System and method for vehicle navigation based on image analysis

Abstract

Systems and methods for vehicle navigation are provided. In one embodiment, at least one processing device may receive at least one captured image representing an environment of a host vehicle, the at least one captured image being captured by a camera of the host vehicle; inputting the at least one captured image into a trained system, the trained system being configured to, for each of a plurality of pixels representing at least a portion of the target vehicle in the at least one captured image, receive the at least one captured image; determining one or more estimated distance values representing a distance from the pixel to at least one edge of the face of the target vehicle; and generating at least a portion of a boundary with respect to the target vehicle based on the determined one or more distance values.

Description

[0001] This patent application is a divisional application of the following invention patent application:

[0002] Application No.: 202080036539.6

[0003] Application Date: May 22, 2020

[0004] Invention Title: Systems and Methods for Vehicle Navigation Based on Image Analysis Cross - reference to Related Applications

[0005] This application claims the priority benefits of U.S. Provisional Patent Application No. 62 / 852,761, filed on May 24, 2019, U.S. Provisional Patent Application No. 62 / 957,009, filed on January 3, 2020, and U.S. Provisional Patent Application No. 62 / 976,059, filed on February 13, 2020. All of the above applications are hereby incorporated by reference in their entirety. Technical Field

[0006] This disclosure generally relates to autonomous vehicle navigation. Background Art

[0007] With the continuous progress of technology, the goal of fully autonomous vehicles that can navigate on roads is on the horizon. Autonomous vehicles may need to consider a wide variety of factors and make appropriate decisions based on those factors to safely and accurately reach the intended destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured from cameras), information from radar or lidar, and may also use information obtained from other sources (e.g., from GPS devices, speed sensors, accelerometers, suspension sensors, etc.). At the same time, to navigate to a destination, an autonomous vehicle may also need to identify its position within a particular road (e.g., a particular lane in a multi - lane road), navigate side - by - side with other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and drive from one road to another at appropriate intersections or junctions. Harnessing and interpreting the large amount of information collected by the vehicle when it reaches its destination poses many design challenges. The vast amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that an autonomous vehicle may need to analyze, access, and / or store poses challenges that may actually limit or even adversely affect autonomous navigation. In addition, if autonomous vehicles rely on traditional mapping techniques to navigate, the vast amount of data required to store and update maps will pose significant challenges. Summary of the Invention

[0008] Embodiments consistent with the present disclosure provide systems and methods for autonomous vehicle navigation. The disclosed embodiments may use cameras to provide autonomous vehicle navigation features. For example, consistent with the disclosed embodiments, the disclosed system may include one, two, or more cameras that monitor the environment of the vehicle. The disclosed system may provide a navigation response, for example, based on an analysis of images captured by one or more cameras.

[0009] In one embodiment, a navigation system for a host vehicle includes at least one processor. The processor may be programmed to receive at least one captured image representing the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; input the at least one captured image into a trained system that is configured to determine, for each of a plurality of pixels representing at least a portion of a target vehicle in the at least one captured image, one or more estimated distance values representing a distance from the pixel to at least one edge of a face of the target vehicle; and generate, based on the determined one or more distance values, at least a portion of a boundary relative to the target vehicle.

[0010] In one embodiment, a navigation system for a host vehicle includes at least one processor. The processor may be programmed to receive at least one captured image representing the environment of the host vehicle from a camera of the host vehicle; and analyze one or more pixels of the at least one captured image to determine whether the one or more pixels represent at least a portion of a target vehicle. For pixels determined to represent at least a portion of the target vehicle, the processor may determine one or more estimated distance values from the one or more pixels to at least one edge of a face of the target vehicle. Additionally, the processor may generate at least a portion of a boundary relative to the target vehicle based on an analysis of the one or more pixels, including the determined one or more distance values associated with the one or more pixels.

[0011] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one captured image representing the environment of the host vehicle from a camera of the host vehicle; and analyze one or more pixels of the at least one captured image to determine whether the one or more pixels represent a target vehicle, wherein at least a portion of the target vehicle is not represented in the at least one captured image. The processor may also be configured to determine an estimated distance from the host vehicle to the target vehicle, wherein the estimated distance is based at least in part on the portion of the target vehicle that is not represented in the at least one captured image.

[0012] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one captured image representing the environment of the host vehicle from a camera of the host vehicle; and analyze two or more pixels of the at least one captured image to determine whether the two or more pixels represent at least a portion of a first target vehicle and at least a portion of a second target vehicle. The processor may be programmed to determine that the portion of the second target vehicle is included in an image representation on the surface of the first target vehicle. The processor may also be programmed to generate at least a portion of a boundary relative to the first target vehicle and not generate a boundary relative to the second target vehicle based on the analysis of the two or more pixels and the determination that the portion of the second target vehicle is included in the image representation on the surface of the first target vehicle.

[0013] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one captured image representing the environment of the host vehicle from a camera of the host vehicle; and analyze two or more pixels of the at least one captured image to determine whether the two or more pixels represent at least a portion of a first target vehicle and at least a portion of a second target vehicle. The processor may be programmed to determine that the second target vehicle is carried or towed by the first target vehicle. The processor may also be programmed to generate at least a portion of a boundary relative to the first target vehicle and not generate a boundary relative to the second target vehicle based on the analysis of the two or more pixels and the determination that the second target vehicle is carried or towed by the first target vehicle.

[0014] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive a first captured image representing the environment of the host vehicle from a camera of the host vehicle; and analyze one or more pixels of the first captured image to determine whether the one or more pixels represent at least a portion of a target vehicle. For pixels determined to represent at least a portion of the target vehicle, the processor may determine one or more estimated distance values from the one or more pixels to at least one edge of a face of the target vehicle. The processor may be programmed to generate at least a portion of a first boundary relative to the target vehicle based on the analysis of the one or more pixels of the first captured image, including the one or more distance values determined to be associated with the one or more pixels of the first captured image. The processor may also be programmed to receive a second captured image representing the environment of the host vehicle from the camera of the host vehicle; and analyze one or more pixels of the second captured image to determine whether the one or more pixels represent at least a portion of the target vehicle. For pixels determined to represent at least a portion of the target vehicle, the processor may determine one or more estimated distance values from the one or more pixels to at least one edge of a face of the target vehicle. The processor may be programmed to generate at least a portion of a second boundary relative to the target vehicle based on the analysis of the one or more pixels of the second captured image, including the one or more distance values determined to be associated with the one or more pixels of the second captured image, and based on the first boundary.

[0015] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive two or more images captured from the environment of the host vehicle from a camera of the host vehicle; and analyze the two or more images to identify representations of at least a portion of a first object and representations of at least a portion of a second object. The processor may determine a first region associated with the first object in at least one image, and the type of the first object; and determine a second region associated with the second object in at least one image, and the type of the second object, wherein the type of the first object is different from the type of the second object.

[0016] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one image captured from the environment of the host vehicle from a camera of the host vehicle; and analyze the at least one image to identify a representation of at least a portion of a first object and a representation of at least a portion of a second object. The processor may be programmed to determine at least one aspect of the geometry of the first object and at least one aspect of the geometry of the second object based on the analysis. Additionally, the processor may be programmed to generate a first label associated with a region of the at least one image that includes the representation of the first object based on at least one aspect of the geometry of the first object; and generate a second label associated with a region of the at least one image that includes the representation of the second object based on at least one aspect of the geometry of the second object.

[0017] In one embodiment, a method for navigating a host vehicle may include: receiving at least one captured image representing the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; inputting the at least one captured image into a trained system configured to determine, for each of a plurality of pixels representing at least a portion of a target vehicle in the at least one captured image, one or more estimated distance values representing a distance from the pixel to at least one edge of a face of the target vehicle; and generating at least a portion of a boundary relative to the target vehicle based on the determined one or more distance values.

[0018] In one embodiment, a non-transitory computer-readable medium storing instructions that, when executed by at least one processor, are configured to cause the at least one processor to perform a method for navigating a host vehicle, the method including: receiving at least one captured image representing the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; inputting the at least one captured image into a trained system configured to determine, for each of a plurality of pixels representing at least a portion of a target vehicle in the at least one captured image, one or more estimated distance values representing a distance from the pixel to at least one edge of a face of the target vehicle; and generating at least a portion of a boundary relative to the target vehicle based on the determined one or more distance values.

[0019] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions executable by at least one processing device and may perform any method described herein.

[0020] The foregoing general description and the following detailed description are merely exemplary and illustrative and are not restrictive of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments. In the drawings:

[0022] Figure 1 is an illustrative representation of an exemplary system consistent with the disclosed embodiments.

[0023] Figure 2A is an illustrative side view representation of an exemplary vehicle including a system consistent with the disclosed embodiments.

[0024] Figure 2B is Figure 2A an illustrative top view representation of the vehicle and system shown in consistent with the disclosed embodiments.

[0025] Figure 2C is an illustrative top view representation of another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0026] Figure 2D is an illustrative top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0027] Figure 2E is an illustrative top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0028] Figure 2F is an illustrative representation of an exemplary vehicle control system consistent with the disclosed embodiments.

[0029] Figure 3A is an illustrative representation of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with the disclosed embodiments.

[0030] Figure 3B is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.

[0031] Figure 3C is Figure 3B an illustration of the camera mount shown in from a different perspective consistent with the disclosed embodiments.

[0032] Figure 3D is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.

[0033] Figure 4 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0034] Figure 5Ais a flowchart showing an exemplary process for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments.

[0035] Figure 5B is a flowchart showing an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments.

[0036] Figure 5C is a flowchart showing an exemplary process for detecting road signs and / or lane geometry information in a set of images consistent with the disclosed embodiments.

[0037] Figure 5D is a flowchart showing an exemplary process for detecting traffic lights in a set of images consistent with the disclosed embodiments.

[0038] Figure 5E is a flowchart showing an exemplary process for causing one or more navigation responses based on a vehicle path consistent with the disclosed embodiments.

[0039] Figure 5F is a flowchart showing an exemplary process for determining whether a vehicle ahead is changing lanes consistent with the disclosed embodiments.

[0040] Figure 6 is a flowchart showing an exemplary process for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments.

[0041] Figure 7 is a flowchart showing an exemplary process for causing one or more navigation responses based on the analysis of three sets of images consistent with the disclosed embodiments.

[0042] Figure 8 shows a sparse map for providing autonomous vehicle navigation consistent with the disclosed embodiments.

[0043] Figure 9A shows a polynomial representation of a portion of a road segment consistent with the disclosed embodiments.

[0044] Figure 9B shows a curve representing the target trajectory of a vehicle in a three-dimensional space representing a specific road segment included in a sparse map consistent with the disclosed embodiments.

[0045] Figure 10 shows example landmarks that may be included in a sparse map consistent with the disclosed embodiments.

[0046] Figure 11A shows a polynomial representation of a trajectory consistent with the disclosed embodiments.

[0047] Figure 11B and Figure 11C shows a target trajectory along a multi-lane road consistent with the disclosed embodiments.

[0048] Figure 11D shows an example road signature profile consistent with the disclosed embodiments.

[0049] Figure 12 is a schematic illustration of a system for autonomous vehicle navigation using crowdsourcing data received from multiple vehicles consistent with the disclosed embodiments.

[0050] Figure 13 shows an example autonomous vehicle road navigation model represented by multiple three-dimensional splines consistent with the disclosed embodiments.

[0051] Figure 14 shows a map skeleton generated according to the combined positioning information from multiple drives consistent with the disclosed embodiments.

[0052] Figure 15 shows an example of the longitudinal alignment of two drives with an example sign as a landmark consistent with the disclosed embodiments.

[0053] Figure 16 shows an example of the longitudinal alignment of multiple drives with an example sign as a landmark consistent with the disclosed embodiments.

[0054] Figure 17 is a schematic illustration of a system for generating driving data using a camera, a vehicle, and a server consistent with the disclosed embodiments.

[0055] Figure 18 is a schematic illustration of a system for crowdsourcing a sparse map consistent with the disclosed embodiments.

[0056] Figure 19 is a flowchart showing an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment consistent with the disclosed embodiments.

[0057] Figure 20 shows a block diagram of a server consistent with the disclosed embodiments.

[0058] Figure 21 shows a block diagram of a memory consistent with the disclosed embodiments.

[0059] Figure 22 shows a process for clustering vehicle trajectories associated with a vehicle consistent with the disclosed embodiments.

[0060] Figure 23 Shows a vehicle navigation system that can be used for autonomous navigation consistent with the disclosed embodiments.

[0061] Figure 24A 、 Figure 24B 、 Figure 24C and Figure 24D Shows exemplary lane markings that can be detected consistent with the disclosed embodiments.

[0062] Figure 24E Shows exemplary mapped lane markings consistent with the disclosed embodiments.

[0063] Figure 24F Shows exemplary anomalies associated with detecting lane markings consistent with the disclosed embodiments.

[0064] Figure 25A Shows an exemplary image of the vehicle's surrounding environment for navigation based on mapped lane markings consistent with the disclosed embodiments.

[0065] Figure 25B Shows the lateral positioning correction of the vehicle based on the mapped lane markings in the road navigation model consistent with the disclosed embodiments.

[0066] Figure 26A Is a flowchart showing an exemplary process for mapping lane markings for autonomous vehicle navigation consistent with the disclosed embodiments.

[0067] Figure 26B Is a flowchart showing an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings consistent with the disclosed embodiments.

[0068] Figure 27 Shows an example analysis performed on pixels associated with a target vehicle consistent with the disclosed embodiments.

[0069] Figure 28 Is an illustration of an example image including a partial representation of a vehicle consistent with the disclosed embodiments.

[0070] Figure 29 Is an illustration of an example image of a vehicle on a conveyance consistent with the disclosed embodiments.

[0071] Figure 30A and Figure 30B Shows example images including vehicle reflections consistent with the disclosed embodiments.

[0072] Figure 31Ais a flowchart showing an example process for navigating a host vehicle based on an analysis of pixels in an image, consistent with the disclosed embodiments.

[0073] Figure 31B is a flowchart showing an example process for navigating a host vehicle based on a partial representation of a vehicle in an image, consistent with the disclosed embodiments.

[0074] Figure 32A is a flowchart showing an example process for navigating a host vehicle based on an analysis of pixels in an image containing a vehicle reflection, consistent with the disclosed embodiments.

[0075] Figure 32B is a flowchart showing an example process for navigating a host vehicle based on an analysis of pixels in an image containing a towed vehicle, consistent with the disclosed embodiments.

[0076] Figure 33 is a flowchart showing an example process for navigating a host vehicle based on an analysis of pixels in a series of images, consistent with the disclosed embodiments.

[0077] Figure 34A and Figure 34B show example image classifications that can be performed, consistent with the disclosed embodiments.

[0078] Figure 35 is a flowchart showing an example process for navigating a host vehicle based on an analysis of pixels in an image, consistent with the disclosed embodiments.

[0079] Figure 36 shows an example database including object label information, consistent with the disclosed embodiments.

[0080] Figure 37 is a flowchart showing an example process for navigating a host vehicle based on object labels and geometry, consistent with the disclosed embodiments. Detailed Description

[0081] The following detailed description refers to the accompanying drawings. Whenever possible, the same reference numbers are used in the drawings and the following description to refer to the same or like parts. Although several illustrative embodiments are described herein, modifications, adaptations, and other embodiments are possible. For example, components shown in the drawings may be replaced, added, or modified, and the illustrative methods described herein may be modified by replacing, reordering, removing, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0082] Overview of Autonomous Vehicles

[0083] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that is capable of effecting at least one navigation change without driver input. "Navigation change" refers to one or more changes in the steering, braking, or acceleration of the vehicle. For a vehicle to be autonomous, it does not need to be fully automatic (e.g., fully operable without a driver or without driver input). Instead, an autonomous vehicle includes vehicles that are capable of operating under the control of a driver during some time periods and operating those vehicles without driver control during other time periods. An autonomous vehicle can also include a vehicle that controls only some aspects of the vehicle's navigation, such as steering (e.g., maintaining the vehicle's route between vehicle lane limits), but can leave other aspects to the driver (e.g., braking). In some cases, an autonomous vehicle can handle some or all aspects of the vehicle's braking, speed control, and / or steering.

[0084] Since human drivers typically rely on visual cues and observations to control a vehicle, the transportation infrastructure has accordingly been built where lane markings, traffic signs, and traffic lights are all designed to provide visual information to the driver. Given these design features of the transportation infrastructure, an autonomous vehicle can include a camera and a processing unit that analyzes visual information captured from the vehicle's environment. Visual information can include, for example, components of the transportation infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) observable by a driver and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, an autonomous vehicle can also use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, a vehicle can use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information related to its environment while the vehicle is in motion, and the vehicle (and other vehicles) can use this information to locate itself on the model.

[0085] In some embodiments of the present disclosure, an autonomous vehicle can use information obtained during navigation (from cameras, GPS devices, accelerometers, speed sensors, suspension sensors, etc.). In other embodiments, an autonomous vehicle can use information obtained from the vehicle's (or other vehicles') past navigation during navigation. In other embodiments, an autonomous vehicle can use a combination of information obtained during navigation and information obtained from past navigation. The following sections provide an overview of a system consistent with the disclosed embodiments, followed by an overview of a forward imaging system and method consistent with the system. The following sections disclose systems and methods for constructing, using, and updating a sparse map for autonomous vehicle navigation.

[0086] System Overview

[0087] Figure 1is a block diagram of a representation system 100 consistent with the disclosed exemplary embodiments. System 100 can include various components depending on the requirements of a particular implementation. In some embodiments, system 100 can include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. The processing unit 110 can include one or more processing devices. In some embodiments, the processing unit 110 can include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, the image acquisition unit 120 can include any number of image acquisition devices and components depending on the requirements of a particular application. In some embodiments, the image acquisition unit 120 can include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 can also communicatively couple the processing device 110 to a data interface 128 of the image acquisition device 120. For example, the data interface 128 can include any wired and / or wireless one or more links for transferring image data acquired by the image acquisition device 120 to the processing unit 110.

[0088] The wireless transceiver 172 can include one or more devices configured to exchange transmissions to one or more networks (e.g., cellular, Internet, etc.) over an air interface using radio frequency, infrared frequency, magnetic field, or electric field. The wireless transceiver 172 can use any known standard to transmit and / or receive data (e.g., Wi-Fi, Bluetooth®, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions can include communication from the host vehicle to one or more remote servers. Such transmissions can also include communication (one-way or two-way) between the host vehicle and one or more target vehicles in the environment of the host vehicle (e.g., to facilitate coordination of the navigation of the host vehicle in view of or in conjunction with the target vehicles in the environment of the host vehicle), or even include broadcast transmissions to unspecified receivers in the vicinity of the transmitting vehicle.

[0089] Both the application processor 180 and the image processor 190 can include various types of hardware-based processing devices. For example, either or both of the application processor 180 and the image processor 190 can include a microprocessor, a pre-processor (such as an image pre-processor), a graphics processor, a central processing unit (CPU), support circuitry, a digital signal processor, an integrated circuit, a memory, or any other type of device suitable for running applications and suitable for image processing and analysis. In some embodiments, the application processor 180 and / or the image processor 190 can include any type of single-core or multi-core processor, a mobile device microcontroller, a central processing unit, etc. Various processing devices can be used, including, for example, processors that can be obtained from manufacturers such as Intel®, AMD®, etc. or GPUs that can be obtained from manufacturers such as NVIDIA®, ATI®, etc., and can include various architectures (e.g., x86 processors, ARM®, etc.).

[0090] In some embodiments, the application processor 180 and / or the image processor 190 can include any EyeQ series processor chip available from Mobileye®. Each of these processor designs includes multiple processing units with local memories and instruction sets. Such a processor can include a video input for receiving image data from multiple image sensors and can also include video output capabilities. In one example, EyeQ2® uses 90 nanometer-micron technology operating at 332Mhz. The EyeQ2® architecture consists of two floating-point hyper-threaded 32-bit RISC CPUs (MIPS32® 34K® cores), five vision computing engines (VCEs), three vector microcode processors (VMP®), a Denali 64-bit mobile DDR controller, a 128-bit internal supersonic interconnect (Sonics Interconnect), dual 16-bit video inputs and 18-bit video output controllers, 16-channel DMA, and several peripheral devices. The MIPS34K CPU manages the five VCEs, three VMP™s and DMA, the second MIPS34K CPU and multi-channel DMA, and other peripheral devices. The five VCEs, three VMP®s, and the MIPS34K CPU can perform the intensive vision computations required for multifunctional bundled applications. In another example, EyeQ3®, which is a third-generation processor and six times more powerful than EyeQ2®, can be used in the disclosed embodiments. In other examples, EyeQ4® and / or EyeQ5® can be used in the disclosed embodiments. Of course, any updated or future EyeQ processing device can also be used with the disclosed embodiments.

[0091] Any processing device disclosed herein may be configured to perform certain functions. Configuring a processing device, such as any of the described EyeQ processors or other controllers or microprocessors, to perform certain functions may include programming computer-executable instructions and making these instructions available to the processing device for execution during operation of the processing device. In some embodiments, configuring the processing device may include directly programming the processing device using architectural instructions. For example, a processing device such as a field-programmable gate array (FPGA), application-specific integrated circuit (ASIC), etc. may be configured using, for example, one or more hardware description languages (HDL).

[0092] In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible to the processing device during operation. For example, the processing device may access the memory during operation to obtain and execute the stored instructions. In either case, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a hardware-based dedicated system that controls multiple hardware-based components of the host vehicle.

[0093] Although Figure 1 FIG. depicts two separate processing devices included in processing unit 110, more or fewer processing devices may be used. For example, in some embodiments, the tasks of application processor 180 and image processor 190 may be completed using a single processing device. In other embodiments, these tasks may be performed by more than two processing devices. Additionally, in some embodiments, system 100 may include one or more of the processing units 110 without including other components such as image acquisition unit 120.

[0094] The processing unit 110 may include various types of devices. For example, the processing unit 110 may comprise various devices such as a controller, an image pre-processor, a central processing unit (CPU), a graphics processing unit (GPU), support circuitry, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image pre-processor may comprise a video processor for capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuitry may be any number of circuits known in the art, including caches, power supplies, clocks, and input / output circuits. The memory may store software that, when executed by the processor, controls the operation of the system. The memory may comprise a database and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage devices, tape storage devices, removable storage devices, and other types of storage devices. In one instance, the memory may be separate from the processing unit 110. In another instance, the memory may be integrated into the processing unit 110.

[0095] Each of the memories 140, 150 may contain software instructions that, when executed by a processor (e.g., the application processor 180 and / or the image processor 190), may control the operation of various aspects of the system 100. These memory units may contain various databases and image processing software, as well as trained systems such as neural networks or, for example, deep neural networks. The memory units may contain random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage devices, tape storage devices, removable storage devices, and / or any other type of storage device. In some embodiments, the memory units 140, 150 may be separate from the application processor 180 and / or the image processor 190. In other embodiments, these memory units may be integrated into the application processor 180 and / or the image processor 190.

[0096] 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 may determine the user's location and speed by processing signals broadcast by global positioning system satellites. The position information from the position sensor 130 may be made available to the application processor 180 and / or the image processor 190.

[0097] In some embodiments, system 100 may include components such as speed sensors (e.g., tachometers, speedometers) for measuring the speed of vehicle 200 and / or accelerometers (single-axis or multi-axis) for measuring the acceleration of vehicle 200.

[0098] User interface 170 may include any device suitable for providing information to and receiving input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including for example touchscreens, microphones, keyboards, pointer devices, trackballs, cameras, knobs, buttons, etc. Using such input devices, a user can provide information input or commands to system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, pointers, or eye-tracking capabilities, or by any other technique suitable for communicating information to system 100.

[0099] User interface 170 may be equipped with one or more processing devices configured to provide and receive information from a user and process such 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 touches and / or gestures made 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 device for providing output information to a user.

[0100] 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 related to the locations of various items in a reference coordinate system, the various items including roads, water features, geographical features, commercial areas, points of interest, restaurants, gas stations, etc. Map database 160 may store not only the locations of such items, but also descriptors associated with such items, including for example names associated with any stored features. In some embodiments, map database 160 may be physically located together with other components of system 100. Alternatively or additionally, map database 160 or a portion thereof may be located remotely 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 a cellular network and / or the Internet, etc.). In some cases, map database 160 may store a sparse data model that includes polynomial representations of certain road features (e.g., lane markings) or the target trajectory of the host vehicle. Systems and methods for generating such maps are discussed below with reference to Figures 8 to 19 discussed systems and methods for generating such maps.

[0101] The image capture devices 122, 124, and 126 can each include any type of device suitable for capturing at least one image from the environment. Additionally, any number of image capture devices can be used to obtain images for input into the image processor. Some embodiments can include only a single image capture device, while other embodiments can include two, three, or even four or more image capture devices. The image capture devices 122, 124, and 126 will be further described with reference to Figures 2B to 2E below.

[0102] The system 100 or its various components can be incorporated into a variety of different platforms. In some embodiments, the system 100 can be included on a vehicle 200, as Figure 2A shown. For example, the vehicle 200 can be equipped with a processing unit 110 of the system 100 and any other components as described above with respect to Figure 1 . Although in some embodiments the vehicle 200 can be equipped with only a single image capture device (e.g., a camera), in other embodiments, such as those discussed in conjunction with Figures 2B - 2E , multiple image capture devices can be used. For example, as Figure 2A shown, either of the image capture devices 122 and 124 of the vehicle 200 can be part of an ADAS (Advanced Driver Assistance System) imaging set.

[0103] The image capture device included on the vehicle 200 as part of the image acquisition unit 120 can be positioned at any suitable location. In some embodiments, as Figures 2A - 2E well as Figures 3A - 3C shown, the image capture device 122 can be located near the rearview mirror. This location can provide a line of sight similar to that of the driver of the vehicle 200, which can help determine what is visible and not visible to the driver. The image capture device 122 can be positioned at any location near the rearview mirror, and placing the image capture device 122 on the driver's side of the mirror can further help obtain an image representing the driver's field of view and / or line of sight.

[0104] Other localizations may also be used for the image capture device of the image acquisition unit 120. For example, the image capture device 124 may be located on or in the bumper of the vehicle 200. Such a localization may be particularly suitable for image capture devices with a wide field of view. The line of sight of an image capture device located on the bumper may be different from the driver's line of sight, and thus, the bumper image capture device and the driver may not always see the same object. The image capture devices (e.g., image capture devices 122, 124, and 126) may also be located in other localizations. For example, the image capture device may be located on or in one or both of the side mirrors of the vehicle 200, on the roof of the vehicle 200, on the hood of the vehicle 200, on the trunk of the vehicle 200, on the side of the vehicle 200, mounted on any window of the vehicle 200, located behind any window of the vehicle 200, or located in front of any window of the vehicle 200, and in or near a lamp mounted on the front and / or rear of the vehicle 200, etc.

[0105] In addition to the image capture device, the vehicle 200 may also include various other components of the system 100. For example, the processing unit 110 may be included on the vehicle 200, integrated or separated from the vehicle's engine control unit (ECU). The vehicle 200 may also be equipped with a position sensor 130 such as a GPS receiver, and may also include a map database 160 as well as memory units 140 and 150.

[0106] As previously discussed, the wireless transceiver 172 may transmit and / or receive data via one or more networks (e.g., cellular networks, the Internet, etc.). For example, the wireless transceiver 172 may upload data collected by the system 100 to one or more servers and download data from one or more servers. For example, via the wireless transceiver 172, the system 100 may receive periodic or on-demand updates to the data stored in the map database 160, the memory 140, and / or the memory 150. Similarly, the wireless transceiver 172 may upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, the vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0107] System 100 may upload data to a server (e.g., to the cloud) based on a privacy level setting. For example, System 100 may implement a privacy level setting to specify or limit the types of data (including metadata) that can uniquely identify the vehicle and / or the driver / owner of the vehicle that are transmitted to the server. Such a setting may be set by the user via, for example, wireless transceiver 172, may be initialized by factory default settings, or by data received by wireless transceiver 172.

[0108] In some embodiments, System 100 may upload data according to a "high" privacy level, and in the case of a set setting, System 100 may transmit data (e.g., location information related to the journey, captured images, etc.) without any details about a particular vehicle and / or driver / owner. For example, when uploading data according to a "high" privacy setting, System 100 may not include the vehicle identification number (VIN) or the name of the driver or owner of the vehicle, and may instead transmit data such as captured images and / or restricted location information related to the journey.

[0109] Other privacy levels may be anticipated. For example, System 100 may transmit data to the server according to a "medium" privacy level, and may include additional information that is not included in the "high" privacy level, such as the make and / or model and / or vehicle type of the vehicle (e.g., passenger car, sport utility vehicle, truck, etc.). In some embodiments, System 100 may upload data according to a "low" privacy level. In the case of a "low" privacy level setting, System 100 may upload data and include information sufficient to uniquely identify a specific vehicle, owner / driver, and / or part or all of the journey traveled by the vehicle. Such "low" privacy level data may include one or more of the following: for example, VIN, driver / owner name, origin of the vehicle before departure, intended destination of the vehicle, make and / or model of the vehicle, vehicle type, etc.

[0110] Figure 2A is an illustrative side view representation of an exemplary vehicle imaging system consistent with the disclosed embodiments. Figure 2B is Figure 2A an illustrative top view illustration of the embodiment shown in. As Figure 2B shown, the disclosed embodiments may include a vehicle 200 that includes System 100 in its body, the System 100 having a first image capture device 122 positioned near the rearview mirror of the vehicle 200 and / or near the driver, a second image capture device 124 positioned above or within the bumper region of the vehicle 200 (e.g., one of the bumper regions 210), and a processing unit 110.

[0111] As Figure 2C shown, both image capture devices 122 and 124 can be positioned near the rearview mirror of the vehicle 200 and / or near the driver. Additionally, although Figure 2B and Figure 2C two image capture devices 122 and 124 are shown, it should be understood that other embodiments can include more than two image capture devices. For example, in the Figure 2D and 2E illustrated embodiment, a first image capture device 122, a second image capture device 124, and a third image capture device 126 are included in the system 100 of the vehicle 200.

[0112] As Figure 2D shown, the image capture device 122 can be positioned near the rearview mirror of the vehicle 200 and / or near the driver, and the image capture devices 124 and 126 can be positioned above or within the bumper region of the vehicle 200 (e.g., one of the bumper regions 210). And as Figure 2E shown, the image capture devices 122, 124, and 126 can be positioned near the rearview mirror of the vehicle 200 and / or near the driver's seat. The disclosed embodiments are not limited to any specific number and configuration of image capture devices, and the image capture devices can be positioned in any suitable location within or on the vehicle 200.

[0113] It should be understood that the disclosed embodiments are not limited to vehicles and can be applied in other scenarios. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200 and can be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0114] The first image capture device 122 can include any suitable type of image capture device. The image capture device 122 can include an optical axis. In one example, the image capture device 122 can include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capture device 122 can provide a resolution of 1280×960 pixels and can include a rolling shutter. The image capture device 122 can include various optical elements. In some embodiments, one or more lenses can be included, such as to provide a desired focal length and field of view for the image capture device. In some embodiments, the image capture device 122 can be associated with a 6-mm lens or a 12-mm lens. In some embodiments, as Figure 2DAs shown, the image capture device 122 can be configured to capture an image with a desired field of view (FOV) 202. For example, the image capture device 122 can be configured to have a conventional FOV, such as in the range of 40 degrees to 56 degrees, including 46-degree FOV, 50-degree FOV, 52-degree FOV, or a larger FOV. Alternatively, the image capture device 122 can be configured to have a narrow FOV in the range of 23 degrees to 40 degrees, such as 28-degree FOV or 36-degree FOV. Additionally, the image capture device 122 can be configured to have a wide FOV in the range of 100 degrees to 180 degrees. In some embodiments, the image capture device 122 can include a wide-angle bumper camera or a camera with an FOV of up to 180 degrees. In some embodiments, the image capture device 122 can be a 7.2M pixel image capture device with an aspect ratio of approximately 2:1 (e.g., HxV = 3800×1900 pixels) and a horizontal FOV of approximately 100 degrees. Such an image capture device can be used in place of a three-image capture device configuration. Due to significant lens distortion, in embodiments where the image capture device uses a radially symmetric lens, the vertical FOV of such an image capture device can be significantly less than 50 degrees. For example, such a lens can be non-radially symmetric, which would allow a vertical FOV greater than 50 degrees in the case of a 100-degree horizontal FOV.

[0115] The first image capture device 122 can acquire a plurality of first images of a scene associated with the vehicle 200. Each of the plurality of first images can be acquired as a series of image scan lines, which can be captured using a rolling shutter. Each scan line can include a plurality of pixels.

[0116] The first image capture device 122 can have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate can refer to the rate at which the image sensor can acquire image data associated with each pixel included in a particular scan line.

[0117] The image capture devices 122, 124, and 126 can include any suitable type and number of image sensors, e.g., including CCD sensors or CMOS sensors, etc. In one embodiment, a CMOS image sensor can be employed with a rolling shutter such that each pixel in a row is read one at a time, and the scanning of the rows is performed on a row-by-row basis until the entire image frame has been captured. In some embodiments, the rows can be captured sequentially from the top to the bottom of the frame.

[0118] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) can constitute a high-resolution imager and can have a resolution greater than 5M pixels, 7M pixels, 10M pixels, or more pixels.

[0119] The use of a rolling shutter may cause pixels in different rows to be exposed and captured at different times, which may cause skewing and other image artifacts in the captured image frame. On the other hand, when the image capture device 122 is configured to operate using a global or synchronous shutter, all pixels can be exposed for the same amount of time and during a common exposure period. As a result, the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a particular time. In contrast, in a rolling shutter application, each row in the frame is exposed and data is captured at different times. Thus, in an image capture device with a rolling shutter, moving objects may appear distorted. This phenomenon will be described in more detail below.

[0120] 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 can include an optical axis. In one embodiment, each of the image capture devices 124 and 126 can include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 can include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 can be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image capture devices 124 and 126 can provide FOVs (such as FOV 204 and 206) that are equal to or narrower than the FOV (such as FOV 202) associated with the image capture device 122. For example, the image capture devices 124 and 126 can have FOVs of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0121] The image capture devices 124 and 126 can acquire a plurality of second and third images of a scene associated with the vehicle 200. Each of the plurality of second and third images can be acquired as second and third series of image scan lines, which can be captured using a rolling shutter. Each scan line or row can have a plurality of pixels. The image capture devices 124 and 126 can have second and third scan rates associated with the acquisition of each image scan line included in the second and third series.

[0122] Each of the image capture devices 122, 124, and 126 can be positioned at any suitable location and orientation relative to the vehicle 200. The relative positions of the image capture devices 122, 124, and 126 can be selected to assist in fusing the information obtained from the image capture devices. For example, in some embodiments, the FOV associated with the image capture device 124 (such as FOV 204) may partially or completely overlap with the FOV associated with the image capture device 122 (such as FOV 202) and the FOV associated with the image capture device 126 (such as FOV 206).

[0123] The image capture devices 122, 124, and 126 can be located at any suitable relative height on the vehicle 200. In one example, there can be a height difference between the image capture devices 122, 124, and 126, which can provide sufficient parallax information to enable stereoscopic analysis. For example, as Figure 2A shown, two of the image capture devices 122 and 124 are at different heights. For example, there can also be a lateral displacement difference between the image capture devices 122, 124, and 126 to give additional parallax information for the stereoscopic analysis by the processing unit 110. The difference in lateral displacement can be represented by dx, as Figure 2C and Figure 2D shown. In some embodiments, there can be a forward or backward displacement (e.g., range displacement) between the image capture devices 122, 124, and 126. For example, the image capture device 122 can be located 0.5 to 2 meters or more behind the image capture device 124 and / or the image capture device 126. Such a type of displacement can enable one of the image capture devices to cover potential blind spots of the other image capture device(s).

[0124] The image capture device 122 can have any suitable resolution capability (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with the image capture device 122 can be higher, lower, or the same as the resolution of the image sensor(s) associated with the image capture devices 124 and 126. In some embodiments, the image sensor(s) associated with the image capture device 122 and / or the image capture devices 124 and 126 can have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0125] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame before proceeding to capture pixel data associated with the next image frame) can be controllable. The frame rate associated with image capture device 122 can be higher, lower, or the same as the frame rates associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 can depend on various factors that may affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 can include selectable pixel delay periods that are applied before or after acquiring image data associated with one or more pixels of an image sensor in image capture devices 122, 124, and / or 126. Generally, image data corresponding to each pixel can be acquired according to the clock rate used for the device (e.g., one pixel per clock cycle). Additionally, in embodiments that include a rolling shutter, one or more of image capture devices 122, 124, and 126 can include selectable horizontal blanking periods that are applied before or after acquiring image data associated with a row of pixels of an image sensor in image capture devices 122, 124, and / or 126. Further, one or more of image capture devices 122, 124, and / or 126 can include selectable vertical blanking periods that are applied before or after acquiring image data associated with an image frame of image capture devices 122, 124, and 126.

[0126] These timing controls can enable synchronization of the frame rates associated with image capture devices 122, 124, and 126, even if the line scan rates of each are different. Additionally, as will be discussed in more detail below, these selectable timing controls and other factors (e.g., image sensor resolution, maximum line scan rate, etc.) can enable synchronization of image capture from regions where the FOV of image capture device 122 overlaps one or more FOVs of image capture devices 124 and 126, even if the field of view of image capture device 122 is different from the FOVs of image capture devices 124 and 126.

[0127] The frame rate timing in 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 two devices, if one device includes an image sensor with a resolution of 640×480 and another device includes an image sensor with a resolution of 1280×960, it takes more time to acquire one frame of image data from the higher resolution sensor.

[0128] 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, it will take a certain minimum amount of time to acquire one line of image data from the image sensors included in image capture devices 122, 124, and 126. Assuming no pixel delay periods are added, this minimum amount of time for acquiring one line of image data will be related to the maximum line scan rate for a particular device. Devices that provide a higher maximum line scan rate have the potential to provide a higher frame rate than devices with a lower maximum line scan rate. In some embodiments, one or more of image capture devices 124 and 126 may have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture device 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more times the maximum line scan rate of image capture device 122.

[0129] 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 that is 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 that is 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 times the line scan rate of image capture device 122.

[0130] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric. In other words, they may include cameras with different fields of view (FOV) and focal lengths. For example, the fields of view of image capture devices 122, 124, and 126 may include any desired regions of the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, behind vehicle 200, to the side of vehicle 200, or a combination thereof.

[0131] In addition, the focal length associated with each of the image capture devices 122, 124, and / or 126 may be selectable (e.g., by including an appropriate lens, etc.) such that each device captures an image of an object at a desired distance range relative to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 may capture images of nearby objects within a few meters of the vehicle. The image capture devices 122, 124, and 126 may also be configured to capture images of objects at a greater distance from the vehicle (e.g., 25 meters, 50 meters, 100 meters, 150 meters, or more). Additionally, the focal lengths of the image capture devices 122, 124, and 126 may be selected such that one image capture device (e.g., image capture device 122) can capture images of objects relatively close to the vehicle (e.g., within 10 meters or within 20 meters), while other image capture devices (e.g., image capture devices 124 and 126) can capture images of objects farther from the vehicle 200 (e.g., greater than 20 meters, 50 meters, 100 meters, 150 meters, etc.).

[0132] According to some embodiments, the FOV of one or more of the image capture devices 122, 124, and 126 may be wide-angle. For example, an FOV of 140 degrees may be advantageous, particularly for the image capture devices 122, 124, and 126 that can be used to capture images of areas near the vehicle 200. For example, the image capture device 122 may be used to capture images of areas on the right or left side of the vehicle 200, and in such an embodiment, it may be desirable for the image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0133] The field of view associated with each of the image capture 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.

[0134] The image capture devices 122, 124, and 126 may be configured to have any suitable field of view. In one particular example, the image capture device 122 may have a horizontal FOV of 46 degrees, the image capture device 124 may have a horizontal FOV of 23 degrees, and the image capture device 126 may have a horizontal FOV between 23 degrees and 46 degrees. In one particular example, the image capture device 122 may have a horizontal FOV of 52 degrees, the image capture device 124 may have a horizontal FOV of 26 degrees, and the image capture device 126 may have a horizontal FOV between 26 degrees and 52 degrees. In some embodiments, the ratio of the FOV of the image capture device 122 to the FOV of the image capture device 124 and / or the image capture device 126 may vary from 1.5 to 2.0. In other embodiments, the ratio may vary between 1.25 and 2.25.

[0135] System 100 may be configured such that the field of view of image capture device 122 at least partially or fully overlaps with the field of view of image capture device 124 and / or image capture device 126. In some embodiments, System 100 may be configured such that the fields of view of image capture devices 124 and 126, for example, fall within (e.g., are narrower than) the field of view of image capture device 122 and share 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 fields of view of image capture devices 122, 124, and 126 may be aligned such that the centers of the narrower FOV image capture devices 124 and / or 126 may be located in the lower half of the field of view of the wider FOV device 122.

[0136] Figure 2F is an illustrative representation of an exemplary vehicle control system consistent with the disclosed embodiments. As Figure 2F indicated, vehicle 200 may include a throttle regulation 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 throttle regulation system 220, braking system 230, and steering system 240 via one or more data links (e.g., any wired and / or wireless link for transmitting data). For example, based on the analysis of images acquired by image capture devices 122, 124, and / or 126, System 100 may provide control signals to one or more of throttle regulation system 220, braking system 230, and steering system 240 to navigate vehicle 200 (e.g., by causing acceleration, steering, lane shift, etc.). Additionally, System 100 may receive inputs from one or more of throttle regulation system 220, braking system 230, and steering system 240 that indicate the operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or steering, etc.). Further details are provided below in conjunction with Figures 4 to 7 provide further details.

[0137] As Figure 3AAs shown, vehicle 200 may also include a user interface 170 for interacting with the driver or passenger of vehicle 200. For example, the user interface 170 in a vehicle application may include a touch screen 320, a knob 330, buttons 340, and a microphone 350. The driver or passenger of vehicle 200 may also use a handle (e.g., located on or near the steering column of vehicle 200 and including, for example, a turn signal handle), buttons (e.g., located on the steering wheel of vehicle 200), etc. to interact with system 100. In some embodiments, the microphone 350 may be positioned adjacent to the rearview mirror 310. Similarly, in some embodiments, the image capture device 122 may be located near the rearview mirror 310. In some embodiments, the 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., alerts) via the speakers 360.

[0138] Figures 3B to 3D is an illustration of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and against a vehicle windshield, as Figure 3B shown. The camera mount 370 may include image capture devices 122, 124, and 126. The image capture devices 124 and 126 may be positioned behind a sunshade 380, which may be flush with the vehicle windshield and include a composite of thin film and / or anti-reflective material. For example, the sunshade 380 may be positioned such that the occlusion is aligned with the vehicle windshield having a matching bevel. In some embodiments, each of the image capture devices 122, 124, and 126 may be positioned behind the sunshade 380, e.g., as depicted in Figure 3D . The disclosed embodiments are not limited to any particular configuration of the image capture devices 122, 124, and 126, the camera mount 370, and the sunshade 380. Figure 3C is Figure 3B an illustration of the camera mount 370 from a front perspective, as shown.

[0139] As will be understood by those skilled in the art who benefit from this disclosure, many changes and / or modifications may be made to the foregoing disclosed embodiments. For example, not all components are necessary for the operation of system 100. Additionally, when providing the functions of the disclosed embodiments, any component may be located in any suitable part of system 100 and the components may be rearranged into various configurations. Accordingly, the foregoing configurations are exemplary, and regardless of the configurations discussed above, system 100 may provide a wide range of functions to analyze the surroundings of vehicle 200 and navigate vehicle 200 in response to that analysis.

[0140] As discussed in more detail below and in accordance with various disclosed embodiments, system 100 may provide various features regarding autonomous driving and / or driver assistance technologies. For example, system 100 may analyze image data, location data (e.g., GPS positioning 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, location sensor 130, and other sensors. Additionally, 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 transmitting control signals to one or more of throttle regulation system 220, braking system 230, and steering system 240). Further, 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 regarding various embodiments provided by system 100 are provided below.

[0141] Forward Multi - Imaging System

[0142] As discussed above, system 100 can provide driving assistance functions using a multi-camera system. The multi-camera system can use one or more cameras facing the front of the vehicle. In other embodiments, the multi-camera system can include one or more cameras facing the side or the rear of the vehicle. In one embodiment, for example, system 100 can use a dual-camera imaging system, where the first camera and the second camera (e.g., image capture devices 122 and 124) can be positioned in front of and / or at the side of a vehicle (e.g., vehicle 200). The first camera can have a field of view that is greater than, less than, or partially overlapping with the field of view of the second camera. Additionally, the first camera can be connected to a first image processor for performing monocular image analysis on the images provided by the first camera, and the second camera can be connected to a second image processor for performing monocular image analysis on the images provided by the second camera. The outputs (e.g., processed information) of the first and second image processors can be combined. In some embodiments, the second image processor can receive images from both the first camera and the second camera to perform stereo analysis. In another embodiment, system 100 can use a triple-camera imaging system, where each camera has a different field of view. Thus, such a system can make decisions based on information derived from objects located at different distances in front of and at the side of the vehicle. References to monocular image analysis can refer to instances of image analysis based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis can refer to instances of image analysis based on two or more images captured using one or more variations in image capture parameters. For example, images captured suitable for performing stereo image analysis can include images captured from two or more different positions, from different fields of view, using different focal lengths, and together with parallax information, etc.

[0143] For example, in one embodiment, system 100 may implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees or other values selected from a range of approximately 20 degrees to 45 degrees, etc.), image capture device 124 may provide a wide field of view (e.g., 150 degrees or other values selected from a range of approximately 100 degrees to approximately 180 degrees), and image capture device 126 may provide an intermediate field of view (e.g., 46 degrees or other values selected from a range of approximately 35 degrees to approximately 60 degrees). In some embodiments, image capture device 126 may serve as the primary or base camera. Image capture devices 122, 124, and 126 may be positioned behind rearview mirror 310 and be positioned substantially side by side (e.g., 6 centimeters apart). Additionally, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 may be mounted behind sun visor 380 that is flush with the windshield of vehicle 200. Such shielding may be used to minimize the impact of any reflections from inside the vehicle on image capture devices 122, 124, and 126.

[0144] In another embodiment, as discussed above in connection with Figure 3B and Figure 3C the wide field of view camera (e.g., image capture device 124 in the above example) may be mounted lower than the narrow field of view camera and the primary field of view camera (e.g., image capture devices 122 and 126 in the above example). Such a configuration may provide a clear line of sight from the wide field of view camera. To reduce reflections, the camera may be mounted close to the windshield of vehicle 200, and a polarizer may be included on the camera to attenuate the reflected light.

[0145] The three-camera system may provide certain performance characteristics. For example, some embodiments may include the ability for one camera to verify the detection of an object based on the detection results from another camera. In the three-camera configuration discussed above, processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), where each processing device is dedicated to processing the images captured by one or more of image capture devices 122, 124, and 126.

[0146] In a three-camera system, a first processing device can receive images from both a main camera and a narrow field-of-view camera, and perform vision processing on the narrow FOV camera, for example to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the first processing device can calculate the disparity of pixels between the images from the main camera and the narrow camera, and create a 3D reconstruction of the environment of vehicle 200. Then the first processing device can combine the 3D reconstruction with 3D map data, or combine the 3D reconstruction with 3D information calculated based on information from another camera.

[0147] A second processing device can receive images from the main camera and perform vision processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the second processing device can calculate a camera displacement, and based on that displacement calculate the disparity of pixels between consecutive images, and create a 3D reconstruction of the scene (e.g., structure from motion). The second processing device can transmit the structure from motion based on the 3D reconstruction to the first processing device for combination with a stereoscopic 3D image.

[0148] A third processing device can receive images from a wide FOV camera, and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device can further execute additional processing instructions to analyze the images to identify moving objects in the images, such as vehicles changing lanes, pedestrians, etc.

[0149] In some embodiments, enabling the flow of image-based information to be captured and processed independently can provide an opportunity to provide redundancy in the system. Such redundancy can include, for example, using a first image capture device and the 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.

[0150] In some embodiments, system 100 may use two image capture devices (e.g., image capture devices 122 and 124) to provide navigation assistance for 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 such a configuration, image capture devices 122 and 124 may provide images for stereoscopic analysis by system 100 to navigate vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of information obtained based on images captured by image capture device 122 and / or image capture device 124. In other words, image capture device 126 (and the corresponding processing device) may be considered to provide a redundant subsystem for providing an examination of the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Additionally, in some embodiments, redundancy and verification of 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 external to the vehicle, etc.).

[0151] Those skilled in the art will recognize that the above camera configurations, camera placements, number of cameras, camera positions, etc. are merely examples. Without departing from the scope of the disclosed embodiments, these components and other components described with respect to the overall system may be assembled and used in a variety of different configurations. Further details regarding the use of multi-camera systems to provide driver assistance and / or autonomous vehicle functionality are provided below.

[0152] Figure 4 is an exemplary functional block diagram of memory 140 and / or memory 150, which may be stored / programmed with instructions for performing one or more operations consistent with the embodiments of the present disclosure. Although the following refers to memory 140, those skilled in the art will recognize that the instructions may be stored in memory 140 and / or 150.

[0153] As Figure 4 shown, memory 140 may store a monocular image analysis module 402, a stereoscopic image analysis module 404, a speed and acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Additionally, application processor 180 and / or image processor 190 may execute the instructions stored in any of modules 402, 404, 406, and 408 contained in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion may refer separately or jointly to application processor 180 and image processor 190. Accordingly, the steps of any of the following processes may be performed by one or more processing devices.

[0154] In one embodiment, the monocular image analysis module 402 may store instructions (such as 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 set of images with additional sensory information (e.g., information from radar, lidar, etc.) for monocular image analysis. As described below in connection with Figures 5A to 5D The monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as 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 the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in connection with the navigation response module 408.

[0155] In one embodiment, the stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform stereo image analysis on a first set and a second set of images acquired by a combination of image capture devices selected from any of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first set and the second set of images with additional sensory information (e.g., information from radar) for stereo image analysis. For example, the stereo image analysis module 404 may include instructions for performing stereo image analysis based on the first set of images acquired by the image capture device 124 and the second set of images acquired by the image capture device 126. As described below in connection with Figure 6 The stereo image analysis module 404 may include instructions for detecting a set of features within the first set and the second set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, etc. Based on this analysis, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in connection with the navigation response module 408. Additionally, in some embodiments, the stereo image analysis module 404 may implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems, such as the system may be configured to use computer vision algorithms to detect and / or label objects in the environment from which sensory 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.

[0156] 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 vehicle 200, where the one or more computing and electromechanical devices are configured to cause a change in the speed and / or acceleration of 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 vehicle 200 based on data derived from executing the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, a target position, speed, and / or acceleration, the position and / or speed of vehicle 200 relative to nearby vehicles, pedestrians, or road objects, position information of vehicle 200 relative to the lane markings of the road, etc. Additionally, the processing unit 110 may calculate the target speed of vehicle 200 based on sensory input (e.g., information from radar) and inputs from other systems of vehicle 200, such as the throttle regulation system 220, the braking system 230, and / or the steering system 240. Based on the calculated target speed, the processing unit 110 may transmit electrical signals to the throttle regulation system 220, the braking system 230, and / or the steering system 240 of vehicle 200 to trigger a change in speed and / or acceleration by, for example, physically depressing the brakes or releasing the accelerator of vehicle 200.

[0157] In one embodiment, the navigation response module 408 may store software executable by the processing unit 110 to determine a desired navigation response based on data derived from executing the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, target position information of vehicle 200, etc. Additionally, in some embodiments, the navigation response may be (partially or fully) based on map data, a predetermined position of vehicle 200, and / or the relative speed or relative acceleration between 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 a desired navigation response based on sensory input (e.g., information from radar) and inputs from other systems of vehicle 200, such as the throttle regulation system 220, the braking system 230, and the steering system 240 of vehicle 200. Based on the desired navigation response, the processing unit 110 may transmit electrical signals to the throttle regulation system 220, the braking system 230, and the steering system 240 of vehicle 200 to effect a rotation of a predetermined angle by, for example, turning the steering wheel of vehicle 200, thereby triggering the desired navigation response. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as an input to the execution of the speed and acceleration module 406 for calculating a change in the speed of vehicle 200.

[0158] In addition, any module disclosed herein (e.g., modules 402, 404, and 406) may implement techniques associated with a trained system, such as a neural network or a deep neural network, or an untrained system.

[0159] Figure 5A is a flowchart illustrating an exemplary process 500A for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via a data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera (such as the image capture device 122 having a field of view 202) included in the image acquisition unit 120 may capture a plurality of images of the area in front of the vehicle 200 (e.g., or the side or rear of the vehicle) and transmit them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). At step 520, the processing unit 110 may execute the monocular image analysis module 402 to analyze the plurality of images, as further described in detail below in conjunction with Figures 5B to 5D By performing this analysis, the processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0160] At step 520, the processing unit 110 may also execute the monocular image analysis module 402 to detect various road hazards, such as, for example, components of a truck tire, a fallen road sign, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of such hazards more difficult. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on the plurality of images to detect road hazards. For example, the processing unit 110 may estimate the camera motion between consecutive image frames and calculate the disparity in pixels between the frames to construct a 3D map of the road. Then, the processing unit 110 may use the 3D map to detect the road surface and hazards present on the road surface.

[0161] At step 530, the processing unit 110 may execute the navigation response module 408 based on the analysis performed at step 520 and as described above in conjunction with Figure 4The described technology is used to cause one or more navigation responses. The navigation responses can include, for example, steering, lane change, braking, change in acceleration, etc. In some embodiments, the processing unit 110 can use the data derived from the execution speed and acceleration module 406 to cause the one or more navigation responses. Additionally, multiple navigation responses can occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 can cause the vehicle 200 to change a lane and then accelerate by, for example, sequentially transmitting control signals to the steering system 240 and the throttle adjustment system 220 of the vehicle 200. Alternatively, the processing unit 110 can cause the vehicle 200 to brake while changing lanes by, for example, simultaneously transmitting control signals to the braking system 230 and the steering system 240 of the vehicle 200.

[0162] Figure 5B FIG. 5 is a flow chart showing an exemplary process 500B for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments. The processing unit 110 can execute the monocular image analysis module 402 to implement the process 500B. At step 540, the processing unit 110 can determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, the processing unit 110 can scan one or more images, compare the images with one or more predetermined patterns, and identify possible locations within each image that may contain an object of interest (e.g., a vehicle, a pedestrian, or a part thereof). The predetermined patterns can be designed in such a way as to achieve a high "false hit" rate and a low "miss" rate. For example, the processing unit 110 can use a low similarity threshold for the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. Doing so can allow the processing unit 110 to reduce the likelihood of missing (e.g., not identifying) candidate objects representing vehicles or pedestrians.

[0163] At step 542, the processing unit 110 can filter the set of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria can be derived from various attributes associated with object type categories stored in a database (e.g., a database stored in the memory 140). The attributes can include object shape, size, texture, location (e.g., relative to the vehicle 200), etc. Thus, the processing unit 110 can use one or more sets of criteria to reject false candidates from the set of candidate objects.

[0164] At step 544, the processing unit 110 may analyze multiple frames of images to determine whether the objects in the set of candidate objects represent vehicles and / or pedestrians. For example, the processing unit 110 may track the detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to the vehicle 200, etc.). Additionally, the processing unit 110 may estimate the parameters of the detected objects and compare the frame-by-frame position data of the object with the predicted position.

[0165] At step 546, the processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to the vehicle 200) associated with the detected objects. In some embodiments, the processing unit 110 may construct the measurements based on estimation techniques such as Kalman filters or linear quadratic estimation (LQE) that use a series of time-based observations and / or based on modeling data available for different object classes (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). A Kalman filter may be based on a measurement of the scale of an object, where the scale measurement is proportional to the time to collision (e.g., the amount of time for the vehicle 200 to reach the object). Thus, by performing steps 540 to 546, the processing unit 110 can identify vehicles and pedestrians that appear within the set of captured images and derive information associated with the vehicles and pedestrians (e.g., position, velocity, size). Based on this identification and the derived information, the processing unit 110 may cause one or more navigation responses in the vehicle 200, as described above in connection with Figure 5A as described.

[0166] At step 548, the processing unit 110 may perform an optical flow analysis on one or more images to reduce the likelihood of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing motion patterns in one or more images that are associated with other vehicles and pedestrians relative to the vehicle 200 and that are distinct from the motion of the road surface. The processing unit 110 may calculate the motion of a candidate object by observing the different positions of the object across multiple image frames captured at different times. The processing unit 110 may use the position and time values as inputs to a mathematical model for calculating the motion of the candidate object. Thus, optical flow analysis may provide an alternative method for detecting vehicles and pedestrians in the vicinity of the vehicle 200. The processing unit 110 may perform the optical flow analysis in conjunction with steps 540 to 546 to provide redundancy for detecting vehicles and pedestrians and to improve the reliability of the system 100.

[0167] Figure 5CIt is a flowchart showing an exemplary process 500C for detecting road signs and / or lane geometry information in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500C. At step 550, the processing unit 110 may detect a set of objects by scanning one or more images. To detect lane signs, lane geometry information, and sections of other relevant road signs, the processing unit 110 may filter the set of objects to exclude objects determined to be irrelevant (e.g., small potholes, small stones, etc.). At step 552, the processing unit 110 may group together sections of the same road sign or lane sign detected in step 550. Based on this grouping, the processing unit 110 may generate a model representing the detected sections, such as a mathematical model.

[0168] At step 554, the processing unit 110 may construct a set of measurements associated with the detected sections. In some embodiments, the processing unit 110 may create a projection of the detected sections from the image plane onto the real-world plane. A cubic polynomial with coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivative of the detected road, for example, may be used to characterize the projection. When generating the projection, the processing unit 110 may consider changes in the road surface, as well as the pitch and roll rate associated with the vehicle 200. In addition, the processing unit 110 may model the road elevation by analyzing position and motion cues present on the road surface. Further, the processing unit 110 may estimate the pitch and roll rate associated with the vehicle 200 by tracking a set of feature points in one or more images.

[0169] At step 556, the processing unit 110 may perform multi-frame analysis by, for example, tracking the detected sections across consecutive image frames and accumulating frame-by-frame data associated with the detected sections. Since the processing unit 110 performs multi-frame analysis, the set of measurements constructed at step 554 may become more reliable and associated with an increasingly high confidence level. Thus, by performing steps 550, 552, 554, and 556, the processing unit 110 may identify road signs present in the set of captured images and derive lane geometry information. Based on this identification and the derived information, the processing unit 110 may cause one or more navigation responses in the vehicle 200, as described above in connection with Figure 5A as described.

[0170] At step 558, the processing unit 110 may consider additional information sources to further generate a safety model of the vehicle 200 in its surrounding environment. The processing unit 110 may use the safety model to define the context in which the system 100 may perform autonomous control of the vehicle 200 in a safe manner. To generate the safety model, in some embodiments, the processing unit 110 may consider the positions and movements of other vehicles, detected curbs and guardrails, and / or a general road shape description extracted from map data (such as data from the map database 160). By considering additional information sources, the processing unit 110 may provide redundancy for detecting road signs and lane geometries and increase the reliability of the system 100.

[0171] Figure 5D is a flowchart showing an exemplary process 500D for detecting traffic lights in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500D. At step 560, the processing unit 110 may scan the set of images and identify objects that appear in the images at locations that may contain traffic lights. For example, the processing unit 110 may filter the identified objects to build a set of candidate objects, excluding those objects that are unlikely to correspond to traffic lights. The filtering may be done based on various attributes associated with traffic lights, such as shape, size, texture, location (e.g., relative to the vehicle 200), etc. Such attributes may be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, the processing unit 110 may perform multi-frame analysis on the set of candidate objects that reflect possible traffic lights. For example, the processing unit 110 may track candidate objects across consecutive image frames, estimate the real-world positions of the candidate objects, and filter out those objects that move (which are unlikely to be traffic lights). In some embodiments, the processing unit 110 may perform color analysis on the candidate objects and identify the relative positions of the detected colors that appear within the possible traffic lights.

[0172] At step 562, the 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 the vehicle 200, (ii) signs detected on the road (such as arrow signs), and (iii) a description of the intersection extracted from map data (such as data from the map database 160). The processing unit 110 may use the information derived from executing the monocular analysis module 402 to perform the analysis. In addition, the processing unit 110 may determine the correspondence between the traffic lights detected at step 560 and the lanes that appear near the vehicle 200.

[0173] At step 564, as vehicle 200 approaches the intersection, processing unit 110 may update the confidence level associated with the analyzed intersection geometry and the detected traffic lights. For example, comparing the estimated number of traffic lights that appear at the intersection with the actual number of traffic lights that appear at the intersection may affect the confidence level. Thus, based on this 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 can identify the traffic lights present within the set of captured images and analyze the intersection geometry information. Based on this identification and analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in connection with Figure 5A as described.

[0174] Figure 5E is a flowchart of an exemplary process 500E for causing one or more navigation responses in vehicle 200 based on a vehicle path, consistent with the disclosed embodiments. At step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path may 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 may fall within the range of 1 to 5 meters. In one embodiment, processing unit 110 may use two polynomials, such as a left road polynomial and a right road polynomial, to construct the initial vehicle path. Processing unit 110 may calculate the geometric midpoint between the two polynomials and offset each point to be included in the resulting vehicle path by a predetermined offset (e.g., intelligent lane offset), if any (a zero offset may correspond to driving in the middle of the lane). The offset may be in a direction perpendicular to the section between any two points in the vehicle path. In another embodiment, processing unit 110 may use one polynomial and an estimated lane width to offset each point of the vehicle path by half of the estimated lane width plus a predetermined offset (e.g., intelligent lane offset).

[0175] At step 572, processing unit 110 may update the vehicle path constructed at step 570. Processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution such that the d between two points in the set of points representing the vehicle path k is less than the distance d as described above i . For example, the distance dk may fall within the range of 0.1 to 0.3 meters. Processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may produce a cumulative distance vector S corresponding to the total length of the vehicle path (i.e., based on the set of points representing the vehicle path).

[0176] At step 574, the processing unit 110 may determine a look-ahead point (expressed in coordinates as (x l , z l )) based on the updated vehicle path constructed at step 572. The processing unit 110 may extract the look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance may have a lower limit ranging from 10 meters to 20 meters and may be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, as the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower limit). The look-ahead time may range from 0.5 to 1.5 seconds and may be inversely proportional to the gain of one or more control loops such as a heading error tracking control loop associated with causing a navigation response in the vehicle 200. For example, the gain of the heading error tracking control loop may depend on the bandwidths of a yaw rate loop, a steering actuator loop, vehicle lateral dynamics, etc. Thus, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0177] At step 576, the processing unit 110 may determine a heading error and a yaw rate command based on the look-ahead point determined at step 574. The processing unit 110 may determine the heading error by calculating the arctangent of the look-ahead point, e.g., arctan(x l / z l ). The processing unit 110 may determine the yaw rate command as the product of the heading error and a high-level control gain. If the look-ahead distance is not at the lower limit, the high-level control gain may be equal to: (2 / look-ahead time). Otherwise, the high-level control gain may be equal to: (2 × speed of the vehicle 200 / look-ahead distance).

[0178] Figure 5F is a flowchart showing an exemplary process 500F for determining whether a vehicle ahead is changing lanes consistent with the disclosed embodiments. At step 580, the processing unit 110 may determine navigation information associated with a vehicle ahead (e.g., a vehicle traveling in front of the vehicle 200). For example, the processing unit 110 may use the techniques described above in connection with Figure 5A and Figure 5B to determine the position, speed (e.g., direction and speed), and / or acceleration of the vehicle ahead. The processing unit 110 may also use the techniques described above in connection with Figure 5E to determine one or more road polynomials, a look-ahead point (associated with the vehicle 200), and / or a tracking trajectory (e.g., a set of points describing the path taken by the vehicle ahead).

[0179] At step 582, the processing unit 110 may analyze the navigation information determined at step 580. In one embodiment, the processing unit 110 may calculate the distance between the tracking trajectory and the road polynomial (e.g., along the trajectory). If the change in this distance along the trajectory 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 sharp-turn road), then the processing unit 110 may determine that the vehicle ahead is likely changing lanes. In a situation where multiple vehicles are detected traveling ahead of vehicle 200, the processing unit 110 may compare the tracking trajectories associated with each vehicle. Based on this comparison, the processing unit 110 may determine that a vehicle whose tracking trajectory does not match the tracking trajectories of other vehicles is likely changing lanes. The processing unit 110 may additionally compare the curvature of the tracking trajectory (associated with the vehicle ahead) with the expected curvature of the road segment on which the vehicle ahead is traveling. The expected curvature may be extracted from map data (e.g., data from the map database 160), from the road polynomial, from the tracking trajectories of other vehicles, from the existing knowledge about the road, etc. If the difference between the curvature of the tracking trajectory and the expected curvature of the road segment exceeds a predetermined threshold, then the processing unit 110 may determine that the vehicle ahead is likely changing lanes.

[0180] In another embodiment, the processing unit 110 may compare the instantaneous position of the vehicle ahead with the front view point (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 vehicle ahead and the front view point changes during this 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 sharp-turn road), then the processing unit 110 may determine that the vehicle ahead is likely changing lanes. In another embodiment, the processing unit 110 may analyze the geometry of the tracking trajectory by comparing the lateral distance traveled along the tracking trajectory with the expected curvature of the tracking path. The expected radius of curvature may be determined according to the calculation: (δ z 2 + δ x 2 ) / 2 / (δ x ), where δ x represents the lateral travel distance and δ zThe longitudinal distance traveled. If the difference between the lateral distance traveled and the desired curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 may determine that the vehicle ahead is likely changing lanes. In another embodiment, the processing unit 110 may analyze the position of the vehicle ahead. If the position of the vehicle ahead occludes the road polynomial (e.g., the leading vehicle covers above the road polynomial), the processing unit 110 may determine that the vehicle ahead is likely changing lanes. In a case where the position of the vehicle ahead is such that another vehicle is detected ahead of the vehicle ahead and the tracking trajectories of the two vehicles are not parallel, the processing unit 110 may determine that the (nearer) vehicle ahead is likely changing lanes.

[0181] In step 584, the processing unit 110 may determine whether the vehicle ahead 200 is changing lanes based on the analysis performed in step 582. For example, the processing unit 110 may make this determination based on a weighted average of the various analyses performed in step 582. In such a scenario, for example, a determination that the vehicle ahead is likely changing lanes made by the processing unit 110 based on a particular type of analysis may be assigned a value of "1" (and "0" to represent a determination that the vehicle ahead is unlikely changing lanes). Different analyses performed at step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0182] Figure 6 is a flowchart showing an exemplary process 600 for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments. At step 610, the processing unit 110 may receive a first and a second plurality of images via the data interface 128. For example, cameras included in the image acquisition unit 120 (such as image capture devices 122 and 124 having fields of view 202 and 204) may capture a first and a second plurality of images of the area in front of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first and the second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0183] At step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis of the first and the second plurality of images 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. This may be done in a manner consistent with that described above in connection with Figures 5A to 5DStereo image analysis is performed in a similar manner to the described steps. For example, the processing unit 110 may execute the stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) within the first and second pluralities of images, filter out a subset of the candidate objects based on various criteria, and perform multi-frame analysis, construct measurements, and determine a confidence level for the remaining candidate objects. When performing the above steps, the processing unit 110 may consider information from both the first and second pluralities of images, rather than only considering information from one set of images. For example, the processing unit 110 may analyze the differences in pixel-level data (or other subsets of data from the two streams of captured images) of candidate objects that appear in both the first and second pluralities of images. As another example, the processing unit 110 may estimate the position and / or speed of a candidate object (e.g., relative to vehicle 200) by observing that the object appears in one of the pluralities of images but not in the other, or other possible differences relative to the object that appears in both image streams. For example, the position, speed, and / or acceleration relative to vehicle 200 may be determined based on characteristics such as the trajectory, position, movement characteristics, etc. associated with an object that appears in one or both of the image streams.

[0184] At step 630, the processing unit 110 may execute the navigation response module 408 to cause one or more navigation responses in vehicle 200 based on the analysis performed at step 620 and the techniques described above in connection with Figure 4 The navigation responses may include, for example, steering, lane changes, changes in acceleration, changes in speed, braking, etc. In some embodiments, the processing unit 110 may use data derived from executing the speed and acceleration module 406 to cause the one or more navigation responses. Additionally, the multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0185] Figure 7FIG. 700 is a flowchart showing an exemplary process 700 for causing one or more navigation responses based on the analysis of three sets of images consistent with the disclosed embodiments. At step 710, the processing unit 110 may receive a first, second, and third plurality of images via the data interface 128. For example, cameras included in the image acquisition unit 120, such as image capture devices 122, 124, and 126 having fields of view 202, 204, and 206, may capture a first, second, and third plurality of images of regions in front of and / or to the sides of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first, second, and third plurality of images via three or more data interfaces. For example, each of the image capture devices 122, 124, 126 may have an associated data interface for communicating data to the processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0186] At step 720, the processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. The analysis may be performed in a manner similar to the steps described above in connection with Figures 5A - 5D and Figure 6 . For example, the processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., via the execution of the monocular image analysis module 402 and based on the steps described above in connection with Figures 5A to 5D . Alternatively, the processing unit 110 may perform stereo 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 the execution of the stereo image analysis module 404 and based on the steps described above in connection with Figure 6 . The processed information corresponding to the analysis of the first, second, and / or third plurality of images may be combined. In some embodiments, the processing unit 110 may perform a combination of monocular and stereo image analysis. For example, the processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via the execution of the monocular image analysis module 402) and stereo image analysis on the second and third plurality of images (e.g., via the execution of the stereo image analysis module 404). The configuration of the 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 particular configuration of the image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0187] In some embodiments, the processing unit 110 may test the system 100 based on the images acquired and analyzed in steps 710 and 720. Such testing may provide an indicator of the overall performance of the system 100 for certain configurations of the image acquisition devices 122, 124, and 126. For example, the processing unit 110 may determine the ratios of "false positives" (e.g., situations where the system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses".

[0188] At step 730, the processing unit 110 may cause one or more navigation responses in the vehicle 200 based on information derived from two of the first, second, and third pluralities of images. The selection of two of the first, second, and third pluralities of images may depend on various factors such as, for example, the number, type, and size of the objects detected in each of the pluralities of images. The processing unit 110 may also make the selection based on image quality and resolution, the effective field of view reflected in the images, the number of frames captured, the extent 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 the object that appears in each such frame), and the like.

[0189] In some embodiments, the processing unit 110 may select the information derived from two of the first, second, and third pluralities of images by determining the degree of consistency between the information derived from one image source and the information derived from other image sources. For example, the processing unit 110 may combine the processed information derived from each of the image capture devices 122, 124, and 126 (whether by monocular analysis, stereoscopic analysis, or any combination of the two) and determine visual indicators of consistency (e.g., lane markings, detected vehicles and their positioning and / or paths, detected traffic lights, etc.) between the images captured from each of the image capture devices 122, 124, and 126. The processing unit 110 may also exclude information that is inconsistent between the captured images (e.g., a vehicle changing lanes, a lane model indicating that a vehicle is too close to the vehicle 200). Thus, the processing unit 110 may select the information derived from two of the first, second, and third pluralities of images based on the determined consistent and inconsistent information.

[0190] The navigation response may include, for example, steering, lane change, braking, change in acceleration, etc. The processing unit 110 may be based on the analysis performed in step 720 and as described above in connection with Figure 4The described techniques are used to cause one or more navigation responses. The processing unit 110 may also use data derived from the execution speed and acceleration module 406 to cause one or more navigation responses. In some embodiments, the processing unit 110 may cause one or more navigation responses based on the relative position, relative speed, and / or relative acceleration between the vehicle 200 and an object detected within any of the first, second, and third pluralities of images. The plural navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0191] Sparse Road Model for Autonomous Vehicle Navigation

[0192] In some embodiments, the disclosed systems and methods may use a sparse map for autonomous vehicle navigation. In particular, the sparse map may be used for autonomous vehicle navigation along a road segment. For example, the sparse map may provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed in more detail below, an autonomous vehicle may use the sparse map to navigate one or more roads based on one or more stored trajectories.

[0193] Sparse Map for Autonomous Vehicle Navigation

[0194] In some embodiments, the disclosed systems and methods may generate a sparse map for autonomous vehicle navigation. For example, the sparse map may provide sufficient information for navigation without requiring excessive data storage or data transfer rate. As discussed in more detail below, a vehicle (which may be an autonomous vehicle) may use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map may contain data related to roads and potential landmarks along the roads, which may be sufficient for vehicle navigation but also exhibit a small data footprint. For example, the sparse data map described in detail below may require significantly less storage space and data transfer bandwidth compared to a digital map that contains detailed map information such as image data collected along the road.

[0195] For example, a sparse data map may store a three-dimensional polynomial representation of preferred vehicle paths along a road instead of storing a detailed representation of road segments. These paths may require very little data storage space. Additionally, in the described sparse data map, landmarks can be identified and included in the sparse map road model to assist in navigation. These landmarks can be positioned at any spacing suitable for enabling vehicle navigation, but in some cases, these landmarks do not need to be identified and included in the model at a high density and short spacing. Instead, in some cases, navigation based on landmarks spaced at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart is possible. As will be discussed in more detail in other chapters, a sparse map can be generated based on data collected or measured by a vehicle equipped with various sensors and devices such as image capture devices, global positioning system sensors, motion sensors, etc. while the vehicle is traveling along a road. In some cases, a sparse map can be generated based on data collected during multiple drives of one or more vehicles along a particular road. Generating a sparse map using multiple drives of one or more vehicles can be referred to as "crowdsourcing" a sparse map.

[0196] Consistent with the disclosed embodiments, an autonomous vehicle system can use a sparse map for navigation. For example, the disclosed systems and methods can allocate a sparse map for generating a road navigation model for an autonomous vehicle and can use the sparse map and / or the generated road navigation model to navigate the autonomous vehicle along a road segment. A sparse map consistent with the present disclosure can include one or more three-dimensional profiles that can represent a predetermined trajectory that an autonomous vehicle can traverse as it moves along an associated road segment.

[0197] A sparse map consistent with the present disclosure can also include data representing one or more road features. Such road features can include identified landmarks, road signature profiles, and any other road-related features useful in vehicle navigation. A sparse map consistent with the present disclosure can enable autonomous navigation of a vehicle based on a relatively small amount of data contained in the sparse map. For example, the disclosed embodiments of a sparse map may require relatively little storage space (and relatively little bandwidth when parts of the sparse map are transmitted to a vehicle), but can still adequately provide autonomous vehicle navigation instead of including a detailed representation of a road such as a curb, road curvature, an image associated with a road segment, or data detailing other physical features associated with a road segment. In some embodiments, the small data footprint of the disclosed sparse map can be achieved by storing a representation of road-related elements that require little data but still enable autonomous navigation, which will be discussed in further detail below.

[0198] For example, the disclosed sparse map can store a polynomial representation of one or more trajectories that a vehicle can follow along a road, rather than storing a detailed representation of the various aspects of the road. Thus, using the disclosed sparse map, a vehicle can be navigated along a specific road segment without storing (or having to transmit) details about the physical properties of the road to enable navigation along the road. In some cases, instead of having to interpret the physical aspects of the road, the vehicle can be navigated by aligning the path it travels with a trajectory (e.g., a polynomial spline) along a specific road segment. In this way, the vehicle can be navigated primarily based on the stored trajectory (e.g., polynomial spline), which can require significantly less storage space compared to stored methods involving road images, road parameters, road layouts, etc.

[0199] In addition to the polynomial representation of the trajectory along the road segment that is stored, the disclosed sparse map can also include small data objects that can represent road features. In some embodiments, the small data object can include a digital signature that is derived from a digital image (or digital signal) obtained from a sensor (e.g., a camera or other sensor, such as a suspension sensor) on a vehicle traveling along the road segment. The digital signature can have a reduced size relative to the signal acquired by the sensor. In some embodiments, the digital signature can be created to be compatible with a classifier function that is configured to detect and identify road features, for example, from signals acquired by the sensor during subsequent driving. In some embodiments, the digital signature can be created such that it has the smallest possible footprint while retaining the ability to associate or match a road feature with the stored signature based on an image of the road feature (or, if the stored signature is not image-based and / or includes other data, a digital signal generated by the sensor), the image of the road feature being captured by a camera on a vehicle traveling along the same road segment subsequently.

[0200] In some embodiments, the size of the data object can be further associated with the uniqueness of the road feature. For example, for a road feature that can be detected by a camera on a vehicle, and where the camera system on the vehicle is coupled to a classifier that is capable of differentiating image data corresponding to the road feature as being associated with a specific type of road feature (e.g., a road sign), and where such a road sign is locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), it may be sufficient to store data indicating the type of the road feature and its location.

[0201] As will be discussed in further detail below, road features (e.g., landmarks along a road segment) can be stored as small data objects that can represent the road features in relatively few bytes while providing sufficient information for identifying and using such features for navigation. In one example, a road sign can be recognized as an identified landmark on which vehicle navigation can be based. The representation of the road sign can be stored in a sparse map to include, for example, several bytes of data indicating the type of the landmark (e.g., a stop sign) and several bytes of data indicating the location of the landmark (e.g., coordinates). Navigation based on such a data-light representation of landmarks (e.g., using a representation sufficient to localize, identify, and navigate based on landmarks) can provide a desired level of navigation functionality associated with the sparse map without significantly increasing the data overhead associated with the sparse map. Such a compact representation of landmarks (and other road features) can utilize sensors and processors included on such vehicles that are configured to detect, identify, and / or classify specific road features.

[0202] For example, when a sign in a given area or even a particular type of sign is locally unique (e.g., when there are no other signs or no other signs of the same type), the sparse map can use data indicating the type of the landmark (the sign or the particular type of sign), and during navigation (e.g., autonomous navigation), when a camera on an autonomous vehicle captures an image of an area containing the sign (or the particular type of sign), the processor can process the image, detect the sign (if it is indeed present in the image), classify the image as the sign (or the particular type of sign), and associate the location of the image with the location of the sign stored in the sparse map.

[0203] Generating Sparse Map

[0204] In some embodiments, the sparse map can include at least one line representation of a road surface feature extending along a road segment and a plurality of landmarks associated with the road segment. In some aspects, the sparse map can be generated via "crowdsourcing", e.g., by performing image analysis on a plurality of images obtained when one or more vehicles traverse the road segment.

[0205] Figure 8Illustrated is a sparse map 800 that one or more vehicles (e.g., vehicle 200 which may be an autonomous vehicle) can access for providing autonomous vehicle navigation. The sparse map 800 can be stored in a memory, such as memory 140 or 150. Such a memory device can comprise any type of non-transitory storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 can comprise a hard disk drive, an optical disk, flash memory, a magnetic-based memory device, an optical-based memory device, etc. In some embodiments, the sparse map 800 can be stored in a database (e.g., map database 160), which can be stored in memory 140 or 150 or other types of storage devices.

[0206] In some embodiments, the sparse map 800 can be stored on a storage device or non-transitory computer-readable medium provided on vehicle 200 (e.g., a storage device included in a navigation system on vehicle 200). A processor provided on vehicle 200 (e.g., processing unit 110) can access the sparse map 800 stored in the storage device or computer-readable medium provided on vehicle 200 to generate navigation instructions for guiding autonomous vehicle 200 as the vehicle traverses a road segment.

[0207] However, the sparse map 800 does not need to be stored locally with respect to the vehicle. In some embodiments, the sparse map 800 can be stored on a storage device or computer-readable medium provided on a remote server that communicates with vehicle 200 or a device associated with vehicle 200. A processor provided on vehicle 200 (e.g., processing unit 110) can receive data included in the sparse map 800 from the remote server and can execute data for guiding the autonomous driving of vehicle 200. In such an embodiment, the remote server can store all or only a portion of the sparse map 800. Accordingly, a storage device or computer-readable medium provided on vehicle 200 and / or on one or more additional vehicles can store the (multiple) remaining portions of the sparse map 800.

[0208] In addition, in such an embodiment, the sparse map 800 can be accessed by multiple vehicles (e.g., dozens, hundreds, thousands, or millions of vehicles, etc.) traversing different road segments. It should also be noted that the sparse map 800 can contain multiple sub-maps. For example, in some embodiments, the sparse map 800 can contain hundreds, thousands, millions, or more sub-maps that can be used for vehicle navigation. Such sub-maps can be referred to as local maps, and vehicles traveling along the road can access any number of local maps relevant to the location where the vehicle is traveling. The local map portion of the sparse map 800 can be stored together with a Global Navigation Satellite System (GNSS) key as an index to the database of the sparse map 800. Thus, while the calculation of the steering angle for navigating the host vehicle in this system can be performed without relying on the GNSS position, road features, or landmarks of the host vehicle, such GNSS information can be used to retrieve the relevant local maps.

[0209] Generally, the sparse map 800 can be generated based on data collected from one or more vehicles as they travel along the road. For example, using sensors (e.g., cameras, speedometers, GPS, accelerometers, etc.) on one or more vehicles, the trajectories of one or more vehicles traveling along the road can be recorded, and a polynomial representation of the preferred trajectory of vehicles making subsequent trips along the road 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 landmarks along a particular road. Data collected from the traversing vehicles can also be used to identify road profile information, such as road width profile, road roughness profile, traffic line spacing profile, road conditions, etc. Using the collected information, the sparse map 800 can be generated and distributed (e.g., for local storage or via in-flight data transfer) 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, as vehicles continue to traverse the roads included in the sparse map 800, the sparse map 800 can be continuously or periodically updated based on data collected from the vehicles.

[0210] The data recorded in the sparse map 800 can include location information based on Global Positioning System (GPS) data. For example, location information can be included in the sparse map 800 for various map elements, including, for example, landmark location, road contour location, and the like. The location of the map elements included in the sparse map 800 can be obtained using GPS data collected from vehicles passing through the road. For example, a vehicle passing by the identified landmark can use the GPS location information associated with the vehicle and the determination of the location of the identified landmark relative to the vehicle (e.g., based on image analysis of data collected from one or more cameras on the vehicle) to determine the location of the identified landmark. When additional vehicles pass by the location of the identified landmark, this location determination of the identified landmark (or any other feature included in the sparse map 800) can be repeated. Some 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 landmark. For example, in some embodiments, multiple location measurements relative to a particular feature stored in the sparse map 800 can be averaged together. However, any other mathematical operation can also be used to refine the stored location of a map element based on multiple determined locations of the map element.

[0211] The sparse maps of the disclosed embodiments can enable autonomous navigation of vehicles using a relatively small amount of stored data. In some embodiments, the sparse map 800 can 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, landmarks, and any other stored road features). In some embodiments, the data density of the sparse map 800 can 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 not more than 10 kB per kilometer of road, or not more than 20 kB per kilometer of road. In some embodiments, a sparse map with a total of 4 GB or less of data can also be used to autonomously navigate most (if not all) of the roads in the United States. These data density values can represent the average over the entire sparse map 800, a local map within the sparse map 800, and / or a particular road segment within the sparse map 800.

[0212] As described above, the sparse map 800 may include representations 810 of multiple target trajectories for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as three-dimensional splines. For example, the target trajectories stored in the sparse map 800 may be determined based on two or more reconstructed trajectories of a vehicle's previous traversal 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 an intended path of traveling along the road in a first direction, and a second target trajectory may be stored to represent an intended path of traveling along the road in another direction (e.g., opposite to the first direction). Additional target trajectories may be stored for a particular road segment. For example, on a multi-lane road, one or more target trajectories may be stored, which represent the intended paths of vehicles traveling in one or more lanes associated with the multi-lane road. In some embodiments, each lane of a multi-lane road may be associated with its own target trajectory. In other embodiments, the stored target trajectories may be fewer than the number of lanes present on the multi-lane road. In such a case, a vehicle navigating on a multi-lane road may use any stored target trajectory to guide its navigation by considering the lane offset from the lane of the stored target trajectory (e.g., if a vehicle is traveling in the leftmost lane of a three-lane highway and the target trajectory is stored only for the middle lane of the highway, when generating navigation instructions, by considering the lane offset between the middle lane and the leftmost lane, the vehicle may use the target trajectory of the middle lane to navigate).

[0213] In some embodiments, the target trajectory may represent an ideal path that a vehicle should follow when traveling. The target trajectory may be located, for example, at the approximate center of the lane of travel. In other cases, the target trajectory may be located elsewhere relative to the road segment. For example, the target trajectory may approximately coincide with the center of the road, the edge of the road, or the edge of the lane, etc. In such a case, navigation based on the target trajectory may include determining an offset for maintaining positioning relative to the target trajectory. Additionally, in some embodiments, the determined offset for maintaining positioning relative to the target trajectory may vary based on the type of vehicle (e.g., a passenger vehicle with two axes may have a different offset from a truck with more than two axes along at least a portion of the target trajectory).

[0214] The sparse map 800 may also include data related to multiple predefined landmarks 820, which are associated with a particular road segment, a local map, etc. As discussed in more detail below, these landmarks may be used for the navigation of an autonomous vehicle. For example, in some embodiments, the landmarks may be used to determine the current position of the vehicle relative to the stored target trajectory. Using this position information, the autonomous vehicle can adjust its heading direction to match the direction of the target trajectory at the determined location.

[0215] Multiple landmarks 820 can be identified and stored in the sparse map 800 at any suitable spacing. In some embodiments, the landmarks can be stored at a relatively high density (e.g., every few meters or more). However, in some embodiments, significantly larger landmark spacing values can be employed. For example, in the sparse map 800, the identified (or recognized) landmarks can be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, the identified landmarks can be located at distances even exceeding 2 kilometers from each other.

[0216] Between the landmarks, and thus between the determinations of the vehicle's position relative to the target trajectory, the vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to determine its ego motion and estimate its position relative to the target trajectory. Since errors can accumulate during navigation by dead reckoning, over time, the determination of the position relative to the target trajectory can become increasingly inaccurate. The vehicle can use the landmarks (and their known localizations) that appear in the sparse map 800 to eliminate the errors caused by dead reckoning in the position determination. In this way, the identified landmarks included in the sparse map 800 can be used as navigation anchors from which the accurate position of the vehicle relative to the target trajectory can be determined. Since a certain amount of error in position localization can be acceptable, the identified landmarks do not need to always be available to the autonomous vehicle. Instead, suitable navigation can even be based on landmark spacings of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more as described above. In some embodiments, a density of 1 identified landmark per 1 kilometer of road is sufficient to maintain the longitudinal position determination accuracy within 1 meter. Thus, it is not necessary to store every potential landmark that appears along a road segment in the sparse map 800.

[0217] In addition, in some embodiments, lane markings can be used for the localization of the vehicle during landmark spacing. By using lane markings during landmark spacing, the accumulation during navigation by dead reckoning can be minimized.

[0218] In addition to the target trajectory and the identified landmarks, the sparse map 800 can contain information related to various other road features. For example, Figure 9A shows a representation of a curve along a particular road segment that can be stored in the sparse map 800. In some embodiments, a single lane of a road can be modeled by a three-dimensional polynomial description of the left and right sides of the road. Figure 9A Such polynomials representing the left and right sides of a single lane are shown. Regardless of how many lanes a road may have, the road can be represented using polynomials in a manner similar to Figure 9A shown. For example, the left and right sides of a multi-lane road can be represented by polynomials similar toFigure 9A represented by the polynomials shown, and intermediate lane markings on a multi-lane road (e.g., dashed markings indicating lane boundaries, solid yellow lines indicating the boundary between lanes traveling in different directions, etc.) can also be represented using polynomials such as Figure 9A represented by the polynomials shown.

[0219] As Figure 9A shown, a lane 900 can be represented using a polynomial (e.g., a first-order, second-order, third-order, or any suitable order polynomial). For illustration, lane 900 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. As Figure 9A shown, lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial can be used to represent the positioning of each side of a road or lane boundary. For example, each of the left side 910 and the right side 920 can be represented by a plurality of polynomials of any suitable length. In some cases, the polynomials can have a length of approximately 100 m, although other lengths greater than or less than 100 m can also be used. Additionally, the polynomials can overlap with each other so that when the host vehicle travels along the road, seamless transitions in navigation are facilitated based on the polynomials encountered subsequently. For example, each of the left side 910 and the right side 920 can be represented by a plurality of third-order polynomials that are divided into segments approximately 100 meters long (an example of a first predetermined range) and overlap each other by approximately 50 meters. The polynomials representing the left side 910 and the right side 920 can have the same or different orders. For example, in some embodiments, some polynomials can be second-order polynomials, some can be third-order polynomials, and some can be fourth-order polynomials.

[0220] In Figure 9A 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. Although these two sets are generally parallel to each other, they follow the positioning of their respective road sides. The polynomial segments 911, 912, 913, 914, 915, and 916 have a length of approximately 100 meters and overlap with adjacent segments in the series by approximately 50 meters. However, as previously mentioned, polynomials of different lengths and different amounts of overlap can also be used. For example, the polynomials can have a length of 500 m, 1 km, or longer, and the amount of overlap can vary from 0 to 50 m, 50 m to 100 m, or greater than 100 m. Additionally, although Figure 9A shown as representing polynomials extending in a 2D space (e.g., on the surface of a piece of paper), it should be understood that these polynomials can represent curves extending in three dimensions (e.g., including a height component) to represent elevation changes in a road segment in addition to the X-Y curvature. InFigure 9A In the example shown, the right side 920 of lane 900 is further represented by a first set having polynomial segments 921, 922, and 923 and a second set having polynomial segments 924, 925, and 926.

[0221] Returning to the target trajectory of the sparse map 800, Figure 9B a three-dimensional polynomial representing the target trajectory of a vehicle traveling along a particular road segment is shown. The target trajectory represents not only the X-Y path that the host vehicle should travel along the particular road segment, but also the elevation change that the host vehicle will experience as it travels along that road segment. Thus, each target trajectory in the sparse map 800 can be represented by one or more three-dimensional polynomials, such as Figure 9B the three-dimensional polynomial 950 shown in. The sparse map 800 can contain multiple trajectories (e.g., millions or billions or more, to represent the trajectories of vehicles along various road segments along roads around the world). In some embodiments, each target trajectory can correspond to a spline connecting three-dimensional polynomial segments.

[0222] Regarding the data footprint of the polynomial curves stored in the sparse map 800, in some embodiments, each cubic polynomial can be represented by four parameters, each parameter requiring four bytes of data. A cubic polynomial that requires approximately 192 bytes of data per 100 m can be used to obtain a suitable representation. For a host vehicle traveling at approximately 100 km / hr, this can translate to a data usage / transmission requirement of approximately 200 kB per hour.

[0223] The sparse map 800 can use a combination of geometric structure descriptors and metadata to describe the lane network. The geometric structure can be described by polynomials or splines as described above. The metadata can describe the number of lanes, special features (such as shared lanes), and possibly other sparse labels. The total footprint of such indicators may be negligible.

[0224] Accordingly, a sparse map according to an embodiment of the present disclosure can include at least one line representation of a road surface feature extending along a road segment, each line representation representing a path that substantially corresponds to the road surface feature along the road segment. In some embodiments, as described above, the at least one line representation of the road surface feature can include a spline, a polynomial representation, or a curve. Additionally, in some embodiments, the road surface feature can include at least one of a curb or a lane marker. Further, as discussed below with respect to "crowdsourcing," the road surface feature can be identified by image analysis of multiple images acquired when one or more vehicles traverse the road segment.

[0225] As described above, the sparse map 800 may include a plurality of predefined landmarks associated with road segments. Each landmark in the sparse map 800 can be represented and identified using less data than would be required to store the actual image, rather than storing the actual image of the landmark and relying on, for example, image recognition analysis based on the captured image and the stored image. The data representing the landmark can still contain sufficient information for describing or identifying the landmark along the road. Storing data characterizing the landmark, rather than the actual image of the landmark, can reduce the size of the sparse map 800.

[0226] Figure 10 An example of the types of landmarks that can be represented in the sparse map 800 is shown. A landmark can include any visible and recognizable object along a road segment. Landmarks can be selected such that they are stationary and do not change frequently with respect to their positioning and / or content. The landmarks included in the sparse map 800 are useful for determining the positioning of the vehicle 200 relative to the target trajectory when the vehicle traverses a particular road segment. Examples of landmarks can include traffic signs, direction signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lamp posts, reflectors, etc.), and any other suitable categories. In some embodiments, lane signs on the road can also be included as landmarks in the sparse map 800.

[0227] Figure 10 Examples of landmarks shown include traffic signs, direction signs, roadside fixtures, and general signs. Traffic signs can 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), stop signs (e.g., stop sign 1020). Direction signs can include signs that contain one or more arrows that indicate one or more directions to different places. For example, a direction sign can include a highway sign 1025 having arrows for guiding the vehicle to different roads or places, an exit sign 1030 having an arrow for guiding the vehicle off the road, and so on. Accordingly, at least one of the plurality of landmarks can include a road sign.

[0228] General signs can be unrelated to traffic. For example, a general sign may include a billboard for advertising, or a welcome sign near the boundary between two countries, states, counties, cities, or towns. Figure 10 A general sign 1040 (“Joe's Diner”) is shown. Although the general sign 1040 can have a rectangular shape, as Figure 10 shown, the general sign 1040 can have other shapes, such as square, circular, triangular, etc.

[0229] Landmarks may also include roadside fixtures. Roadside fixtures may not be signs or may be unrelated to traffic or direction. For example, roadside fixtures may include lamp posts (e.g., lamp post 1035), power line poles, traffic light poles, etc.

[0230] Landmarks may also include beacons specifically designed for an autonomous vehicle navigation system. For example, such beacons may include separate structures placed at predetermined intervals to assist in navigating the host vehicle. Such beacons may also include visual / graphic information (e.g., icons, badges, barcodes, etc.) added to existing road signs that can be recognized or discerned by vehicles traveling along a road segment. Such beacons may also include electronic components. In such an embodiment, an electronic beacon (e.g., an RFID tag, etc.) may be used to transmit non-visual information to the host vehicle. Such information may include, for example, landmark identification and / or landmark positioning information that the host vehicle can use when determining its position along a target trajectory.

[0231] In some embodiments, the landmarks included in the sparse map 800 may be represented by data objects of a predetermined size. The data representing the landmarks may include any suitable parameters for identifying a particular landmark. For example, in some embodiments, the landmarks stored in the sparse map 800 may include parameters such as the physical size of the landmark (e.g., to support an estimate of the distance to the landmark based on a known size / scale), the distance to a previous landmark, lateral offset, height, type code (e.g., landmark type - what type of direction sign, traffic sign, etc.), GPS coordinates (e.g., to support global positioning), and any other suitable parameters. Each parameter may be associated with a data size. For example, 8 bytes of data may be used to store the landmark size. 12 bytes of data may be used to specify the distance to a previous landmark, lateral offset, and height. The type code associated with a landmark such as a direction sign or traffic sign may require approximately 2 bytes of data. For a general sign, a 50-byte data storage device may be used to store the image signature enabling the recognition of the general sign. The landmark GPS position may be associated with a 16-byte data storage device. These data sizes for each parameter are only examples, and other data sizes may also be used.

[0232] Representing landmarks in the sparse map 800 in this way can provide a streamlined solution for efficiently representing landmarks in a database. In some embodiments, signs can be classified as semantic signs and non-semantic signs. Semantic signs can include any category of signs with a standardized meaning (e.g., speed limit signs, warning signs, direction signs, etc.). Non-semantic signs can include any signs not associated with a standardized meaning (e.g., general advertising signs, signs identifying commercial establishments, etc.). For example, each semantic sign can be represented with 38 bytes of data (e.g., 8 bytes for size; 12 bytes for distance to the previous landmark, lateral offset, and height; 2 bytes for type code; and 16 bytes for GPS coordinates). The sparse map 800 can use a tagging system to represent landmark types. In some cases, each traffic sign or direction sign can be associated with its own tag, which can be stored in the database as part of the landmark identification. For example, the database can contain approximately 1000 different tags to represent various traffic signs, and approximately 10,000 different tags to represent direction signs. Of course, any suitable number of tags can be used, and additional tags can be created as needed. In some embodiments, general-purpose signs can use less than about 100 bytes (e.g., about 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).

[0233] Thus, for semantic road signs that do not require an image signature, even at a relatively high landmark density of approximately 1 per 50 meters, the data density impact on the sparse map 800 can be approximately 760 bytes per kilometer (e.g., 20 landmarks per kilometer × 38 bytes per landmark = 760 bytes). Even for general-purpose signs that include an image signature component, the data density impact is approximately 1.72 kilobytes per kilometer (e.g., 20 landmarks per kilometer × 86 bytes per landmark = 1,720 bytes). For semantic road signs, this corresponds to approximately 76 kB of data usage per hour for a vehicle traveling at 100 km / hr. For general-purpose signs, this corresponds to approximately 170 kB of data usage per hour for a vehicle traveling at 100 km / hr.

[0234] In some embodiments, a generally rectangular object, such as a rectangular sign, can be represented in the sparse map 800 by no more than 100 bytes of data. The representation of a generally rectangular object (e.g., the general sign 1040) in the sparse map 800 can include a condensed image signature (e.g., the condensed image signature 1045) associated with the generally rectangular object. Such a condensed image signature can be used, for example, to assist in the identification of the general sign, such as as a recognizable landmark. Such a condensed image signature (e.g., image information derived from the actual image data representing the object) can obviate the need to store the actual image of the object or the need to perform comparative image analysis on the actual image to identify the landmark.

[0235] Reference Figure 10 , the sparse map 800 can include or store the condensed 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., the image capture devices 122, 124, or 126) captures an image of the general sign 1040, a processor (e.g., the image processor 190 that can process the image or any other processor, which is on the host vehicle or located remotely relative to the host vehicle) can perform image analysis to extract / create the condensed image signature 1045 that includes a unique signature or pattern associated with the general sign 1040. In one embodiment, the condensed image signature 1045 can include a shape, a color pattern, a brightness pattern, or any other feature that can be extracted from the image of the general sign 1040 and that describes the general sign 1040.

[0236] For example, in Figure 10 , the circles, triangles, and stars shown in the condensed image signature 1045 can represent regions of different colors. The pattern represented by the circles, triangles, and stars can be stored in the sparse map 800, for example, within 50 bytes designated to contain the image signature. It is noted that the circles, triangles, and stars are not necessarily intended to indicate that these shapes are stored as part of the image signature. Instead, these shapes are intended to conceptually represent distinguishable regions of color, text regions, graphic shapes, or other variations of characteristics that can be associated with the general sign. Such a condensed image signature can be used to identify landmarks in the form of general signs. For example, the condensed image signature can be used to perform the same or different analysis based on a comparison of the stored condensed image signature with, for example, image data captured using a camera on an autonomous vehicle.

[0237] Accordingly, multiple landmarks can be identified by performing image analysis on multiple images obtained when one or more vehicles pass through a road segment. As explained below with respect to "crowdsourcing", in some embodiments, the image analysis for identifying multiple landmarks can include accepting a potential landmark when the ratio of the images in which the landmark actually appears to the images in which the landmark does not appear exceeds a threshold. Additionally, in some embodiments, the image analysis for identifying multiple landmarks can include rejecting a potential landmark when the ratio of the images in which the landmark does not appear to the images in which the landmark actually appears exceeds a threshold.

[0238] Returning to the target trajectory that the host vehicle can use to navigate a particular road segment, Figure 11A Illustrated is a polynomial representation of a trajectory captured during the construction or maintenance of the sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 can be determined based on two or more previously traversed reconstructed trajectories of the vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be an aggregation of two or more previously traversed reconstructed trajectories of the vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be an average of two or more previously traversed reconstructed trajectories of the vehicle along the same road segment. Other mathematical operations can also be used to construct the target trajectory along the road path based on the reconstructed trajectories collected from vehicles traversing the road segment.

[0239] As Figure 11A shown, the road segment 1100 can be traveled by multiple vehicles 200 at different times. Each vehicle 200 can collect data related to the path the vehicle takes 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 the vehicles traveling along the road segment, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) can be determined for a particular road segment. Such a target trajectory can represent the preferred path of the vehicle (e.g., as guided by an autonomous navigation system) as the host vehicle travels along the road segment.

[0240] In Figure 11AIn the example shown, the first reconstructed trajectory 1101 can be determined based on data received from a first vehicle that traversed road segment 1100 during a first time period (e.g., the first day), the second reconstructed trajectory 1102 can be obtained from a second vehicle that traversed road segment 1100 during a second time period (e.g., the second day), and the third reconstructed trajectory 1103 can be obtained from a third vehicle that traversed road segment 1100 during a third time period (e.g., the third day). Each of the trajectories 1101, 1102, and 1103 can be represented by a polynomial, such as a three-dimensional polynomial. It should be noted that in some embodiments, any of the reconstructed trajectories can be assembled on a vehicle that traversed road segment 1100.

[0241] Additionally or alternatively, such a reconstructed trajectory can be determined on the server side based on information received from vehicles that traversed road segment 1100. For example, in some embodiments, vehicles 200 can transmit data related to their movement along road segment 1100 (e.g., steering angle, heading, time, location, speed, sensed road geometry, and / or sensed landmarks, etc.) to one or more servers. The server can reconstruct the trajectories of vehicles 200 based on the received data. The server can also generate a target trajectory for guiding an autonomous vehicle that will travel along the same road segment 1100 at a later time based on the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. Although a target trajectory can be associated with a single previous traversal of a road segment, in some embodiments, each target trajectory included in the sparse map 800 can be determined based on two or more reconstructed trajectories of vehicles that traversed the same road segment. In Figure 11A which, the target trajectory is represented by 1110. In some embodiments, the target trajectory 1110 can be generated based on the average of the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 can be an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories.

[0242] Figure 11B and Figure 11C The concept of a target trajectory associated with a road segment present within a geographic region 1111 is further illustrated. As Figure 11BAs shown, the first road segment 1120 within the geographical area 1111 may include a multi-lane road that includes two lanes 1122 designated for vehicles to travel in a first direction and two additional lanes 1124 designated for vehicles to travel in a second direction opposite to the first direction. The lanes 1122 and 1124 may be separated by a double yellow line 1123. The geographical area 1111 may also include a branch road segment 1130 that intersects the road segment 1120. The road segment 1130 may include a two-lane road, with each lane designated for a different travel direction. The geographical area 1111 may also include other road features, such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0243] As Figure 11C As shown, the sparse map 800 may include a local map 1140 that includes a road model for assisting in the autonomous navigation of vehicles within the geographical area 1111. For example, the local map 1140 may include target trajectories of one or more lanes associated with the road segments 1120 and / or 1130 within the geographical area 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that an autonomous vehicle may access or rely on when passing through the lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that an autonomous vehicle may access or rely on when passing through the lane 1124. In addition, the local map 1140 may include target trajectories 1145 and / or 1146 that an autonomous vehicle may access or rely on when passing through the road segment 1130. The target trajectory 1147 represents the preferred path that an autonomous vehicle should follow when transitioning from the lane 1120 (specifically, relative to the target trajectory 1141 associated with the rightmost lane of the lane 1120) to the road segment 1130 (specifically, relative to the target trajectory 1145 associated with the first side of the road segment 1130). Similarly, the target trajectory 1148 represents the preferred path that an autonomous vehicle should follow when transitioning from the road segment 1130 (specifically, relative to the target trajectory 1146) to a portion of the road segment 1124 (specifically, as shown, relative to the target trajectory 1143 associated with the left lane of the lane 1124).

[0244] The sparse map 800 may also include a representation of other road-related features associated with the geographical region 1111. For example, the sparse map 800 may also include a representation of one or more landmarks identified in the geographical region 1111. These landmarks may include a first landmark 1150 associated with a stop line 1132, a second landmark 1152 associated with a stop sign 1134, a third landmark associated with a speed limit sign 1154, and a fourth landmark 1156 associated with a hazard sign 1138. Such landmarks can be used, for example, to help an autonomous vehicle determine its current position relative to any shown target trajectory, such that the vehicle can adjust its heading to match the direction of the target trajectory at the determined position.

[0245] In some embodiments, the sparse map 800 may also include a road signature profile. Such a road signature profile may be associated with any distinguishable / measurable change in at least one road-associated parameter. For example, in some cases, such a profile may be associated with a change in road surface information, such as a change in the surface roughness of a particular road segment, a change in road width on a particular road segment, a change in the distance between dashed lines drawn along a particular road segment, a change in the road curvature along a particular road segment, etc. Figure 11D An example of a road signature profile 1160 is shown. Although the profile 1160 may represent any of the above parameters or other parameters, in one example, the profile 1160 may represent a measurement of road surface roughness, for example, as obtained by monitoring one or more sensors that provide an output indicative of the amount of suspension displacement of a vehicle while traveling on a particular road segment.

[0246] Alternatively or concurrently, the profile 1160 may represent a change in road width, as determined based on image data obtained via a camera on a vehicle traveling on a particular road segment. For example, such a profile is useful in determining the particular position of an autonomous vehicle relative to a particular target trajectory. That is, when it crosses a road segment, the autonomous vehicle can measure a profile associated with one or more parameters associated with the road segment. If the measured profile can be correlated / matched with a predetermined profile that maps parameter changes relative to the position along the road segment, the measured and predetermined profiles can be used (e.g., by overlaying corresponding portions of the measured and predetermined profiles) in order to determine the current position along the road segment and, thus, the current position relative to the target trajectory along the road segment.

[0247] In some embodiments, the sparse map 800 can 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 can be generated based on different user preferences and / or profiles. The sparse map 800 that includes such different trajectories can be provided to different autonomous vehicles of different users. For example, some users may prefer to avoid toll roads, while other users may prefer the shortest or fastest route regardless of whether there are toll roads on the route. The disclosed system can 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-moving lanes, while other users may prefer to always maintain a position in the center lane.

[0248] Based on different environmental conditions, such as day and night, snowing, raining, foggy, etc., different trajectories can be generated and included in the sparse map 800. Autonomous vehicles traveling in different environmental conditions can be provided with the sparse map 800 generated based on such different environmental conditions. In some embodiments, cameras provided on the autonomous vehicle can detect the environmental conditions, and this information can be provided back to the server that generates and provides the sparse map. For example, the server can generate or update the sparse map 800 that has already been generated to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. When the autonomous vehicle is traveling along the road, the update of the sparse map 800 based on the environmental conditions can be performed dynamically.

[0249] Other different driving-related parameters can also be used as a basis for generating different sparse maps and providing different sparse maps to different autonomous vehicles. For example, when an autonomous vehicle is traveling at a high speed, turning can be tighter. Trajectories associated with a specific lane rather than the road can be included in the sparse map 800 so that when the vehicle follows a specific trajectory, the autonomous vehicle can stay within a specific lane. When an image captured by a camera on the autonomous vehicle indicates that the vehicle has drifted out of the lane (e.g., crossed the lane markings), an action can be triggered within the vehicle to bring the vehicle back to the designated lane according to the specific trajectory.

[0250] Crowdsourced Sparse Map

[0251] In some embodiments, the disclosed systems and methods can generate a sparse map 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 system of roads. As used herein, "crowdsourcing" means receiving data from various vehicles (e.g., autonomous vehicles) traveling on road segments at different times, and this data is used to generate and / or update a road model. The model can in turn be transmitted to vehicles traveling along the road segment later or to other vehicles for assisting autonomous vehicle navigation. The road model can include a plurality of target trajectories that represent preferred trajectories that an autonomous vehicle should follow when traversing a road segment. The target trajectory can be the same as the reconstructed actual trajectory collected from vehicles traversing the road segment, which can be transmitted from the vehicle to the server. In some embodiments, the target trajectory can be different from the actual trajectories previously taken by one or more vehicles when traversing the road segment. The target trajectory can be generated based on the actual trajectory (e.g., by averaging or any other suitable operation).

[0252] The vehicle trajectory data that a vehicle can upload to the server can correspond to the vehicle's actual reconstructed trajectory or can correspond to a recommended trajectory that can be based on or related to the vehicle's actual reconstructed trajectory but can be different from the actual reconstructed trajectory. For example, vehicles can modify their actual reconstructed trajectories and submit (e.g., recommend) the modified actual trajectories to the server. The road model can use the recommended, modified trajectories as target trajectories for other vehicles' autonomous navigation.

[0253] In addition to trajectory information, other information that can potentially be used in constructing the sparse data map 800 can include information related to potential landmark candidates. For example, through crowdsourcing of information, the disclosed systems and methods can identify potential landmarks in the environment and refine the landmark locations. The navigation system of an autonomous vehicle can use these landmarks to determine and / or adjust the vehicle's position along the target trajectory.

[0254] The reconstructed trajectory that a vehicle can generate while traveling along a road can be obtained by any suitable method. In some embodiments, the reconstructed trajectory can be produced by stitching together segments of the vehicle's motion using, for example, ego-motion estimation (e.g., three-dimensional translation and three-dimensional rotation of the camera (and thus the vehicle body)). The rotation and translation estimation can be determined based on an analysis of images captured by one or more image capture devices and information from other sensors or devices such as inertial sensors and speed sensors. For example, the inertial sensor can include an accelerometer or other suitable sensor configured to measure changes in vehicle body translation and / or rotation. The vehicle can include a speed sensor that measures the vehicle's speed.

[0255] In some embodiments, the ego - motion of the camera (and thus the vehicle body) can be estimated based on the optical flow analysis of the captured images. The optical flow analysis of the image sequence identifies the movement of pixels in the image sequence and, based on the identified movement, determines the movement of the vehicle. The ego - motion can be integrated over time and along a road segment to reconstruct the trajectory associated with the road segment that the vehicle has followed.

[0256] Data (e.g., reconstructed trajectories) collected by multiple vehicles during multiple drives at different times along a road segment can be used to construct a road model (e.g., including target trajectories, etc.) contained in the sparse data map 800. The data collected by multiple vehicles during multiple drives at different times along a road segment can also be averaged to improve the accuracy of the model. In some embodiments, data regarding road geometry and / or landmarks can be received from multiple vehicles that cross a common road segment at different times. Such data received from different vehicles can be combined to generate and / or update a road model.

[0257] The geometry of the reconstructed trajectory (and the target trajectory) along a 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 by analyzing the video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a localization is identified in each frame or image a few meters ahead of the current position of the vehicle. The localization is the position where the vehicle is expected to travel within a predetermined time period. This operation can be repeated frame - by - frame, and meanwhile, the vehicle can calculate the ego - motion (rotation and translation) of the camera. In each frame or each image, the vehicle generates a short - range model of the desired path in the 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 certain coordinate system, which can be an arbitrary or a predetermined coordinate system. Then, the three - dimensional model of the road can be fitted with a spline, which can contain or connect one or more polynomials of a suitable order.

[0258] To summarize the short - range road model at 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 mapping lane markings on the road. This module can look for edges in the image and assemble them together to form lane markings. A second module can be used together 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 camera.

[0259] Although the reconstructed trajectory modeling method may introduce the accumulation of errors due to the integration of self-motion over a long time period, which may contain noise components, such errors may be insignificant because the generated model can provide sufficient accuracy for navigation at a local scale. Additionally, the integration errors can be eliminated by using external information sources such as satellite images or geodesy. For example, the disclosed systems and methods can use a GNSS receiver to eliminate the accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed systems and methods can enable steering applications that weakly depend on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be restricted. For example, in some embodiments, the disclosed system can use GNSS signals only for database indexing purposes.

[0260] In some embodiments, the range scale (e.g., local scale) associated with the autonomous vehicle navigation 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 mainly used for two purposes: planning the forward trajectory and positioning the vehicle on the road model. In some embodiments, when the control algorithm steers the vehicle based on a target point located 1.3 seconds (or any other time, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.) ahead, the planning task can use a model within a typical range of 40 meters (or any other suitable forward distance, such as 20 meters, 30 meters, 50 meters) ahead. The positioning task uses a road model within a typical range of 60 meters (or any other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.) behind the vehicle. According to a method called "tail alignment" described in more detail in another section. The disclosed systems and methods can generate a geometric model with sufficient accuracy over a specific range (such as 100 meters) such that the planned trajectory does not deviate from the lane center by more than, for example, 30 centimeters.

[0261] As described above, a three-dimensional road model can be constructed by detecting short-range portions and stitching them together. The stitching can be enabled by calculating a six-degree-of-freedom self-motion model using video and / or images captured by a camera, data from inertial sensors that reflect the motion of the vehicle, and the primary vehicle speed signal. The accumulated errors may be small enough over a certain local range scale (such as approximately 100 meters). All of this can be done during a single drive on a specific road segment.

[0262] In some embodiments, multiple drives can be used to average the resulting models and further improve their accuracy. The same vehicle can drive the same route multiple times, or multiple vehicles can transmit the model data they collect to a central server. In any case, a matching process can be performed to identify overlapping models and enable averaging in order to generate a target trajectory. Once convergence criteria are met, the constructed model (e.g., containing the target trajectory) can be used for steering. Subsequent drives can be used for further model improvement and adaptation to infrastructure changes.

[0263] If multiple vehicles are connected to a central server, it becomes feasible to share driving experiences (such as sensed data) among them. Each vehicle client can store a partial copy of the general road model, which can be related to its current location. A two-way update process between the vehicle and the server can be performed by the vehicle and the server. The small footprint concept discussed above enables the disclosed systems and methods to perform two-way updates using a very small bandwidth.

[0264] Information related to potential landmarks can also be determined and forwarded to the central server. For example, the disclosed systems and methods can determine one or more physical attributes of a potential landmark based on one or more images containing the landmark. The physical attributes can include the physical size of the landmark (e.g., height, width), the distance from the vehicle to the landmark, the distance between the landmark and a previous landmark, the lateral position of the landmark (e.g., the position of the landmark relative to the driving lane), the GPS coordinates of the landmark, the type of the landmark, the text identification on the landmark, etc. For example, a vehicle can analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

[0265] A vehicle can determine the distance from the vehicle to a landmark based on the analysis of one or more images. In some embodiments, suitable image analysis methods, such as scaling methods and / or optical flow methods, can be used to determine the distance based on the analysis of an image of the landmark. In some embodiments, the disclosed systems and methods can be configured to determine the type or classification of a potential landmark. In the case where a vehicle determines that a certain potential landmark corresponds to a predetermined type or classification stored in the sparse map, it is sufficient for the vehicle to communicate an indication of the type or classification of the landmark along with its location to the server. The server can store such an indication. At a later time, other vehicles can capture an image of the landmark, process the image (e.g., using a classifier), and compare the result of processing the image with the indication of the landmark type stored in the server. There can be various types of landmarks, and different types of landmarks can be associated with different types of data uploaded to and stored in the server. Different processes on the vehicle can detect landmarks and communicate information about the landmarks to the server, and the system on the vehicle can receive landmark data from the server and use the landmark data for identifying landmarks in autonomous navigation.

[0266] In some embodiments, multiple autonomous vehicles traveling on a road segment can communicate with a server. The vehicles (or clients) can generate a curve describing their driving in any coordinate system (e.g., by integrating self-motion). The vehicles can detect landmarks and localize them in the same frame. The vehicles can upload the curve and the landmarks to the server. The server can collect data from multiple driving vehicles and generate a unified road model. Or for example, as discussed below with reference to Figure 19 the server can use the uploaded curves and landmarks to generate a sparse map with a unified road model.

[0267] The server can also assign the model to the clients (e.g., vehicles). For example, the server can assign the sparse map to one or more vehicles. When new data is received from a vehicle, the server can update the model continuously or periodically. For example, the server can process the new data to evaluate whether the data contains information that should trigger an update or creation of new data on the server. The server can assign the updated model or the update to the vehicle for use in providing autonomous vehicle navigation.

[0268] The server can use one or more criteria to determine whether new data received from a vehicle should trigger an update to the model or trigger the creation of new data. For example, when the new data indicates that a previously identified landmark at a specific location no longer exists or has been replaced by another landmark, the server can determine that the new data should trigger an update to the model. As another example, when the new data indicates that a road segment has been closed and this has been confirmed by data received from other vehicles, the server can determine that the new data should trigger an update to the model.

[0269] The server can assign the updated model (or the updated part of the model) to one or more vehicles traveling on the road segment associated with the model update. The server can also assign the updated model to vehicles that will travel on the road segment or whose planned itinerary includes a road segment associated with the model update. For example, when an autonomous vehicle is traveling along another road segment before reaching the road segment associated with the update, the server can assign the update or the updated model to the autonomous vehicle before it reaches the road segment.

[0270] In some embodiments, a remote server can collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a common road segment). The server can match the landmarks with the curves and create an average road model based on the trajectories collected from multiple vehicles. The server can also calculate a graph of the road and the most likely paths for each node or junction of the road segments. For example, the remote server can align the trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0271] The server can average the landmark attributes received from multiple vehicles traveling along a common road segment, such as the distance between one landmark and another (e.g., the previous landmark along the road segment) measured by the multiple vehicles, to determine the arc length parameter and support the positioning and speed calibration of each client vehicle along the path. The server can average the physical dimensions of landmarks measured by multiple vehicles traveling along a common road segment and identifying the same landmarks. The average physical dimension can be used to support distance estimation, such as the distance from the vehicle to the landmark. The server can average the lateral position of landmarks (e.g., the position from the lane in which the vehicle is traveling to the landmark) measured by multiple vehicles traveling along a common road segment and identifying the same landmarks. The average lateral portion can be used to support lane assignment. The server can average the GPS coordinates of landmarks measured by multiple vehicles traveling along the same road segment and identifying the same landmarks. The average GPS coordinates of the landmarks can be used to support the global positioning (localization) or positioning of the landmarks in the road model.

[0272] In some embodiments, based on the data received from the vehicles, the server can identify model changes, such as construction, detours, new signs, removal of signs, etc. When new data is received from the vehicles, the server can update the model continuously or periodically or instantaneously. The server can assign the update to the model or the updated model to the vehicles for providing autonomous navigation. For example, as discussed further below, the server can use crowdsourced data to filter out "ghost" landmarks detected by the vehicles.

[0273] In some embodiments, the server can analyze driver interventions during autonomous driving. The server can analyze the data received from the vehicle at the time of the intervention and the positioning, and / or the data received before the time of the intervention. The server can identify certain portions of the data that cause the intervention or are closely related to the intervention, for example, the data indicating the setting of a temporary lane closure, the data indicating pedestrians in the road. The server can update the model based on the identified data. For example, the server can modify one or more trajectories stored in the model.

[0274] Figure 12 is a schematic diagram of a system for generating a sparse map using crowdsourcing (and for assigning and navigating using the crowdsourced sparse map). Figure 12 Shows a road segment 1200 including one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 can travel on the road segment 1200 at the same time or at different times (although in Figure 12shown as being on road segment 1200 at the same time). At least one of vehicles 1205, 1210, 1215, 1220, and 1225 can be an autonomous vehicle. For simplicity of this example, assume that all vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0275] Each vehicle can be similar to the vehicles disclosed in other embodiments (e.g., vehicle 200), and can include components or devices that are included in or associated with the vehicles disclosed in other embodiments. Each vehicle can be equipped with an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle can communicate with a remote server 1230 via one or more networks (e.g., via a cellular network and / or the Internet, etc.) through a wireless communication path 1235 as shown by the dashed line. Each vehicle can transmit data to the server 1230 and receive data from the server 1230. For example, the server 1230 can collect data from multiple vehicles traveling on road segment 1200 at different times, and can process the collected data to generate an autonomous vehicle road navigation model or an update to the model. The server 1230 can transmit the autonomous vehicle road navigation model or an update to the model to the vehicles that transmit data to the server 1230. The server 1230 can transmit the autonomous vehicle road navigation model or an update to the model to other vehicles that will later travel on road segment 1200.

[0276] When vehicles 1205, 1210, 1215, 1220, and 1225 are traveling on road segment 1200, the navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 can be transmitted to server 1230. In some embodiments, the navigation information can be associated with the common road segment 1200. The navigation information can include the trajectories associated with each of vehicles 1205, 1210, 1215, 1220, and 1225 as each vehicle travels on road segment 1200. In some embodiments, the trajectory can be reconstructed based on data sensed by various sensors and devices provided on vehicle 1205. For example, the trajectory can be reconstructed based on at least one of accelerometer data, speed data, landmark data, road geometry or profile data, vehicle position data, and self-motion data. In some embodiments, the trajectory can be reconstructed based on data from an inertial sensor (such as an accelerometer) and the speed of vehicle 1205 sensed by a speed sensor. Additionally, in some embodiments, the trajectory can be determined based on the self-motion of a sensed camera (e.g., by a processor on each of vehicles 1205, 1210, 1215, 1220, and 1225), and the self-motion of the sensed camera can indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The self-motion of the camera (and thus the vehicle body) can be determined by analyzing one or more images captured by the camera.

[0277] In some embodiments, the trajectory of vehicle 1205 can be determined by a processor provided on vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 can receive data sensed by various sensors and devices provided in vehicle 1205 and determine the trajectory based on the data received from vehicle 1205.

[0278] In some embodiments, the navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 can include data regarding the road surface, road geometry, or road profile. The geometry of road segment 1200 can include lane structure and / or landmarks. The lane structure can include the total number of lanes on road segment 1200, lane types (e.g., single lane, double lane, driving lane, overtaking lane, etc.), signs on the lane, lane width, etc. In some embodiments, the navigation information can include lane assignment, e.g., in which lane of the multiple lanes the vehicle is traveling. For example, the lane assignment can be associated with the numerical value "3", which indicates that the vehicle is traveling on the third lane from the left or right. As another example, the lane assignment can be associated with the text value "center lane", which indicates that the vehicle is traveling on the center lane.

[0279] Server 1230 may store navigation information on a non - transitory computer - readable medium, such as a hard - disk drive, an optical disc, a magnetic tape, a 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 for public road segment 1200 based on navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225, and may store the 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 multiple trajectories determined from crowdsourced navigation data. Server 1230 may transmit the model or the updated portion of the model to one or more of autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or to any other autonomous vehicle traveling on the road segment at a later time, for updating an existing autonomous vehicle road navigation model provided in the vehicle's navigation system. The autonomous vehicle road navigation model may be used by autonomous vehicles for autonomous navigation along public road segment 1200.

[0280] As described above, the autonomous vehicle road navigation model may be included in a sparse map (e.g., Figure 8 the sparse map 800 depicted therein). The sparse map 800 may include sparse records of data related to the road geometry and / or landmarks along the road, which may provide sufficient information for guiding the autonomous navigation of autonomous vehicles, but do not require excessive data storage. In some embodiments, the autonomous vehicle road navigation model may be stored separately from the sparse map 800, and when the model is executed for navigation, map data from the sparse map 800 may be used. In some embodiments, the autonomous vehicle road navigation model may use map data included in the sparse map 800 to determine a target trajectory along road segment 1200 for guiding the autonomous navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225 or other vehicles traveling along road segment 1200 at a later time. 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 cause the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory included in the sparse map 800 to verify and / or correct the current driving route of vehicle 1205.

[0281] In an autonomous vehicle road navigation model, the geometric structure of a road feature or a target trajectory can be encoded by a curve in three-dimensional space. In one embodiment, the curve can be a three-dimensional spline that includes one or more connected three-dimensional polynomials. As understood by those skilled in the art, a spline can be a numerical function for fitting data that is defined piecewise by a series of polynomials. The spline for fitting the three-dimensional geometric structure data of a road can include a linear spline (first order), a quadratic spline (second order), a cubic spline (third order), or any other spline (other order), or a combination thereof. The spline can include one or more three-dimensional polynomials of different orders that connect (e.g., fit) the data points of the three-dimensional geometric structure data of the 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., road segment 1200) or a lane of road segment 1200.

[0282] As described above, the autonomous vehicle road navigation model included in the sparse map can include other information, such as the identification of at least one landmark along road segment 1200. The landmark can be 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 can capture an image of the landmark. A processor (e.g., processor 180, 190, or processing unit 110) provided on vehicle 1205 can process the image of the landmark to extract the identification information of the landmark. The landmark identification information, rather than the actual image of the landmark, can be stored in the sparse map 800. The landmark identification information can require much less storage space than the actual image. Other sensors or systems (e.g., GPS system) can also provide certain identification information of the landmark (e.g., the location of the landmark). The landmark can include at least one of a traffic sign, an arrow sign, a lane sign, a dashed lane sign, a traffic light, a stop line, a direction sign (e.g., a highway exit sign having an arrow indicating a direction, a highway sign having arrows pointing to different directions or places), a landmark beacon, or a lamppost. A landmark beacon refers to a device (e.g., an RFID device) installed along a road segment that transmits or reflects a signal to a receiver mounted on a vehicle, such that when the vehicle passes by the device, the beacon received by the vehicle and the location of the device (e.g., determined from the GPS positioning of the device) can be used as a landmark to be included in the autonomous vehicle road navigation model and / or the sparse map 800.

[0283] The identification of at least one landmark may include the location of at least one landmark. The location of the landmark may be determined based on position measurements performed using sensor systems (e.g., global positioning system, inertial-based positioning system, landmark beacons, etc.) associated with multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of the landmark 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 drives. For example, vehicles 1205, 1210, 1215, 1220, and 1225 may transmit position measurements to server 1230, and server 1230 may average the position measurements and use the averaged position measurements as the location of the landmark. The location of the landmark may be continuously refined by measurements received from vehicles in subsequent drives.

[0284] The identification of the landmark may include the size of the landmark. A processor provided on a vehicle (e.g., 1205) may estimate the physical size of the landmark based on an analysis of an image. Server 1230 may receive multiple estimates of the physical size of the same landmark from different vehicles over different drives. Server 1230 may average the different estimates to arrive at the physical size of the landmark and store the landmark size in the road model. The physical size estimate may be used to further determine or estimate the distance from the vehicle to the landmark. The distance to the landmark may be estimated based on the current speed of the vehicle and based on the scale of the expansion of the landmark as it appears in the image relative to the extended focus of the camera. For example, the distance to the landmark may be estimated by Z = V * dt * R / D, where V is the speed of the vehicle, R is the distance from the landmark at time t1 to the extended focus in the image, and D is the change in the distance of the landmark in the image from t1 to t2. dt represents (t2 - t1). For example, the distance to the landmark may be estimated by Z = V * dt * R / D, where V is the speed of the vehicle, R is the distance between the landmark and the extended focus in the image, dt is the time interval, and D is the image displacement of the landmark along the epipolar line. Other equations equivalent to the above equation, such as Z = V * ω / Δω, may be used to estimate the distance to the landmark. Here, V is the vehicle speed, ω is the image length (similar to object width), and Δω is the change in this image length per unit time.

[0285] When the physical size of the landmark is known, the distance to the landmark may also be determined based on the equation: 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 when the landmark leaves the image. According to the above equation, ΔZ = f * W * Δω / ω may be used. 2+f *ΔW / ω is used to calculate the change in distance Z, where ΔW decays to zero through averaging, and where Δω is the number of pixels representing the bounding box accuracy in the image. The value of the estimated physical size of the landmark can be calculated by averaging multiple observations on the server side. The final error in distance estimation can be very small. When using the above equation, two sources of error may occur, namely ΔW and Δω. Their contributions to the distance error are given by ΔZ = f * W *Δω / ω 2 +f *ΔW / ω. However, ΔW decays to zero through averaging; thus, ΔZ is determined by Δω (e.g., the inaccuracy of the bounding box in the image).

[0286] For a landmark of unknown size, the distance to the landmark can be estimated by tracking feature points on the landmark between consecutive frames. For example, certain features that appear 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 the distance estimate. As another example, the average of the distance distribution can be used as the distance estimate.

[0287] Figure 13 An example autonomous vehicle road navigation model represented by multiple three-dimensional splines 1301, 1302, and 1303 is shown. Figure 13 The curves 1301, 1302, and 1303 shown are for illustrative purposes only. Each spline can include one or more three-dimensional polynomials connecting multiple data points 1310. Each polynomial can be a first-order polynomial, a second-order polynomial, a third-order polynomial, or a combination of any suitable polynomials of different orders. Each data point 1310 can be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 can be associated with data related to a landmark (e.g., the size, location, and identification information of the landmark) and / or road signature profile (e.g., road geometry, road roughness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 can be associated with data related to a landmark, while other data points can be associated with data related to a road signature profile.

[0288] Figure 14Shows the original positioning data 1410 (e.g., GPS data) received from five separate drives. A drive can be separated from another drive if one drive is crossed by separate vehicles at the same time, the same vehicle at separate times, or separate vehicles at separate times. To account for errors in the positioning data 1410 and the different positions of vehicles within the same lane (e.g., one vehicle may be closer to the left side of the lane than another), the server 1230 can use one or more statistical techniques to generate a map skeleton 1420 to determine whether changes in the original positioning data 1410 represent actual deviations or statistical errors. Each path within the skeleton 1420 can be linked back to the original data 1410 that formed that path. For example, the path between A and B within the skeleton 1420 is linked to the original data 1410 from drives 2, 3, 4, and 5 but not from drive 1. The skeleton 1420 may not be detailed enough for navigating a vehicle (e.g., because unlike the splines described above, the skeleton 1420 combines drives from multiple lanes on the same road), but can provide useful topological information and can be used to define intersections.

[0289] Figure 15 Shows an example of how additional details can be generated for a sparse map within a section of the map skeleton (e.g., section A to section B within the skeleton 1420). As Figure 15 shown, data (e.g., ego-motion data, road sign data, etc.) can be shown as a function of the position S (or S1 or S2) along the drive. The server 1230 can identify the landmarks of the sparse map by identifying the unique matches between the landmarks 1501, 1503, and 1505 of drive 1510 and the landmarks 1507 and 1509 of drive 1520. Such a matching algorithm can result in the identification of the landmarks 1511, 1513, and 1515. However, those skilled in the art will recognize that other matching algorithms can be used. For example, probabilistic optimization can be used instead of or in combination with the unique match. The server 1230 can longitudinally align the drives to align the matched landmarks. For example, the server 1230 can select one drive (e.g., drive 1520) as a reference drive and then shift and / or elastically stretch the other drive(s) (e.g., drive 1510) for alignment.

[0290] Figure 16 Shows an example of aligned landmark data used in a sparse map. In the Figure 16 example, the landmark 1610 includes a road sign. Figure 16 The example further depicts data from multiple drives 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the Figure 16In the example, the data from drive 1613 contains "ghost" landmarks, and the server 1230 can identify it as such because drives 1601, 1603, 1605, 1607, 1609, and 1611 do not contain the identification of landmarks near the landmarks identified in drive 1613. Accordingly, when the ratio of images in which the landmark does appear to images in which the landmark does not appear exceeds a threshold, the server 1230 can accept the potential landmark, and / or when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold, the server 1230 can reject the potential landmark.

[0291] Figure 17 FIG. depicts a system 1700 for generating driving data, which can be used for crowdsourcing sparse maps. As Figure 17 shown, the system 1700 can include a camera 1701 and a locating device 1703 (e.g., a GPS locator). The camera 1701 and the locating device 1703 can be mounted on a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). The camera 1701 can generate multiple types of data, e.g., ego-motion data, traffic sign data, road data, etc. The camera data and the location data can be segmented into driving segments 1705. For example, the driving segments 1705 can each have camera data and location data from less than 1 kilometer of driving.

[0292] In some embodiments, the system 1700 can remove redundancy in the driving segments 1705. For example, if a landmark appears in multiple images from the camera 1701, the system 1700 can remove the redundant data such that the driving segment 1705 contains only one copy of the location of the landmark and any metadata associated with the landmark. As a further example, if a lane marker appears in multiple images from the camera 1701, the system 1700 can remove the redundant data such that the driving segment 1705 contains only one copy of the location of the lane marker and any metadata associated with the lane marker.

[0293] The system 1700 also includes a server (e.g., server 1230). The server 1230 can receive the driving segments 1705 from the vehicle and reorganize the driving segments 1705 into a single drive 1707. This arrangement can reduce bandwidth requirements when transmitting data between the vehicle and the server, while also allowing the server to store data related to the entire drive.

[0294] Figure 18 FIG. depicts a system 1700 that is further configured for crowdsourcing sparse maps Figure 17 As Figure 17As shown, system 1700 includes vehicle 1810, which uses, for example, cameras (which generate, for example, ego-motion data, traffic sign data, road data, etc.) and positioning devices (such as GPS locators) to capture driving data. As Figure 17 shown, vehicle 1810 segments the collected data into driving segments (depicted as "DS1 1", "DS2 1", "DSN 1" in Figure 18 ). Then, server 1230 receives the driving segments and reconstructs the drive from the received segments (described as "Drive 1" in Figure 18 ).

[0295] As Figure 18 further depicted, system 1700 also receives data from additional vehicles. For example, vehicle 1820 also uses, for example, cameras (which generate, for example, ego-motion data, traffic sign data, road data, etc.) and positioning devices (such as GPS locators) to capture driving data. Similar to vehicle 1810, vehicle 1820 segments the collected data into driving segments (depicted as "DS1 2", "DS2 2", "DSN 2" in Figure 18 ). Then, server 1230 receives the driving segments and reconstructs the drive from the received segments (described as "Drive 2" in Figure 18 ). Any number of additional vehicles can be used. For example, Figure 18 also includes "Car N", which captures driving data, segments it into driving segments (depicted as "DS1 N", "DS2 N", "DSN N" in Figure 18 ), and transmits it to server 1230 for reconstruction into a drive (depicted as "Drive N" in Figure 18 ).

[0296] As Figure 18 shown, server 1230 can use the reconstructed drives (such as "Drive 1", "Drive 2", and "Drive N") collected from multiple vehicles (such as "Car 1" (also labeled vehicle 1810), "Car 2" (also labeled vehicle 1820), and "Car N") to build a sparse map (depicted as "Map").

[0297] Figure 19 is a flow chart showing an example process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 can be executed by one or more processing devices included in server 1230.

[0298] Process 1900 may include receiving a plurality of images obtained when one or more vehicles cross a road segment (step 1905). Server 1230 may receive images from cameras included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, when vehicle 1205 travels along road segment 1200, camera 122 may capture one or more images of the environment around vehicle 1205. In some embodiments, server 1230 may also receive stripped down image data that has been made redundant by a processor on vehicle 1205, as discussed above with reference to Figure 17 discussed.

[0299] Process 1900 may further include identifying at least one line representation of a road surface feature extending along the road segment based on the plurality of images (step 1910). Each line representation may represent a path along the road segment that substantially corresponds to the road surface feature. For example, server 1230 may analyze the environmental images received from camera 122 to identify a curb or lane marking and determine a travel trajectory along road segment 1200 associated with the curb or lane marking. In some embodiments, the trajectory (or line representation) may include a spline, polynomial representation, or curve. Server 1230 may determine the travel trajectory of vehicle 1205 based on the camera ego-motion (e.g., three-dimensional translation and / or three-dimensional rotational motion) received at step 1905.

[0300] Process 1900 may also include identifying a plurality of landmarks associated with the road segment based on the plurality of images (step 1910). For example, server 1230 may analyze the environmental images received from camera 122 to identify one or more landmarks, such as road signs along road segment 1200. Server 1230 may use the analysis of the plurality of images obtained when one or more vehicles cross the road segment to identify landmarks. To enable crowdsourcing, the analysis may include rules for accepting and rejecting potential landmarks associated with the road segment. For example, the analysis may include accepting a potential landmark when the ratio of images in which the landmark does appear to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

[0301] Process 1900 may include other operations or steps performed by server 1230. For example, the navigation information may include a target trajectory for a vehicle to travel along a road segment, and process 1900 may include clustering, by server 1230, vehicle trajectories associated with multiple vehicles traveling on the road segment and determining the target trajectory based on the clustered vehicle trajectories, as discussed further in detail below. Clustering the vehicle trajectories may include clustering, by server 1230, multiple trajectories associated with vehicles traveling on the road segment into multiple clusters based on at least one of an absolute heading of the vehicle or a lane assignment of the vehicle. Generating the target trajectory may include averaging, by server 1230, the clustered trajectories. As a further 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.

[0302] 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 on the earth's surface may be used. To use a map for steering, the host vehicle may determine its position and orientation relative to the map. It may seem natural to use a GPS device on the vehicle to locate the vehicle on the map and to find the rotation transformation between the body reference frame and the world reference frame (e.g., north, east, and down). Once the body reference frame is aligned with the map reference frame, the desired route may be expressed in the body reference frame, and a steering command may be calculated or generated.

[0303] The disclosed systems and methods may enable autonomous vehicle navigation (e.g., steering control) with low footprint models that may be collected by the autonomous vehicle itself without the assistance of expensive surveying instruments. To support autonomous navigation (e.g., steering applications), the road model may include a sparse map that has the geometric structure of the road, its lane structure, and landmarks that may be used to determine the positioning or location of the vehicle along a trajectory included in the model. As described above, the generation of the sparse map may be performed by a remote server that communicates with vehicles traveling on the road and receives data from the vehicles. The data may include sensed data, trajectories reconstructed based on the sensed data, and / or recommended trajectories that may represent modified reconstructed trajectories. As described below, the server may transmit the model back to the vehicle or other vehicles traveling on the road later to assist with autonomous navigation.

[0304] Figure 20A block diagram of a server is shown. Server 1230 may include a communication unit 2005, which may include hardware components (e.g., communication control circuits, switches, and antennas) and software components (e.g., communication protocols, computer code). For example, communication unit 2005 may include at least one network interface. Server 1230 may communicate with vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. For example, server 1230 may receive navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. Server 1230 may assign an autonomous vehicle road navigation model to one or more autonomous vehicles via communication unit 2005.

[0305] Server 1230 may include at least one non-transitory storage medium 2010, such as a hard disk drive, optical disk, 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 a sparse map (e.g., the sparse map 800 discussed above with reference to Figure 8 ).

[0306] In addition to or instead of storage device 2010, server 1230 may include a memory 2015. Memory 2015 may be similar to or different from memory 140 or 150. Memory 2015 may be a 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 of the sparse map 800), an autonomous vehicle road navigation model, and / or navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225.

[0307] Server 1230 may include at least one processing device 2020 configured to execute computer code or instructions stored in a memory 2015 to perform various functions. For example, the 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 the analysis. The processing device 2020 may control the 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 that later travels on the road segment 1200). The processing device 2020 may be similar to or different from the processors 180, 190, or the processing unit 110.

[0308] Figure 21 A block diagram of the memory 2015 is shown. The memory 2015 may store computer code or instructions for performing one or more operations for generating a road navigation model for autonomous vehicle navigation. As Figure 21 shown, the memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, the memory 2015 may include a model generation module 2105 and a model distribution module 2110. The processor 2020 may execute instructions stored in any of the modules 2105 and 2110 included in the memory 2015.

[0309] 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, when 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 vehicle trajectories of each different cluster. Such an operation may include finding the mean or average trajectory of the vehicle trajectories of the cluster within each cluster (e.g., by averaging the data representing the vehicle trajectories of the cluster). In some embodiments, the target trajectory may be associated with a single lane of the common road segment 1200.

[0310] A road model and / or a sparse map may store trajectories associated with road segments. These trajectories may be referred to as target trajectories, which are provided to an autonomous vehicle for autonomous navigation. The target trajectories may be received from multiple vehicles, or may be generated based on actual trajectories or recommended trajectories (actual trajectories with some modifications) received from multiple vehicles. The target trajectories included in the road model or the sparse map may be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0311] Vehicles traveling on a road segment may collect data through various sensors. This data may include landmarks, 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, which will reconstruct the actual trajectory of the vehicle. In some embodiments, the vehicle may transmit data related to the trajectory (e.g., a curve in any reference frame), landmark data, and lane assignment along the driving path to server 1230. Various vehicles traveling along the same road segment in various driving manners may have different trajectories. Server 1230 may identify the routes or trajectories associated with each lane from the trajectories received from the vehicles through a clustering process.

[0312] Figure 22 A process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine a target trajectory for a common road segment (e.g., road segment 1200) is shown. The target trajectory 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 landmark, 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, 2225, and 2230, as Figure 22 shown.

[0313] Various criteria can be used to perform clustering. In some embodiments, all the drives in a cluster can be similar in terms of the absolute heading along road segment 1200. The absolute heading can be obtained from the GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, dead reckoning can be used to obtain the absolute heading. As understood by those skilled in the art, dead reckoning can be used to determine the current position of vehicles 1205, 1210, 1215, 1220, and 1225 and thus their headings by using previously determined positions, estimated speeds, etc. Trajectories clustered by absolute heading can help identify routes along the road.

[0314] In some embodiments, all the drives in a cluster can be similar with respect to lane assignment of the drives along road segment 1200 (e.g., in the same lane before and after an intersection). Trajectories clustered by lane assignment can help identify lanes along the road. In some embodiments, both criteria (e.g., absolute heading and lane assignment) can be used for clustering.

[0315] In each of the clusters 2205, 2210, 2215, 2220, 2225, and 2230, the trajectories can be averaged to obtain a target trajectory associated with a particular cluster. For example, the trajectories from multiple drives associated with the same lane cluster can be averaged. The average trajectory can be the target trajectory associated with a particular lane. To average a set of trajectories, server 1230 can select a reference frame of any trajectory C0. For all the other trajectories (C1,..., Cn), server 1230 can find the rigid transformation that maps Ci to C0, where i = 1, 2,..., n, where n is a positive integer corresponding to the total number of trajectories included in the cluster. Server 1230 can calculate the mean curve or trajectory in the reference frame of C0.

[0316] In some embodiments, landmarks can define an arc length match between different drives, which can be used for alignment of the trajectories with the lanes. In some embodiments, lane signs before and after an intersection can be used for alignment of the trajectories with the lanes.

[0317] To assemble lanes from the trajectories, server 1230 can select a reference frame of any lane. Server 1230 can map the partially overlapping lanes to the selected reference frame. Server 1230 can continue mapping until all the lanes are in the same reference frame. Adjacent lanes to each other can be aligned as if they were the same lane and they can be laterally shifted.

[0318] Landmarks 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 landmark can be identified multiple times by multiple vehicles in multiple drives. Data received in different drives regarding the same landmark may vary slightly. Such data can be averaged and mapped to the same reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of the data of the same landmark received in multiple drives can be calculated.

[0319] In some embodiments, each lane of road segment 120 can be associated with a target trajectory and certain landmarks. The target trajectory or multiple such target trajectories can be included in an autonomous vehicle road navigation model, which can be used later by other autonomous vehicles traveling along the same road segment 1200. As the vehicle travels along road segment 1200, the landmarks identified by vehicles 1205, 1210, 1215, 1220, and 1225 can be recorded in association with the target trajectory. The data of the target trajectory and the landmarks can be continuously or periodically updated using new data received from other vehicles in subsequent drives.

[0320] For the positioning of an autonomous vehicle, the disclosed systems and methods can use an extended Kalman filter. The positioning of the vehicle can be determined based on three-dimensional position data and / or three-dimensional orientation data, and the prediction of the future positioning in front of the vehicle's current positioning through the integration of self-motion. The positioning of the vehicle can be corrected or adjusted through the image observation of landmarks. For example, when the vehicle detects a landmark within an image captured by a camera, the landmark can be compared with known landmarks stored in the road model or the sparse map 800. The known landmarks can have known positions (e.g., GPS data) along the target trajectory stored in the road model and / or the sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark can be estimated. The positioning of the vehicle along the target trajectory can be adjusted based on the distance to the landmark and the known position of the landmark (stored in the road model or the sparse map 800). The position / orientation data of the landmarks stored in the road model and / or the sparse map 800 (e.g., the mean from multiple drives) can be assumed to be accurate.

[0321] In some embodiments, the disclosed system can form a closed-loop subsystem, where the estimation of the vehicle's six-degree-of-freedom positioning (e.g., three-dimensional position data plus three-dimensional orientation data) can be used for the navigation of the autonomous vehicle (e.g., steering the wheels of the autonomous vehicle) to reach a desired point (e.g., stored 1.3 seconds ahead). In turn, the data from the steering and the actual navigation measurements can be used to estimate the six-degree-of-freedom positioning.

[0322] In some embodiments, poles along a road, such as lampposts and electrical or cable poles, can be used as landmarks for positioning a vehicle. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along a road segment, can also be used as landmarks for positioning a vehicle. When poles are used for positioning, the x-view of the pole (i.e., from the perspective of the vehicle) can be used instead of the y-view (i.e., the distance to the pole), because the bottom of the pole may be occluded and sometimes they are not in the road plane.

[0323] Figure 23 A navigation system for a vehicle is shown, which can be used for autonomous navigation using a crowdsourced sparse map. For illustration, the vehicle is referred to as vehicle 1205. Figure 23 The vehicle shown in 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. As Figure 12 shown, vehicle 1205 can communicate with server 1230. Vehicle 1205 can include an image capture device 122 (e.g., camera 122). Vehicle 1205 can include a navigation system 2300, which is configured to provide navigation guidance for vehicle 1205 to travel on a road (e.g., road segment 1200). Vehicle 1205 can also include other sensors, such as a speed sensor 2320 and an accelerometer 2325. The speed sensor 2320 can be configured to detect the speed of vehicle 1205. The accelerometer 2325 can be configured to detect the acceleration or deceleration of vehicle 1205. Figure 23 The vehicle 1205 shown in can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, vehicle 1205 can also be a non-autonomous, human-controlled vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0324] The navigation system 2300 may include a communication unit 2305 configured to communicate with a 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 also 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 a storage device 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 camera 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 such as road surface roughness, road width, road height, road curvature, etc. For example, the road profile sensor 2330 may include devices that measure the movement of the vehicle's suspension 2305 to deduce the road roughness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor to measure the distance from the vehicle 1205 to the road edge (e.g., an obstacle on the road edge) to thereby measure the road width. In some embodiments, the road profile sensor 2330 may include devices configured to measure the elevation of the road. In some embodiments, the road profile sensor 2330 may include devices configured to measure the road curvature. For example, a camera (e.g., camera 122 or another camera) may be used to capture road images that show the road curvature. The vehicle 1205 may use such images to detect the road curvature.

[0325] The at least one processor 2315 may be programmed to receive at least one environmental image associated with the vehicle 1205 from the camera 122. The at least one processor 2315 may analyze the at least one environmental image to determine navigation information related to the vehicle 1205. The navigation information may include a trajectory associated with the vehicle 1205 traveling along a road segment 1200. The at least one processor 2315 may determine the trajectory based on the movement of the camera 122 (and thus the vehicle), e.g., three-dimensional translation and three-dimensional rotational movement. In some embodiments, the at least one processor 2315 may determine the translational and rotational movement of the camera 122 based on an analysis of a plurality of images acquired by the camera 122. In some embodiments, the navigation information may include lane assignment information (e.g., in which lane the vehicle 1205 is traveling along the road segment 1200). The navigation information transmitted from the vehicle 1205 to the server 1230 may be used by the server 1230 to generate and / or update an autonomous vehicle road navigation model, which may be transmitted back from the server 1230 to the vehicle 1205 for providing autonomous navigation guidance to the vehicle 1205.

[0326] 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 together with road information. The road location information may include at least one of GPS signals received by GPS unit 2310, landmark information, road geometry, lane information, etc. At least one processor 2315 may receive an autonomous vehicle road navigation model or a portion of the model 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, accelerating, passing another vehicle, etc.) of vehicle 1205 based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0327] At least one processor 2315 may be configured to communicate with various sensors and components included in vehicle 1205, including communication unit 1705, GPS unit 2315, camera 122, speed sensor 2320, accelerometer 2325, and road profile sensor 2330. At least one processor 2315 may collect information or data from the various sensors and components and transmit the information or data to server 1230 via communication unit 2305. Alternatively or additionally, the various sensors or components of vehicle 1205 may also communicate with server 1230 and transmit the data or information collected by the sensors or components to server 1230.

[0328] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may communicate with each other and may share navigation information with each other such that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 may generate an autonomous vehicle road navigation model using crowdsourcing, for example, based on information shared by other vehicles. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may share navigation information with each other and each vehicle may update the autonomous vehicle road navigation model provided in its own vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) may act as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) may perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle may communicate with other vehicles and receive navigation information from other vehicles. At least one processor 2315 of the hub vehicle may generate an autonomous vehicle road navigation model or an update to the model based on the shared information received from other vehicles. At least one processor 2315 of the hub vehicle may transmit the autonomous vehicle road navigation model or an update to the model to other vehicles to provide autonomous navigation guidance.

[0329] Mapping Lane Markings and Navigation Based on Mapped Lane Markings

[0330] As previously mentioned, the autonomous vehicle road navigation model and / or the sparse map 800 may include a plurality of mapped lane markers associated with road segments. As discussed in more detail below, these mapped lane markers may be used when an autonomous vehicle is navigating. For example, in some embodiments, the mapped lane markers may be used to determine a lateral position and / or orientation relative to a planned trajectory. Using this position information, the autonomous vehicle can adjust its heading direction to match the direction of the target trajectory at the determined position.

[0331] Vehicle 200 can be configured to detect lane markings in a given road segment. A road segment can include any markings on a road for guiding vehicle traffic on the road. For example, a lane marking can be a solid or dashed line that demarcates the edge of a driving lane. A lane marking can also include double lines, such as double solid lines, double dashed lines, or a combination of solid and dashed lines, to indicate, for example, whether passing is allowed in an adjacent lane. A lane marking can also include highway entrance and exit signs indicating, for example, a deceleration lane for an exit ramp, or dashed lines indicating that a lane is for turning only or that the lane is about to end. Markings can also indicate a work zone, a temporary lane change, a driving path through an intersection, a median, a dedicated lane (e.g., a bicycle lane, an HOV lane, etc.), or various other markings (e.g., a crosswalk, a speed hump, a railway crossing, a stop line, etc.).

[0332] Vehicle 200 can use cameras, such as image capture devices 122 and 124 included in image acquisition unit 120, to capture images of surrounding lane markings. Vehicle 200 can analyze the images based on features identified in one or more captured images to detect point locations associated with lane markings. These point locations can be uploaded to a server to represent lane markings in sparse map 800. Depending on the location and field of view of the camera, lane markings on both sides of the vehicle can be detected simultaneously from a single image. In other embodiments, different cameras can be used to capture images on multiple sides of the vehicle. Instead of uploading the actual images of the lane markings, the lane markings can be stored as splines or a series of points in sparse map 800, thereby reducing the size of sparse map 800 and / or the data that has to be remotely uploaded by the vehicle.

[0333] Figures 24A - 24D Exemplary point locations that can be detected by vehicle 200 to represent a particular lane marking are shown. Similar to the landmarks described above, vehicle 200 can use various image recognition algorithms or software to identify point locations within the captured images. For example, vehicle 200 can identify a series of edge points, corner points, or various other point locations associated with a particular lane marking. Figure 24A A solid lane marking 2410 that can be detected by vehicle 200 is shown. Lane marking 2410 can represent the outer edge of a road, indicated by a white solid line. As Figure 24AAs shown, vehicle 200 may be configured to detect a plurality of edge location points 2411 along a lane marking. The location points 2411 may be collected at any interval sufficient to represent the lane marking in a sparse map. For example, the lane marking may be represented by one point per meter of the detected edge, one point per five meters of the detected edge, or at other suitable spacings. In some embodiments, the spacing may be determined by other factors rather than at a set interval, such as, for example, points ranked based on the highest confidence in the vehicle 200's localization of the detected points at that location. Although Figure 24A edge location points on the inner edge of lane marking 2410 are shown, these points may be collected on the outer edge of the line or along both edges. Additionally, although Figure 24A a single line is shown, similar edge points may be detected for double solid lines. For example, points 2411 may be detected along the edge of one or both solid lines.

[0334] Depending on the type or shape of the lane marking, vehicle 200 may also represent the lane marking differently. Figure 24B An exemplary dashed lane marking 2420 that may be detected by vehicle 200 is shown. Instead of identifying edge points as in Figure 24A , the vehicle may detect a series of corner points 2421 representing the corners of the lane dashes to define the complete boundary of the dashes. Although Figure 24B each corner of a given dashed marking that is located is shown, vehicle 200 may detect or upload a subset of the points shown in the figure. For example, vehicle 200 may detect the leading edge or leading corner of a given dashed marking, or may detect the two corner points closest to the inside of the lane. Additionally, not every dashed marking may be captured. For example, vehicle 200 may capture and / or record points representing samples (e.g., every other, every third, every fifth, etc.) of the dashed marking, or points representing the dashed marking at a predetermined spacing (e.g., per meter, per five meters, per ten meters, etc.). Corner points of similar lane markings (such as markings indicating that a lane is for an exit ramp, a marking indicating that a particular lane is ending, or various other lane markings that may have detectable corner points) may also be detected. Corner points of lane markings consisting of double dashes or a combination of solid and dashed lines may also be detected.

[0335] In some embodiments, the points uploaded to the server to generate the mapped lane marking may represent other points in addition to the detected edge points or corner points. Figure 24CShows a series of points that can represent the centerline of a given lane marking. For example, a solid lane 2410 can be represented by centerline points 2441 along the centerline 2440 of the lane marking. In some embodiments, vehicle 200 can be configured to use various image recognition techniques (such as convolutional neural network (CNN), scale-invariant feature transform (SIFT), histogram of oriented gradient (HOG) features, or other techniques) to detect these center points. Alternatively, vehicle 200 can detect other points, such as Figure 24A The edge points 2411 shown, and the centerline points 2441 can be calculated, for example, by detecting points along each edge and determining the midpoint between the edge points. Similarly, a dashed lane marking 2420 can be represented by centerline points 2451 along the centerline 2450 of the lane marking. The centerline points can be located at the edge of the dashed line, as shown in Figure 24C, or at various other positions along the centerline. For example, each dashed line can be represented by a single point at the geometric center of the dashed line. These points can also be spaced apart at a predetermined interval (e.g., every meter, every 5 meters, every 10 meters, etc.) along the centerline. The centerline points 2451 can be directly detected by vehicle 200 or can be calculated based on other detected reference points (such as corner points 2421), as Figure 24B Shown. Using techniques similar to those described above, the centerline can also be used to represent other lane marking types, such as double lines.

[0336] In some embodiments, vehicle 200 can identify points representing other features, such as the vertex between two intersecting lane markings. Figure 24D Shows exemplary points representing the intersection between two lane markings 2460 and 2465. Vehicle 200 can calculate the vertex 2466 representing the intersection between the two lane markings. For example, one of the lane markings 2460 or 2465 can represent a train crossing area or other crossing area in a section of road. Although lane markings 2460 and 2465 are shown intersecting perpendicularly to each other, various other configurations can be detected. For example, lane markings 2460 and 2465 can intersect at other angles, or one or both lane markings can 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 further information about the orientation of lane markings 2460 and 2465.

[0337] Vehicle 200 can associate real-world coordinates with each detected point of a lane marker. For example, a localization identifier (including the coordinates of each point) can be generated for uploading to a server for mapping the lane marker. The localization identifier can also include other identification information about the point, including whether the point represents a corner point, an edge point, a center point, etc. Thus, vehicle 200 can be configured to determine the real-world position of each point based on the analysis of an image. For example, vehicle 200 can detect other features in the image (such as the various landmarks described above) to locate the real-world position of the lane marker. This can include determining the localization of the lane marker in the image relative to the detected landmarks, or determining the position of the vehicle based on the detected landmarks and then determining the distance from the vehicle (or the target trajectory of the vehicle) to the lane marker. When landmarks are not available, the localization of the lane marker points can be determined relative to the position of the vehicle determined based on dead reckoning. The real-world coordinates included in the localization identifier can be represented as absolute coordinates (e.g., latitude / longitude coordinates), or can be relative to other features, such as a longitudinal position along the target trajectory and a lateral distance from the target trajectory. The localization identifier can then be uploaded to the server for generating a mapped lane marker in a navigation model (such as sparse map 800). In some embodiments, the server can construct a spline representing the lane markers of a road segment. Alternatively, vehicle 200 can generate the spline and upload it to the server for recording in the navigation model.

[0338] Figure 24E An exemplary navigation model or sparse map showing a corresponding road segment including mapped lane markers is shown. The sparse map can include a target trajectory 2475 that the vehicle follows along the road segment. As described above, the target trajectory 2475 can represent the ideal path that the vehicle takes when traveling on the corresponding road segment, or can be located elsewhere on the road (e.g., the centerline of the road, etc.). The target trajectory 2475 can be calculated using the various methods described above, for example, based on the aggregation (e.g., weighted combination) of two or more reconstructed trajectories of the vehicle passing through the same road segment.

[0339] In some embodiments, the target trajectory 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 can also be considered when generating the target trajectory. Different target trajectories can be generated for different types of vehicles (e.g., private cars, light trucks, and full trailers). For example, a relatively smaller turning radius target trajectory can be generated for a small private car compared to a larger semi-trailer truck. In some embodiments, road, vehicle, and environmental conditions can also be considered. For example, different target trajectories can be generated for different road conditions (e.g., wet, snowy, icy, dry, etc.), vehicle conditions (e.g., tire conditions or estimated tire conditions, braking conditions or estimated braking conditions, remaining fuel amount, etc.), or environmental factors (e.g., time of day, visibility, weather, etc.). The target trajectory can also depend on one or more aspects or features of a particular road segment (e.g., speed limit, turning frequency and size, slope, etc.). In some embodiments, various user settings can also be used to determine the target trajectory, such as a set driving mode (e.g., desired driving aggressiveness, economy mode, etc.).

[0340] The sparse map can also include mapped lane markers 2470 and 2480 representing lane markers along a road segment. The mapped lane markers can be represented by a plurality of localization identifiers 2471 and 2481. As described above, the localization identifiers can include the localization of points associated with detected lane markers in real-world coordinates. Similar to the target trajectory in the model, the lane markers can also include elevation data and can be represented as curves in three-dimensional space. For example, the curve can be a spline connecting three-dimensional polynomials of a suitable order. The curve can be calculated based on the localization identifiers. The mapped lane markers can also include other information or metadata about the lane markers, such as identifiers of the type of lane marker (e.g., lane marker between two lanes with the same driving direction, lane marker between two lanes with opposite driving directions, curb, etc.) and / or other characteristics of the lane marker (e.g., solid line, dashed line, single line, double line, yellow, white, etc.). In some embodiments, for example, crowdsourcing techniques can be used to continuously update the mapped lane markers within the model. The same vehicle can upload localization identifiers during multiple instances of traveling the same road segment, or data can be selected from multiple vehicles (such as 1205, 1210, 1215, 1220, and 1225) traveling the road segment at different times. The sparse map 800 can then be updated or refined based on subsequent localization identifiers received from the vehicles and stored in the system. As the mapped lane markers are updated and refined, the updated road navigation model and / or sparse map can be assigned to multiple autonomous vehicles.

[0341] Generating mapped lane markings in a sparse map may also include detecting and / or mitigating errors based on anomalies in the image or in the actual lane markings themselves. Figure 24F An exemplary anomaly 2495 associated with detecting lane markings 2490 is shown. Anomaly 2495 may occur in an image captured by vehicle 200 from, for example, an object that obstructs the camera's view of the lane markings, debris on the lens, etc. In some cases, the anomaly may be due to the lane markings themselves, which may be damaged or worn, or partially covered by dust, debris, water, snow, or other materials on the road. Anomaly 2495 may result in error points 2491 detected by vehicle 200. Sparse map 800 may provide the correct mapped lane markings and exclude the errors. In some embodiments, vehicle 200 may detect error points 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 detecting the anomaly, the vehicle may omit point 2491, or may adjust it to be consistent with other detected points. In other embodiments, for example, the error may be corrected after the point has been uploaded by determining that the point is outside an expected threshold based on other points uploaded during the same trip or based on an aggregation of data from previous trips along the same road segment.

[0342] The mapped lane markings in the navigation model and / or sparse map may also be used for navigation of an autonomous vehicle across a corresponding road. For example, a vehicle navigating along a target trajectory may periodically use the mapped lane markings in the sparse map to align itself with the target trajectory. As described above, between landmarks, the vehicle may navigate based on dead reckoning, where the vehicle uses sensors to determine its self-motion and estimate its position relative to the target trajectory. Errors may accumulate over time, and the vehicle's position determination relative to the target trajectory may become increasingly inaccurate. Accordingly, the vehicle may use the lane markings (and their known positioning) that appear in sparse map 800 to reduce the errors caused by dead reckoning in position determination. In this way, the identified lane markings included in sparse map 800 may be used as navigation anchors from which the vehicle's accurate position relative to the target trajectory may be determined.

[0343] Figure 25A An exemplary image 2500 of the vehicle's surrounding environment that may be used for navigation based on mapped lane markings is shown. Image 2500 may be captured, for example, by vehicle 200 through 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, as Figure 25A shown. Image 2500 may also include one or more landmarks 2521, such as road signs, for navigation as described above. Figure 25ASome elements (such as elements 2511, 2530, and 2520) that are shown in [reference] but do not appear in the captured image 2500 but are detected and / or determined by the vehicle 200 are also shown for reference.

[0344] Using the various techniques referenced above Figures 24A - 24D and Figure 24F described, the vehicle can analyze the image 2500 to identify lane markings 2510. Various points 2511 corresponding to features of the lane markings in the image can be detected. For example, the points 2511 can correspond to the edges of the lane markings, the corners of the lane markings, the midpoints of the lane markings, the vertices between two intersecting lane markings, or various other features or locations. The points 2511 can be detected as locations corresponding to points stored in a navigation model received from a server. For example, if a sparse map containing points representing the centerlines of mapped lane markings is received, the points 2511 can also be detected based on the centerlines of the lane markings 2510.

[0345] The vehicle can also determine the longitudinal position represented by the element 2520 and located along the target trajectory. For example, by detecting landmarks 2521 within the image 2500 and comparing the measured locations to known landmark locations stored in a road model or sparse map 800, the longitudinal position 2520 can be determined from the image 2500. Then, the vehicle's position along the target trajectory can be determined based on the distance to the landmark and the known location of the landmark. The longitudinal position 2520 can also be determined from images other than the image used to determine the position of the lane markings. For example, the longitudinal position 2520 can be determined by detecting landmarks in images taken by other cameras within the image acquisition unit 120 that are taken simultaneously or near-simultaneously with the image 2500. In some cases, the vehicle may not be near any landmarks 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 self-motion and estimate the longitudinal position 2520 relative to the target trajectory. The vehicle can also determine the distance 2530 representing the actual distance between the vehicle and the lane markings 2510 observed in the captured (multiple) images. When determining the distance 2530, camera angle, vehicle speed, vehicle width, or various other factors can be considered.

[0346] Figure 25BShows the lateral positioning correction of a vehicle based on mapped lane signs 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 sign 2510. Vehicle 200 can also access a road navigation model (such as sparse map 800), which can include mapped lane signs 2550 and target trajectory 2555. The mapped lane signs 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 previously. Vehicle 200 can also determine or estimate the longitudinal position 2520 along the target trajectory 2555, as referenced above Figure 25A above. Vehicle 200 can then determine the expected distance 2540 based on the lateral distance between the target trajectory 2555 and the mapped lane signs 2550 corresponding to the longitudinal position 2520. The lateral positioning of vehicle 200 can be corrected or adjusted by comparing the actual distance 2530 measured using the captured image(s) with the expected distance 2540 from the model.

[0347] Figure 26A Is a flowchart showing an exemplary process 2600A for mapping lane signs for autonomous vehicle navigation consistent with the disclosed embodiments. At step 2610, process 2600A can include receiving two or more location identifiers associated with detected lane signs. For example, step 2610 can be performed by server 1230 or one or more processors associated with the server. The location identifiers can include the location of points associated with the detected lane signs in real-world coordinates, as referenced above Figure 24EAs described above. In some embodiments, the location identifier may also include other data, such as additional information about road segments or lane markings. Additional data, such as accelerometer data, speed data, landmark data, road geometry or profile data, vehicle location data, self-motion data, or various other forms of data as described above, may also be received during step 2610. The location identifier may be generated by a vehicle (such as vehicles 1205, 1210, 1215, 1220, and 1225) based on images captured by the vehicle. For example, an identifier may be determined based on obtaining at least one image representing the environment of the host vehicle from a camera associated with the host vehicle, analyzing the at least one image to detect lane markings in the environment of the host vehicle, and analyzing the at least one image to determine the position of the detected lane markings relative to the location associated with the host vehicle. As described above, lane markings may include various different types of markings, and the location identifier may correspond to various points relative to the lane markings. For example, in the case where the detected lane marking is part of a dashed line marking a lane boundary, these points may correspond to the detected corners of the lane marking. In the case where the detected lane marking is part of a solid line marking a lane boundary, these points may correspond to the detected edges of the lane marking with various spacings as described above. In some embodiments, these points may correspond to the centerline of the detected lane marking, as Figure 24C shown, or may correspond to at least one of the vertex between two intersecting lane markings and two other points associated with the intersecting lane markings, as Figure 24D shown.

[0348] In step 2612, process 2600A may include associating the detected lane markings with the corresponding road segment. For example, server 1230 may analyze the real-world coordinates or other information received during step 2610 and compare the coordinates or other information with the location information stored in the autonomous vehicle road navigation model. Server 1230 may determine the road segment in the model that corresponds to the real-world road segment where the lane markings were detected.

[0349] 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 the 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 be based on the above reference Figure 24EUpdate the model using the various methods or processes described. In some embodiments, updating the autonomous vehicle road navigation model may include storing one or more location indicators of detected lane markers in real-world coordinates. The autonomous vehicle road navigation model may also include at least one target trajectory that the vehicle follows along a corresponding road segment, as Figure 24E shown.

[0350] In step 2616, process 2600A may include assigning the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles. For example, server 1230 may assign the updated autonomous vehicle road navigation model to vehicles 1205, 1210, 1215, 1220, and 1225, which may use the model for navigation. The autonomous vehicle road navigation model may be assigned via one or more networks (e.g., via a cellular network and / or the Internet, etc.), via wireless communication path 1235, as Figure 12 shown.

[0351] In some embodiments, data received from multiple vehicles (such as via crowdsourcing techniques) may be used to map lane markers, as referenced above Figure 24E described. For example, process 2600A may include receiving a first communication from a first host vehicle that includes a positioning identifier associated with a detected lane marker, and receiving a second communication from a second host vehicle that includes an additional positioning identifier associated with the detected lane marker. For example, the second communication may be received from a subsequent vehicle traveling on the same road segment, or from the same vehicle during a subsequent trip along the same road segment. Process 2600A may also include refining the determination of at least one location associated with the detected lane marker based on the positioning identifier received in the first communication and based on the additional positioning identifier received in the second communication. This may include using an average of the multiple positioning identifiers and / or filtering out "ghost" identifiers that may not reflect the real-world location of the lane marker.

[0352] Figure 26B is a flowchart showing an exemplary process 2600B for autonomously navigating a host vehicle along a road segment using mapped lane markers. Process 2600B may be performed, for example, by processing unit 110 of 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 host vehicle along a road segment and positioning identifiers associated with one or more lane markers associated with the road segment. For example, vehicle 200 may receive sparse map 800 or another road navigation model generated using process 2600A. In some embodiments, the target trajectory may be represented as a three-dimensional spline, e.g., asFigure 9B as shown. As described above in the reference Figures 24A - 24F The positioning identifier may include the positioning of points associated with lane markings in real-world coordinates (e.g., corner points of a dashed lane marking, edge points of a solid lane marking, vertices between two intersecting lane markings, and other points associated with intersecting lane markings, centerlines associated with lane markings, etc.).

[0353] In step 2621, process 2600B may include receiving at least one image representing the environment of the vehicle. The image may be received from an image capture device of the vehicle (such as 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 as described above.

[0354] In step 2622, process 2600B may include determining the longitudinal position of the host vehicle along the target trajectory. As described above in the reference Figure 25A This may be based on other information (e.g., landmarks, etc.) in the captured image or by dead reckoning of the vehicle between detected landmarks.

[0355] In step 2623, process 2600B may include determining an expected lateral distance to a lane marking based on the determined longitudinal position of the host vehicle along the target trajectory and based on two or more positioning identifiers associated with at least one lane marking. For example, vehicle 200 may use sparse map 800 to determine the expected lateral distance to a lane marking. As Figure 25B shown, the longitudinal position 2520 along target trajectory 2555 may be determined in step 2622. Using sparse map 800, vehicle 200 may determine the expected distance 2540 to mapped lane marking 2550 corresponding to longitudinal position 2520.

[0356] 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 example, lane marking 2510 may be detected by image analysis of image 2500, as Figure 25A shown.

[0357] In step 2625, process 2600B may include determining an actual lateral distance to at least one lane marking based on the analysis of at least one image. For example, the vehicle may determine distance 2530 representing the actual distance between the vehicle and lane marking 2510, as Figure 25A shown. When determining distance 2530, camera angle, vehicle speed, vehicle width, the position of the camera relative to the vehicle, or various other factors may be considered.

[0358] In step 2626, process 2600B may include determining an autonomous steering action of the host vehicle based on a difference between an expected lateral distance to at least one lane marker and a determined actual lateral distance to the at least one lane marker. For example, as referenced above Figure 25B described, vehicle 200 may compare actual distance 2530 with expected distance 2540. The difference between the actual distance and the expected distance may indicate an error (and its magnitude) between the actual position of the vehicle and the target trajectory that the vehicle is to follow. Accordingly, the vehicle may determine an autonomous steering action or other autonomous actions based on this difference. For example, if actual distance 2530 is less than expected distance 2540, as Figure 25B shown, the vehicle may determine an autonomous steering action to guide the vehicle away from lane marker 2510. Thus, the position of the vehicle relative to the target trajectory may be corrected. Process 2600B may be used, for example, to improve the navigation of the vehicle between landmarks.

[0359] Navigation Based on Image Analysis

[0360] As described above, an autonomous or semi-autonomous vehicle navigation system may rely on sensor inputs to gather information about current conditions, infrastructure, objects, etc. in the vehicle's environment. Based on the information gathered, the navigation system may determine one or more navigation actions to take (based on, for example, applying one or more driving strategies to the information gathered), and may implement the one or more navigation actions via actuation systems available on the vehicle.

[0361] In some cases, the sensors used to gather information about the vehicle's environment may include one or more cameras, such as image capture devices 122, 124, and 126 described above. Each frame captured by a relevant camera may be analyzed by one or more components of the vehicle navigation system in order to provide the desired functionality of the vehicle navigation system. For example, the captured images may be provided to a separate module responsible for detecting certain objects or features in the environment and navigating in the presence of the detected objects or features. For example, the navigation system may include separate modules for detecting one or more of pedestrians, other vehicles, objects in the roadway, road boundaries, road markings, traffic lights, traffic signs, parked vehicles, lateral movement of nearby vehicles, open doors of parked vehicles, wheels / road boundaries of nearby vehicles, rotations associated with detected wheels of nearby vehicles, road surface conditions (e.g., wet, snow, ice, gravel, etc.), and more.

[0362] Each module or function can involve the analysis of the provided images (e.g., each captured frame) to detect the presence of certain features on which the logic of that module or function is based. Additionally, various image analysis techniques can be employed to streamline the computational resources used for processing and analyzing the captured images. For example, in the case of a module responsible for detecting an open door, the image analysis techniques associated with that module can include scanning the image pixels to determine if any pixels are associated with a parked car. If no pixels representing a parked car are identified, the operation of the module can end with respect to a particular image frame. However, if a parked car is identified, the module can focus on identifying which pixels associated with the parked car represent the door edge (e.g., the rearmost door edge). These pixels can be analyzed to determine if there is evidence that the door is open or fully closed. The pixels and characteristics of the associated door edges can be compared across multiple image frames to further confirm if the detected door is in an open state. In each case, a particular function or module may need to focus only on a portion of the captured image frame to provide the desired functionality.

[0363] However, although various image analysis techniques can be employed to streamline the analysis for efficient use of the available computational resources, parallel processing of image frames across multiple functions / modules can involve a significant use of computational resources. In fact, if each module / function is responsible for its own image analysis to identify the features it depends on, each additional module / function added to the navigation system can add an image analysis component (e.g., a component associated with pixel-by-pixel inspection and classification). Assuming each captured frame includes millions of pixels, multiple frames are captured per second, and these frames are provided to dozens or hundreds of different modules / functions for analysis, the computational resources required to perform the analysis across many functions / modules and at a rate suitable for driving (e.g., at least as fast as the frames are captured) can be quite substantial. In many cases, considering hardware constraints and the like, the computational requirements of the image analysis phase can limit the number of functions or features that the navigation system can provide.

[0364] The described embodiments include an image analysis architecture to address these challenges in a vehicle navigation system. For example, the described embodiments can include a unified image analysis framework that can remove the image analysis burden from individual navigation system modules / functions. Such a unified image analysis framework can include, for example, a single image analysis layer that receives the captured image frames as input, analyzes and characterizes the pixels associated with the captured image frames, and provides the characterized image frames as output. The characterized image frames can then be provided to multiple different functions / modules of the navigation system for generating and implementing appropriate navigation actions based on the characterized image frames.

[0365] In some embodiments, each pixel of an image can be analyzed to determine whether the pixel is associated with certain types of objects or features in the environment of the host vehicle. For example, each pixel within the image or a portion of the image can be analyzed to determine whether it is associated with another vehicle in the environment of the host vehicle. Additional information can be determined for each pixel, such as whether the pixel corresponds to an edge of the vehicle, a face of the vehicle, etc. Such information can allow for more accurate identification and more appropriate orientation of bounding boxes, which can be drawn around the detected vehicle for navigation purposes.

[0366] Figure 27 An example analysis performed on pixels associated with a target vehicle consistent with the disclosed embodiments is shown. Figure 27 This can represent an image or a portion of an image captured by an image capture device such as image acquisition unit 120. The image can include a representation of vehicle 2710 within the environment of the host vehicle (e.g., vehicle 200 as described above). The image can be composed of a plurality of individual pixels, such as pixels 2722 and 2724. A navigation system (e.g., processing unit 110) can analyze each pixel to determine whether it is associated with the target vehicle. As used herein, the target vehicle can refer to a vehicle within the environment of the host vehicle that has the potential to navigate relative to the host vehicle. This can exclude, for example, a vehicle being transported on a trailer or carrier, a reflection of a vehicle, or other representations of a vehicle that can be detected in the image, as discussed in more detail below. The analysis can be performed on each pixel of the captured image, or on each pixel within a recognized candidate region relative to the captured image.

[0367] The navigation system can also be configured to analyze each pixel to determine other relevant information. For example, each pixel determined to be associated with the target vehicle can be analyzed to determine which part of the vehicle the pixel is associated with. This can include determining whether the pixel is associated with an edge of the vehicle. For example, as Figure 27As shown, vehicle 2710 can be associated with edge 2712 represented in the image. When analyzing pixel 2724, the navigation system can determine that pixel 2724 is a boundary pixel and thus includes edge 2712. In some embodiments, pixels can also be analyzed to determine if they are associated with a face of the vehicle. The terms "boundary", "edge", and "face" relate to a virtual shape defined by the navigation system and the virtual shape at least partially borders or surrounds an object of interest (and in this example, vehicle 2710). The shape can take any form and can be fixed or specific to an object type or object class. Generally speaking, for example, the shape can include a rectangle that closely fits around the outline of the object of interest. In other examples, for at least some object classes, a 3D box and each face of the box can closely bound the face of the corresponding face of a 3D object in the environment of the host vehicle. In this particular example, the 3D box bounds vehicle 2710.

[0368] Thus, for example, the navigation system can analyze pixel 2722 to determine that it lies on face 2730 of vehicle 2710. The navigation system can also determine one or more estimated distance values from pixel 2722. In some embodiments, one or more distances from pixel 2722 to the edge of face 2730 can be estimated. In the case of a 3D box, the distance from a given pixel to the edge of the face of the 3D box that bounds the pixel can be determined. For example, the navigation system can estimate distance 2732 to the side edge of face 2730 and distance 2734 to the bottom edge of face 2730. The estimate can be based on which part 2722 of the vehicle is determined to represent face 2730 and the typical dimensions from this part of the vehicle to the edge of face 2730. For example, pixel 2722 can correspond to a specific part of the bumper identified by the system. Other pixels (such as pixels representing a license plate, taillight, tire, exhaust pipe, etc.) can be associated with different estimated distances. Although not shown in Figure 27 it, various other distances can be estimated, including: the distance to the top edge of face 2730, the distance to the front or rear (depending on the orientation of vehicle 2710), the distance to edge 2712 of vehicle 2710, etc. These distances can be measured in any suitable unit for analysis by the navigation system. In some embodiments, these distances can be measured in pixels relative to the image. In other embodiments, these distances can represent real-world distances measured relative to the target vehicle (e.g., in centimeters, meters, inches, feet, etc.).

[0369] The processing unit 110 can use any suitable method to provide the pixel-based analysis described above. In some embodiments, the navigation system can include a trained neural network that characterizes individual pixels within an image according to the training protocol of the neural network. The training data set for training the neural network can include a plurality of captured images including representations of vehicles. Each pixel of the image can be examined and characterized according to a predetermined set of characteristics that the neural network is supposed to identify. For example, each pixel can be classified to indicate whether it is part of the representation of the target vehicle, whether it includes an edge of the target vehicle, whether it represents a face of the target vehicle, the measured distance from the pixel to the edge of the face (which can be measured in pixels or real-world distances), or other relevant information. The specified images can be used as the training data set for the neural network.

[0370] The resulting trained model can be used to analyze information associated with a pixel or a cluster of pixels to identify whether it represents the target vehicle, whether it is on the face or edge of the vehicle, the distance to the edge of the face, or other information. Although the system is described throughout this disclosure as a neural network, various other machine learning algorithms can be used, including logistic regression, linear regression, regression, random forest, K-nearest neighbor (KNN) model, K-means model, decision tree, cox proportional hazards regression model, naive Bayes model, support vector machine (SVM) model, gradient boosting algorithm, deep learning model, or any suitable form of machine learning model or algorithm.

[0371] Based on the mapping of each pixel to the boundary or face of the target vehicle 2710, the navigation system can more accurately determine the boundary of the vehicle 2710, which can allow the host vehicle to accurately determine one or more appropriate navigation actions. For example, the system can be able to determine the complete boundary of the vehicle represented by the edge 2712. In some embodiments, the navigation system can determine a bounding box 2720 of the vehicle, which can represent the boundary of the vehicle within the image. The bounding box 2720 determined based on the analysis of each pixel can define the boundary of the vehicle 2710 more accurately than conventional object detection methods.

[0372] In addition, the system can determine an oriented boundary that more accurately represents the orientation of the target vehicle. For example, based on a combined analysis of pixels (e.g., pixel 2722) within the face 2730 of vehicle 2710, the edge of face 2730 can be estimated. By identifying the discrete faces of vehicle 2710 represented in the image, the system can more accurately determine the orientation of bounding box 2720 such that it corresponds to the orientation of vehicle 2710. The improved accuracy of the orientation of the bounding box can improve the system's ability to determine appropriate navigation action responses. For example, for a vehicle detected by a side-facing camera, an inappropriate orientation of the bounding box may inappropriately indicate that the vehicle is traveling towards the host vehicle (e.g., a cut-in scenario). The disclosed techniques may be particularly beneficial in situations where the target vehicle occupies most (if not all) of the captured image (e.g., there is no at least one edge of the vehicle to indicate the orientation of the bounding box), the image of the target vehicle is included in the image, the vehicle is towed or carried by a towing vehicle or carrier, etc.

[0373] Figure 28 FIG. is an illustration of an example image 2800 including a partial representation of vehicle 2810 that is consistent with the disclosed embodiments. As shown, at least one edge (or portion of an edge) of vehicle 2810 may be excluded from image 2800. In some embodiments, this may be because a portion of vehicle 2810 is outside the field of view of the camera. In other embodiments, a portion of vehicle 2810 may be occluded and not visible, for example, by a building, vegetation, another vehicle, etc. While the configuration in image 2800 is provided as an example, in some embodiments, vehicle 2810 may occupy a greater portion of image 2800 such that some or all of the edges are excluded.

[0374] Using traditional object detection techniques, the detected boundaries for vehicle 2810 may be inaccurate because edges that are not included in the image may be required to determine the shape and / or orientation of the vehicle. This is especially true for images where the vehicle occupies most or all of the image. Using the techniques disclosed herein, each pixel in image 2800 associated with vehicle 2810 can be analyzed to determine bounding box 2820, regardless of whether a complete vehicle 2810 is represented in the image. For example, a trained neural network model can be used to determine that pixel 2824 includes an edge of vehicle 2810. The trained model can also determine that pixel 2822 is on the face of vehicle 2810, similar to pixel 2722. The system can also determine one or more distances from pixel 2822 to an edge of the face of the vehicle, similar to distances 2732 and 2734 described above. In some embodiments, the estimated distance information can be used to define the vehicle boundaries that are not included in the image. For example, pixel 2822 can be analyzed to determine an estimated distance from pixel 2822 to a certain edge of vehicle 2810, where that edge of vehicle 2810 extends beyond the edge of the image frame. Thus, based on a combined analysis of the pixels that do appear in the image and are associated with vehicle 2810, the accurate boundaries of vehicle 2810 can be determined. This information can be used to determine navigation actions for the host vehicle. For example, the invisible rear of a vehicle (e.g., a truck, bus, trailer, etc.) can be determined based on the portion of the vehicle that is within the image frame. Thus, the navigation system can estimate what clearance the target vehicle requires to determine whether the host vehicle needs to brake or slow down, move to an adjacent lane, accelerate, etc.

[0375] In some embodiments, the disclosed techniques can be used to determine a bounding box for a vehicle that is not the target vehicle and thus should not be associated with the bounding box for navigation determination purposes. In some embodiments, this can include a vehicle that is being towed or carried by another vehicle. Figure 29 FIG. 2900 is an illustration of an example image of a vehicle on a conveyance that is consistent with the disclosed embodiments. Image 2900 can be captured by a camera of the host vehicle, such as image capture device 120 of vehicle 200 described above. In Figure 29 the example shown, image 2900 can be a side view image taken by a camera located on the side of vehicle 200. Image 2900 can include a conveyance vehicle 2910 that can carry one or more vehicles 2920 and 2930. Although conveyance vehicle 2910 is shown as an auto transport trailer, various other vehicle conveyances can be identified. For example, conveyance vehicle 2910 can include a flatbed trailer, a tractor, a single compartment trailer, an inclined bed conveyance, a gooseneck trailer, a drop deck trailer, a wedge trailer, a car hauler train car, or any other vehicle used to transport another vehicle.

[0376] Using the techniques described above, each pixel in an image can be analyzed to identify the boundaries of a vehicle. For example, as described above, pixels associated with the conveyance vehicle 2910 can be analyzed to determine the boundaries of the conveyance vehicle 2910. The system can also analyze pixels associated with vehicles 2920 and 2930. Based on the analysis of the pixels, the system can determine that vehicles 2920 and 2930 are not the target vehicle and should not, therefore, be associated with a bounding box. This analysis can be performed in a variety of ways. For example, a training data set that includes images of the conveyance vehicle can be used to train the trained neural network described above. Pixels associated with the conveyance vehicle in the image can be designated as the conveyance vehicle or a non-target vehicle. Thus, the trained neural network model can determine that vehicles 2920 and 2930 are being transported on the conveyance vehicle 2910 based on the pixels in image 2900. For example, the neural network can be trained such that pixels within vehicles 2920 or 2930 are associated with the edges of vehicle 2910 rather than the edges of vehicles 2920 or 2930. Thus, no bounding box can be determined for the conveyance vehicles. Other techniques can also be used to identify vehicles 2920 and 2930 as conveyance vehicles, such as based on the position of the vehicles relative to vehicle 2910, the orientation of the vehicles, the position of the vehicles relative to other elements in the image, etc.

[0377] In some embodiments, the system can similarly determine that a vehicle reflection within an image should not be considered a target vehicle and can, therefore, not determine the boundaries of the reflection. Figure 30A and Figure 30B Example images 3000A and 3000B that include vehicle reflections are shown that are consistent with the disclosed embodiments. In some embodiments, the reflection can be based on the surface of the road. For example, as Figure 30A shown, image 3000A can include a vehicle 3010 driving on a reflective or at least partially reflective surface (e.g., a wet road). Thus, image 3000A can also include a reflection 3030 of vehicle 3010. Such a reflection can be problematic in an automated vehicle system because, in some cases, the reflection 3030 can be interpreted by the system as a target vehicle. Thus, the reflection 3030 can be associated with its own bounding box and the reflection 3030 can be considered in vehicle navigation decisions. For example, the host vehicle 200 can determine that the reflection 3030 is much closer than vehicle 3010, which can cause the vehicle 200 to make unnecessary navigation maneuvers (e.g., apply brakes, perform a lane change, etc.).

[0378] Using the disclosed method, the pixels associated with the image 3030 can be analyzed to determine that the image 3030 is not the target vehicle and, therefore, the boundaries of the imaged vehicle should not be determined. This can be performed in a manner similar to the method described above for vehicles on a conveyance. For example, an image containing a vehicle image can be used to train a neural network model such that individual pixels associated with the image can be identified as indicating the image or not indicating the target vehicle. Thus, the trained model can be capable of distinguishing pixels associated with the target vehicle (e.g., vehicle 3010) and the image 3030. In some embodiments, the image 3030 can be identified as an image based on its orientation, its position relative to the vehicle 3010, its position relative to other elements of the image 3000A, etc. The system can determine the bounding box 3020 associated with the vehicle 3010, but can refrain from determining a bounding box or other boundary associated with the image 3030. Although the image 3030 is described above as appearing on a wet road surface, the image can also appear on other surfaces, such as a metal or other reflective surface, a mirage image due to a heated road surface, etc.

[0379] In addition to images on the road, images of vehicles can also be detected based on images of other surfaces. For example, as Figure 30B shown, an image of a vehicle can appear within an image on the surface of another vehicle. The image 3000B can represent an image captured by a camera (e.g., a side-view camera) of the vehicle 200. The image 3000B can include a representation of another vehicle 3050, which, in this example, can be traveling beside the vehicle 200. The surface of the vehicle 3050 can be at least partially reflective such that an image 3060 of the second vehicle can appear in the image 3000B. The image 3060 can be an image of the host vehicle 200 appearing on the surface of the vehicle 3050, or can be an image of another target vehicle. Similar to the image 3030, the system can analyze the pixels associated with the image 3060 to determine that the image 3060 does not represent the target vehicle and, therefore, a boundary should not be determined for the image 3060. For example, a neural network can be trained such that the pixels within the image 3060 are associated with the edges of the vehicle 3050 rather than the edges of the representation of the imaged vehicle. Thus, a boundary can be refrained from being determined for the image 3060. Once the image 3060 is identified as an image, it can be ignored for the purpose of determining navigation actions. For example, if the movement of the image appears to be towards the host vehicle, the host vehicle may not brake or perform other navigation actions, whereas if the movement is performed by a target vehicle, the host vehicle may perform these navigation actions. Although the image 3060 is Figure 30Bis shown as appearing on the side of a tanker truck, but it can also appear on other surfaces, such as the shiny painted surfaces of another vehicle (e.g., doors, side panels, bumpers, etc.), chrome surfaces, the glass surfaces of another vehicle (e.g., windows, etc.), buildings (e.g., building windows, metal surfaces, etc.), or any other reflective surface that can reflect an image of the target vehicle.

[0380] Figure 31A is a flowchart showing an example process 3100 for navigating a host vehicle based on an analysis of pixels in an image consistent with the disclosed embodiments. As described above, process 3100 can be performed by at least one processing device, such as processing unit 110. It should be understood that the term "processor" throughout this disclosure is used as a shorthand for "at least one processor." In other words, a processor can include one or more structures that perform logical operations, whether these structures are juxtaposed, connected, or distributed. In some embodiments, a non-transitory computer-readable medium can contain instructions that, when executed by a processor, cause the processor to perform process 3100. Additionally, process 3100 is not necessarily limited to Figure 31A the steps shown, and any steps or processes described throughout the various embodiments of this disclosure can also be included in process 3100, including those described above with respect to Figures 27 - 30B those steps or processes.

[0381] In step 3110, process 3100 can include receiving at least one captured image representing the environment of the host vehicle from a camera of the host vehicle. For example, image acquisition unit 120 can capture one or more images representing the environment of host vehicle 200. The captured images can correspond to those such as described above with respect to Figures 27 - 30B those images.

[0382] In step 3120, process 3100 can include analyzing one or more pixels of the at least one captured image to determine whether the one or more pixels represent at least a portion of a target vehicle. For example, pixels 2722 and 2724 can be analyzed as described above to determine that these pixels represent a portion of vehicle 2710. In some embodiments, the analysis can be performed on each pixel of the captured image. In other embodiments, the analysis can be performed on a subset of pixels. For example, the analysis can be performed on each pixel of a target vehicle candidate region identified with respect to the captured image. As described in detail below, such a region can be determined, for example, using process 3500. The analysis can be performed using various techniques, including the trained systems described above. Thus, a trained system that can include one or more neural networks can perform at least a portion of the analysis of one or more pixels.

[0383] In step 3130, process 3100 may include, for pixels determined to represent at least a portion of the target vehicle, determining one or more estimated distance values from the one or more pixels to at least one edge of a face of the target vehicle. For example, as described above, processing unit 110 may determine that pixel 2722 represents face 2730 of vehicle 2710. Accordingly, one or more distances to the edges of face 2730 may be determined, such as distances 2732 and 2734. For example, the distance values may include the distance from a particular pixel to at least one of the front, rear, side, top, or bottom edges of the target vehicle. The distance values may be measured in pixels based on the image, or may be measured in real-world distances relative to the target vehicle. In some embodiments, process 3100 may further include determining whether the one or more pixels include boundary pixels that include a representation of at least a portion of at least one edge of the target vehicle. For example, as described above, pixel 2724 may be identified as a pixel that includes a representation of edge 2712.

[0384] In step 3140, process 3100 may include generating, based on an analysis of one or more pixels, at least a portion of a boundary relative to the target vehicle, the analysis including the one or more distance values determined to be associated with the one or more pixels. For example, step 3140 may include determining a portion of the boundary represented by edge 3712, as Figure 27 shown. This may be determined based on a combined analysis of all pixels associated with target vehicle 2710 within the image. For example, edge 3712 may be estimated based on a combination of the estimated distance values generated based on the pixels included on the face of the vehicle and the pixels identified as including edge 3712. In some embodiments, this portion of the boundary may include at least a portion of a bounding box (e.g., bounding box 2720).

[0385] Process 3100 may be performed in a particular scenario to improve the accuracy of the determined boundary of the target vehicle. For example, in some embodiments, at least a portion of at least one edge (or one or more edges) of the target vehicle may not be represented in the captured image, as Figure 28 shown. Using process 3100, the boundary of the target vehicle may be determined based on the pixels that do appear in the image and are associated with the target vehicle (e.g., vehicle 2810). In some embodiments, process 3100 may further include determining whether the target vehicle is being carried by another vehicle or a trailer based on an analysis of the captured image, as described above with respect to Figure 29 Accordingly, processing unit 110 may not determine the boundary of the vehicle being carried. Similarly, process 3100 may include determining whether the target vehicle is included in a mirror representation within at least one image based on an analysis of the captured image, as described above with respect to Figure 30A and Figure 30BAs described. In such an embodiment, the processing unit 110 may not determine the boundaries of the vehicle image.

[0386] In some embodiments, process 3100 may include additional steps based on the above analysis. For example, process 3100 may include determining the orientation of at least a portion of the boundary generated with respect to the target vehicle. As described above, th...

Claims

1. A navigation system for a host vehicle, the system comprising: at least one processor, including circuitry and memory, wherein the memory includes instructions that, when executed by the circuitry, cause the at least one processor to: receive at least one captured image representative of the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; input the at least one captured image into a trained system configured to determine, for each of a plurality of pixels representative of at least a portion of a target vehicle in the at least one captured image, one or more estimated distance values representative of a distance from the pixel to at least one edge of a face of the target vehicle; and generate, based on the determined one or more distance values, at least a portion of a boundary relative to the target vehicle.

2. The navigation system of claim 1, wherein the one or more distance values are measured in pixels.

3. The navigation system of claim 1, wherein the one or more distance values correspond to real-world distances measured relative to the target vehicle.

4. The navigation system of claim 1, wherein the one or more distance values include a distance from a particular pixel to at least one of a front edge, a rear edge, a side edge, a top edge, or a bottom edge of the target vehicle.

5. The navigation system of claim 1, wherein the at least one processor is further programmed to determine an orientation of at least a portion of the boundary generated relative to the target vehicle.

6. The navigation system according to claim 5, wherein, The at least one processor is further programmed to determine a navigation action of the host vehicle based on the determined orientation of at least a portion of the boundary and cause the vehicle to effectuate the determined navigation action.

7. The navigation system of claim 5, wherein the determined orientation indicates a maneuver of the target vehicle toward the path of the host vehicle.

8. The navigation system of claim 5, wherein the determined orientation indicates a lateral movement of the target vehicle relative to the host vehicle.

9. The navigation system of claim 1, wherein the at least one processor is further programmed to determine whether the one or more pixels include boundary pixels, the boundary pixels including a representation of at least a portion of at least one edge of the target vehicle.

10. The navigation system of claim 1, wherein the analysis is performed for each pixel of the captured image.

11. The navigation system of claim 1, wherein the analysis is performed for each pixel of a target vehicle candidate region identified relative to the captured image.

12. The navigation system of claim 1, wherein the portion of the boundary includes at least a portion of a bounding box.

13. The navigation system of claim 1, wherein the at least one processor is further programmed to determine a distance of the portion of the boundary to the host vehicle and cause the vehicle to effectuate a navigation action based at least on the determined distance.

14. The navigation system of claim 1, wherein the trained system includes one or more neural networks.

15. The navigation system according to claim 1, wherein at least a part of at least one side of the target vehicle is not represented in the captured image.

16. The navigation system according to claim 1, wherein one or more sides of the target vehicle are not represented in the captured image.

17. The navigation system according to claim 1, wherein the at least one processor is further programmed to determine whether the target vehicle is being carried by another vehicle or a trailer based on an analysis of the captured image.

18. The navigation system according to claim 17, wherein the at least one processor is further programmed not to determine the boundaries of the vehicle being carried.

19. The navigation system according to claim 1, wherein the at least one processor is further programmed to determine whether the target vehicle is included in a silhouette representation in the at least one image based on an analysis of the captured image.

20. The navigation system according to claim 19, wherein the at least one processor is further programmed not to determine the boundaries of the vehicle silhouette.

21. The navigation system according to claim 1, wherein the at least one processor is further programmed to output the type of the target vehicle.

22. The navigation system according to claim 21, wherein the type of the target vehicle is at least based on the size of the portion of the boundary.

23. The navigation system according to claim 21, wherein, The type of the target vehicle is at least partially based on the number of pixels included within the boundary.

24. The navigation system according to claim 21, wherein the type of the target vehicle includes at least one of a bus, a truck, a bicycle, a motorcycle, or a car.

25. A method for navigating a host vehicle, the method comprising: receiving at least one captured image representing the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; inputting the at least one captured image into a trained system configured to determine, for each of a plurality of pixels representing at least a part of a target vehicle in the at least one captured image, one or more estimated distance values representing a distance from the pixel to at least one side of a face of the target vehicle; and generating at least a part of a boundary relative to the target vehicle based on the determined one or more distance values.

26. The method according to claim 25, wherein the one or more distance values include a distance from a particular pixel to at least one of a front side, a rear side, a side, a top side, or a bottom side of the target vehicle.

27. The method according to claim 25, further comprising determining whether the one or more pixels include boundary pixels, the boundary pixels including a representation of at least a part of at least one side of the target vehicle.

28. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, are configured to cause the at least one processor to perform a method for navigating a host vehicle, the method comprising: receiving at least one captured image representing the environment of the host vehicle, the at least one captured image being captured by a camera of the host vehicle; Input the at least one captured image into a trained system, the trained system being configured to determine, for each of a plurality of pixels representing at least a portion of a target vehicle in the at least one captured image, one or more estimated distance values representing a distance from the pixel to at least one edge of a face of the target vehicle; and generate, based on the determined one or more distance values, at least a portion of a boundary relative to the target vehicle.

29. The non-transitory computer-readable medium according to claim 28, wherein the method further comprises determining an orientation of at least a portion of the boundary generated relative to the target vehicle.

30. The non-transitory computer-readable medium according to claim 29, wherein the method further comprises determining a navigation action of the host vehicle based on the determined orientation of at least a portion of the boundary and causing the vehicle to implement the determined navigation action.

Images