features may include identified road signs, road signature profiles, and any other road-related features useful to the navigation vehicle. The sparse map according to this disclosure enables autonomous vehicle navigation based on the relatively small amount of data contained within it. For example, instead of containing a detailed representation of the road (e.g., road edges, road curvature, images associated with road segments, or data detailing other physical features associated with road segments), the disclosed embodiments of the sparse map may require relatively little storage space (and relatively little bandwidth when portions of the sparse map are transmitted to the vehicle), yet still adequately provide autonomous vehicle navigation. The small data footprint of the disclosed sparse map, discussed in more detail below, can be achieved in some embodiments by storing representations of road-related elements that require a small amount of data but still enable autonomous navigation.

[0214] For example, instead of storing detailed representations of all aspects of a road, the published sparse map can store a polynomial representation of one or more trajectories along which a vehicle can travel. Therefore, instead of storing (or necessarily transmitting) details related to the physical properties of the road for navigation along it, using the published sparse map, a vehicle can be navigated along specific road segments without, in some cases, interpreting the physical aspects of the road, by aligning its travel path with a trajectory (e.g., a polynomial spline) along those segments. In this way, the vehicle can navigate primarily based on the stored trajectory (e.g., the polynomial spline), which requires significantly less storage space than methods involving the storage of road images, road parameters, road layouts, etc.

[0215] In addition to the stored polynomial representation of the trajectory along the road segment, the disclosed sparse map may also include small data objects that can represent road features. In some embodiments, the small data objects may include digital signatures derived from digital images (or digital signals) obtained from sensors (e.g., cameras) on vehicles traveling along the road segment or other sensors, such as suspension sensors. The digital signatures may have a reduced size relative to the signals acquired by the sensors. In some embodiments, the digital signatures may be created to be compatible with a classifier function configured to detect and identify road features, for example, from signals acquired by sensors during subsequent driving. In some embodiments, the digital signatures may be created such that they have the smallest possible footprint while maintaining the ability to correlate or match road features with stored signatures based on images of road features captured at subsequent times by cameras on vehicles traveling along the same road segment (or digital signals generated by sensors, if the stored signatures are not based on images and / or include other data).

[0216] In some embodiments, the size of the data object may be further associated with the uniqueness of the road feature. For example, for a road feature detectable by a camera on a vehicle, and where the camera system on the vehicle is coupled to a classifier capable of classifying the image data corresponding to that road feature as associated with a specific type of road feature (e.g., a road sign), and where such a road sign is locally unique in that area (e.g., there are no identical road signs or road signs of the same type nearby), storing data indicating the type and location of the road feature may be sufficient.

[0217] As will be discussed in more detail below, road features (such as road signs along a road segment) can be stored as small data objects that can represent road features with fewer bytes while providing sufficient information for identification and navigation using such features. In one example, a road sign can be identified as an identified road sign that forms the basis for a vehicle's navigation. The representation of a road sign can be stored in a sparse map to include, for example, a few bytes of data indicating the type of road sign (e.g., a stop sign) and a few bytes of data indicating the location of the road sign (e.g., coordinates). Navigation based on this data-light representation of road signs (e.g., using a representation sufficient for road sign-based localization, identification, and navigation) can provide the expected level of navigation functionality associated with a sparse map without significantly increasing the data overhead associated with the sparse map. This lean representation of road signs (and other road features) can leverage sensors and processors included on such vehicles, configured to detect, identify, and / or classify certain road features.

[0218] When, for example, a sign or even a sign of a specific type is locally unique in a given area (e.g., when no other sign or another sign of the same type is present), the sparse map can use data indicating the type of road sign (sign or sign of a specific type), and during navigation (e.g., autonomous navigation) when a camera on an autonomous vehicle captures an image of an area including a sign (or sign of a specific type), the processor can process the image, detect signs (if they actually exist in the image), classify the image as a sign (or classify it as a sign of a specific type), and correlate the location of the image with the location of signs, such as those stored in the sparse map.

[0219] Generating sparse maps

[0220] In some embodiments, a sparse map may include at least one line representation of road surface features extending along a road segment and multiple road signs associated with that road segment. In some aspects, a sparse map may be generated, for example, via crowdsourcing through image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0221] Figure 8 A sparse map 800 is shown that is accessible to one or more vehicles, such as vehicle 200 (which may be an autonomous vehicle), for providing autonomous vehicle navigation. The sparse map 800 may be stored in memory (e.g., memory 140 or 150). Such memory devices may include any type of non-temporary storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 may include a hard disk drive, a compact optical disk, flash memory, a magnetic-based memory device, a light-based memory device, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150 or other types of storage devices.

[0222] In some embodiments, the sparse map 800 may be stored on a storage device provided on the vehicle 200 or on a non-transitory computer-readable medium (e.g., a storage device included in a navigation system on the vehicle 200). A processor (e.g., processing unit 110) provided on the vehicle 200 may access the sparse map 800 stored on the storage device or computer-readable medium provided on the vehicle 200 to generate navigation instructions for guiding the autonomous vehicle 200 as the vehicle traverses a road segment.

[0223] However, it is not necessary to store the sparse map 800 locally relative to the vehicle. In some embodiments, the sparse map 800 may be stored on a storage device or computer-readable medium provided on a remote server that communicates with the vehicle 200 or devices associated with the vehicle 200. A processor (e.g., processing unit 110) provided on the vehicle 200 may receive data contained in the sparse map 800 from the remote server and may execute the data to guide autonomous driving of the vehicle 200. In such embodiments, the remote server may store the entire sparse map 800 or only a portion thereof. Accordingly, storage devices or computer-readable media on the vehicle 200 and / or one or more attached vehicles may store the remaining(s) portions of the sparse map 800.

[0224] Furthermore, in such embodiments, the sparse map 800 can be accessed by multiple vehicles (e.g., tens, hundreds, thousands, or millions of vehicles) traversing various road segments. It should also be noted that the sparse map 800 may include multiple sub-maps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, millions, or more sub-maps available for navigation in vehicles. These sub-maps may be referred to as local maps, and any number of local maps related to the location a vehicle is traveling along the road can be accessed. The local map portion of the sparse map 800 may be stored, with a Global Navigation Satellite System (GNSS) key serving as an index into the database of the sparse map 800. Therefore, while the calculation of the steering angle used for navigating the primary vehicle in this system can be performed without relying on the GNSS position of the primary vehicle, road features, or road signs, this GNSS information can be used to retrieve the relevant local map.

[0225] Generally, sparse map 800 can be generated based on data collected from one or more vehicles traveling along a highway. For example, using sensors on one or more vehicles (e.g., cameras, speedometers, GPS, accelerometers, etc.), the trajectories of one or more vehicles traveling along the highway can be recorded, and a polynomial representation of the preferred trajectories of subsequent vehicles traveling along the highway can be determined based on the collected trajectories traveled by one or more vehicles. Similarly, data collected by one or more vehicles can help identify potential road signs along a particular highway. Data collected from vehicles currently crossing the highway can also be used to identify road profile information, such as road width profiles, road roughness profiles, traffic line spacing profiles, road conditions, etc. Using the collected information, sparse map 800 can be generated and distributed (e.g., for local storage or via real-time data transmission) for use in navigating one or more autonomous vehicles. However, in some embodiments, map generation may not end at the initial generation of the map. As will be discussed in more detail below, sparse map 800 can be continuously or periodically updated based on data collected from those vehicles as they continue to traverse the highways included in sparse map 800.

[0226] The data recorded in the sparse map 800 may include location information based on Global Positioning System (GPS) data. For example, location information may be included in the sparse map 800 for various map elements, including, for example, landmark locations, road profile locations, etc. The locations of map elements included in the sparse map 800 can be obtained using GPS data collected from vehicles crossing a road. For example, a vehicle passing an identified landmark can determine the location of the identified landmark using GPS location information associated with the vehicle and a determination of the landmark's position relative to the vehicle (e.g., image analysis based on data collected from one or more cameras on the vehicle). Such location determination of the identified landmark (or any other feature included in the sparse map 800) can be repeated as additional vehicles pass the location of the identified landmark. Part or all of the additional location determinations can be used to refine the location information stored in the sparse map 800 relative to the identified landmarks. For example, in some embodiments, multiple location measurements relative to a specific feature stored in the sparse map 800 may be averaged together. However, any other mathematical operations may also be used to refine the stored location of a map element based on multiple determined locations of the map element.

[0227] The sparse maps disclosed in the embodiments can enable autonomous vehicle navigation using a relatively small amount of stored data. In some embodiments, the sparse map 800 may have a data density of less than 2 Mb per kilometer of road, less than 1 Mb per kilometer of road, less than 500 kB per kilometer of road, or less than 100 kB per kilometer of road (e.g., including data representing target trajectories, road signs, and any other stored road features). In some embodiments, the data density of the sparse map 800 may be less than 10 kB per kilometer of road or even less than 2 kB per kilometer of road (e.g., 1.6 kB per kilometer), or no more than 10 kB per kilometer of road or no more than 20 kB per kilometer of road. In some embodiments, most (if not all) of U.S. highways can be autonomously navigated using a sparse map with a total of 4 GB or less of data. These data density values ​​may represent the average for the entire sparse map 800, for the local map within the sparse map 800, and / or for a specific road segment within the sparse map 800.

[0228] As described, the sparse map 800 may include representations of multiple target trajectories 810 for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as 3D splines. The target trajectories stored in the sparse map 800 may be determined, for example, based on two or more reconstructed trajectories previously traversed by a vehicle along a particular road segment. A road segment may be associated with a single target trajectory or multiple target trajectories. For example, on a two-lane road, a first target trajectory may be stored to represent the expected travel path along the road in a first direction, and a second target trajectory may be stored to represent the expected travel path along the road in another direction (e.g., opposite to the first direction). Additional target trajectories may be stored relative to a specific road segment. For example, on a multi-lane road, one or more target trajectories may be stored representing the expected travel paths of vehicles in one or more lanes associated with the multi-lane road. In some embodiments, each lane of the multi-lane road may be associated with its own target trajectory. In other embodiments, fewer target trajectories may be stored than the number of lanes present on a multi-lane road. In such cases, vehicles traveling on multi-lane roads can be guided to navigate using any of the stored target trajectories by taking into account the lane offset between the target trajectories and the lane where they are stored (for example, if a vehicle is traveling in the leftmost lane of a three-lane highway and the target trajectories are stored only for the middle lane of the highway, the vehicle can navigate using the target trajectories of the middle lane by taking into account the lane offset between the middle lane and the leftmost lane when generating navigation instructions).

[0229] In some embodiments, the target trajectory may represent the ideal path that the vehicle should take while driving. The target trajectory may be located approximately at the center of, for example, a driving lane. In other cases, the target trajectory may be located at other locations relative to a road segment. For example, the target trajectory may roughly coincide with the center of the road, the edge of the road, or the edge of a lane. In such cases, navigation based on the target trajectory may include a determined offset from which the position will be maintained relative to the target trajectory. Furthermore, in some embodiments, the determined offset from which the position will be maintained relative to the target trajectory may vary depending on the type of vehicle (e.g., a passenger car with two axles may have a different offset along at least a portion of the target trajectory than a truck with more than two axles).

[0230] The sparse map 800 may also include data associated with a plurality of predetermined landmarks 820, which are linked to specific road segments, local maps, etc. As discussed in more detail below, these landmarks can be used in the navigation of autonomous vehicles. For example, in some embodiments, the landmarks can be used to determine the vehicle's current position relative to a stored target trajectory. Using this position information, the autonomous vehicle can adjust its heading to match the direction of the target trajectory at the determined location.

[0231] Multiple road signs 820 can be identified and stored in the sparse map 800 at any suitable interval. In some embodiments, road signs can be stored at a higher density (e.g., every few meters or more). However, in some embodiments, significantly larger road sign spacing values ​​may be used. For example, in the sparse map 800, identified (or recognized) road signs may be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, identified road signs may be located at distances of more than 2 kilometers apart.

[0232] Between landmarks and thus between the determination of the vehicle's position relative to a target trajectory, the vehicle can navigate based on dead reckoning, whereby the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Because errors can accumulate during navigation via dead reckoning, the position determination relative to the target trajectory can become increasingly inaccurate over time. The vehicle can use landmarks (and their known locations) appearing in sparse map 800 to remove errors caused by dead reckoning in the position determination. Thus, the identified landmarks included in sparse map 800 can be used as navigation anchors from which the vehicle's precise position relative to the target trajectory can be determined. Because a certain amount of error can be acceptable in position localization, the identified landmarks need not always be available to the autonomous vehicle. Appropriate navigation, as described above, can also be based on landmark spacing of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more. In some embodiments, a density of one identified landmark per 1 km of road may be sufficient to maintain longitudinal position determination accuracy within 1 m. Therefore, not every potential road sign that appears along the road segment needs to be stored in the sparse map 800.

[0233] Furthermore, in some embodiments, lane markings can be used for vehicle positioning during the mark spacing period. By using lane markings during the mark spacing period, the accumulation of navigation time estimated by dead reckoning can be minimized.

[0234] In addition to the target trajectory and identified road signs, the sparse map 800 may also include information related to various other road features. For example, Figure 9A This illustrates a representation of a curve along a specific road segment that can be stored in a sparse map 800. In some embodiments, a single lane of the road can be modeled using a three-dimensional polynomial description of the left and right sides of the road. Such polynomials representing the left and right sides of a single lane are shown in... Figure 9A As shown in the diagram. Regardless of the number of lanes a road has, it can be followed according to... Figure 9A The road is represented using a polynomial in a similar manner. For example, the left and right sides of a multi-lane road can be represented by a polynomial. Figure 9ASimilar polynomials can be used to represent this, and the markings for intermediate lanes on multi-lane roads (e.g., dashed lines indicating lane boundaries, solid yellow lines indicating boundaries between lanes traveling in different directions) can also be represented using, for example... Figure 9A The polynomial shown is used to represent this.

[0235] like Figure 9A As shown, lane 900 can be represented using a polynomial (e.g., first-order, second-order, third-order, or any suitable order polynomial). For ease of illustration, lane 900 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. Figure 9A As shown, lane 900 includes a left lane 910 and a right lane 920. In some embodiments, more than one polynomial may be used to represent the position of each side of the road or lane boundary. For example, each of the left lane 910 and right lane 920 may be represented by multiple polynomials of any suitable length. In some cases, the polynomials may have a length of approximately 100 m, but other lengths greater or less than 100 m may also be used. Additionally, polynomials may overlap to facilitate a seamless transition in navigation based on polynomials subsequently encountered by the primary vehicle as it travels along the road. For example, each of the left lane 910 and right lane 920 may be represented by multiple third-order polynomials, which are divided into segments of approximately 100 meters in length (an example of a first predetermined range) and overlap approximately 50 meters. The polynomials representing the left lane 910 and right lane 920 may or may not have the same order. For example, in some embodiments, some polynomials may be second-order polynomials, some may be third-order polynomials, and some may be fourth-order polynomials.

[0236] exist Figure 9A In the example shown, the left side 910 of lane 900 is represented by two sets of third-order polynomials. The first set includes polynomial segments 911, 912, and 913. The second set includes polynomial segments 914, 915, and 916. The two sets are substantially parallel to each other, but follow the position of the corresponding side of the road. Polynomial segments 911, 912, 913, 914, 915, and 916 have a length of approximately 100 meters, and adjacent segments in the overlapping series are approximately 50 meters apart. However, as previously mentioned, polynomials of different lengths and different overlaps can also be used. For example, polynomials can have lengths of 500 m, 1 km, or more, and overlaps can vary from 0 to 50 m, 50 m to 100 m, or greater than 100 m. Furthermore, although... Figure 9A The polynomials are shown as polynomials extending in 2D space (e.g., on a paper surface), but it should be understood that these polynomials can represent curves extending in three dimensions (e.g., including a height component) to represent elevation changes of a road segment in addition to XY curvature. Figure 9AIn the example shown, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922 and 923 and a second group having polynomial segments 924, 925 and 926.

[0237] Returning to the target trajectory on the sparse map 800, Figure 9B The diagram shows a three-dimensional polynomial representing the target trajectory of a vehicle traveling along a specific road segment. The target trajectory represents not only the XY path the vehicle should take along the specific road segment, but also the elevation changes the vehicle will encounter while traveling along that segment. Therefore, each target trajectory in the sparse map 800 can be represented by one or more three-dimensional polynomials (e.g., Figure 9B The sparse map 800 can be represented by a three-dimensional polynomial 950. It may include multiple trajectories (e.g., millions or billions or more, to represent the trajectories of vehicles along various segments of highways worldwide). In some embodiments, each target trajectory may correspond to a spline connecting segments of the three-dimensional polynomial.

[0238] Regarding the data footprint of polynomials stored in the sparse map 800, in some embodiments, each cubic polynomial can be represented by four parameters that each require four bytes of data. A suitable representation can be obtained using a cubic polynomial requiring approximately 192 bytes of data per 100 m. This translates to approximately 200 kB per hour in data usage / transmission requirements for a master vehicle traveling at approximately 100 km / hr.

[0239] Sparse maps 800 can use a combination of geometric descriptors and metadata to describe lane networks. The geometry can be described using polynomials or splines as described above. Metadata can describe the number of lanes, special characteristics (e.g., shared lanes for cars), and any other possible sparse labels. The total area occupied by these indicators can be negligible.

[0240] Accordingly, a sparse map according to embodiments of this disclosure may include at least one line representation of road surface features extending along a road segment, each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as described above, at least one line representation of the road surface feature may include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature may include at least one road edge or lane marking. Additionally, as described below with respect to “crowdsourcing,” the road surface feature may be identified through image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0241] As previously described, the sparse map 800 may include multiple predetermined landmarks associated with road segments. Instead of storing actual images of the landmarks and relying on image recognition analysis, such as based on captured and stored images, less data than would originally be required to represent and identify each landmark in the sparse map 800 can be used. The data representing the landmarks can still include sufficient information to describe or identify landmarks along the road. Storing data describing the characteristics of the landmarks instead of actual images of them reduces the size of the sparse map 800.

[0242] Figure 10 Examples of road signs that can be represented in sparse map 800 are shown. Road signs may include any visible and identifiable object along a road segment. Road signs may be selected such that they are fixed and do not change frequently relative to their position and / or content. Road signs included in sparse map 800 can be useful in determining the position of vehicle 200 relative to a target trajectory as it traverses a particular road segment. Examples of road signs may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lampposts, reflectors, etc.), and any other suitable categories. In some embodiments, lane markings on the road may also be included as road signs in sparse map 800.

[0243] Figure 10 Examples of road signs shown include traffic signs, directional signs, roadside fixtures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), yield signs (e.g., yield sign 1005), route number signs (e.g., route number sign 1010), traffic light signs (e.g., traffic light sign 1015), and stop signs (e.g., stop sign 1020). Directional signs may include signs that include one or more arrows indicating one or more directions to different locations. For example, directional signs may include: highway sign 1025 with arrows for guiding vehicles to different roads or locations; exit sign 1030 with arrows for guiding vehicles off the road; and so on. Accordingly, at least one of the plurality of road signs may include a road sign.

[0244] General signs may not be related to traffic. For example, general signs may include billboards used for advertising or welcome signs adjacent to the border between two countries, states, counties, cities, or towns. Figure 10 The general sign 1040 is shown (“Joe’s Restaurant”). While the general sign 1040 is as... Figure 10 The shape shown can be rectangular, but the general mark 1040 can have other shapes, such as square, circle, triangle, etc.

[0245] Road signs may also include roadside fixtures. Roadside fixtures may not be the subject of the sign and may not be traffic- or direction-related. For example, roadside fixtures may include lampposts (e.g., lamppost 1035), utility poles, traffic light poles, etc.

[0246] Road signs may also include beacons that are specifically designed for use in autonomous vehicle navigation systems. For example, such beacons may include freestanding structures placed at predetermined intervals to aid in the navigation of the host vehicle. These beacons may also include visual / graphical information (e.g., icons, badges, barcodes, etc.) added to existing road signs, information that can be identified or recognized by vehicles traveling along the road segment. These beacons may also include electronic components. In such embodiments, electronic beacons (e.g., RFID tags, etc.) may be used to transmit non-visual information to the host vehicle. This information may include, for example, road sign identification and / or road sign location information that the host vehicle can use to determine its position along a target trajectory.

[0247] In some embodiments, landmarks included in the sparse map 800 can be represented by data objects of a predetermined size. The data representing a landmark can include any appropriate parameters for identifying a particular landmark. For example, in some embodiments, landmarks stored in the sparse map 800 can include parameters such as the landmark's physical size (e.g., to support estimating distances to landmarks based on known size / scale), distance to the previous landmark, lateral offset, altitude, type code (e.g., landmark type—which type of directional sign, traffic sign, etc.), GPS coordinates (e.g., to support Global Positioning), and any other appropriate parameters. Each parameter can be associated with a data size. For example, 8 bytes of data can be used to store the landmark size. 12 bytes of data can be used to specify the distance to the previous landmark, lateral offset, and altitude. The type code associated with a landmark (e.g., a directional sign or traffic sign) can require approximately 2 bytes of data. For general landmarks, 50 bytes of data storage can be used to store an image signature that enables recognition of the general landmark. The landmark's GPS location can be associated with 16 bytes of data storage. These data sizes for each parameter are merely examples, and other data sizes may also be used.

[0248] Representing road signs in this way in a sparse map 800 provides a lean solution for efficiently representing road signs in a database. In some embodiments, signs may be referred to as semantic signs and non-semantic signs. Semantic signs may include any class of signs for which a standardized meaning exists (e.g., speed limit signs, warning signs, directional signs, etc.). Non-semantic signs may include any sign not associated with a standardized meaning (e.g., general advertising signs, signs identifying commercial establishments, etc.). For example, each semantic sign may be represented using 38 bytes of data (e.g., 8 bytes for size; 12 bytes for distance, lateral offset, and height to the previous road sign; 2 bytes for type code; and 16 bytes for GPS coordinates). The sparse map 800 may use a labeling system to represent road sign types. In some cases, each traffic sign or directional sign may be associated with its own label, which may be stored in a database as part of the road sign identification. For example, the database may include approximately 1,000 different labels representing various traffic signs and approximately 10,000 different labels representing directional signs. Of course, any appropriate number of labels may be used, and additional labels may be created as needed. In some embodiments, fewer than approximately 100 bytes may be used to represent a general flag (e.g., approximately 86 bytes, including: 8 bytes for size; 12 bytes for distance to the previous landmark, lateral offset, and height; 50 bytes for image signature; and 16 bytes for GPS coordinates).

[0249] Therefore, for semantic road signs that do not require image signatures, the data density impact on sparse map 800 is approximately 760 bytes per kilometer even at a higher road sign density of about one per 50 m (e.g., 20 road signs per kilometer × 38 bytes per road sign = 760 bytes). Even for generic signs that include image signature components, the data density impact is approximately 1.72 kB per kilometer (20 road signs per kilometer × 86 bytes per road sign = 1720 bytes). For semantic road signs, this equates to approximately 76 kB of data usage per hour for a vehicle traveling at 100 km / hr. For generic signs, this equates to approximately 170 kB per hour for a vehicle traveling at 100 km / hr.

[0250] In some embodiments, a general rectangular object (e.g., a rectangular marker) can be represented in the sparse map 800 using no more than 100 bytes of data. The representation of a general rectangular object (e.g., a general marker 1040) in the sparse map 800 may include a compressed image signature (e.g., compressed image signature 1045) associated with the general rectangular object. This compressed image signature can, for example, be used to help identify generic markers, such as road signs. Such a compressed image signature (e.g., image information derived from the actual image data representing the object) avoids the need to store the actual image of the object or to perform comparative image analysis on the actual image to identify the road sign.

[0251] Reference Figure 10 The sparse map 800 may include or store a compressed image signature 1045 associated with the general sign 1040 instead of the actual image of the general sign 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of the general sign 1040, a processor (e.g., image processor 190 or any other processor capable of processing images located on or remotely relative to the host vehicle) may perform image analysis to extract / create a compressed image signature 1045, which includes a unique signature or pattern associated with the general sign 1040. In one embodiment, the compressed image signature 1045 may include a shape, color pattern, brightness pattern, or any other feature that can be extracted from the image of the general sign 1040 to describe the general sign 1040.

[0252] For example, in Figure 10 In the compressed image signature 1045, circles, triangles, and stars can represent areas of different colors. Patterns represented by circles, triangles, and stars can be stored in the sparse map 800, for example, within 50 bytes designated to include the image signature. It is important to note that circles, triangles, and stars are not necessarily intended to indicate that such shapes are stored as part of the image signature. Rather, these shapes are intended conceptually to represent identifiable areas with discernible color differences, text areas, graphic areas, or other variations of characteristics that can be associated with general signs. Such compressed image signatures can be used to identify road signs taking the form of general signs. For example, compressed image signatures can be used to perform same-not-same analysis based on a comparison of the stored compressed image signature with image data captured, for example, using a camera on an autonomous vehicle.

[0253] Accordingly, multiple road signs can be identified through image analysis of multiple images acquired as one or more vehicles traverse a road segment. As described below with respect to “crowdsourcing,” in some embodiments, the image analysis for identifying multiple road signs may include accepting a potential road sign when the ratio of images in which the road sign appears to images in which the road sign does not appear exceeds a threshold. Furthermore, in some embodiments, the image analysis for identifying multiple road signs may include rejecting a potential road sign when the ratio of images in which the road sign does appear to images in which the road sign does not appear exceeds a threshold.

[0254] Returning to the main vehicle allows for navigation of a target trajectory on a specific road segment. Figure 11A The diagram illustrates a polynomial representation of the trajectory captured during the process of constructing or maintaining the sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 may be determined based on two or more reconstructed trajectories previously traversed by a vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be an aggregation of two or more reconstructed trajectories previously traversed by a vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be the average of two or more reconstructed trajectories previously traversed by a vehicle along the same road segment. Other mathematical operations may also be used to construct the target trajectory along the road path based on the reconstructed trajectories collected from vehicles traveling along the road segment.

[0255] like Figure 11A As shown, road segment 1100 can be traveled by multiple vehicles 200 at different times. Each vehicle 200 can collect data related to the path taken by that vehicle along the road segment. The path traveled by a particular vehicle can be determined based on camera data, accelerometer information, speed sensor information and / or GPS information, as well as other potential sources. This data can be used to reconstruct the trajectories of vehicles traveling along the road segment, and based on these reconstructed trajectories, target trajectories (or multiple target trajectories) can be determined for a particular road segment. Such target trajectories can represent the preferred path for a master vehicle (e.g., guided by an autonomous navigation system) traveling along the road segment.

[0256] exist Figure 11A In the example shown, the first reconstructed trajectory 1101 may be determined based on data received from a first vehicle passing through road segment 1100 during a first time period (e.g., day 1), the second reconstructed trajectory 1102 may be obtained from a second vehicle passing through road segment 1100 during a second time period (e.g., day 2), and the third reconstructed trajectory 1103 may be obtained from a third vehicle passing through road segment 1100 during a third time period (e.g., day 3). Each trajectory 1101, 1102, and 1103 may be represented by a polynomial (e.g., a three-dimensional polynomial). It should be noted that in some embodiments, any of the reconstructed trajectories may be mounted on a vehicle passing through road segment 1100.

[0257] As a supplement or alternative, such reconstructed trajectories can be determined on the server side based on information received from vehicles traversing road segment 1100. For example, in some embodiments, vehicles 200 may transmit data related to their movement along road segment 1100 (e.g., steering angle, heading, time, position, speed, sensed road geometry and / or sensed road signs, etc.) to one or more servers. The server can reconstruct the trajectory of vehicle 200 based on the received data. The server may also generate target trajectories based on first, second, and third trajectories 1101, 1102, and 1103 for navigation of autonomous vehicles subsequently traveling along the same road segment 1100. While target trajectories may be associated with a single previous crossing of the road segment, in some embodiments, each target trajectory included in the sparse map 800 may be determined based on two or more reconstructed trajectories of vehicles traversing the same road segment. Figure 11A In this context, the target trajectory is represented by 1110. In some embodiments, the target trajectory 1110 may be generated based on the average of the first, second, and third trajectories 1101, 1102, and 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 may be an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories.

[0258] Figure 11B and Figure 11C This further illustrates the concept of a target trajectory associated with road segments existing within geographic region 1111. For example... Figure 11B As shown, a first road segment 1120 within geographic area 1111 may include a multi-lane road comprising two lanes 1122 designated for vehicles traveling in a first direction and two additional lanes 1124 designated for vehicles traveling in a second direction opposite to the first direction. Lanes 1122 and lanes 1124 may be separated by double yellow lines 1123. Geographic area 1111 may also include branch road segments 1130 intersecting with road segment 1120. Road segment 1130 may include two-lane roads, each lane designated for a different direction of travel. Geographic area 1111 may also include other road features such as stop lines 1132, stop signs 1134, speed limit signs 1136, and hazard signs 1138.

[0259] like Figure 11CAs shown, the sparse map 800 may include a local map 1140, which includes a road model for assisting autonomous navigation of vehicles within geographic region 1111. For example, the local map 1140 may include target trajectories for one or more lanes associated with road segments 1120 and / or 1130 within geographic region 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that are accessible or relied upon by the autonomous vehicle when crossing lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that are accessible or relied upon by the autonomous vehicle when crossing lane 1124. Furthermore, the local map 1140 may include target trajectories 1145 and / or 1146 that are accessible or relied upon by the autonomous vehicle when crossing road segment 1130. Target trajectory 1147 represents the preferred path that the autonomous vehicle should follow when transitioning from lane 1120 (and specifically, relative to target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (and specifically, relative to target trajectory 1145 associated with the first side of road segment 1130). Similarly, target trajectory 1148 represents the preferred path that the autonomous vehicle should follow when transitioning from road segment 1130 (and specifically, relative to target trajectory 1146) to a portion of road segment 1124 (and specifically, as shown, relative to target trajectory 1143 associated with the left lane of lane 1124).

[0260] The sparse map 800 may also include representations of other road-related features associated with geographic region 1111. For example, the sparse map 800 may also include representations of one or more road signs identified in geographic region 1111. Such road signs may include a first road sign 1150 associated with stop line 1132, a second road sign 1152 associated with stop sign 1134, a third road sign associated with speed limit sign 1154, and a fourth road sign 1156 associated with hazard sign 1138. Such road signs can, for example, help an autonomous vehicle determine its current position relative to any of the indicated target trajectories, allowing the vehicle to adjust its heading to match the direction of the target trajectory at the determined position.

[0261] In some embodiments, the sparse map 800 may also include road signature profiles. Such road signature profiles may be associated with any identifiable / measurable change in at least one parameter of the associated road. For example, in some cases, such profiles may be associated with changes in road surface information, such as changes in surface roughness of a particular road segment, changes in road width of a particular road segment, changes in the distance between dashed lines drawn along a particular road segment, changes in road curvature along a particular road segment, etc. Figure 11DAn example of a road signature profile 1160 is shown. While profile 1160 may represent any of the parameters mentioned above, in one example, profile 1160 may represent a measure of road surface roughness obtained by monitoring one or more sensors that provide outputs indicating the amount of suspension displacement when a vehicle travels on a particular road segment.

[0262] Alternatively or concurrently, profile 1160 may represent changes in road width, as determined based on image data obtained from a camera on a vehicle traveling along a specific road segment. Such profiles can be useful, for example, in determining a specific position of an autonomous vehicle relative to a specific target trajectory. That is, as the autonomous vehicle traverses a road segment, it can measure a profile associated with one or more parameters related to that road segment. If the measured profile can be correlated / matched with a predetermined profile that plots the changes in parameters relative to the position along the road segment, the measured and predetermined profiles (e.g., by overlapping corresponding portions of the measured and predetermined profiles) can be used to determine the current position along the road segment and the current position relative to the target trajectory of the road segment.

[0263] In some embodiments, the sparse map 800 may include different trajectories based on different characteristics associated with the user of the autonomous vehicle, environmental conditions, and / or other driving-related parameters. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or profiles. The sparse map 800 including such different trajectories may be provided to different autonomous vehicles of different users. For example, some users may prefer to avoid toll roads, while others may prefer to take the shortest or fastest route, regardless of whether there are toll roads on the route. The disclosed system may generate different sparse maps with different trajectories based on such different user preferences or profiles. As another example, some users may prefer to drive in the fast lane, while others may prefer to always stay in the center lane.

[0264] Different trajectories can be generated and included in the sparse map 800 based on different environmental conditions (e.g., day and night, snow, rain, fog, etc.). Autonomous vehicles driving under different environmental conditions can be provided with sparse maps 800 generated based on these different environmental conditions. In some embodiments, a camera device provided on the autonomous vehicle can detect environmental conditions and provide this information to a server that generates and provides the sparse map. For example, the server can generate or update the already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. Updates to the sparse map 800 based on environmental conditions can be performed dynamically as the autonomous vehicle travels along the road.

[0265] Other driving-related parameters can also be used as a basis for generating different sparse maps and providing them to different autonomous vehicles. For example, when an autonomous vehicle is traveling at high speed, turning may be more precise. Trajectories associated with specific lanes rather than roads can be included in the sparse map 800, allowing the autonomous vehicle to stay within a specific lane while following a specific trajectory. When an image captured by a camera on the autonomous vehicle indicates that the vehicle has drifted out of its lane (e.g., crossed lane markings), an action can be triggered inside the vehicle to bring it back to the designated lane along the specific trajectory.

[0266] Crowdsourced sparse map

[0267] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, the disclosed systems and methods can use crowdsourced data to generate a sparse map that one or more autonomous vehicles can use to navigate along a road system. As used herein, “crowdsourcing” means receiving data from various vehicles (e.g., autonomous vehicles) traveling on a road segment at different times, and this data is used to generate and / or update a road model. The model can then be transmitted to vehicles or other vehicles subsequently traveling along the road segment to assist the autonomous vehicle in navigation. The road model may include multiple target trajectories representing preferred paths that the autonomous vehicle should follow when traversing the road segment. The target trajectories may be the same as reconstructed actual trajectories collected from vehicles traversing the road segment, which may be transmitted from the vehicles to a server. In some embodiments, the target trajectories may differ from the actual trajectories taken by one or more vehicles when previously traversing the road segment. The target trajectories may be generated based on the actual trajectories (e.g., by averaging or any other suitable operation).

[0268] The vehicle trajectory data that a vehicle can upload to the server can correspond to the vehicle's actual reconstructed trajectory, or it can correspond to a recommended trajectory, which can be based on or related to the vehicle's actual reconstructed trajectory, but may differ from it. For example, a vehicle can modify its actual reconstructed trajectory and submit (e.g., a recommendation) the modified actual trajectory to the server. The road model can use the recommended modified trajectory as the target trajectory for other vehicles' autonomous navigation.

[0269] In addition to trajectory information, other information that may be used in constructing a sparse data map 800 may include information related to potential landmark candidates. For example, through information crowdsourcing, the disclosed systems and methods can identify potential landmarks in the environment and refine landmark locations. Landmarks can be used by the navigation systems of autonomous vehicles to determine and / or adjust the positions of vehicles along the target trajectory.

[0270] A reconstructed trajectory that can be generated when a vehicle travels along a road can be obtained by any suitable method. In some embodiments, a reconstructed trajectory can be formed by stitching together segments of the vehicle's motion using, for example, self-motion estimation (e.g., a photographic device and therefore, three-dimensional translation and three-dimensional rotation of the vehicle's body). Rotation and translation estimations can be determined based on analysis of images captured by one or more image capture devices along with information from other sensors or devices, such as inertial sensors and velocity sensors. For example, inertial sensors may include accelerometers or other suitable sensors configured to measure changes in the translation and / or rotation of the vehicle body. The vehicle may include a velocity sensor that measures the vehicle's speed.

[0271] In some embodiments, the self-motion of the photographic device (and therefore the vehicle body) can be estimated based on optical flow analysis of the captured images. Optical flow analysis of the image sequence identifies pixel movement from the image sequence and determines the vehicle's motion based on the identified movement. The self-motion can be integrated over time and along road segments to reconstruct a trajectory associated with the road segments the vehicle has already followed.

[0272] Data collected from multiple drives of multiple vehicles along a road segment at different times (e.g., reconstructed trajectories) can be used to construct a road model (e.g., including target trajectories) contained in a sparse map 800. Data collected from multiple drives of multiple vehicles along a road segment at different times can also be averaged to increase the model's accuracy. In some embodiments, data related to road geometry and / or road signs can be received from multiple vehicles traveling through a common road segment at different times. This data received from different vehicles can be combined to generate and / or update the road model.

[0273] The geometry of the reconstructed trajectory (and target trajectory) along the road segment can be represented by a curve in three-dimensional space, which can be a spline connecting three-dimensional polynomials. The reconstructed trajectory curve can be determined from a video stream captured by a camera mounted on the vehicle or from the analysis of multiple images. In some embodiments, a position is identified in each frame or image a few meters ahead of the vehicle's current position. This position is the position the vehicle is expected to reach within a predetermined time period. This operation can be repeated frame by frame, while the vehicle can simultaneously calculate the self-motion (rotation and translation) of the camera. In each frame or image, a short-range model of the expected path is generated by the vehicle in a reference frame attached to the camera. The short-range models can be stitched together to obtain a three-dimensional model of the road in a coordinate system, which can be arbitrary or predetermined. The three-dimensional model of the road can then be fitted using splines, which can include or connect one or more polynomials of appropriate order.

[0274] To infer short-range road models in each frame, one or more detection modules can be used. For example, a bottom-up lane detection module can be used. The bottom-up lane detection module can be useful when drawing lane markings on a road. This module finds edges in the image and assembles them to form lane markings. A second module can be used in conjunction with the bottom-up lane detection module. The second module is an end-to-end deep neural network that can be trained to predict the correct short-range path from the input image. In both modules, the road model can be detected in the image coordinate system and transformed into a three-dimensional space that can be virtually attached to the photographic device.

[0275] While reconstructed trajectory modeling methods may introduce accumulated errors (including noise components) due to the integration of self-motion over long time periods, such errors can be insignificant because the generated model provides sufficient accuracy for navigation on the local scale. Furthermore, it is possible to eliminate integration errors by using external information sources, such as satellite imagery or geodesy. For example, the disclosed systems and methods can use a GNSS receiver to eliminate accumulated errors. However, GNSS positioning signals may not necessarily be available and accurate. The disclosed systems and methods enable steering applications that depend weakly on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals can be limited. For example, in some embodiments, the disclosed system may use GNSS signals solely for the purpose of facilitating database indexing.

[0276] In some embodiments, the range scale (e.g., local scale) associated with the autonomous vehicle navigation and steering application can be approximately 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances can be used because the geometric road model is primarily used for two purposes: planning the trajectory ahead and locating the vehicle on the road model. In some embodiments, when the control algorithm maneuvers the vehicle to a target point located 1.3 seconds ahead (or any other time, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.), the planning task can use the model with a typical range of 40 meters ahead (or any other suitable distance ahead, such as 20 meters, 30 meters, 50 meters). The localization task uses the road model with a typical range of 60 meters behind the vehicle (or any other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.) according to a method described in more detail in another section, referred to as "tail alignment." The disclosed systems and methods can generate a geometric model that is sufficiently accurate for a specific range (e.g., 100 meters) such that the planned trajectory will not deviate from the lane center by more than, for example, 30 cm.

[0277] As described above, a three-dimensional road model can be constructed by detecting short segments and stitching them together. This stitching can be achieved by calculating a six-degree-of-freedom motion model using video and / or images captured by a camera, data from inertial sensors reflecting vehicle motion, and the main vehicle's speed signal. The accumulated error can be sufficiently small for a local scale, for example, approximately 100 meters. This entire process can be completed in a single drive through a specific road segment.

[0278] In some embodiments, multiple drives can be used to average the resulting model and further increase its accuracy. The same vehicle may drive the same route multiple times, or multiple vehicles may send their collected model data to a central server. In any case, a matching process can be performed to identify overlapping models and achieve averaging to generate a target trajectory. Once convergence criteria are met, the resulting model (e.g., including the target trajectory) can be used for maneuvering. Subsequent drives can be used for further model improvements and to adapt to infrastructure changes.

[0279] Sharing driving experiences (e.g., sensed data) among multiple vehicles becomes feasible when they are connected to a central server. Each vehicle client can store a partial copy of a common road model, which may be related to its current location. The bidirectional update process between the vehicle and the server can be performed by both the vehicle and the server. The small footprint concept described above enables the disclosed system and method to perform bidirectional updates using very little bandwidth.

[0280] Information related to potential road signs can also be identified and forwarded to a central server. For example, the disclosed systems and methods can determine one or more physical properties of potential road signs based on one or more images including the road sign. Physical properties may include the physical size of the road sign (e.g., height, width), the distance from the vehicle to the road sign, the distance between the road sign and the preceding road sign, the lateral position of the road sign (e.g., the position of the road sign relative to the driving lane), the GPS coordinates of the road sign, the type of road sign, the identification of text on the road sign, etc. For example, a vehicle can analyze one or more images captured by a camera to detect potential road signs (e.g., speed limit signs).

[0281] Vehicles can determine the distance from a road sign based on the analysis of one or more images. In some embodiments, the distance can be determined based on the analysis of the road sign's image using appropriate image analysis methods (e.g., scaling methods and / or optical flow methods). In some embodiments, the disclosed systems and methods can be configured to determine the type or classification of potential road signs. If a vehicle determines that a potential road sign corresponds to a predetermined type or classification stored in a sparse map, it may be sufficient for the vehicle to transmit an indication of the road sign's type or classification along with its location to a server. The server may store such indications. Other vehicles may subsequently capture images of the road sign, process the images (e.g., using a classifier), and compare the results from the processed images with indications of the road sign's type stored in the server. Various types of road signs may exist, and different types of road signs may be associated with different types of data to be uploaded to and stored in the server; different processing on the vehicle may detect road signs and transmit road sign-related information to the server; and systems on the vehicle may receive road signs from the server and use the road sign data to identify road signs in autonomous navigation.

[0282] In some embodiments, multiple autonomous vehicles traveling on a road segment can communicate with a server. A vehicle (or client) can generate curves describing its driving in an arbitrary coordinate system (e.g., through self-motion integration). Vehicles can detect road signs and position them within the same frame. Vehicles can upload curves and road signs to the server. The server can collect data from the vehicles across multiple drives and generate a unified road model. For example, as follows... Figure 19 The server can use the uploaded curves and road signs to generate a sparse map with a uniform road model.

[0283] The server can also distribute the model to clients (e.g., vehicles). For example, the server can distribute sparse maps to one or more vehicles. The server can update the model continuously or periodically as it receives new data from vehicles. For example, the server can process new data to assess whether the data contains information that should trigger an update or the creation of new data on the server. The server can distribute the updated model or updates to vehicles to provide autonomous vehicle navigation.

[0284] The server may use one or more criteria to determine whether new data received from vehicles should trigger an update to the model or the creation of new data. For example, when new data indicates that a previously identified road sign at a particular location no longer exists or has been replaced by another road sign, the server may determine that the new data should trigger an update to the model. As another example, when new data indicates that a road segment is closed, and this is confirmed by data from other vehicles, the server may determine that the new data should trigger an update to the model.

[0285] The server can distribute the updated model (or an updated portion of the model) to one or more vehicles traveling on the road segment associated with the update. The server can also distribute the updated model to vehicles that will travel on the road segment associated with the update or whose planned journey includes that road segment. For example, even if an autonomous vehicle travels along another road segment before reaching the road segment associated with the update, the server can distribute the updated or already updated model to that vehicle before the autonomous vehicle reaches that road segment.

[0286] In some embodiments, a remote server may collect trajectories and road signs from multiple clients, such as vehicles traveling along a public road segment. The server can use the road signs to match curves and create an average road model based on the trajectories collected from the multiple vehicles. The server may also calculate a graph of the road and the most probable path at each node or junction of the road segment. For example, the remote server may align trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0287] The server can average the properties of road signs received from multiple vehicles traveling along a common road segment, such as the distance between one road sign and another (e.g., the previous road sign along the road segment) measured by multiple vehicles, to determine arc length parameters and support path-based positioning and speed calibration for each customer vehicle. The server can average the physical dimensions of road signs measured by multiple vehicles traveling along a common road segment and recognizing the same road sign. The average physical dimensions can be used to support distance estimation, such as the distance from a vehicle to a road sign. The server can average the lateral position of road signs measured by multiple vehicles traveling along a common road segment and recognizing the same road sign (e.g., from the lane the vehicle is traveling in to the location of the road sign). The average lateral position can be used to support lane assignment. The server can average the GPS coordinates of road signs measured by multiple vehicles traveling along the same road segment and recognizing the same road sign. The average GPS coordinates of road signs can be used to support global localization or positioning of road signs in the road model.

[0288] In some embodiments, the server may identify model changes based on data received from the vehicle, such as construction, detours, new signs, sign removal, etc. The server may update the model continuously, periodically, or instantaneously as it receives new data from the vehicle. The server may distribute updated or already updated models to the vehicle for use in providing autonomous navigation. For example, as discussed further below, the server may use crowdsourced data to filter out “virtual” road signs detected by the vehicle.

[0289] In some embodiments, the server may analyze driver interventions during autonomous driving. The server may analyze data received from the vehicle at the time and location of the intervention and / or data received prior to the intervention. The server may identify portions of the data that caused or is closely related to the intervention, such as data indicating the establishment of a temporary lane closure or data indicating pedestrians in the road. The server may update the model based on the identified data. For example, the server may modify one or more trajectories stored in the model.

[0290] Figure 12 This is a diagram of a system that uses crowdsourcing to generate sparse maps (and uses crowdsourced sparse maps for distribution and navigation). Figure 12 The diagram shows a road segment 1200 comprising one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 may travel on road segment 1200 at the same time or at different times (although...). Figure 12 (These are shown as vehicles appearing on road segment 1200 at the same time). At least one of vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. For the sake of simplicity in this example, all vehicles 1205, 1210, 1215, 1220, and 1225 are assumed to be autonomous vehicles.

[0291] Each vehicle may be similar to the vehicles disclosed in other embodiments (e.g., vehicle 200) and may include components or devices contained in or associated with the vehicles disclosed in other embodiments. Each vehicle may be equipped with an image capture device or a photographic device (e.g., image capture device 122 or photographic device 122). Each vehicle may communicate with a remote server 1230 via one or more networks (e.g., via cellular networks and / or the Internet) through a wireless communication path 1235 (as shown by dashed lines). Each vehicle may transmit data to and receive data from the server 1230. For example, the server 1230 may collect data from multiple vehicles traveling on road segment 1200 at different times and may process the collected data to generate an autonomous vehicle road navigation model or an update to the model. The server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to vehicles (which transmit data to the server 1230). The server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to other vehicles subsequently traveling on road segment 1200.

[0292] When vehicles 1205, 1210, 1215, 1220, and 1225 travel on road segment 1200, navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 may be transmitted to server 1230. In some embodiments, the navigation information may be associated with the common road segment 1200. The navigation information may include a trajectory associated with each vehicle as each of vehicles 1205, 1210, 1215, 1220, and 1225 travels through road segment 1200. In some embodiments, the trajectory may be reconstructed based on data sensed by various sensors and devices provided on vehicle 1205. For example, the trajectory may be reconstructed based on at least one of accelerometer data, speed data, road sign data, road geometry or profile data, vehicle positioning data, and self-motion data. In some embodiments, the trajectory may be reconstructed based on data from inertial sensors (e.g., accelerometers) and the speed of vehicle 1205 sensed by speed sensors. Additionally, in some embodiments, the trajectory may be determined by a processor on each of vehicles 1205, 1210, 1215, 1220, and 1225 based on the self-motion sensed by the camera device, which may indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The self-motion of the camera device (and therefore the vehicle body) may be determined from the analysis of one or more images captured by the camera device.

[0293] In some embodiments, the trajectory of vehicle 1205 may be determined by a processor provided on vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 may receive data sensed by various sensors and devices provided in vehicle 1205 and determine the trajectory based on the data received from vehicle 1205.

[0294] In some embodiments, navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 may include data relating to road surface, road geometry, or road profile. The geometry of road segment 1200 may include lane structure and / or road markings. Lane structure may include the total number of lanes in road segment 1200, lane types (e.g., one-way lanes, two-way lanes, driving lanes, overtaking lanes, etc.), lane markings, lane widths, etc. In some embodiments, navigation information may include lane assignments, such as which lane a vehicle is traveling in among multiple lanes. For example, a lane assignment may be associated with the value "3," indicating that the vehicle is traveling in the third lane from the left or right. As another example, a lane assignment may be associated with the text value "center lane," indicating that the vehicle is traveling in the center lane.

[0295] Server 1230 may store navigation information on a non-transitory computer-readable medium (e.g., hard disk drive, compact optical disc, magnetic tape, memory, etc.). Server 1230 may generate (e.g., via a processor included in server 1230) at least a portion of an autonomous vehicle road navigation model of a common road segment 1200 based on navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225, and may store this model as part of a sparse map. Server 1230 may determine a trajectory associated with each lane based on crowdsourced data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling in lanes of the road segment at different times. Server 1230 may generate an autonomous vehicle road navigation model or a portion of the model (e.g., an updated portion) based on the multiple trajectories determined according to the crowdsourced navigation data. Server 1230 may transmit the model, or an updated portion thereof, to one or more of the autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or to any other autonomous vehicle subsequently traveling on the road segment, to update the existing autonomous vehicle road navigation model provided in the vehicle's navigation system. The autonomous vehicle road navigation model can be used by autonomous vehicles for autonomous navigation along the public road segment 1200.

[0296] As mentioned above, autonomous vehicle road navigation models can be included in sparse maps (e.g., Figure 8 The sparse map 800 shown may include sparse records of data relating to road geometry and / or road signs along a road, which may provide sufficient information to guide autonomous vehicle navigation without requiring excessive data storage. In some embodiments, the autonomous vehicle road navigation model may be stored separately from the sparse map 800 and may use map data from the sparse map 800 when the model is executed for navigation. In some embodiments, the autonomous vehicle road navigation model may use the map data contained in the sparse map 800 to determine a target trajectory along road segment 1200 for guiding autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles traveling along road segment 1200 thereafter. For example, when the autonomous vehicle road navigation model is executed by a processor included in the navigation system of vehicle 1205, the model may enable the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory contained in the sparse map 800 to verify and / or correct the current driving route of vehicle 1205.

[0297] In autonomous vehicle road navigation models, the geometry of road features or target trajectories can be encoded using curves in three-dimensional space. In one embodiment, the curve can be a three-dimensional spline, comprising one or more splines connecting three-dimensional polynomials. As those skilled in the art will understand, a spline can be a numerical function defined piecewise by a series of polynomials for fitting data. Splines used to fit the three-dimensional geometry of a road can include linear splines (first order), quadratic splines (second order), cubic splines (third order), or any other splines (other orders) or combinations thereof. Splines can include one or more three-dimensional polynomials of different orders connecting (e.g., fitting) data points of the three-dimensional geometry of a road. In some embodiments, the autonomous vehicle road navigation model can include a three-dimensional spline corresponding to a target trajectory along a common road segment (e.g., segment 1200) or a lane of segment 1200.

[0298] As described above, the autonomous vehicle road navigation model included in the sparse map may include other information, such as the identification of at least one road sign along road segment 1200. The road sign is visible within the field of view of a camera (e.g., camera 122) mounted on each of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 may capture an image of the road sign. A processor (e.g., processor 180, 190, or processing unit 110) provided on vehicle 1205 may process the image of the road sign to extract its identification information. The road sign identification information, rather than the actual image of the road sign, may be stored in the sparse map 800. The road sign identification information may require significantly less storage space than the actual image. Other sensors or systems (e.g., a GPS system) may also provide some identification information about the road sign (e.g., the location of the road sign). Road signs may include at least one of the following: traffic signs, arrow markings, lane markings, dashed lane markings, traffic lights, stop lines, directional markings (e.g., highway exit signs with directional indicators, highway signs with arrows pointing in different directions or locations), road beacons, or lampposts. Road beacons represent devices (e.g., RFID devices) installed along a road segment that transmit or reflect signals to receivers installed on vehicles, such that when a vehicle passes the device, the beacon received by the vehicle and the device's location (e.g., determined from the device's GPS location) can be used as road signs to be included in the autonomous vehicle road navigation model and / or sparse map 800.

[0299] The identification of at least one road sign may include the location of at least one road sign. The location of the road sign may be determined based on position measurements performed using sensor systems (e.g., GPS, inertial positioning systems, road beacons, etc.) associated with multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of the road sign may be determined by averaging position measurements detected, collected, or received by sensor systems on different vehicles 1205, 1210, 1215, 1220, and 1225 over multiple driving operations. For example, vehicles 1205, 1210, 1215, 1220, and 1225 may transmit position measurement data to server 1230, which may average the position measurements and use the average position measurement as the location of the road sign. The location of the road sign may be continuously refined by measurements received from the vehicles in subsequent driving operations.

[0300] The identification of a road sign may include its size. A processor provided on a vehicle (e.g., 1205) can estimate the physical size of the road sign based on image analysis. Server 1230 can receive multiple estimates of the physical size of the same road sign from different vehicles through different drivers. Server 1230 can average the different estimates to arrive at the physical size of the road sign and store that road sign size in the road model. The physical size estimate can be used to further determine or estimate the distance from the vehicle to the road sign. The distance to the road sign can be estimated based on the vehicle's current speed and an extended scale according to the position of the road sign in the image relative to the extended focus of the camera. For example, the distance to the road sign can be estimated as Z = V × dt × R / D, where V is the vehicle's speed, R is the distance from the road sign in the image to the extended focus from time t1, and D is the change in distance of the road sign in the image from t1 to t2. dt represents (t2 - t1). For example, the distance to a road sign can be estimated using Z = V × dt × R / D, where V is the vehicle speed, R is the distance between the image road sign and the extended focal point, dt is the time interval, and D is the image displacement of the road sign along the epipolar line. Other equivalent equations (e.g., Z = V × ω / Δω) can be used to estimate the distance to a road sign. Here, V is the vehicle speed, ω is the image length (e.g., object width), and Δω is the change in that image length per unit time.

[0301] When the physical size of a landmark is known, the distance to the landmark can be determined based on the following formula: Z = f × W / ω, where f is the focal length, W is the size of the landmark (e.g., height or width), and ω is the number of pixels the landmark leaves the image. From the above formula, ΔZ = f × W × Δω / ω can be used. 2The change in distance Z is calculated using f×ΔW / ω, where ΔW decays to zero by averaging, and Δω is the number of pixels representing the precision of the bounding box in the image. The estimated physical size of the landmark can be calculated by averaging multiple observations on the server side. The error introduced in distance estimation can be very small. There are two sources of error that can occur when using the above formula: ΔW and Δω. Their share of the distance error is expressed as ΔZ = f×W×Δω / ω. 2 + f×ΔW / ω is given. However, ΔW is obtained by averaging the decay to zero; therefore, ΔZ is determined by Δω (e.g., the inaccuracy of the bounding box in the image).

[0302] For road signs of unknown size, the distance to the road sign can be estimated by tracking feature points on the road sign between consecutive frames. For example, certain features appearing on a speed limit sign can be tracked between two or more image frames. Based on these tracked features, a distance distribution for each feature point can be generated. The distance estimate can be extracted from the distance distribution. For example, the most frequently occurring distance in the distance distribution can be used as a distance estimate. As another example, the mean of the distance distribution can be used as a distance estimate.

[0303] Figure 13 An example autonomous vehicle road navigation model is shown, represented by multiple three-dimensional splines 1301, 1302, and 1303. Figure 13 Curves 1301, 1302, and 1303 shown are for illustrative purposes only. Each spline may include one or more three-dimensional polynomials connecting multiple data points 1310. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or a combination of any suitable polynomials with different orders. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to road signs (e.g., road sign size, location, and identification information) and / or road signature profiles (e.g., road geometry, road roughness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 may be associated with road sign-related data, while other data points may be associated with data related to road signature profiles.

[0304] Figure 14The diagram illustrates raw location data 1410 (e.g., GPS data) received from five individual drives. A drive can be separated from another drive if it is traversed by a single vehicle at the same time, by the same vehicle at a separate time, or by a single vehicle at a separate time. To account for errors in the location data 1410 and the different positions of vehicles within the same lane (e.g., one vehicle may be driving closer to the left side of the lane than another), server 1230 may use one or more statistical techniques to generate a map outline 1420 to determine whether variations in the raw location data 1410 represent actual differences or statistical errors. Each path within the outline 1420 can be linked to the raw data 1410 that forms that path. For example, the path between A and B within the outline 1420 is linked to the raw data 1410 from drives 2, 3, 4, and 5, but not from drive 1. The outline 1420 may not be detailed enough to be used for vehicle navigation (e.g., because it combines drives from multiple lanes on the same road, unlike the splines described above), but it can provide useful topological information and can be used to define intersections.

[0305] Figure 15 The example shown illustrates how additional detail can be generated from a sparse map within a map outline segment (e.g., segments A to B within outline 1420). Figure 15 As shown, data (e.g., self-motion data, road marking data, etc.) can be represented as a function of the driving position S (or S1 or S2). Server 1230 can identify road signs in a sparse map by recognizing unique matches between road signs 1501, 1503, and 1505 of driving 1510 and road signs 1507 and 1509 of driving 1520. This matching algorithm can produce identifiers for road signs 1511, 1513, and 1515. However, those skilled in the art will know that other matching algorithms can be used. For example, probabilistic optimization can be used instead of or in combination with unique matching. Server 1230 can longitudinally align driving to align matching road signs. For example, server 1230 can select one driving (e.g., driving 1520) as a reference driving and then offset and / or elastically stretch other (one or more) drivings (e.g., driving 1510) for alignment.

[0306] Figure 16 This shows an example of aligned landmark data used in sparse maps. Figure 16 In the example, road sign 1610 includes road signs. Figure 16 The example further illustrates data from multiple drivers: 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In Figure 16In the example, the data from driver 1613 consists of “virtual” road signs, and server 1230 can identify it in this way because no drivers 1601, 1603, 1605, 1607, 1609, and 1611 include the identifier of a road sign near the identified road sign in driver 1613. Accordingly, server 1230 can accept a potential road sign when the ratio of images in which the road sign appears to images in which the road sign does not appear exceeds a threshold, and / or can reject a potential road sign when the ratio of images in which the road sign does appear to images in which the road sign does not appear exceeds a threshold.

[0307] Figure 17 A system 1700 is shown for generating driving data that can be used to crowdsource sparse maps. For example... Figure 17 As shown, system 1700 may include a camera device 1701 and a positioning device 1703 (e.g., a GPS locator). The camera device 1701 and positioning device 1703 may be mounted on a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). The camera device 1701 may generate multiple types of data, such as self-motion data, traffic sign data, road data, etc. The camera data and location data may be segmented into driving segments 1705. For example, each driving segment 1705 may have camera data and location data from a driving distance of less than 1 km.

[0308] In some embodiments, system 1700 may remove redundancy in driving segment 1705. For example, if a road sign appears in multiple images from camera device 1701, system 1700 may strip redundant data so that driving segment 1705 contains only a copy of the road sign's location and any metadata associated with the road sign. As another example, if lane markings appear in multiple images from camera device 1701, system 1700 may strip redundant data so that driving segment 1705 contains only a copy of the lane marking's location and any metadata associated with the lane markings.

[0309] System 1700 also includes a server (e.g., server 1230). Server 1230 can receive driving segments 1705 from the vehicle and recombine the driving segments 1705 into a single drive 1707. This arrangement allows for reduced bandwidth requirements when transmitting data between the vehicle and the server, while also allowing the server to store data related to the entire driving process.

[0310] Figure 18 Further configurations for crowdsourced sparse maps are shown. Figure 17 System 1700. Like Figure 17Similarly, system 1700 includes vehicle 1810, which uses, for example, a camera (which generates, for example, self-motion data, traffic sign data, road data, etc.) and a positioning device (for example, a GPS locator) to capture driving data. Figure 17 Similar to the previous example, vehicle 1810 divides the collected data into driving segments (…). Figure 18 The values ​​are shown as "DS1 1", "DS2 1", and "DSN 1". Server 1230 then receives the driving segment and reconstructs the driving segment from the received segment. Figure 18 (The text is marked as "Driving 1").

[0311] like Figure 18 As further shown, system 1700 also receives data from an attached vehicle. For example, vehicle 1820 also uses, for example, a camera (which generates, for example, self-motion data, traffic sign data, road data, etc.) and a positioning device (e.g., a GPS locator) to capture driving data. Similar to vehicle 1810, vehicle 1820 segments the collected data into driving segments ( Figure 18 The values ​​are shown as "DS1 2", "DS2 2", and "DSN 2". Server 1230 then receives the driving segment and reconstructs the driving segment from the received segment. Figure 18 (Indicated as "Driving 2"). Any number of additional vehicles can be used. For example, Figure 18 It also includes "vehicle N", which captures driving data and segments it into driving segments ( Figure 18 The data is displayed as "DS1 N", "DS2 N", and "DSN N", and is sent to server 1230 for reconstruction into a driving ( Figure 18 (This is shown as "Driving N" in the middle).

[0312] like Figure 18 As shown, server 1230 can use reconstructed driving data (e.g., "driving 1", "driving 2", and "driving N") collected from multiple vehicles (e.g., "car 1" (also labeled 1810), "car 2" (also labeled 1820), and "car N") to construct a sparse map.

[0313] Figure 19 This is a flowchart illustrating an example process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 may be executed by one or more processing devices included in server 1230.

[0314] Process 1900 may include receiving multiple images acquired as one or more vehicles traverse the road segment (step 1905). Server 1230 may receive images from a camera included within one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 may also receive stripped image data, which has been deredundanted by a processor on vehicle 1205, as described above for... Figure 17 As stated above.

[0315] Process 1900 may further include identifying at least one line representation of road surface features extending along a road segment based on multiple images (step 1910). Each line representation may represent a path along the road segment that substantially corresponds to the road surface features. For example, server 1230 may analyze environmental images received from camera device 122 to identify road edges or lane markings and determine a driving trajectory along road segment 1200 associated with the road edges or lane markings. In some embodiments, the trajectory (or line representation) may include splines, polynomial representations, or curves. Server 1230 may determine the driving trajectory of vehicle 1205 based on the camera device's self-motion (e.g., three-dimensional translation and / or three-dimensional rotational motion) received in step 1905.

[0316] Process 1900 may also include identifying multiple road signs associated with a road segment based on multiple images (step 1910). For example, server 1230 may analyze environmental images received from camera device 122 to identify one or more road signs (e.g., road signs along road segment 1200). Server 1230 may use analysis of multiple images acquired as one or more vehicles traverse the road segment to identify road signs. To enable crowdsourcing, the analysis may include rules relating to accepting and rejecting potential road signs associated with the road segment. For example, the analysis may include accepting a potential road sign when the ratio of images in which the road sign appears to images in which the road sign does not appear exceeds a threshold, and / or rejecting a potential road sign when the ratio of images in which the road sign does not appear to images in which the road sign appears exceeds a threshold.

[0317] Process 1900 may include other operations or steps performed by server 1230. For example, navigation information may include a target trajectory of a vehicle traveling along a road segment, and process 1900 may include server 1230 clustering vehicle trajectories associated with multiple vehicles traveling on the road segment, and determining a target trajectory based on the clustered vehicle trajectories, as discussed in more detail below. Clustering vehicle trajectories may include server 1230 clustering multiple trajectories associated with vehicles traveling on the road segment into multiple clusters based on at least one of the vehicle's absolute heading or the vehicle's lane assignment. Generating the target trajectory may include server averaging the clustered trajectories. As another example, process 1900 may include aligning the data received in step 1905. As described above, other processes or steps performed by server 1230 may also be included in process 1900.

[0318] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates instead of global coordinates. For autonomous driving, some systems may present data in world coordinates. For example, longitude and latitude coordinates of the Earth's surface may be used. To use the map for maneuvering, the main vehicle can determine its position and orientation relative to the map. It seems natural to use an onboard GPS device to locate the vehicle on the map, and to find the rotational transformation (e.g., north, east, and down) between the vehicle's reference frame and the world reference frame. Once the vehicle's reference frame is aligned with the map reference frame, the intended route can be expressed in the vehicle's reference frame, and steering commands can be calculated or generated.

[0319] The disclosed systems and methods can employ low-occupancy models to achieve autonomous vehicle navigation (e.g., steering control), which can be collected by the autonomous vehicle itself without the need for expensive surveying equipment. To support autonomous navigation (e.g., steering applications), the road model can include a sparse map with road geometry, lane structure, and road signs, which can be used to determine the vehicle's location or position along a trajectory included in the model. As described above, the generation of the sparse map can be performed by a remote server that communicates with and receives data from vehicles traveling on the road. The data may include sensed data, a reconstructed trajectory based on the sensed data, and / or a recommended trajectory that may represent a modified reconstructed trajectory. As described below, the server can feed the model back to the vehicle or other vehicles subsequently traveling on the road to aid in autonomous navigation.

[0320] Figure 20A block diagram of server 1230 is shown. Server 1230 may include a communication unit 2005, which may include hardware components (e.g., communication control circuitry, a switch, and an antenna) and software components (e.g., communication protocols, computer code). For example, communication unit 2005 may include at least one network interface. Server 1230 can communicate with vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. For example, server 1230 can receive navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. Server 1230 can distribute autonomous vehicle road navigation models to one or more autonomous vehicles via communication unit 2005.

[0321] Server 1230 may include at least one non-temporary storage medium 2010, such as a hard disk drive, optical disc, magnetic tape, etc. Storage device 1410 may be configured to store data, such as navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and / or an autonomous vehicle road navigation model generated by server 1230 based on the navigation information. Storage device 2010 may be configured to store any other information, such as sparse maps (e.g., those described above for...). Figure 8 The sparse map 800 mentioned above.

[0322] As a supplement to or alternative to storage device 2010, server 1230 may include memory 2015. Memory 2015 may be similar to or different from memory 140 or 150. Memory 2015 may be non-transitory memory, such as flash memory, random access memory, etc. Memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., processor 2020), map data (e.g., data from sparse map 800), autonomous vehicle road navigation models, and / or navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225.

[0323] Server 1230 may include at least one processing device 2020 configured to execute computer code or instructions stored in memory 2015 to perform various functions. For example, processing device 2020 may analyze navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225, and generate an autonomous vehicle road navigation model based on that analysis. Processing device 2020 may control communication unit 1405 to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles (e.g., one or more of vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicle subsequently traveling on road segment 1200). Processing device 2020 may be similar to or different from processor 180, 190, or processing unit 110.

[0324] Figure 21 A block diagram of a memory 2015 is shown, which may store computer code or instructions for performing one or more operations to generate a road navigation model for use in autonomous vehicle navigation. Figure 21 As shown, memory 2015 may store one or more modules for performing operations that process vehicle navigation information. For example, memory 2015 may include model generation module 2105 and model distribution module 2110. Processor 2020 may execute instructions stored in either module 2105 or 2110 contained in memory 2015.

[0325] The model generation module 2105 may store instructions that, when executed by the processor 2020, may generate at least a portion of an autonomous vehicle road navigation model for a common road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, in generating the autonomous vehicle road navigation model, the processor 2020 may cluster vehicle trajectories along the common road segment 1200 into different clusters. The processor 2020 may determine a target trajectory along the common road segment 1200 based on the clustered vehicle trajectories of each of the different clusters. This operation may include finding the mean or average trajectory of the clustered vehicle trajectories in each cluster (e.g., by averaging data representing the clustered vehicle trajectories). In some embodiments, the target trajectory may be associated with a single lane of the common road segment 1200.

[0326] The road model and / or sparse map can store trajectories associated with road segments. These trajectories, referred to as target trajectories, are provided to autonomous vehicles for autonomous navigation. Target trajectories can be received from multiple vehicles, or generated based on actual trajectories received from multiple vehicles, or recommended trajectories (actual trajectories with some modifications). The target trajectories contained in the road model or sparse map can be continuously updated (or averaged) using new trajectories received from other vehicles.

[0327] Vehicles traveling on a road segment can collect data through various sensors. This data may include road signs, road signature profiles, vehicle motion (e.g., accelerometer data, speed data), vehicle position (e.g., GPS data), and may reconstruct the actual trajectory itself or transmit the data to a server that reconstructs the vehicle's actual trajectory. In some embodiments, vehicles may transmit trajectory-related data (e.g., curves in any reference frame), road sign data, and lane alignment along the driving path to server 1230. Various vehicles traveling along the same road segment multiple times may have different trajectories. Server 1230 can identify routes or trajectories associated with each lane from the trajectories received from the vehicles through a clustering process.

[0328] Figure 22 This diagram illustrates the process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine target trajectories for a common road segment (e.g., road segment 1200). The target trajectories, or multiple target trajectories, determined from the clustering process may be included in an autonomous vehicle road navigation model or a sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 may transmit multiple trajectories 2200 to server 1230. In some embodiments, server 1230 may generate trajectories based on road signs, road geometry, and vehicle motion information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate an autonomous vehicle road navigation model, server 1230 may cluster vehicle trajectories 1600 into multiple clusters 2205, 2210, 2215, 2220, and 2230, as follows: Figure 22 As shown.

[0329] Various criteria can be used to perform clustering. In some embodiments, the absolute headings of all drivers in a cluster relative to road segment 1200 can be similar. Absolute headings can be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, dead reckoning can be used to obtain absolute headings. As those skilled in the art will understand, dead reckoning can be used to determine the current position and thus the headings of vehicles 1205, 1210, 1215, 1220, and 1225 by using previously determined positions, estimated speeds, etc. Trajectories clustered by absolute headings can be useful for identifying routes along the road.

[0330] In some embodiments, the lane assignments of all driving relative to driving along road segment 1200 (e.g., in the same lane before and after an intersection) in a cluster can be similar. Trajectories clustered by lane assignments can be useful for identifying lanes along the road. In some embodiments, both criteria (e.g., absolute heading and lane assignment) can be used for clustering.

[0331] Within each cluster 2205, 2210, 2215, 2220, 2225, and 2230, trajectories can be averaged to obtain a target trajectory associated with a specific cluster. For example, trajectories from multiple drives associated with the same lane cluster can be averaged. The average trajectory can be a target trajectory associated with a specific lane. To average the trajectories across clusters, server 1230 can choose a reference frame for any trajectory C0. For all other trajectories (C1, ..., Cn), server 1230 can find a rigid transformation mapping Ci to C0, where i = 1, 2, ..., n, where n is a positive integer corresponding to the total number of trajectories contained in the cluster. Server 1230 can compute the average curve or trajectory in the C0 reference frame.

[0332] In some embodiments, road signs can define arc length matches between different driving modes, which can be used for trajectory and lane alignment. In some embodiments, lane markings before and after intersections can be used for trajectory and lane alignment.

[0333] To assemble lanes from a trajectory, server 1230 can select a reference frame for any lane. Server 1230 can map partially overlapping lanes to the selected reference frame. Server 1230 can continue mapping until all lanes are in the same reference frame. Lanes adjacent to each other can be aligned as if they were the same lane, and they can be laterally offset.

[0334] Road signs identified along a road segment can be mapped to a common reference frame, first at the lane level and then at the intersection level. For example, the same road sign may be identified multiple times by multiple vehicles in multiple driving scenarios. The data associated with the same road sign received in different driving scenarios may differ slightly. This type of data can be averaged and mapped to the same reference frame, such as the C0 reference frame. As a supplement or alternative, the variation in data for the same road sign received in multiple driving scenarios can be calculated.

[0335] In some embodiments, each lane of road segment 120 may be associated with a target trajectory and certain road signs. The target trajectory, or multiple such target trajectories, may be included in an autonomous vehicle road navigation model that can subsequently be used by other autonomous vehicles traveling along the same road segment 1200. Road signs identified by vehicles 1205, 1210, 1215, 1220, and 1225 while traveling along road segment 1200 may be recorded in association with the target trajectory. The target trajectory and road sign data may be continuously or periodically updated using new data received from other vehicles during subsequent driving.

[0336] For autonomous vehicle localization, the disclosed systems and methods may use an extended Kalman filter. The vehicle's position can be determined based on three-dimensional position data and / or three-dimensional orientation data, through the integration of self-motion and prediction of future positions ahead of the vehicle's current position. Vehicle localization can be corrected or adjusted through image observation of road signs. For example, when the vehicle detects a road sign in an image captured by a camera, the road sign can be compared with known road signs stored in the road model or sparse map 800. Known road signs may have known positions (e.g., GPS data) along a target trajectory stored in the road model and / or sparse map 800. The distance from the vehicle to the road sign can be estimated based on the current speed and the road sign image. The position along the target trajectory can be adjusted based on the distance to the road sign and the known position of the road sign (stored in the road model or sparse map 800). The position / location data of road signs stored in the road model and / or sparse map 800 (e.g., averages from multiple drives) can be assumed to be accurate.

[0337] In some embodiments, the disclosed system may form a closed-loop subsystem in which the estimation of the vehicle's six-DOF position (e.g., three-dimensional position data plus three-dimensional orientation data) can be used to navigate the autonomous vehicle (e.g., maneuvering its steering wheel) to reach a desired point (e.g., the stored previous 1.3 seconds). Data measured from maneuvering and actual navigation can then be used to estimate the six-DOF position.

[0338] In some embodiments, roadside poles (e.g., lampposts and power or cable poles) can be used as road signs for locating vehicles. Other road signs (e.g., traffic signs, traffic lights, arrows on the road, stop lines) and static features or signatures of objects along the road segment can also be used as road signs for locating vehicles. When poles are used for location, the x-view of the pole (i.e., from the vehicle's perspective) can be used instead of the y-view (i.e., the distance to the pole) because the base of the pole can be obscured, and sometimes they are not on the road surface.

[0339] Figure 23 The vehicle's navigation system is shown, which can be used for autonomous navigation using a crowdsourced sparse map. For ease of illustration, the vehicle is referred to as vehicle 1205. Figure 23 The vehicle shown can be any other vehicle disclosed herein, including, for example, vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 shown in other embodiments. Figure 12As shown, vehicle 1205 can communicate with server 1230. Vehicle 1205 may include image capture device 122 (e.g., camera device 122). Vehicle 1205 may include navigation system 2300, which is configured to provide navigation guidance for vehicle 1205 traveling on a road (e.g., road segment 1200). Vehicle 1205 may also include other sensors, such as speed sensor 2320 and accelerometer 2325. Speed ​​sensor 2320 is configured to detect the speed of vehicle 1205. Accelerometer 2325 is configured to detect acceleration or deceleration of vehicle 1205. Figure 23 The vehicle 1205 shown can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, the vehicle 1205 can also be a non-autonomous, manually controlled vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0340] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 via a communication path 1235. The navigation system 2300 may also include a GPS unit 2310 configured to receive and process GPS signals. The navigation system 2300 may further include at least one processor 2315 configured to process data, such as GPS signals, map data from a sparse map 800 (which may be stored on storage provided on the vehicle 1205 and / or received from the server 1230), road geometry sensed by a road profile sensor 2330, images captured by a photographic device 122, and / or an autonomous vehicle road navigation model received from the server 1230. The road profile sensor 2330 may include different types of devices for measuring different types of road profiles (e.g., road surface roughness, road width, road elevation, road curvature, etc.). For example, the road profile sensor 2330 may include a device that measures the motion of the suspension of vehicle 2305 to derive a road roughness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor to measure the distance from vehicle 1205 to the sides of the road (e.g., barriers on either side of the road), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 may include means configured to measure the vertical elevation of the road. In some embodiments, the road profile sensor 2330 may include means configured to measure the curvature of the road. For example, a photographic device (e.g., photographic device 122 or another photographic device) may be used to capture images of the road showing its curvature. Vehicle 1205 may use such images to detect the road curvature.

[0341] At least one processor 2315 may be programmed to receive at least one environmental image associated with vehicle 1205 from camera device 122. At least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with vehicle 1205. The navigation information may include a trajectory associated with the vehicle 1205's travel along road segment 1200. At least one processor 2315 may determine the trajectory based on the motion of camera device 122 (and therefore the vehicle), such as three-dimensional translational and three-dimensional rotational motion. In some embodiments, at least one processor 2315 may determine the translational and rotational motion of camera device 122 based on analysis of multiple images acquired by camera device 122. In some embodiments, the navigation information may include lane assignment information (e.g., which lane vehicle 1205 is traveling in along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 may be used by the server to generate and / or update an autonomous vehicle road navigation model, which may be returned from server 1230 to vehicle 1205 for providing autonomous navigation guidance for vehicle 1205.

[0342] At least one processor 2315 may also be programmed to transmit navigation information from vehicle 1205 to server 1230. In some embodiments, the navigation information may be transmitted to server 1230 along with road information. Road location information may include at least one of GPS signals received by GPS unit 2310, road sign information, road geometry, lane information, etc. At least one processor 2315 may receive an autonomous vehicle road navigation model or a portion thereof from server 1230. The autonomous vehicle road navigation model received from server 1230 may include at least one update based on the navigation information transmitted from vehicle 1205 to server 1230. The portion of the model transmitted from server 1230 to vehicle 1205 may include the updated portion of the model. At least one processor 2315 may cause at least one navigation maneuver (e.g., steering, such as turning, braking, acceleration, overtaking another vehicle, etc.) to be performed by vehicle 1205 based on the received autonomous vehicle road navigation model or the updated portion thereof.

[0343] At least one processor 2315 may be configured to communicate with various sensors and components included in the vehicle 1205, including a communication unit 1705, a GPS unit 2315, a camera device 122, a speed sensor 2320, an accelerometer 2325, and a road profile sensor 2330. The processor 2315 may collect information or data from the various sensors and components and transmit the information or data to the server 1230 via the communication unit 2305. Alternatively or supplementarily, the various sensors or components of the vehicle 1205 may also communicate with the server 1230 and transmit data or information collected by the sensors or components to the server 1230.

[0344] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can communicate with each other and share navigation information, such that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 can, for example, use crowdsourcing based on information shared by other vehicles to generate an autonomous vehicle road navigation model. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can share navigation information with each other, and each vehicle can update its own autonomous vehicle road navigation model provided in the vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) can serve as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) can perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle can communicate with other vehicles and receive navigation information from other vehicles. At least one processor 2315 of the central vehicle can generate an autonomous vehicle road navigation model or update the model based on shared information received from other vehicles. The at least one processor 2315 of the central vehicle can transmit the autonomous vehicle road navigation model or updates to the model to other vehicles for providing autonomous navigation guidance.

[0345] Mapped lane markings and navigation based on mapped lane markings

[0346] As previously described, the autonomous vehicle road navigation model and / or sparse map 800 may include multiple mapped lane markers associated with road segments. These mapped lane markers can be used when the autonomous vehicle is navigating, as discussed in more detail below. For example, in some embodiments, the mapped lane markers can be used to determine the lateral position and / or orientation relative to a planned trajectory. With this positional information, the autonomous vehicle may be able to adjust its heading to match the orientation of the target trajectory at the determined location.

[0347] Vehicle 200 can be configured to detect lane markings in a given road segment. The road segment can include any markings on the road to guide vehicle traffic on the highway. For example, lane markings can be continuous or dashed lines that distinguish the edges of driving lanes. Lane markings can also include double lines, such as double continuous lines, double dashed lines, or a combination of continuous and dashed lines, indicating, for example, whether overtaking is permitted in adjacent lanes. Lane markings can also include highway entrance and exit markings indicating, for example, deceleration lanes for exit ramps, or dashed lines indicating lanes that only turn or end in a lane. Markings can further indicate work zones, temporary lane changes, routes through intersections, median strips, dedicated lanes (e.g., bicycle lanes, HOV lanes, etc.), or a wide variety of other markings (e.g., pedestrian crossings, speed bumps, railway crossings, stop lines, etc.).

[0348] Vehicle 200 may use a photographic device (e.g., image capture devices 122 and 124 included in image acquisition unit 120) to capture images of surrounding lane markings. Vehicle 200 may analyze the images to detect point locations associated with lane markings based on features identified within one or more of the captured images. These point locations may be uploaded to a server to represent lane markings in sparse map 800. Depending on the position and field of view of the photographic device, lane markings may be detected simultaneously on both sides of the vehicle from a single image. In other embodiments, different photographic devices may be used to capture images of multiple sides of the vehicle. Instead of uploading actual images of lane markings, the markings may be stored in sparse map 800 as splines or a series of points, thus reducing the size of sparse map 800 and / or the amount of data that must be remotely uploaded by the vehicle.

[0349] Figures 24A-24D The diagram illustrates the location of a point that can be detected by vehicle 200 to represent a specific lane marking. Similar to the road signs described above, vehicle 200 can use various image recognition algorithms or software to identify point locations within the captured image. For example, vehicle 200 can identify a range of edge points, corner points, or various other point locations associated with a specific lane marking. Figure 24A A continuous lane marking 2410, detectable by vehicle 200, is shown. Lane marking 2410 may represent the outer edge of a road, indicated by a continuous white line. For example... Figure 24A As shown, vehicle 200 can be configured to detect multiple edge location points 2411 along lane markings. Location points 2411 can be collected at any interval sufficient to create a mapped lane marking in a sparse map to represent lane markings. For example, lane markings can be represented by detecting one point per meter of edge, one point per five meters of edge, or at other suitable intervals. In some embodiments, the spacing can be determined by other factors rather than by setting intervals, such as based on the point with the highest confidence rating of the location of the detection point on vehicle 200. Although Figure 24A The edge location point on the inner edge of lane marking 2410 is shown, but the point can be collected at the outer edge of the line or along both edges. Furthermore, although... Figure 24A The diagram shows a single line, but similar edge points can be detected for double continuous lines. For example, point 2411 can be detected along one or both edges of a continuous line.

[0350] Vehicle 200 can also represent lane markings in different ways depending on the type or shape of the lane markings. Figure 24B The example dashed lane marking 2420 is shown and can be detected by vehicle 200. Not as... Figure 24A In addition to identifying edge points, vehicles can detect a series of corner points 2421 representing the corners of the lane dashed lines to define the complete boundary of the dashed lines. Although Figure 24BEach corner of a given dashed line marker is shown, but vehicle 200 can detect or upload a subset of the points shown in the diagram. For example, vehicle 200 can detect the leading edge or leading corner of a given dashed line marker, or the two corners closest to the interior of the lane. Furthermore, not every dashed line marker can be captured; for example, vehicle 200 can capture and / or record samples representing dashed line markers (e.g., every other one, every third, every fifth, etc.) or points of dashed line markers at predefined intervals (e.g., every meter, every five meters, every ten meters, etc.). Corner detection can also be performed on similar lane markings, such as lane markings for exit ramps, lane-end markings, or other various lane markings that may have detectable corners. Corner detection can also be performed on lane markings consisting of double dashed lines or combinations of continuous lines and dashed lines.

[0351] In some embodiments, the points uploaded to the server to generate mapped lane markings may represent points other than detected edge points or corner points. Figure 24C A series of points can be shown to represent the centerline of a given lane marking. For example, a continuous lane 2410 can be represented by centerline point 2441 along the centerline 2440 of the lane marking. In some embodiments, vehicle 200 may be configured to detect these center points using various image recognition techniques, such as convolutional neural networks (CNN), scale-invariant feature transform (SIFT), oriented gradient histogram (HOG) features, or other techniques. Alternatively, vehicle 200 may detect other points (e.g., Figure 24A The edge point 2411 shown is used, and the centerline point 2441 can be calculated, for example, by detecting points along each edge and determining the midpoint between the edge points. Similarly, the dashed lane marking 2420 can be represented by the centerline point 2451 along the centerline 2450 of the lane marking. The centerline point can be as follows: Figure 24C The points are located at the edge of the dashed line or at various other locations along the centerline. For example, each dashed line can be represented by a single point at the geometric center of the dashed line. Points can also be spaced apart along the centerline at predetermined intervals (e.g., every meter, 5 meters, 10 meters, etc.). Centerline point 2451 can be directly detected by vehicle 200, or it can be based on other detected reference points (e.g., corner point 2421, such as...). Figure 24B (As shown) to calculate. The center line can also be used to represent other lane marking types (such as double lines) using similar techniques as described above.

[0352] In some embodiments, vehicle 200 may identify points representing other features, such as vertices between two intersecting lane markings. Figure 24DAn example point representing the intersection between two lane markings 2460 and 2465 is shown. Vehicle 200 can calculate a vertex 2466 representing the intersection between the two lane markings. For example, one of lane markings 2460 or 2465 may represent a train crossing area in a road segment, or the other crossing area. Although lane markings 2460 and 2465 are shown intersecting perpendicularly, various other configurations can be detected. For example, lane markings 2460 and 2465 may intersect at other angles, or one or both lane markings may terminate at vertex 2466. Similar techniques can also be applied to intersections between dashed lines or other lane marking types. In addition to vertex 2466, various other points 2467 can be detected, providing additional information related to the orientation of lane markings 2460 and 2465.

[0353] Vehicle 200 can associate real-world coordinates with each detected point of the lane marking. For example, a location identifier including the coordinates of each point can be generated and uploaded to a server for mapping lane markings. The location identifier can further include other identifying information related to the point, including whether the point represents a corner, edge, center, etc. Therefore, vehicle 200 can be configured to determine the real-world location of each point based on image analysis. For example, vehicle 200 can detect other features in the image (such as the various road signs described above) to locate the real-world location of the lane marking. This may involve determining the position of the lane marking in the image relative to the detected road signs, or determining the vehicle's position based on the detected road signs and then determining the distance from the vehicle (or the vehicle's target trajectory) to the lane marking. When road signs are unavailable, the position of the lane marking point can be determined relative to the vehicle's position determined based on dead reckoning. The real-world coordinates included in the location identifier can be represented as absolute coordinates (e.g., latitude / longitude coordinates) or relative to other features, such as based on the longitudinal position along the target trajectory and the lateral distance from the target trajectory. Location identifiers can then be uploaded to a server for generating mapped lane markings in a navigation model (e.g., sparse map 800). In some embodiments, the server may construct splines representing lane markings for road segments. Alternatively, vehicle 200 may generate splines and upload them to the server for recording in the navigation model.

[0354] Figure 24E An example navigation model or sparse map of the corresponding road segment, including mapped lane markings, is shown. The sparse map may include a target trajectory 2475 that the vehicle is to follow along the road segment. As described above, the target trajectory 2475 may represent the ideal path taken by the vehicle while traveling on the corresponding road segment, or it may be located at other locations on the road (e.g., the centerline of the road). The target trajectory 2475 may be calculated using various methods described above, such as based on the aggregation (e.g., weighted combination) of two or more reconstructed trajectories of vehicles traversing the same road segment.

[0355] In some embodiments, target trajectories can be generated equally for all vehicle types and for all road, vehicle, and / or environmental conditions. However, in other embodiments, various other factors or variables may also be considered in generating the target trajectory. Different target trajectories may be generated for different types of vehicles (e.g., cars, light trucks, and trailers). For example, a target trajectory with a smaller turning radius may be generated for a small car compared to a larger semi-trailer. In some embodiments, road, vehicle, and environmental conditions may also be considered. For example, different target trajectories may be generated for different road conditions (e.g., wet, icy, dry, etc.), vehicle conditions (e.g., tire conditions or estimated tire conditions, braking conditions or estimated braking conditions, remaining fuel, etc.), or environmental factors (e.g., time of day, visibility, weather, etc.). The target trajectory may also depend on one or more aspects or characteristics of a particular road segment (e.g., speed limits, frequency and size of turns, gradient, etc.). In some embodiments, various user settings may also be used to determine the target trajectory, such as setting driving modes (e.g., expected driving aggression, economy mode, etc.).

[0356] The sparse map may also include mapped lane markers 2470 and 2480 representing lane markings along a road segment. The mapped lane markers may be represented by multiple location identifiers 2471 and 2481. As described above, the location identifiers may include the location in real-world coordinates of the point associated with the detected lane marker. Similar to the target trajectory in the model, lane markers may also include elevation data and may be represented as curves in three-dimensional space. For example, the curve may be a spline connecting three-dimensional polynomials of appropriate order, and the curve may be computed based on the location identifiers. The mapped lane markers may also include other information or metadata related to the lane markers, such as identifiers of the type of lane marker (e.g., between two lanes with the same direction of travel, between two lanes with opposite directions of travel, the edge of a road, etc.) and / or other characteristics of the lane markers (e.g., continuous, dashed, single line, double line, yellow, white, etc.). In some embodiments, the mapped lane markers may be continuously updated within the model, for example, using crowdsourcing techniques. The same vehicle can upload location identifiers at multiple times while traveling on the same road segment, or data can be selected from multiple vehicles traveling on the same road segment at different times (e.g., 1205, 1210, 1215, 1220, and 1225). The sparse map 800 can then be updated or refined based on subsequent location identifiers received from the vehicles and stored in the system. As the mapped lane markings are updated and refined, the updated road navigation model and / or sparse map can be distributed to multiple autonomous vehicles.

[0357] Generating mapped lane markings in sparse maps may also include detecting and / or mitigating errors based on anomalies in the image or in the actual lane markings themselves. Figure 24FAn example anomaly 2495 associated with lane marking 2490 is shown. Anomaly 2495 may appear in an image captured by vehicle 200, for example, from an object, debris on a lens, etc., obstructing the view of the lane marking. In some cases, the anomaly may be attributable to the lane marking itself, which may be damaged or worn, or partially covered, for example, by dust, debris, water, snow, or other materials on the road. Anomaly 2495 may cause erroneous point 2491 to be detected by vehicle 200. Sparse map 800 can provide correct mapping of lane markings to exclude errors. In some embodiments, vehicle 200 may detect erroneous point 2491, for example, by detecting anomaly 2495 in the image or by identifying errors based on detected lane marking points before and after the anomaly. Based on the detected anomaly, vehicle may ignore point 2491 or adjust it to be consistent with other detected points. In other embodiments, errors can be corrected after points have already been uploaded, for example, by determining that the point is outside a predicted threshold based on other points uploaded during the same trip or by aggregation of data from previous trips along the same road segment.

[0358] Mapped lane markers in the navigation model and / or sparse map can also be used for navigation by autonomous vehicles traveling on corresponding roads. For example, a vehicle navigating along a target trajectory can periodically use mapped lane markers in the sparse map to align itself with the target trajectory. As mentioned above, between road signs, vehicles can navigate based on dead reckoning, where the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Errors can accumulate over time, and the determination of the vehicle's position relative to the target trajectory can become increasingly inaccurate. Accordingly, the vehicle can use lane markers (and their known locations) appearing in the sparse map 800 to reduce errors caused by dead reckoning in position determination. In this way, the identified lane markers included in the sparse map 800 can be used as navigation anchor points from which the vehicle's precise position relative to the target trajectory can be determined.

[0359] Figure 25A An exemplary image 2500 of the vehicle's surrounding environment, which can be used for navigation based on mapped lane markings, is shown. Image 2500 can be captured, for example, by vehicle 200 via image capture devices 122 and 124 included in image acquisition unit 120. Image 2500 may include an image of at least one lane marking 2510, such as... Figure 25A As shown. Image 2500 may also include one or more road signs 2521, such as road signs, for navigation as described above. Also shown... Figure 25A Some elements are shown for reference, such as elements 2511, 2530 and 2520 that are not present in the captured image 2500 but are detected and / or identified by vehicle 200.

[0360] Use the above to target Figure 24A -D and Figure 24F The various techniques described above allow the vehicle to analyze image 2500 to identify lane markings 2510. Various points 2511 can be detected as features corresponding to lane markings in the image. For example, point 2511 may correspond to the edge of a lane marking, a corner of a lane marking, the midpoint of a lane marking, a vertex between two intersecting lane markings, or various other features or locations. Point 2511 is detected as the location corresponding to points stored in a navigation model received from a server. For example, if a sparse map containing points representing the center lines of mapped lane markings is received, point 2511 can also be detected based on the center lines of lane markings 2510.

[0361] The vehicle can also determine the longitudinal position represented by element 2520 and located along the target trajectory. For example, the longitudinal position 2520 can be determined from image 2500 by detecting road signs 2521 within image 2500 and comparing the measured position with known road sign positions stored in the road model or sparse map 800. The position along the target trajectory can then be determined based on the distance to the road sign and the known location of the road sign. The longitudinal position 2520 can also be determined from images other than those used to determine the position of lane markings. For example, the longitudinal position 2520 can be determined by detecting road signs in images taken simultaneously or nearly simultaneously with image 2500 from other photographic devices within image acquisition unit 120. In some cases, the vehicle may not be near any road signs or other reference points used to determine the longitudinal position 2520. In such cases, the vehicle can navigate based on dead reckoning and can therefore use sensors to determine its own motion and estimate its longitudinal position 2520 relative to the target trajectory. The vehicle can also determine a distance 2530 representing the actual distance between the vehicle and lane markings 2510 observed in one or more captured images. The determination of distance 2530 may take into account factors such as the camera angle, vehicle speed, vehicle width, or various other factors.

[0362] Figure 25B This illustrates lateral positioning correction of a vehicle based on mapped lane markings in a road navigation model. As described above, vehicle 200 can use one or more images captured by vehicle 200 to determine the distance 2530 between vehicle 200 and lane markings 2510. Vehicle 200 may also have access to a road navigation model (e.g., a sparse map 800), which may include mapped lane markings 2550 and a target trajectory 2555. The mapped lane markings 2550 can be modeled using the techniques described above, such as using crowdsourced location identifiers captured by multiple vehicles. The target trajectory 2555 can also be generated using the various techniques described above. Vehicle 200 may also perform lateral positioning corrections as described above for... Figure 25AThe longitudinal position 2520 along the target trajectory 2555 is determined or estimated. The vehicle 200 can then determine the expected distance 2540 based on the lateral distance between the target trajectory 2555 and the mapped lane markings corresponding to the longitudinal position 2520. The lateral positioning of the vehicle 200 can be corrected or adjusted by comparing the actual distance 2530 measured using one or more captured images with the expected distance 2540 from the model.

[0363] Figure 26A This is a flowchart illustrating an exemplary process 2600A for mapping lane markings for use in autonomous vehicle navigation according to the disclosed embodiments. In step 2610, process 2600A may include receiving two or more location identifiers associated with the detected lane markings. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifiers may include the real-world coordinates of the point associated with the detected lane markings, as described above for... Figure 24E In some embodiments, the location identifier may also include other data, such as additional information relating to road segments or lane markings. Additional data may also be received during step 2610, such as accelerometer data, speed data, road sign data, road geometry or profile data, vehicle positioning data, self-motion data, or various other forms of data as described above. The location identifier may be generated by a vehicle (e.g., vehicles 1205, 1210, 1215, 1220, and 1225) based on images captured by the vehicle. For example, the identifier may be determined based on the acquisition of at least one image representing the environment of the main vehicle from a photographic device associated with the main vehicle, analysis of the at least one image to detect lane markings in the environment of the main vehicle, and analysis of the at least one image to determine the position of the detected lane markings relative to the location associated with the main vehicle. As described above, lane markings may include a variety of different marking types, and the location identifier may correspond to a variety of points relative to the lane markings. For example, in the case where the detected lane marking is part of a dashed line marking the lane boundary, the point may correspond to a detected angle of the lane marking. When the detected lane marking is part of a continuous line marking the lane boundary, the point may correspond to the detected edge of the lane marking, having various spacings as described above. In some embodiments, the point may be as follows: Figure 24C The image shown corresponds to the center line of the detected lane marking, or it can be like... Figure 24D The vertex shown corresponds to the point between at least two other points of the two intersecting lane markers and the associated intersecting lane marker.

[0364] In step 2612, process 2600A may include associating the detected lane marking with a corresponding road segment. For example, server 1230 may analyze real-world coordinates or other information received during step 2610 and compare the coordinates or other information with location information stored in the autonomous vehicle road navigation model. Server 1230 may determine the road segment in the model corresponding to the real-world road segment of the detected lane marking.

[0365] In step 2614, process 2600A may include updating the autonomous vehicle road navigation model relative to the corresponding road segment based on two or more location identifiers associated with the detected lane markings. For example, the autonomous road navigation model may be a sparse map 800, and server 1230 may update the sparse map to include or adjust the mapped lane markings in the model. Server 1230 may update the sparse map based on the above-mentioned... Figure 24E The various methods or processes described above are used to update the model. In some embodiments, updating the autonomous vehicle road navigation model may include one or more indicators storing the location in the real-world coordinates of the detected lane markings. The autonomous vehicle road navigation model may also include at least one target trajectory that the vehicle is to follow along the corresponding road segment, such as... Figure 24E As shown.

[0366] In step 2616, process 2600A may include distributing the updated autonomous vehicle road navigation model to multiple autonomous vehicles. For example, server 1230 may distribute the updated autonomous vehicle road navigation model to vehicles 1205, 1210, 1215, 1220, and 1225, which can use the model for navigation. This can be achieved through methods such as... Figure 12 The wireless communication path 1235 shown distributes the autonomous vehicle road navigation model via one or more networks (e.g., via cellular networks and / or the Internet).

[0367] In some embodiments, it can be used, for example, through the methods described above for... Figure 24E The crowdsourcing technology described above maps lane markings from data received from multiple vehicles. For example, process 2600A may include receiving a first communication from a first master vehicle including a location identifier associated with the detected lane marking, and a second communication from a second master vehicle including an additional location identifier associated with the detected lane marking. For example, the second communication may be received from a subsequent vehicle traveling on the same road segment or from the same vehicle traveling a subsequent leg of the same road segment. Process 2600A may further include refining the determination of at least one location associated with the detected lane marking based on the location identifier received in the first communication and based on the additional location identifier received in the second communication. This may include averaging multiple location identifiers and / or filtering out “virtual” identifiers that may not reflect the real-world location of the lane marking.

[0368] Figure 26B This is a flowchart illustrating an exemplary process 2600B of autonomously navigating a master vehicle along a road segment using mapped lane markings. Process 2600B may be executed, for example, by the processing unit 110 of the autonomous vehicle 200. In step 2620, process 2600B may include receiving an autonomous vehicle road navigation model from a server-based system. In some embodiments, the autonomous vehicle road navigation model may include a target trajectory of the master vehicle along the road segment and location identifiers associated with one or more lane markings of the associated road segment. For example, vehicle 200 may receive a sparse map 800 or another road navigation model developed using process 2600A. In some embodiments, the target trajectory may be represented as a three-dimensional spline, for example... Figure 9B As shown above. Figure 24A As described in -F, the location identifier may include the location of the point associated with the lane marker in real-world coordinates (e.g., the corner of a dashed lane marker, the edge of a consecutive lane marker, the vertex between two intersecting lane markers and other points associated with the intersecting lane marker, the centerline associated with the lane marker, etc.).

[0369] In step 2621, process 2600B may include receiving at least one image representing the environment of the vehicle. The image may be received from the vehicle's image capture device, for example, via image capture devices 122 and 124 included in image acquisition unit 120. The image may include images of one or more lane markings, similar to image 2500 described above.

[0370] In step 2622, process 2600B may include determining the longitudinal position of the master vehicle along the target trajectory. (As described above for...) Figure 25A This can be based on other information in the captured images (such as road signs) or by inferring the dead reckoning of vehicles between detected road signs.

[0371] In step 2623, process 2600B may include determining the expected lateral distance to a lane marker based on the determined longitudinal position of the master vehicle along the target trajectory and based on two or more location identifiers associated with at least one lane marker. For example, vehicle 200 may use sparse map 800 to determine the expected lateral distance to the lane marker. Figure 25B As shown, the longitudinal position 2520 along the target trajectory 2555 can be determined in step 2622. Using the sparse map 800, the vehicle 200 can determine the estimated distance 2540 to the mapped lane marker 2550 corresponding to the longitudinal position 2520.

[0372] In step 2624, process 2600B may include analyzing at least one image to identify at least one lane marking. For example, vehicle 200 may use various image recognition techniques or algorithms to identify lane markings within the image, as described above. For instance, lane marking 2510 may be detected through image analysis of image 2500, such as... Figure 25A As shown.

[0373] In step 2625, process 2600B may include determining the actual lateral distance to at least one lane marking based on analysis of at least one image. For example, a vehicle such as Figure 25A The distance 2530 shown represents the actual distance between the vehicle and lane marking 2510. Factors such as the camera angle, vehicle speed, vehicle width, camera position relative to the vehicle, and various other factors may be considered in determining the distance 2530.

[0374] In step 2626, process 2600B may include determining the autonomous steering action of the master vehicle based on the difference between the expected lateral distance to at least one lane mark and the determined actual lateral distance to at least one lane mark. For example, as described above for... Figure 25B The vehicle 200 can compare the actual distance 2530 with the expected distance 2540. The difference between the actual and expected distances indicates the error (and its magnitude) between the vehicle's actual position and the target trajectory to be followed by the vehicle. Accordingly, the vehicle can determine an autonomous steering action or another autonomous action based on this difference. For example, if... Figure 25B If the actual distance 2530 is less than the expected distance 2540, the vehicle can determine an autonomous steering action to guide it to the left, away from lane marker 2510. Therefore, the vehicle's position relative to the target trajectory can be corrected. Process 2600B can be used, for example, to improve vehicle navigation between road signs.

[0375] Navigation and mapping based on the detected arrow orientation

[0376] As described above, vehicle 200 (e.g., via processing unit 110) can be configured to analyze the geometry of various markers detected in the environment. Vehicle 200 can detect one or more markers, such as directional arrows, detected on a road. As discussed in detail below, these directional arrows can be used to generate a road navigation model and / or for vehicle navigation. For example, directional arrows can be analyzed to determine the expected direction of travel on a road or a specific lane of a road. This data can be included in a road navigation model (e.g., sparse map 800) to improve the navigation of autonomous vehicles.

[0377] Vehicle 200 may be configured to detect markings on a highway. The highway may include various arrows indicating the direction of travel associated with a lane. For example, vehicle 200 may use a photographic device (e.g., image capture devices 122 and 124 included in image acquisition unit 120) to capture images of the directional arrows. Processing unit 110 may be configured to analyze the captured images to identify the directional arrows. In some embodiments, processing unit 110 may also analyze the geometry of the detected directional arrows to determine additional information based on the detected directional arrows. For example, the processing unit may determine the position of the arrow relative to a lane or highway, the direction of the directional arrow, and / or the type of arrow. In some embodiments, processing unit 110 may be configured to identify the traffic pattern or other implications represented by the arrow, such as the expected lane use of the traffic lane associated with the arrow (e.g., a vehicle traveling in the lane turning right or left).

[0378] Figure 27A An exemplary directional arrow that can be detected according to the disclosed embodiment is shown. Vehicle 200 can detect a straight arrow 2710 indicating that the direction of travel in this lane continues forward. For example, straight arrow 2710 can be detected at an intersection, indicating that the lane associated with straight arrow 2710 is a "straight only" lane and that traffic in this lane is passing through the intersection. Straight arrow 2710 can also be detected in the middle of the road and can indicate the direction of travel of the associated lane. Vehicle 200 can also detect angular arrows, such as lane-closing arrows 2711. These arrows can indicate that the number of straight lanes on a given highway is decreasing because the highway is narrowing or the lane is about to end. This can instruct the vehicle to request navigation actions, such as turning into an adjacent lane.

[0379] Vehicle 200 may be further configured to detect various turn arrows, such as turn arrow 2712. These arrows may indicate mandatory and / or permitted movement in certain lanes. For example, turn arrow 2712 may be detected at an intersection, indicating that the associated lane is "turn only". This may trigger a navigation action by the vehicle, such as moving to an adjacent lane if the target trajectory does not correspond to the permitted use of the lane. In some embodiments, vehicle 200 may also be configured to detect compound arrow types, such as left-turn / straight arrow 2713. These arrows may indicate that multiple movement or lane use types are permitted for a given lane. For example, left-turn / straight arrow 2713 may be detected at an intersection and may indicate that the vehicle is permitted to turn left or proceed straight through the intersection. Accordingly, vehicle 200 (or processing unit 110) may be configured to detect multiple directions associated with a given direction arrow marker. Various other turn arrows or compound arrows may also be detected. For example, right-turn arrows or right-turn / straight arrows may also be detected. In some cases, the arrow may indicate that a left turn or a right turn is permitted. In some cases, more than two directions can be associated with a given arrow, such as indicating a permitted direction of left or right turn or straight travel. In such cases, vehicle 200 can detect more than one direction associated with a given direction arrow mark, or can treat these directions as separate direction arrows.

[0380] In some embodiments, vehicle 200 may also be configured to detect other road markings that may indicate the direction of travel, even if that is not necessarily the intention of an arrow. For example, vehicle 200 may detect speed bump marking 2714. This marking may be expected, for example, to mark a speed bump on a highway and warn the driver to slow down. However, vehicle 200 may detect and identify speed bump marking 2714 and determine the direction of travel based on this marking. For example, similar to straight arrow 2710, vehicle 200 may use speed bump marking 2714 as an indication of the direction of travel in the associated lane. In some cases, vehicle 200 may also identify it as a speed bump marking and trigger a control action accordingly, such as reducing the vehicle's speed. Other markings similarly indicate the direction of travel in a given lane.

[0381] In some embodiments, vehicle 200 may need to distinguish directional arrows from various road markings that do not indicate an expected direction. For example, yield sign 2715 may indicate an upcoming road configuration where the current lane must yield to other lanes of traffic (e.g., at an intersection or in a merging lane). Vehicle 200 may be configured to distinguish yield sign 2715 or other non-directional arrow markings from directional arrows. For example, vehicle 200 may be configured to distinguish yield sign 2715 from a straight arrow or lane-closing arrow 2711 that indicates the wrong direction of travel within the lane. Accordingly, vehicle 200 may be configured to detect additional features of the detected road marking, such as the absence of a leading arrow or a hollow interior of yield sign 2715. In some embodiments, vehicle 200 may identify it as a yield sign and determine the direction of travel based on the bottom of the yield sign facing adjacent traffic.

[0382] In some embodiments, vehicle 200 may be configured to detect arrows indicating the direction of travel or permitted movement of a corresponding lane from other locations in the surrounding environment. For example, vehicle 200 may be configured to detect arrows on signs (e.g., traffic sign 2716). For example, traffic sign 2716 may be located on the side of a road or above a vehicle (e.g., on a traffic light pole). While vehicle 200 may detect traffic sign 2716 as a road sign, vehicle 200 may also detect one or more directional arrows on the sign and associate the directional arrows with the corresponding lanes. Similar to directional arrows identified on a road, directional arrows from signs or other locations in the surrounding environment may be captured and uploaded to a road navigation model and / or used for navigation by the vehicle.

[0383] Processing unit 110 can be configured to process the detected directional arrows and upload them to a server for representation in a road navigation model (e.g., sparse map 800). Accordingly, processing unit 110 can be configured to further identify specific points or features of the detected directional arrows and process these points or features to extract additional information from the directional arrows.

[0384] Figure 27B An example image processing of the detected directional arrow is shown according to the disclosed embodiment. For example... Figure 27B As shown, vehicle 200 can detect straight arrow 2710. Processing unit 110 can be configured to identify one or more points associated with the directional arrow, which can be used to determine the direction, location, and / or other information associated with the directional arrow. For example, processing unit 110 can use one or more image processing algorithms or techniques to isolate points or features from the captured image.

[0385] In some embodiments, processing unit 110 may identify the tip 2721 of a directional arrow. The tip 2721 may be used, for example, to determine the heading direction of the arrow. One or more points associated with the tip of the arrow may also be identified, such as outer vertices 2722 on either side of the tip of the arrow. Processing unit 110 may also identify inner vertices 2724 associated with the tip of the arrow. In some embodiments, the direction and position of the arrow may be defined solely by one or more points associated with the tip of the arrow. For example, processing unit 110 may determine the midpoint between the outer vertices 2722, and this midpoint, combined with the tip 2721, may indicate the direction of a straight arrow 2710. Other points may also be identified in place of or supplement the points associated with the tip of the arrow. For example, one or more points associated with the body of the arrow may be detected, such as corner points 2723 or endpoints 2728. Inner points may also be detected, such as inner point 2726 representing the center point of the detected arrow or inner point 2725 representing the center point of the tip of the detected arrow. Other points may also be identified. Figure 27B Unidentified additional points or features, such as the edge line of an arrow or various points along the edge line. In some embodiments, two or more identified points may be sufficient to represent the position and orientation of the arrow. In some embodiments, points or features may be selected based on predefined specifications that identify points that should be sampled so that processing can resolve the orientation of the arrow (e.g., at a certain confidence level). For example, a number of points may be specified at the wide edge of the arrow, on the side of the arrow, in the middle or center, and at the tip of the arrow. In some embodiments, the required number of points may depend on various other factors. For example, the number of points may depend on the detected arrow (e.g., arrow type, arrow size, distance to the arrow, etc.), image quality or conditions (e.g., image sharpness, signal-to-noise ratio), the confidence level of the determined points, road conditions (road type or surface, road reflectivity, visibility of arrows on the road, etc.), or vehicle-related factors (e.g., vehicle speed, etc.). Processing unit 110 may also be configured to associate real-world coordinates with one or more of the identified points or features. In yet another embodiment, a trained system (e.g., a neural network) may be trained to resolve the orientation of the arrow.

[0386] Figure 27C An exemplary image 2735 of the vehicle's surroundings, which can be used to detect directional arrows according to the disclosed embodiment, is shown. Image 2735 may be captured, for example, by vehicle 200 via image capture devices 122 and 124 included in image acquisition unit 120. Image 2735 may include an image of at least one directional arrow 2730. Image 2735 may also include one or more road signs 2734, such as road signs and / or lane markings 2733, as described above for navigation and / or lateral positioning. Also shown... Figure 27CSome elements are shown for reference, such as points 2731 and 2732 that are not present in the captured image 2735 but are detected and / or identified by vehicle 200.

[0387] Vehicle 200 can be configured to detect directional arrows 2730 from image 2735 based on various image processing algorithms or techniques. Processing unit 110 can further identify various points 2731 and 2732, which may correspond to specific... Figure 27B The identified points are as described above. Processing unit 110 may be further configured to determine the real-world location of the arrow and / or various points associated with the arrow (e.g., cusp 2731). Accordingly, processing unit 110 may analyze other features (e.g., road signs 2734) of the image 2735 that may have known locations in the sparse map 800. This may involve determining the position of the directional arrow in the image relative to detected road signs, or determining the position of a vehicle based on detected road signs and then determining the distance from the vehicle to the directional arrow. When road signs are unavailable, the position of the directional arrow and / or points may be determined relative to the position of a vehicle that can be determined by dead reckoning. For example, a vehicle may use sensors to determine its own motion and estimate its position relative to a target trajectory, as described above. The real-world coordinates associated with the directional arrow may be represented as absolute coordinates (e.g., latitude / longitude coordinates), or may be relative to other features, such as based on longitudinal position along the target trajectory and lateral distance from the target trajectory.

[0388] Additional information from image 2735 and / or vehicle 200 can also be analyzed to determine the direction of directional arrow 2730. For example, without other context in the image, directional arrow 2730 (which could be a straight arrow on the road surface as shown in image 2735) might appear more like lane reduction arrow 2711 without considering other elements in the captured image. Accordingly, processing unit 110 can be configured to correct or take into account the detected point based on the position of the camera, camera angle, lens distortion, camera viewing angle, or other various factors. In some embodiments, processing unit 110 can also analyze other elements of the image (e.g., lane markings 2733) to determine the position and / or direction of the directional arrow. For example, the lateral position of the directional arrow can be determined or calibrated based on the distance between directional arrow 2730 and lane markings 2733 determined from image 2735. The direction of the directional arrow can similarly be determined or calibrated based on lane markings 2733. For example, the processor can determine that directional arrow 2730 is a straight arrow based on one or more features or points detected in the image. Accordingly, the processing unit 110 can align the direction of the arrow 2730 with the lane marking 2733, or calibrate the direction determined by the detected point based on the lane marking 2733. Various other elements from the image 2735 can also be used to determine or correct the position and / or direction of the detected direction arrow.

[0389] In some embodiments, other processing techniques may also be used. For example, similar to lane marking detection as described above, processing unit 110 may be configured to detect one or more anomalies in an image and correct the detected points or features accordingly. Such anomalies may appear in the image captured by vehicle 200 due to, for example, objects obstructing the view of a camera obstructing lane markings, debris on a lens, etc. In some cases, the anomaly may be on the directional arrow itself, which may be damaged or worn, or partially covered, for example, by dust, debris, water, snow, or other materials on the road. Such anomalies may cause erroneous points or features detected on the arrow. Accordingly, the processor may ignore the erroneous points, or may adjust the points to be consistent with other detected points on the arrow. In other embodiments, errors may be corrected after points have already been uploaded, for example, by determining that a point is outside a predicted threshold based on other points uploaded during the same trip or based on aggregation of data from previous trips along the same road segment. As another example, the detected arrow may have rounded corners and therefore may not have well-defined points. Processing unit 110 may be configured to determine points at the rounded edges to indicate associated vertices (e.g., the tip of the arrow). In other embodiments, the processing unit 110 may extrapolate points based on other detected features of the arrow, for example, by detecting the edge of the arrowhead and extrapolating the edge to find the projected vertex where the edge lines intersect.

[0390] According to the disclosed embodiments, vehicle 200 can be configured to upload data associated with the detected arrows to a central server for processing and inclusion in a road navigation map. For example, vehicle 200 (or vehicles 1205, 1210, 1215, 1220, or 1225) can upload data to server 1230 using the various wireless communication methods described above. Instead of uploading an image of the detected directional arrows, the directional arrows themselves can be included in the sparse map 800 as one or more points, location identifiers, and / or direction indicators, thus reducing the size of the sparse map 800 and / or the amount of data that must be remotely uploaded by the vehicle. For example, the directional arrows can be included via the positional and directional components (e.g., ...) associated with the detected directional arrows. Figure 27B The location identifier can be represented by element 2729 in the table. Figure 27B One of the identified points shown, such as apex 2721 or interior points 2725 or 2726. The location identifier may include real-world coordinates of the identified point that can be identified based on the captured image, as described above. The directional arrow may also be represented by a direction indicator associated with the direction of the detected directional arrow. Various methods of transmitting direction can be used. In some embodiments, the direction indicator may be established based on two or more points associated with the directional arrow as a vector. For example, if the apex of the arrow is known, a single other point (e.g., endpoint 2728) may be sufficient to establish the direction indicator. Accordingly, the real-world location of one or more points may be uploaded by vehicle 200. In other embodiments, the direction indicator may be represented as an angle or compass direction. For example, the direction indicator may represent an angle relative to the direction of travel of a lane or a heading based on a coordinate system of a real-world basic orientation or a road navigation map. In some embodiments, various points or features detected by processing unit 110, as well as locations and directions that can be identified on the server side, may be uploaded. In other embodiments, the location identifier and direction indicator may be determined by vehicle 200.

[0391] In some embodiments, various other information or attributes of the directional arrows may be components of the sparse map 800. For example, a vehicle or server may be configured to identify the type or meaning of the detected directional arrows. Accordingly, a type code or other identifier may be associated with the arrow. In some embodiments, the type code may reference a list of known or predetermined arrow types. For example, the processing unit 110 may further be able to correlate detected images, points, or features with specific arrow types (e.g., straight arrows, turning arrows, etc.). The processing unit 110 may access a database or library of predefined arrows to identify the detected directional arrows by processing the images. For example, the database may be based on road marking templates, guidelines, or standards for one or more regions or jurisdictions. Alternatively, this process may be based on data transmitted by the vehicle appearing on the server side. For example, based on the number of points defining the shape of the directional arrow, the server may access the database to associate the detected directional arrows with type codes. For general or unrecognized directional arrows, an image signature that enables the identification of the directional arrow may also be stored. In some embodiments, location identifiers, direction indicators, and / or any additional information may facilitate the use of the directional arrows as road signs for navigation, as described in detail above.

[0392] In some embodiments, crowdsourcing techniques may be used to continuously update the mapped directional arrows within the model. A particular vehicle may upload location identifiers and direction indicators at multiple points in time while traveling on the same road segment, or data may be selected from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling on the road segment at different times. The sparse map 800 can then be updated or refined based on subsequent location identifiers and direction indicators received from the vehicles and stored in the system. As the mapped directional arrows are updated and refined, the updated road navigation model and / or sparse map can be distributed to multiple autonomous vehicles.

[0393] Embodiments of this disclosure may further provide navigation for autonomous vehicles based on detected arrows and their orientation. After detecting and processing directional arrows on the road surface, vehicle 200 may be configured to determine and / or perform autonomous navigation actions. For example, as described above, vehicle 200 may use image capture devices 122 and 124 included in image acquisition unit 120 to capture images of the surrounding environment. Processing unit 110 may then detect directional arrows within the captured image and determine the direction associated with the arrows. In some embodiments, processing unit 110 may also identify a type code or other indication of the arrow's meaning. Then, as a supplement or alternative to providing data to a server for generating a sparse map associated with road segments, vehicle 200 may be configured to determine autonomous navigation actions based on the detected arrows and directions.

[0394] Figure 28AA plan view is shown illustrating an exemplary autonomous navigation maneuver performed by a vehicle on a straight road segment according to the disclosed embodiment. Vehicle 2800 can detect a straight arrow 2801 within its current lane. In this example, vehicle 2800 can determine that the detected arrow aligns with the vehicle's current target trajectory. Accordingly, the autonomous navigation maneuver determined and performed by vehicle 2800 may include maintaining the current heading direction, as shown in autonomous navigation maneuver 2802.

[0395] Conversely, vehicle 2805 can detect a straight arrow 2806 within the current driving lane. In this example, vehicle 2805 can determine that the detected arrow is inconsistent with the current trajectory. For example, if the detected directional arrow is substantially opposite to the vehicle's direction of travel (e.g., the arrow's direction differs from the vehicle's current heading direction by more than 90 degrees in either direction), the vehicle can determine an autonomous navigation action. For example, the vehicle can initiate braking 2807 to slow or stop the vehicle, and / or perform steering 2808 to move the vehicle into a lane with the correct driving direction. In addition to the directional arrows, other elements within the captured image can be analyzed to inform the determination of navigation actions. For example, vehicle 2805 can detect a straight arrow 2803 in an adjacent lane that aligns with the current driving direction and can perform a steering action to move into the correct lane. Vehicle 2804 can also detect lane markings 2804 and determine that the correct driving lane is on the opposite side of the lane markings.

[0396] Figure 28B This diagram illustrates a demonstration autonomous navigation maneuver performed by a vehicle from a turning lane according to the disclosed embodiment. Vehicle 2800 may be approaching an intersection and may detect a right-turn arrow 2811 in its current lane (lane 2816). Vehicle 2800 may determine that the arrow indicates the current lane is for right turns only, not for through traffic. If the vehicle's target trajectory aligns with a turn (e.g., the vehicle needs to turn right at an intersection), the vehicle may determine an autonomous navigation maneuver to maintain its current heading. The vehicle may also begin preparing for subsequent navigation maneuvers, such as completing a right turn at the intersection. If the vehicle's target trajectory does not align with directional arrow 2811, vehicle 2800 may determine and / or perform a steering maneuver 2812 to move to a lane that aligns with the vehicle's target trajectory or intended route. For example, vehicle 2800 may determine that lane 2815 aligns with the vehicle's route. When the vehicle detects, for example, a lane transition arrow (see example...), Figure 27A When other arrows such as the lane transition arrow 2711 are displayed, similar navigation actions can be performed.

[0397] In another example, vehicle 2800 may be in a straight-only lane, and it can be determined that it needs to be in a turning lane. Figure 28CA plan view is shown illustrating a demonstrative autonomous navigation maneuver performed by a vehicle entering a turning lane according to the disclosed embodiment. Vehicle 2800 can detect a straight arrow 2821 in lane 2815 and determine that the lane usage of the current lane is inconsistent with the target trajectory of the expected route. Accordingly, vehicle 2800 can determine and / or perform a steering maneuver 2822.

[0398] In some embodiments, a vehicle may rely on directional arrows outside its current lane. In such embodiments, processing unit 110 may detect directional arrows within a captured image, but based on the arrow's position relative to the vehicle, processing unit 110 may associate the directional arrow with adjacent lanes. Autonomous vehicle navigation may also be determined from such directional arrows outside the current lane. For example, Figure 28D A plan view illustrates an exemplary autonomous navigation maneuver based on directional arrows outside the current lane 2835, according to the disclosed embodiment. In this example, vehicle 2800 may not detect any directional arrows in the current lane, but may detect a turn arrow 2831 in an adjacent lane. Based on the analysis of the image and the detected arrow, vehicle 2800 may determine that the adjacent lane 2836 is a turn-only lane. If the vehicle's expected route is straight, no autonomous navigation maneuver may be taken, or the autonomous navigation maneuver may be to maintain the vehicle's current heading. If the target trajectory or expected route includes a turn near an intersection, vehicle 2800 may determine and / or perform a turning maneuver 2832 to enter the adjacent lane associated with the detected arrow. Vehicle 2800 may also navigate based on arrows detected in other locations in the surrounding environment, such as traffic signs.

[0399] In some embodiments, an autonomous vehicle may navigate based on directional arrows contained in a road navigation model (e.g., a sparse map 800). For example, the vehicle may receive a sparse map 800 containing mapped directional arrows. As described above, these mapped arrows may be determined based on data from one or more previous vehicles traversing the same road. In some cases, a vehicle navigating based on directional arrows in the sparse map 800 may determine the position and / or direction of the mapped arrows based on arrows detected on the road. In other cases, the vehicle may interpret the mapped directional arrows but may not detect real-world arrows on the road. For example, arrows may be worn, obscured by another object, or covered with dust, snow, or other debris. In such cases, the autonomous vehicle may rely on the mapped arrows used for navigation. Figure 28E This illustrates a demonstrative autonomous navigation maneuver performed by a vehicle based on mapped directional arrows, according to the disclosed embodiment. Vehicle 2840 can receive a sparse map, which, as shown in this example, may correspond to... Figure 28BThe intersection is shown. Vehicle 2840 (overlaid on a sparse map for illustration) can determine its longitudinal alignment along the target trajectory 2846. Vehicle 2840 can then determine autonomous navigation actions based on the mapped arrow 2841. If vehicle 2840 determines that the mapped arrow 2841 aligns with the expected route (e.g., a right turn at the intersection), the autonomous navigation actions may include maintaining the same heading direction and / or reducing the vehicle's speed to prepare for the turn. In other cases, vehicle 2840 may determine that the mapped arrow 2841 does not align with the vehicle's expected route (e.g., if the vehicle's expected route is straight through the intersection). Accordingly, vehicle 2840 can determine and / or perform a steering action 2842, which aligns the vehicle with the new target trajectory 2845. Various other autonomous navigation actions can also be performed, in conjunction with those described above. Figures 28A-28D The similarity.

[0400] Figure 29A This is a flowchart illustrating an exemplary process 2900A for use in autonomous vehicle navigation according to the disclosed embodiments, mapping directional arrows. Process 2900A may be executed by one or more processing devices included in a server (e.g., server 1230).

[0401] In step 2910, process 2900A may include receiving at least one location identifier associated with a detected directional arrow on a road surface. In some embodiments, the location identifier may be determined based on the acquisition of at least one image representing the environment of the main vehicle from a photographic device associated with the main vehicle. The directional arrow may be detected, for example, by vehicle 200 through capturing one or more images via image acquisition unit 120. The location identifier may be further determined by analyzing at least one image to detect directional arrows on a road surface in the environment of the main vehicle. For example, processing unit 110 may then analyze the captured image to identify directional arrows within the captured image. Determining the location identifier may further include analyzing at least one image to determine the position of the detected directional arrow relative to at least one location associated with the main vehicle. Processing unit 110 may, for example, determine the position of the directional arrow relative to the vehicle's position. The position may be further identified by recognizing other features (e.g., road signs or lane markings with known locations) from the captured image.

[0402] The location identifier may also include the real-world coordinates of the point associated with the detected directional arrow. For example, processing unit 110 may determine one or more points associated with the detected arrow, as described above for... Figure 27B As described above. One or more of these points can be associated with real-world coordinates, which can be determined based on the vehicle's position and / or through analysis of the captured images. In some embodiments, the point may correspond to the position of the tip of an associated directional arrow. For example, as... Figure 27BThe tip 2721 is shown for determination. In some cases, the actual tip of the arrow may not be determined, but rather a reference point indicating the direction of the arrow is determined, for example, when the arrow has wear or dots. In other embodiments, the point may coincide with a position inside the arrowhead associated with the direction. For example, the point may coincide with the center point of the arrowhead, the center point of the tip, or other internal reference point.

[0403] In step 2912, process 2900A may include receiving at least one direction indicator associated with the detected directional arrow. Similar to a location identifier, the direction indicator may be determined by processing unit 110 based on an image acquired by vehicle 200. The direction of the arrow may be determined using various methods as described above. For example, the direction indicator may be represented as a vector and may include ordered pairs of points associated with the detected directional arrow. The direction may be determined, for example, by determining the direction of a line from a first point to a second point in the ordered pair (e.g., from tail point to apex, center point to apex, etc.). The direction indicator may also include designating the point associated with the detected directional arrow as the apex of the directional arrow. If at least one other point is known, knowing which point corresponds to the apex is sufficient t...

Claims

1. A navigation system for a vehicle, the navigation system comprising: At least one processor, programmed as follows: Receive a first image captured from the environment of the vehicle from the vehicle's first camera device; Receive a second image captured from the environment of the vehicle from the vehicle's second camera device; The first image is analyzed to generate a first detection result, wherein the first detection result includes an identifier of a first traffic light and a first state of the first traffic light; The second image is analyzed to generate a second detection result, wherein the second detection result includes an identifier of the first traffic light and a second state of the first traffic light; Analyze at least one of the first image or the second image to identify the state of a second traffic light in the environment of the vehicle; The first detection result and the second detection result are compared to determine the confirmation state of the first traffic light based on the first state and the second state being in the same state, wherein the confirmation state is further determined based on map information specifying whether the first traffic light has a state pattern common to the second traffic light; The navigation action of the vehicle is determined based on the confirmation status of the first traffic light; as well as To enable the vehicle to perform the navigation action.

2. The system as claimed in claim 1, wherein, The at least one processor is further programmed to: Determine a first confidence level indicator associated with the first detection result; Determine a second confidence level indicator associated with the second detection result; as well as The confirmation status of the first traffic light is determined based on a comparison between the first confidence level indicator and the second confidence level indicator.

3. The system as described in claim 1, wherein, The determination of the vehicle's navigation actions is further based on the time interval between capturing the first image and the second image.

4. The system as claimed in claim 1, wherein, The at least one processor is further programmed to determine the confirmation state of the first traffic light based at least in part on the previous observed state of the first traffic light.

5. The system as claimed in claim 1, wherein, The at least one processor is further programmed to: Determine the location of the vehicle; and Receive map information specifying the location of the first traffic light, wherein determining the navigation action of the vehicle is further based on a comparison between the vehicle's location and the location of the first traffic light.

6. The system of claim 1, wherein, The at least one processor is further programmed to: The first image is analyzed to identify the second traffic light, and the state of the second traffic light is included in the first detection result; as well as The second image is analyzed to identify the second traffic light, and the state of the second traffic light is included in the second detection result.

7. The system of claim 6, wherein, The second traffic light is adjacent to the first traffic light.

8. The system of claim 6, wherein, The at least one processor is further programmed to: Compare the first detection result and the second detection result; and The confirmation status of the second traffic light is determined at least in part based on the comparison.

9. The system of claim 8, wherein, The determination of the vehicle's navigation action is further based on the confirmation status of the second traffic light.

10. The system of claim 8, wherein, The at least one processor is further programmed to receive map information specifying the spatial relationship between the first traffic light and the second traffic light.

11. The system of claim 1, wherein, The map information indicates that the first traffic light and the second traffic light share a common state mode.

12. The system of claim 1, wherein, The map information specifies that the first traffic light and the second traffic light have opposite state modes.

13. The system of claim 1, wherein, The first photographic device and the second photographic device have at least partially overlapping fields of view.

14. The system of claim 1, wherein, The first photographic device and the second photographic device have different fields of view.

15. The system of claim 1, wherein, The first photographic device and the second photographic device have the same focal length.

16. The system of claim 1, wherein, The first photographic device and the second photographic device have different focal lengths.

17. The system of claim 1, wherein: At least one of the first image or the second image includes a representation of a traffic light group, the traffic light group comprising the first traffic light and the second traffic light; and The at least one processor is further programmed to receive map information specifying the relationship between the first traffic light and the second traffic light in the traffic light group.

18. The system of claim 17, wherein, The at least one processor is further programmed to determine the confirmed detection result based on the map information specifying the relationship between the first traffic light and the second traffic light in the traffic light group.

19. A method for navigating a vehicle, comprising: Receive a first image captured from the environment of the vehicle from the vehicle's first camera device; Receive a second image captured from the environment of the vehicle from the vehicle's second camera device; The first image is analyzed to generate a first detection result, wherein the first detection result includes an identifier of a first traffic light and a first state of the first traffic light; The second image is analyzed to generate a second detection result, wherein the second detection result includes an identifier of the first traffic light and a second state of the first traffic light; Analyze at least one of the first image or the second image to identify the state of a second traffic light in the environment of the vehicle; The first detection result and the second detection result are compared to determine the confirmation state of the first traffic light based on the first state and the second state being in the same state, wherein the confirmation state is further determined based on map information specifying whether the first traffic light has a state pattern common to the second traffic light; The navigation action of the vehicle is determined based on the confirmation status of the first traffic light; as well as To enable the vehicle to perform the navigation action.

20. A non-transitory computer-readable medium comprising instructions, said instructions, when executed by at least one processor, configuring said at least one processor to be programmed to: Receive a first image captured from the environment of the vehicle from the vehicle's first camera device; Receive a second image captured from the environment of the vehicle from the vehicle's second camera device; The first image is analyzed to generate a first detection result, wherein the first detection result includes an identifier of a first traffic light and a first state of the first traffic light; The second image is analyzed to generate a second detection result, wherein the second detection result includes an identifier of the first traffic light and a second state of the first traffic light; Analyze at least one of the first image or the second image to identify the state of a second traffic light in the environment of the vehicle; The first detection result and the second detection result are compared to determine the confirmation state of the first traffic light based on the first state and the second state being in the same state, wherein the confirmation state is further determined based on map information specifying whether the first traffic light has a common state pattern with the second traffic light in the environment of the vehicle. The navigation action of the vehicle is determined based on the confirmation status of the first traffic light; as well as To enable the vehicle to perform the navigation action.

21. A navigation system for a vehicle, the navigation system comprising: At least one processor, programmed as follows: Receive an image captured from the environment of the vehicle, wherein the image has a first resolution; Identify at least one representation of a moving object in the image; Before generating a modified version of the captured image, at least one representation of the identified moving object is excluded from the traffic light analysis; The modified version of the captured image is analyzed to determine at least one traffic light candidate region associated with the modified version of the captured image, wherein the modified version of the captured image has a second resolution that is lower than the first resolution of the captured image; A portion of the captured image to be analyzed is determined based on the at least one traffic light candidate region of the modified version of the captured image, wherein the portion of the captured image corresponds to the at least one traffic light candidate region of the modified version of the captured image; as well as In response to determining the at least one traffic light candidate region of the modified version of the captured image, the determined portion of the captured image is analyzed to confirm that the representation of the traffic light exists in the determined portion of the captured image.

22. The system of claim 21, wherein, The at least one processor is further programmed to determine the state of the traffic light based on the analysis of the at least one traffic light candidate region of the modified version of the captured image.

23. The system of claim 21, wherein, The at least one traffic light candidate area includes a representation of at least one candidate traffic light.

24. The system of claim 21, wherein, The at least one traffic light candidate region is associated with a representation of an object having a rectangular shape.

25. The system of claim 24, wherein, The rectangular object includes a traffic light fixing device.

26. The system of claim 24, wherein, The rectangular objects include traffic lights.

27. The system of claim 21, wherein, The at least one processor is further programmed to analyze the portion of the captured image to determine the state of the traffic light.

28. The system of claim 27, wherein, The at least one processor is further programmed to determine the vehicle's navigation actions based on the state of the traffic lights.

29. The system of claim 28, wherein, The at least one processor is further programmed to enable the vehicle to perform the navigation action.

30. The system of claim 21, wherein, The modified version of the captured image has a resolution that is at least half that of the original captured image.

31. The system of claim 21, wherein, The modified version of the captured image has a resolution that is at least one-third that of the original captured image.

32. The system of claim 21, wherein, The modified version of the captured image has a resolution that is at least one-quarter of the resolution of the captured image.

33. A method for detecting traffic lights, comprising: Receive an image captured from the vehicle's environment, wherein the image has a first resolution; Identify at least one representation of a moving object in the image; Before generating a modified version of the captured image, at least one representation of the identified moving object is excluded from the traffic light analysis; The modified version of the captured image is analyzed to determine at least one traffic light candidate region associated with the modified version of the captured image, wherein the modified version of the captured image has a second resolution that is lower than the first resolution of the captured image; A portion of the captured image to be analyzed is determined based on the at least one traffic light candidate region of the modified version of the captured image, wherein the portion of the captured image corresponds to the at least one traffic light candidate region of the modified version of the captured image; as well as In response to determining the at least one traffic light candidate region of the modified version of the captured image, the determined portion of the captured image is analyzed to confirm that the representation of the traffic light exists in the determined portion of the captured image.

34. The method of claim 33, wherein, The at least one traffic light candidate region is associated with a representation of an object having a rectangular shape.

35. The method of claim 34, wherein, The rectangular object includes a traffic light fixing device.

36. The method of claim 34, wherein, The rectangular objects include traffic lights.

37. The method of claim 33, further comprising analyzing said portion of the captured image to determine the state of the traffic light.

Images