SYSTEMS AND METHODS FOR DETERMINING THE RELEVANCE OF TRAFFIC SIGNS

Abstract

Systems and methods for navigating a host vehicle are disclosed. In one embodiment, a system includes a processor configured to receive at least one image captured by a front camera of the host vehicle; to analyze the at least one image to recognize a representation of a traffic sign in the environment of the host vehicle; to determine the relevance of the traffic sign to the host vehicle, wherein the relevance of the traffic sign to the host vehicle is determined based on a trajectory of the host vehicle relative to a location of the traffic sign; and to cause the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle.

Description

Cross-reference to related patent applications

[0001] The present application claims priority over US application no. 63 / 687,523, filed on August 27, 2024, which is incorporated herein in its entirety. STATE OF THE ART Technical field

[0002] The present disclosure relates generally to vehicle navigation and in particular to systems and methods for determining the relevance of traffic signs. Background information

[0003] With the steady advancement of technology, the goal of a fully autonomous vehicle capable of navigating roads is drawing closer. Autonomous vehicles may need to consider a multitude of factors and make appropriate decisions based on these factors to reach an intended destination safely and accurately. For example, an autonomous vehicle may need to process and interpret visual information (e.g., information captured by a camera) and may also use information from other sources (e.g., from a GPS device, a speed sensor, an accelerometer, a suspension sensor, etc.). At the same time, in order to navigate to a destination, an autonomous vehicle may also need to determine its position within a specific lane (e.g.,Identifying a specific lane within a multi-lane road, navigating alongside other vehicles, avoiding obstacles and pedestrians, observing traffic signals and signs, and driving from one road to another at appropriate intersections or junctions. Utilizing and interpreting the vast amounts of information gathered by an autonomous vehicle as it travels to its destination presents a multitude of design challenges. The sheer volume of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that an autonomous vehicle may require to analyze, retrieve, and / or store poses challenges that could actually limit or even negatively impact autonomous navigation.Furthermore, if an autonomous vehicle relies on traditional map technology for navigation, the enormous volume of data required to store and update the map presents significant challenges. SUMMARY

[0004] The disclosed embodiments may include a system for navigating a host vehicle (e.g., an autonomous or semi-autonomous vehicle). The system may include at least one processor. In some embodiments, the at least one processor may comprise switching logic and memory. In other embodiments, the memory may be separate from the at least one processor. The memory may contain instructions which, when executed, cause the at least one processor to perform one of the processes or steps described herein.

[0005] The disclosed system for navigating a host vehicle can receive at least one image captured by a camera on the host vehicle from within the host vehicle's environment. For example, the camera could be a front-facing camera on the host vehicle. The at least one image can include a representation of an object. The object could be, for example, a target vehicle or a pedestrian.

[0006] In one embodiment, the disclosed system can receive at least one image captured by a front camera of the host vehicle and analyze the at least one image to recognize a representation of a traffic sign in the vicinity of the host vehicle. The disclosed system can determine the relevance of the traffic sign to the host vehicle based on the trajectory of the host vehicle relative to the location of the traffic sign. The disclosed system can cause the at least one processor to instruct the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle in the embodiment.

[0007] In some embodiments, the trajectory of the host vehicle includes at least one road segment, wherein a first section of the at least one road segment lies in front of a front of the traffic sign and a second section of the at least one road segment lies behind a rear of the traffic sign. For example, the host vehicle may have traveled the first section of the at least one road segment before it has traveled the second section of the at least one road segment.

[0008] In some embodiments, the determination of the traffic sign's relevance to the host vehicle is performed while the host vehicle is navigating its surroundings. That is, the process can be performed online and on board the host vehicle (as opposed to a server-side process) based on images captured in the environment as the vehicle travels.

[0009] In some embodiments, the relevance of the traffic sign to the host vehicle is further determined based on at least one lane marking in the vicinity of the host vehicle. This at least one lane marking can also provide context as to whether the host vehicle ultimately traveled a route associated with the traffic sign.

[0010] In some embodiments, the relevance of the traffic sign to the host vehicle is further determined based on at least one edge in the vicinity of the host vehicle. As in the preceding discussion regarding a lane marking, this at least one edge can further provide context as to whether the host vehicle ultimately traveled a route associated with the traffic sign.

[0011] As previously discussed, the relevance of the traffic sign to the host vehicle can further be determined based on an analysis of a plan view. For example, the plan view may include a first indicator of the host vehicle's trajectory and a second indicator of the traffic sign's location. The plan view may also include an indicator for the traffic sign at an origin of a coordinate system associated with the plan view. Furthermore, the plan view may include an indicator for at least one lane of a road segment and / or at least one edge in the vicinity of the host vehicle. Alternatively or additionally, the plan view may be associated with information specifying the traffic sign's orientation.

[0012] In some embodiments, the top-down image can be generated based on an analysis of a multitude of images captured by the host vehicle's front camera. In some embodiments, the disclosed system can provide the top-down image to a trained system (e.g., a neural network), and the trained system can be configured to determine the relevance of the traffic sign to the host vehicle.

[0013] In some embodiments, the disclosed system can send an indicator of the relevance of the traffic sign from the host vehicle to a server. The server can be configured to store the indicator in a navigation map, and / or the indicator can be stored in conjunction with a drivable route.

[0014] If the traffic sign is a speed limit sign, the disclosed system can, in some embodiments, determine a speed limit associated with the speed limit sign, for example, by analyzing the at least one image. The disclosed system can further determine at least one navigation action for the host vehicle based on the speed limit or on the basis of other information represented in the traffic sign. For example, the at least one navigation action includes braking, steering, or accelerating the host vehicle.

[0015] In some embodiments, the disclosed system can determine a speed limit that differs from the speed limit associated with the speed limit sign. For example, the disclosed system can detect a speed limit sign and determine that the speed limit sign should be obeyed by the host vehicle, but after the vehicle has passed the speed limit sign, the disclosed system can further determine (e.g., based on the host vehicle's trajectory after passing the speed limit sign and / or other indicators) that the speed limit sign is not relevant to the vehicle (i.e., the speed limit sign is instead relevant for a trajectory that the host vehicle does not follow). Accordingly, in some cases, it can be determined that the traffic sign (e.g.,a speed limit sign is not relevant for the host vehicle, and the traffic sign can be determined as not relevant for the host vehicle after the host vehicle has passed the traffic sign by a predetermined distance. According to the disclosed system, in some embodiments, the system can determine a speed limit associated with the speed limit sign, and the system can determine a different speed limit for the host vehicle.

[0016] In one embodiment, the disclosed system can receive at least one image captured by a front camera of the host vehicle and analyze the at least one image to detect a representation of a speed limit sign in the environment of the host vehicle. The disclosed system can determine a first speed limit associated with the speed limit sign (e.g., the first speed limit associated with the speed limit sign can be determined by analyzing the at least one image) and determine the relevance of the speed limit sign to the host vehicle.The relevance of the speed limit sign to the host vehicle can be determined based on the host vehicle's trajectory relative to the location of the speed limit sign. The speed limit sign is determined to be irrelevant to the host vehicle after the host vehicle has passed the speed limit sign by a predetermined distance. After determining that the speed limit sign is irrelevant to the host vehicle, the disclosed system can determine a second speed limit for the host vehicle that differs from the first speed limit and cause the host vehicle to perform at least one navigation action based on the second speed limit in the embodiment.

[0017] In one embodiment, the disclosed system can receive at least one image captured by a front camera of the host vehicle and analyze that image to detect a representation of a traffic sign in the vicinity of the host vehicle. The representation of the traffic sign may be at least partially obscured by an object (e.g., a tree, a parked vehicle, or a truck, etc.). The disclosed system can determine the relevance of the traffic sign to the host vehicle. This relevance can be determined based on the trajectory of the host vehicle relative to the location of the traffic sign. In this embodiment, the disclosed system can cause the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle.

[0018] In one embodiment, the disclosed system can receive at least one image captured by a front camera of the host vehicle, analyze at least one image to detect a representation of a traffic sign in the environment of the host vehicle, generate a top-down image based on the analysis of a plurality of images captured by the host vehicle's front camera, and provide the top-down image to a trained system configured to determine the relevance of the traffic sign to the host vehicle based on the trajectory of the host vehicle relative to a location of the traffic sign. The trained system can further be configured to output an indicator of the relevance of the traffic sign to the host vehicle based on an analysis of the top-down image.The disclosed system can receive the traffic sign relevance indicator for the host vehicle from the trained system and cause the host vehicle to perform at least one navigation action based on the traffic sign relevance indicator for the host vehicle in embodiment.

[0019] A person skilled in the art will recognize that systems, non-transitory computer-readable media and methods are identical to the disclosed embodiments and can store program instructions that can be executed by at least one process to perform one of the methods disclosed herein. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings, which are incorporated into and form part of this disclosure, illustrate various disclosed embodiments. The drawings include: Fig. Figure 1 shows a schematic representation of an exemplary system, in accordance with the disclosed embodiments. Fig. Figure 2A shows a schematic side view of an exemplary vehicle including a system, in accordance with the disclosed embodiments. Fig. 2B shows a schematic top view of the in Fig. 2A vehicle and system shown, in accordance with the disclosed embodiments. Fig. Figure 2C shows a schematic top view of another embodiment of a vehicle including a system, in accordance with the disclosed embodiments. Fig. Figure 2D shows a schematic top view of yet another embodiment of a vehicle including a system, in accordance with the disclosed embodiments. Fig. 2E shows a schematic top view of yet another embodiment of a vehicle including a system, in accordance with the disclosed embodiments. Fig. Figure 2F shows a schematic representation of exemplary vehicle control systems, in accordance with the disclosed embodiments. Fig. Figure 3A shows a schematic representation of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system, in accordance with the disclosed embodiments. Fig. Figure 3B shows an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield, in accordance with the disclosed embodiments. Fig. 3C shows an illustration of the in Fig. 3B camera mount shown from a different perspective, in accordance with the disclosed embodiments. Fig. Figure 3D shows an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield, in accordance with the disclosed embodiments. Fig. Figure 4 shows an exemplary block diagram of a memory configured to store instructions for performing one or more operations, in accordance with the disclosed embodiments. Fig. Figure 5A shows a flowchart illustrating an exemplary process for initiating one or more navigation responses based on monocular image analysis, in accordance with the disclosed embodiments. Fig. Figure 5B shows a flowchart illustrating an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images, in accordance with the disclosed embodiments. Fig. Figure 5C shows a flowchart illustrating an exemplary process for detecting road markings and / or lane geometry information in a set of images, in accordance with the disclosed embodiments. Fig. Figure 5D shows a flowchart illustrating an exemplary process for detecting traffic lights in a set of images, in accordance with the disclosed embodiments. Fig. Figure 5E shows a flowchart illustrating an exemplary process for initiating one or more navigation responses based on a vehicle path, in accordance with the disclosed embodiments. Fig. Figure 5F shows a flowchart illustrating an exemplary process for determining whether a vehicle ahead is changing lanes, in accordance with the disclosed embodiments. Fig. Figure 6 shows a flowchart illustrating an exemplary process for initiating one or more navigation responses based on a stereo image analysis, in accordance with the disclosed embodiments. Fig. Figure 7 shows a flowchart illustrating an exemplary process for initiating one or more navigation responses based on an analysis of three sets of images, in accordance with the disclosed embodiments. Fig. Figure 8 shows a sparsely populated map for providing autonomous vehicle navigation, in accordance with the disclosed embodiments. Fig. Figure 9A illustrates a polynomial representation of sections of a road segment, in accordance with the disclosed embodiments. Fig. Figure 9B illustrates a curve in three-dimensional space representing a target trajectory of a vehicle for a particular road segment contained in a sparsely populated map, in accordance with the disclosed embodiments. Fig. Figure 10 illustrates examples of landmarks that may be included in a sparsely populated map consistent with the disclosed embodiments. Fig. Figure 11A shows polynomial representations of trajectories, in accordance with the disclosed embodiments. Fig. 11B and Fig. Figure 11C shows target trajectories along a multi-lane road, in accordance with the disclosed embodiments. Fig. Figure 11D shows an exemplary road signature profile, in accordance with the disclosed embodiments. Fig. Figure 12 shows a schematic illustration of a system that uses crowdsourcing data received from a variety of vehicles for autonomous vehicle navigation, in accordance with the disclosed embodiments. Fig. Figure 13 illustrates an exemplary road navigation model of the autonomous vehicle, represented by a multitude of three-dimensional splines, in accordance with the disclosed embodiments. Fig. Figure 14 shows a map skeleton generated by combining location information from many journeys, in accordance with the disclosed embodiments. Fig. Figure 15 shows an example of a longitudinal alignment of two journeys with exemplary symbols as reference points, in accordance with the disclosed embodiments. Fig. Figure 16 shows an example of a longitudinal alignment of many journeys with an exemplary sign as a reference point, in accordance with the disclosed embodiments. Fig. Figure 17 shows a schematic illustration of a system for generating driving data using a camera, a vehicle and a server, in accordance with the disclosed embodiments. Fig. Figure 18 shows a schematic illustration of a system for crowdsourcing a sparsely populated map, in accordance with the disclosed embodiments. Fig. Figure 19 shows a flowchart illustrating an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment, in accordance with the disclosed embodiments. Fig. Figure 20 illustrates a block diagram of a server, in accordance with the disclosed embodiments. Fig. Figure 21 illustrates a block diagram of a memory, in accordance with the disclosed embodiments. Fig. Figure 22 illustrates a process for clustering vehicle trajectories associated with vehicles in accordance with the disclosed embodiments. Fig. Figure 23 illustrates a navigation system for a vehicle that can be used for autonomous navigation, in accordance with the disclosed embodiments. Fig. 24A, Fig. 24B, Fig. 24C and Fig. Figure 24D illustrates exemplary lane markings that can be detected in accordance with the disclosed embodiments. Fig. Figure 24E shows exemplary mapped lane markings, in accordance with the disclosed embodiments. Fig. Figure 24F shows an exemplary anomaly associated with the detection of a lane marking, in accordance with the disclosed embodiments. Fig. Figure 25A shows an exemplary image of the environment of a vehicle for navigation based on the mapped lane markings, in accordance with the disclosed embodiments. Fig. Figure 25B illustrates a lateral localization correction of a vehicle based on mapped lane markings in a road navigation model, in accordance with the disclosed embodiments. Fig. 25°C and Fig. 25D provides conceptual representations of a localization technique for locating a host vehicle along a target trajectory using mapped features contained in a sparse map. Fig. 26A shows a flowchart illustrating an exemplary process for mapping a lane marking for use in autonomous vehicle navigation, in accordance with the disclosed embodiments. Fig. Figure 26B shows a flowchart illustrating an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings, in accordance with the disclosed embodiments. Fig. Figure 27 is a flowchart showing an exemplary process for autonomously navigating a host vehicle along a road segment by determining the relevance of traffic signs in accordance with the disclosed embodiments. Fig. Figure 28A shows an exemplary image of the environment of a host vehicle for navigation based on the relevance of traffic signs according to the disclosed embodiments. Fig. Figure 28B shows a schematic top-down view based on the exemplary image of the environment of a host vehicle from Fig. 28A according to the disclosed embodiments. Fig. 29A shows an exemplary image of the environment of a host vehicle for navigation based on the relevance of traffic signs, in accordance with the disclosed embodiments. Fig. Figure 29B shows a schematic top view based on the exemplary image of the environment of a host vehicle from Fig. 29A, which is consistent with the disclosed embodiments. Fig. Figure 30A shows an exemplary image of the environment of a host vehicle for navigation based on the relevance of traffic signs, according to the disclosed embodiments. Fig. Figure 30B shows a schematic top-down view based on the example image of the environment of a host vehicle. Fig. 30A is based and corresponds to the disclosed embodiments. DETAILED DESCRIPTION

[0021] The following detailed description refers to the accompanying drawings. Where possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several illustrative embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the components illustrated in the drawings, and the illustrative methods described herein may be modified by replacing, rearranging, removing, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the correct scope is defined by the accompanying claims. Overview of autonomous vehicles (AV)

[0022] As used throughout this disclosure, the term “autonomous vehicle” refers to a vehicle capable of implementing at least one navigation change without driver input. A “navigation change” refers to a modification of one or more of the vehicle’s steering, braking, or acceleration operations. To be autonomous, a vehicle need not be fully automatic (e.g., operating entirely without a driver or without driver input). Rather, autonomous vehicles include those capable of operating under driver control during certain periods and without driver control during other periods. Autonomous vehicles may also include vehicles that control only certain aspects of vehicle navigation, such as steering (e.g., to maintain the vehicle’s course within lane restrictions), while leaving other aspects to the driver (e.g., braking).In some cases, autonomous vehicles can take over some or all aspects of braking, speed control and / or steering the vehicle.

[0023] Since human drivers typically rely on visual cues and observation to control a vehicle, traffic infrastructures are designed accordingly, with lane markings, traffic signs, and traffic lights all intended to provide drivers with visual information. Given these design characteristics of traffic infrastructures, an autonomous vehicle can include a camera and a processing unit that analyzes visual information captured from the vehicle's surroundings. This visual information can include, for example, components of the traffic infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) that can be observed by drivers, as well as other obstacles (e.g., other vehicles, pedestrians, debris, etc.).Additionally, an autonomous vehicle can also use stored information, such as information provided by a model of the vehicle's surroundings when navigating. For example, the vehicle can use GPS data, sensor data (e.g., from an accelerometer, a speed sensor, a suspension sensor, etc.), and / or other map data to provide information about its environment while driving, and the vehicle (as well as other vehicles) can use this information to locate itself on the model.

[0024] In some embodiments disclosed in this disclosure, an autonomous vehicle may use information obtained during navigation (e.g., from a camera, GPS device, accelerometer, speed sensor, suspension sensor, etc.). In other embodiments, an autonomous vehicle may use information obtained from previous navigations performed by the vehicle (or by other vehicles) during navigation. In still other embodiments, an autonomous vehicle may use a combination of information obtained during navigation and information obtained from previous navigations. The following sections provide an overview of a system in accordance with the disclosed embodiments, followed by an overview of a forward-facing imaging system and methods consistent with the system.The following sections revealed systems and procedures for constructing, using, and updating a sparse map for autonomous vehicle navigation. System overview

[0025] Fig. Figure 1 shows a block diagram representation of a system 100, in accordance with the exemplary disclosed embodiments. The system 100 can include various components, depending on the requirements of a particular implementation. In some embodiments, the system 100 can include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more storage 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 another 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 the image capture device 122, the image capture device 124, and the image capture device 126. The system 100 can also include a data interface 128 that provides communication between the processing unit 110 and the image acquisition unit 120. For example, the data interface 128 can include one or more wired and / or wireless connections for transmitting the image data acquired by the image acquisition unit 120 to the processing unit 110.

[0026] The Wireless Transceiver 172 can include one or more devices configured to exchange transmissions over an air interface with one or more networks (e.g., cellular, internet, etc.) using a radio frequency, an infrared frequency, a magnetic field, or an electric field. The Wireless Transceiver 172 can use any known standard for transmitting and / or receiving data (e.g., Wi-Fi, Bluetooth®, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions can include communications from the host vehicle to one or more remote servers. Such transmissions can also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the vicinity of the host vehicle (e.g.,to facilitate the coordination of the host vehicle's navigation with respect to or together with target vehicles in the vicinity of the host vehicle) or even include a broadcast transmission to unspecified receivers in an environment of the transmitting vehicle.

[0027] Both the Application Processor 180 and the Image Processor 190 can include various types of processing devices. For example, one or both of the Application Processor 180 and the Image Processor 190 can include a microprocessor, preprocessors (such as an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), support circuitry, digital signal processors, integrated circuits, memory, or any other type of device suitable for running applications and for image processing and analysis. In some embodiments, the Application Processor 180 and / or the Image Processor 190 can include any type of single- or multi-core processor, mobile device microcontroller, central processing unit, etc.Various processing devices can be used, including, for example, processors available from manufacturers such as Intel®, AMD®, etc., or GPUs available from manufacturers such as NVIDIA®, ATI®, etc., and can include various architectures (e.g., x86 processor, ARM®, etc.).

[0028] In some embodiments, the Application Processor 180 and / or the Image Processor 190 can include any of the EyeQ series of processor chips available from Mobileye®. These processor designs each include multiple processing units with local memory and instruction sets. Such processors can include video inputs for receiving image data from multiple image sensors and can also include video output capabilities. In one example, the EyeQ2® uses 90 nm micrometer technology operating at 332 MHz. The EyeQ2® architecture consists of two floating-point hyper-thread 32-bit RISC CPUs (MIPS32® 34K® cores), five VCE, three VMP®, Denali 64-bit Mobile DDR controllers, 128-bit internal Sonics interconnect, dual 16-bit video input and 18-bit video output controllers, 16-channel DMA, and multiple peripherals.The MIPS34K CPU manages the five VCEs, three VMP™ and the DMA, the second MIPS34K CPU and the multi-channel DMA, as well as the other peripherals. The five VCEs, three VMP®, and the MIPS34K CPU can perform intensive vision calculations required by multi-function bundle applications. In another example, the EyeQ3®, a third-generation processor six times more powerful than the EyeQ2®, can be used in the disclosed embodiments. In other examples, the EyeQ4® and / or the EyeQ5® can be used in the disclosed embodiments. Of course, any newer or future EyeQ processing devices can also be used in conjunction with the disclosed embodiments.

[0029] Any of the processing devices disclosed herein can be configured to perform specific functions. Configuring a processing device, such as any of the described EyeQ processors or other controller or microprocessor, to perform specific functions may involve programming computer-executable instructions and providing these instructions to the processing device for execution during its operation. In some embodiments, configuring a processing device may involve directly programming the processing device with architectural instructions.For example, processing devices such as field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), and the like can be configured using, for example, one or more hardware description languages ​​(HDLs).

[0030] In other embodiments, configuring a processing device may include storing executable instructions in memory accessible to the processing device during operation. For example, the processing device may access the memory to retrieve and execute the stored instructions during operation. In any case, the processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein constitutes a specialized hardware-based system that controls multiple hardware-based components of a host vehicle.

[0031] Although Fig. While Figure 1 represents two separate processing devices enclosed within the processing unit 110, more or fewer processing devices can also be used. For example, in some embodiments, a single processing device can be used to perform the tasks of the application processor 180 and the image processor 190. In other embodiments, these tasks can be performed by more than two processing devices. Furthermore, in some embodiments, the system 100 can include one or more processing units 110 without including other components, such as the image acquisition unit 120.

[0032] The Processing Unit 110 can comprise various types of devices. For example, the Processing Unit 110 can include various devices such as a controller, an image preprocessor, a central processing unit (CPU), a graphics processing unit (GPU), support circuitry, digital signal processors, integrated circuits, memory, or any other type of device for image processing and analysis. The image preprocessor can include a video processor for capturing, digitizing, and processing the image data from the image sensors. The CPU can comprise any number of microcontrollers or microprocessors. The GPU can also comprise any number of microcontrollers or microprocessors.The supporting circuitry can be any number of circuits that are generally well-known in the field, including cache, power supply, clock, and input / output circuits. Memory can store software that, when executed by the processor, controls the operation of the system. Memory can include databases and image processing software. Memory can include any number of random-access memory types, read-only memory, flash memory, disk drives, optical memory, tape memory, removable storage, and other types of storage. In one case, the memory can be separate from the Processing Unit 110. In another case, the memory can be integrated into the Processing Unit 110.

[0033] Each memory unit 140, 150 can contain software instructions which, when executed by a processor (e.g., application processor 180 and / or image processor 190), can control the operation of various aspects of the system 100. These memory units can include various databases and image processing software, as well as a trained system, such as a neural network or a deep neural network. The memory units can include random-access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage, tape storage, removable storage, and / or any other type of storage. In some embodiments, the memory units 140, 150 can be separate from the application processor 180 and / or image processor 190. In other embodiments, these memory units can be integrated into the application processor 180 and / or the image processor 190.

[0034] The position sensor 130 can include any type of device suitable for determining a location associated with at least one component of the system 100. In some embodiments, the position sensor 130 can include a GPS receiver. Such receivers can determine a user's position and speed by processing signals broadcast by satellites of the global positioning system. Position information from the position sensor 130 can be made available to the application processor 180 and / or image processor 190.

[0035] In some embodiments, the system may include 100 components, such as a speed sensor (e.g. a speedometer, a speedometer) for measuring the speed of the vehicle 200 and / or an accelerometer (either single-axis or multi-axis) for measuring the acceleration of the vehicle 200.

[0036] The user interface 170 can include any device suitable for providing information to or receiving input from one or more users of the system 100. In some embodiments, the user interface 170 can include user input devices such as a touchscreen, microphone, keyboard, pointing devices, trackwheels, cameras, knobs, buttons, etc. With such input devices, a user can provide information inputs or commands to the 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 suitable techniques for communicating information to the system 100.

[0037] The user interface 170 can be equipped with one or more processing devices configured to provide and receive information to and from a user and to process this information for use by, for example, the application processor 180. In some embodiments, such processing devices can execute instructions for detecting and tracking eye movements, receiving and interpreting speech commands, detecting and interpreting touches and / or gestures on a touchscreen, responding to keyboard input or menu selections, etc. In some embodiments, the user interface 170 can include a display, a speaker, a tactile device, and / or any other devices for providing output information to a user.

[0038] The map database 160 can include any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 can include data relating to the position of various elements in a reference coordinate system, including roads, water features, geographic features, businesses, landmarks, restaurants, gas stations, etc. The map database 160 can store not only the locations of such elements but also descriptors relating to these elements, including, for example, names associated with the stored features. In some embodiments, the map database 160 can be physically connected to other components of the system 100. Alternatively or additionally, the map database 160, or a part thereof, can be located remotely with respect to other components of the system 100 (e.g., the processing unit 110).In such embodiments, information from the map database 160 can be downloaded to a network (e.g., via a mobile network and / or the Internet, etc.) via a wired or wireless data connection. In some cases, the map database 160 can store a sparse data model that includes polynomial representations of certain road features (e.g., lane markings) or target trajectories for the host vehicle. Systems and methods for generating such a map are described below with reference to the following. Fig. 8 to 19 discussed.

[0039] The image acquisition devices 122, 124, and 126 can each include any type of device suitable for capturing at least one image from an environment. Furthermore, any number of image acquisition devices can be used to capture images for input into the image processor. Some embodiments may include only a single image acquisition device, while other embodiments may include two, three, or even four or more image acquisition devices. The image acquisition devices 122, 124, and 126 are described below. Fig. 2B to 2E are further described.

[0040] System 100, or various components thereof, can be integrated into different platforms. In some embodiments, System 100 can be enclosed within a Vehicle 200, as in Fig. 2A shown. For example, the vehicle 200 can be equipped with a processing unit 110 and any of the other components of the system 100, as above in relation to Fig. 1 described. While in some embodiments the vehicle 200 may only be equipped with a single image acquisition device (e.g. a camera), in other embodiments, such as those in conjunction with the Fig. As discussed in sections 2B to 2E, several image acquisition devices can be used. For example, each of the image acquisition devices 122 and 124 of vehicle 200, as described in Fig. 2A shown, is part of an ADAS (Advanced Driver Assistance Systems) imaging set.

[0041] The image acquisition devices enclosed in the vehicle 200 as part of the image acquisition unit 120 can be positioned at any suitable location. In some embodiments, such as in the Fig. As shown in Figures 2A to 2E and 3A to 3C, the image acquisition device 122 can be located near the rearview mirror. This position can provide a line of sight similar to that of the driver of vehicle 200, which can help determine what is visible and not visible to the driver. The image acquisition device 122 can be positioned anywhere near the rearview mirror, but placing the image acquisition device 122 on the driver's side of the mirror can further help in obtaining images that are representative of the driver's field of vision and / or line of sight.

[0042] Other locations for the image capture devices of the image acquisition unit 120 can also be used. For example, the image capture device 124 can be located on or in a bumper of the vehicle 200. Such a location can be particularly suitable for image capture devices with a wide field of view. The line of sight of the image capture devices located on the bumper may differ from that of the driver, and therefore the bumper image capture device and the driver may not always see the same objects. The image capture devices (e.g., image capture devices 122, 124, and 126) can also be located in other places.For example, the image capture devices 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 and on the sides of the vehicle 200, mounted on one of the windows of the vehicle 200, positioned behind or in front of it, and mounted in or near light figures on the front and / or rear of the vehicle 200, etc.

[0043] In addition to the image acquisition devices, the vehicle 200 can include various other components of the system 100. For example, the processing unit 110 can be included in the vehicle 200, either integrated with or separate from the vehicle's engine control unit (ECU). The vehicle 200 can also be equipped with a position sensor 130, such as a GPS receiver, and can also include a map database 160 and storage units 140 and 150.

[0044] As previously discussed, the wireless transceiver 172 can transmit and / or receive data over one or more networks (e.g., mobile networks, the internet, etc.). For example, the wireless transceiver 172 can upload data collected by the system 100 to one or more servers and download data from those servers. The wireless transceiver 172 can allow the system 100 to receive, for example, periodically or on-demand updated data stored in the map database 160, memory 140, and / or memory 150. Similarly, the wireless transceiver 172 can upload any data (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, vehicle control systems, etc.) from the system 100 and / or any data processed by the processing unit 110 to the one or more servers.

[0045] The System 100 can upload data to a server (e.g., the cloud) based on a data protection level setting. For example, the System 100 can implement data protection level settings to regulate or limit the types of data (including metadata) sent to the server that could uniquely identify a vehicle and / or a driver / owner of a vehicle. Such settings can be configured by the user, for example, via the Wireless Receiver 172, initialized through factory default settings, or through data received by the Wireless Receiver 172.

[0046] In some embodiments, the system can upload 100 data points according to a "high" privacy level, and under a specific setting, the system can transmit 100 data points (e.g., location information related to a route, captured images, etc.) without any details about the specific vehicle and / or driver / owner. For example, when data is uploaded according to a "high" privacy setting, the system cannot include a vehicle identification number (VIN) or the name of a driver or owner of the vehicle and can instead transmit data such as captured images and / or limited location information related to a route.

[0047] Other data protection levels are considered. For example, the system can transmit 100 data points to a server according to a "medium" data protection level and include additional information not included under a "high" data protection level, such as a vehicle's make and / or model and / or vehicle type (e.g., a passenger car, an SUV, a truck, etc.). In some embodiments, the system can upload 100 data points according to a "low" data protection level. Under a "low" data protection setting, the system can upload 100 data points and include information sufficient to uniquely identify a specific vehicle, a specific owner / driver, and / or a section or the entirety of a route traveled by the vehicle.Such “low” level data protection data may include one or more of, for example, a VIN, a driver / owner's name, a vehicle's point of origin before departure, a vehicle's intended destination, a vehicle's make and / or model, a vehicle type, etc.

[0048] Fig. Figure 2A shows a schematic side view representation of an exemplary vehicle imaging system, in accordance with the disclosed embodiments. Fig. Figure 2B shows a schematic top view illustration of the in Fig. 2A embodiment shown. As in Fig. As illustrated in Figure 2B, the disclosed embodiments may include a vehicle 200 which incorporates in its body a system 100 comprising a first image acquisition device 122 positioned near the rearview mirror and / or near the driver of the vehicle 200, a second image acquisition device 124 positioned on or in a bumper area (e.g. one of the bumper areas 210) of the vehicle 200, and a processing unit 110.

[0049] As in Fig. As illustrated in Figure 2C, the image acquisition devices 122 and 124 can both be positioned near the rearview mirror and / or near the driver of vehicle 200. Additionally, it should be noted that in the Fig. 2B and Fig. As shown in Figure 2C, it should be understood that other embodiments may include more than two image acquisition devices. For example, in the figures shown in Fig. 2D and Fig. In embodiments 2E shown, a first, second and third image acquisition device 122, 124 and 126 is integrated into the system 100 of the vehicle 200.

[0050] As in Fig. As illustrated in 2D, the image acquisition device 122 can be positioned near the rearview mirror and / or near the driver of the vehicle 200, and the image acquisition devices 124 and 126 can be positioned on or in a bumper area (e.g., one of the bumper areas 210) of the vehicle 200. And as shown in Fig. As shown in Figure 2E, the image acquisition devices 122, 124, and 126 can be positioned near the rearview mirror and / or near the driver's seat of the vehicle 200. The disclosed embodiments are not limited to a specific number and configuration of the image acquisition devices, and the image acquisition devices can be positioned at any suitable location inside and / or on the vehicle 200.

[0051] It is understood that the disclosed embodiments are not limited to vehicles and could be applied in other contexts. It is also understood that the disclosed embodiments are not limited to a specific vehicle type 200 and may be applicable to all vehicle types, including automobiles, trucks, trailers, and other vehicle types.

[0052] The first image acquisition device 122 can include any suitable type of image acquisition device. The image acquisition device 122 can include an optical axis. In one instance, the image acquisition device 122 can include a WVGA sensor of the Aptina M9V024 type with a global shutter. In other embodiments, the image acquisition device 122 can provide a resolution of 1280x960 pixels and include a rolling shutter. The image acquisition device 122 can include various optical elements. In some embodiments, one or more lenses can be included to provide, for example, a desired focal length and field of view for the image acquisition device. In some embodiments, the image acquisition device 122 can be associated with a 6 mm lens or a 12 mm lens.In some embodiments, the image acquisition device 122 can be configured to capture images with a desired field of view (FOV) 202, as shown in . Fig. 2D illustration. For example, the image acquisition device 122 can be configured to have a regular FOV, such as within a range of 40 to 56 degrees, including a 46-degree FOV, 50-degree FOV, 52-degree FOV, or larger. Alternatively, the image acquisition device 122 can be configured to have a narrow FOV in the range of 23 to 40 degrees, such as a 28-degree FOV or 36-degree FOV. Additionally, the image acquisition device 122 can be configured to have a wide FOV in the range of 100 to 180 degrees. In some embodiments, the image acquisition device 122 can include a wide-angle bumper camera or one with up to a 180-degree FOV. In some embodiments, the image acquisition device 122 can be an image acquisition device with 7.2 M pixels with an aspect ratio of about 2:1 (e.g. HxV = 3800x1900 pixels) with a horizontal FOV of about 100 degrees.Such an image acquisition device can be used in place of a three-image acquisition device configuration. Due to significant lens distortion, the vertical field of view (FOV) of such an image acquisition device can be significantly less than 50 degrees in implementations where the image acquisition device uses a radially symmetrical lens. For example, such a lens may not be radially symmetrical, which would allow a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

[0053] The first image acquisition device 122 can acquire a plurality of first images relative to a scene associated with the vehicle 200. Each 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 encompass a plurality of pixels.

[0054] The first image acquisition device 122 can have a sampling rate associated with the acquisition of each of the first set of image scan lines. The sampling rate can refer to the rate at which an image sensor can acquire image data associated with each pixel enclosed in a given scan line.

[0055] The image acquisition devices 122, 124, and 126 can include any suitable type and number of image sensors, including, for example, CCD or CMOS sensors. In one embodiment, a CMOS image sensor can be used in conjunction with a rolling shutter, such that each pixel in a row is read sequentially, and the scanning of the rows is performed on a row-by-row basis until an entire single image has been acquired. In some embodiments, the rows can be acquired sequentially from top to bottom with respect to the frame.

[0056] In some embodiments, one or more of the image acquisition devices disclosed herein (e.g. image acquisition devices 122, 124 and 126) can form a high-resolution image transmitter and have a resolution of more than 5 M pixels, 7 M pixels, 10 M pixels or more.

[0057] The use of a rolling shutter can cause pixels in different rows to be exposed and captured at different times, which can lead to distortion and other image artifacts in the captured frame. Conversely, if the image capture device 122 is configured to operate with 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 by a system using a global shutter represents a snapshot of the entire field of view (such as FOV 202) at a specific point in time. In contrast, in a rolling shutter application, each row in a frame is exposed, and data is captured at different times. Therefore, moving objects may appear distorted in an image capture device using a rolling shutter.This phenomenon is described in more detail below.

[0058] The second image acquisition device 124 and the third image acquisition device 126 can be any type of image acquisition device. Like the first image acquisition device 122, each of the image acquisition devices 124 and 126 can include an optical axis. In one embodiment, each of the image acquisition devices 124 and 126 can include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image acquisition devices 124 and 126 can include a rolling shutter. Like the image acquisition device 122, the image acquisition devices 124 and 126 can be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image acquisition devices 124 and 126 can provide FOVs (such as FOVs 204 and 206) that are equal to or narrower than an FOV (such as FOV 202) associated with the image acquisition device 122.For example, the image capture devices can have 124 and 126 FOVs of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees or less.

[0059] The image acquisition devices 124 and 126 can acquire a plurality of second and third images relative to a scene associated with the vehicle 200. Each plurality of second and third images can be acquired as a second and third series of image scan lines, which can be acquired using a rolling shutter. Each scan line or series can have a plurality of pixels. The image acquisition devices 124 and 126 can have second and third sampling rates associated with the acquisition of each of the image scan lines included in the second and third series.

[0060] Each image acquisition device 122, 124, and 126 can be positioned at any suitable location and orientation relative to the vehicle 200. The relative positioning of the image acquisition devices 122, 124, and 126 can be selected to aid in combining the information acquired by the image acquisition devices. For example, in some embodiments, an FOV (such as FOV 204) associated with image acquisition device 124 can partially or completely overlap with an FOV (such as FOV 202) associated with image acquisition device 122 and an FOV (such as FOV 206) associated with image acquisition device 126.

[0061] The image acquisition devices 122, 124, and 126 can be located on the vehicle 200 at any suitable relative heights. In one case, there can be a height difference between the image acquisition devices 122, 124, and 126 that can provide sufficient parallax information to enable stereo analysis. For example, as in Fig. As shown in Figure 2A, the two image acquisition devices 122 and 124 are located at different heights. There can also be a lateral displacement difference between the image acquisition devices 122, 124, and 126, which, for example, provides additional parallax information for stereo analysis by the processing unit 110. The difference in lateral displacement can be denoted by dx, as shown in the Fig. 2C and Fig. The image is shown in 2D. In some embodiments, a forward or backward displacement (e.g., distance displacement) may exist between the image acquisition devices 122, 124, and 126. For example, the image acquisition device 122 may be located 0.5 to 2 meters or more behind the image acquisition device 124 and / or the image acquisition device 126. This type of displacement may allow one of the image acquisition devices to cover potential blind spots of the other image acquisition device(s).

[0062] The image acquisition devices 122 can have any suitable resolution (e.g., number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with the image acquisition device 122 can be higher, lower, or equal to the resolution of the image sensor(s) associated with the image acquisition devices 124 and 126. In some embodiments, the image sensor(s) associated with the image acquisition device 122 and / or the image acquisition devices 124 and 126 can have a resolution of 640 x 480, 1024 x 768, 1280 x 960, or any other suitable resolution.

[0063] The frame rate (e.g., the rate at which an image acquisition device acquires a set of pixel data from a single frame before moving to acquire pixel data associated with the next frame) can be controllable. The frame rate associated with image acquisition device 122 can be higher, lower, or equal to the frame rate associated with image acquisition devices 124 and 126. The frame rate associated with image acquisition devices 122, 124, and 126 can depend on a variety of factors that can affect the timing of the frame rate. For example, one or more of the image acquisition devices 122, 124, and 126 can include a selectable pixel delay period imposed before or after the acquisition of image data associated with one or more pixels of an image sensor in the image acquisition device 122, 124, and / or 126.In general, image data corresponding to each pixel can be acquired according to a clock rate for the device (e.g., one pixel per clock cycle). Additionally, in embodiments that include a rolling shutter, one or more of the image acquisition devices 122, 124, and 126 can include a selectable horizontal blanking period imposed before or after the acquisition of image data associated with a set of pixels of an image sensor in the image acquisition device 122, 124, and / or 126. Furthermore, one or more of the image acquisition devices 122, 124, and / or 126 can include a selectable vertical blanking period imposed before or after the acquisition of image data associated with a single frame of the image acquisition device 122, 124, and 126.

[0064] These timing controls can enable the synchronization of frame rates associated with image acquisition devices 122, 124, and 126, even if their line sampling rates differ. Additionally, as discussed in more detail below, these selectable timing controls, along with other factors (e.g., image sensor resolution, maximum line sampling rates, etc.), can enable the synchronization of image acquisition from an area where the field of view (FOV) of image acquisition device 122 overlaps with one or more FOVs of image acquisition devices 124 and 126, even if the field of view of image acquisition device 122 differs from the FOVs of image acquisition devices 124 and 126.

[0065] The timing of the frame rate in the image acquisition device 122, 124, and 126 can depend on the resolution of the associated image sensors. For example, assuming similar line sampling rates for both devices, if one device includes an image sensor with a resolution of 640 x 480 and another device includes an image sensor with a resolution of 1280 x 960, then more time will be required to acquire a single frame of image data from the sensor with the higher resolution.

[0066] Another factor that can affect the timing of image data acquisition in the image acquisition devices 122, 124, and 126 is the maximum line sampling rate. For example, acquiring a series of image data from an image sensor enclosed in the image acquisition devices 122, 124, and 126 requires a minimum duration. Assuming no pixel delay periods are added, this minimum duration for acquiring a series of image data refers to the maximum line sampling rate for a given device. Devices offering higher maximum line sampling rates have the potential to provide higher frame rates than devices with lower maximum line sampling rates.In some embodiments, one or more of the image acquisition devices 124 and 126 may have a maximum line sampling rate that is higher than a maximum line sampling rate associated with the image acquisition device 122. In some embodiments, the maximum line sampling rate of the image acquisition device 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more of a maximum line sampling rate of the image acquisition device 122.

[0067] In another embodiment, the image acquisition devices 122, 124, and 126 can have the same maximum line sampling rate, but image acquisition device 122 can be operated at a sampling rate that is less than or equal to its maximum sampling rate. The system can be configured such that one or more of the image acquisition devices 124 and 126 operate at a line sampling rate that is equal to the line sampling rate of image acquisition device 122. In other cases, the system can be configured such that the line sampling rate of image acquisition device 124 and / or image acquisition device 126 can be 1.25, 1.5, 1.75, or 2 times or more of the line sampling rate of image acquisition device 122.

[0068] In some embodiments, the image acquisition devices 122, 124, and 126 can be asymmetrical. That is, they can include cameras with different fields of view (FOV) and focal lengths. The fields of view of the image acquisition devices 122, 124, and 126 can, for example, encompass any desired area in relation to the environment of the vehicle 200. In some embodiments, one or more of the image acquisition devices 122, 124, and 126 can be configured to acquire image data from an environment in front of the vehicle 200, behind the vehicle 200, on the sides of the vehicle 200, or combinations thereof.

[0069] Furthermore, the focal length associated with each image acquisition device 122, 124, and / or 126 can be selectable (e.g., by including suitable lenses, etc.) so that each device captures images of objects within a desired distance range relative to the vehicle 200. For example, in some embodiments, the image acquisition devices 122, 124, and 126 can capture images of close-up objects within a few meters of the vehicle. The image acquisition devices 122, 124, and 126 can also be configured to capture images of objects at distances farther from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or more). Furthermore, the focal lengths of the image acquisition devices 122, 124 and 126 can be selected such that an image acquisition device (e.g. image acquisition device 122) can capture images of objects relatively close to the vehicle (e.g.within 10 m or within 20 m) can take pictures, while the other image acquisition devices (e.g. image acquisition devices 124 and 126) can take pictures of objects further away (e.g. greater than 20 m, 50 m, 100 m, 150 m etc.) from the vehicle 200.

[0070] According to some embodiments, the field of view (FOV) of one or more image capture devices 122, 124, and 126 can have a wide angle. For example, it may be advantageous to have an FOV of 140 degrees, particularly for the image capture devices 122, 124, and 126, which can be used to capture images of the area near the vehicle 200. For example, the image capture device 122 can be used to capture images of the area to the right or left of the vehicle 200, and in such embodiments, it may be desirable for the image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0071] The field of view associated with each of the image acquisition devices 122, 124 and 126 can depend on the respective focal lengths. For example, if the focal length increases, the corresponding field of view decreases.

[0072] The image acquisition devices 122, 124, and 126 can be configured to have any suitable fields of view. In one particular example, image acquisition device 122 can have a horizontal FOV of 46 degrees, image acquisition device 124 can have a horizontal FOV of 23 degrees, and image acquisition device 126 can have a horizontal FOV between 23 and 46 degrees. In another case, image acquisition device 122 can have a horizontal FOV of 52 degrees, image acquisition device 124 can have a horizontal FOV of 26 degrees, and image acquisition device 126 can have a horizontal FOV between 26 and 52 degrees. In some embodiments, the ratio of the FOV of image acquisition device 122 to the FOVs of image acquisition device 124 and / or image acquisition device 126 can vary from 1.5 to 2.0. In other embodiments, this ratio can vary between 1.25 and 2.25.

[0073] The system 100 can be configured such that a field of view of the image acquisition device 122 overlaps at least partially or completely with a field of view of the image acquisition device 124 and / or the image acquisition device 126. In some embodiments, the system 100 can be configured such that the fields of view of the image acquisition devices 124 and 126, for example, fall within the field of view of the image acquisition device 122 (e.g., are narrower than it) and share a common center with it. In other embodiments, the image acquisition devices 122, 124, and 126 can capture adjacent fields of view or have a partial overlap in their fields of view.In some embodiments, the fields of view of the image acquisition devices 122, 124 and 126 can be aligned such that a center of the narrower FOV image acquisition devices 124 and / or 126 can be located in a lower half of the field of view of the wider FOV image acquisition device 122.

[0074] Fig. Figure 2F shows a schematic representation of exemplary vehicle control systems, in accordance with the disclosed embodiments. As in Fig. As specified in 2F, the vehicle 200 can include a throttle system 220, a brake system 230, and a steering system 240. The system 100 can provide inputs (e.g., control signals) to one or more of a throttle system 220, a brake system 230, and a steering system 240 via one or more data connections (e.g., any wired and / or wireless connection or connections for transmitting data). For example, based on an analysis of images acquired by the image acquisition devices 122, 124, and / or 126, the system 100 can provide control signals to one or more of a throttle system 220, a brake system 230, and a steering system 240 to navigate the vehicle 200 (e.g., by initiating acceleration, turning, lane changes, etc.).Furthermore, the system can receive 100 inputs from one or more of a throttle system 220, a brake system 230, and a steering system 24, indicating the operating conditions of the vehicle 200 (e.g., speed, whether the vehicle 200 is braking and / or turning, etc.). Further details are available in conjunction with the following. Fig. 4 to 7 provided.

[0075] As in Fig. As shown in Figure 3A, the vehicle 200 can also include a user interface 170 for interacting with a driver or passenger of the vehicle 200. For example, in a vehicle application, the user interface 170 can include a touchscreen 320, knobs 330, buttons 340, and a microphone 350. A driver or passenger of the vehicle 200 can also use handles (located, for example, on or near the steering column of the vehicle 200, including, for example, turn signal handles), buttons (located, for example, on the steering wheel of the vehicle 200), and the like to interact with the system 100. In some embodiments, the microphone 350 can be positioned adjacent to a rearview mirror 310. Similarly, in some embodiments, the image capture device 122 can be located near the rearview mirror 310. In some embodiments, the user interface 170 can also include one or more loudspeakers 360 (e.g.,This includes the speakers of a vehicle audio system. For example, the system can provide 100 different notifications (e.g., warnings) via the 360-degree speakers.

[0076] Fig. Figures 3B to 3D show illustrations of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and against a vehicle windshield, in accordance with the disclosed embodiments. As shown in Fig. As shown in Figure 3B, the camera mount 370 can include image capture devices 122, 124, and 126. The image capture devices 124 and 126 can be positioned behind a glare shield 380, which can be flush with the vehicle windshield and can include a composition of film and / or antireflective materials. For example, the glare shield 380 can be positioned to align with a vehicle windshield that has a matching slope. In some embodiments, each of the image capture devices 122, 124, and 126 can be positioned behind the glare shield 380, as shown, for example, in Fig. 3D representation. The disclosed embodiments are not limited to a specific configuration of the image acquisition devices 122, 124 and 126, the camera mount 370 and the glare shield 380. Fig. 3C shows an illustration of the 370 camera mount, which is in Fig. 3B is shown from a front perspective.

[0077] As a person skilled in the art, benefiting from this disclosure, will recognize, numerous variations and / or modifications can be made to the embodiments disclosed above. For example, not all components are essential for the operation of the system 100. Furthermore, any component can be located in any suitable part of the system 100, and the components can be rearranged into a variety of configurations while still providing the functionality of the disclosed embodiments. Therefore, the configurations given above are examples, and regardless of the configurations discussed above, the system 100 can provide a wide range of functionality to analyze the environment of the vehicle 200 and to navigate the vehicle 200 in response to the analysis.

[0078] As discussed in more detail below and in accordance with various disclosed embodiments, the system 100 can provide a variety of features relating to autonomous driving and / or driver assistance technology. For example, the system 100 can analyze image data, position data (e.g., GPS location information), map data, speed data, and / or data from sensors included in the vehicle 200. The system 100 can collect the data for analysis from, for example, the image acquisition unit 120, the position sensor 130, and other sensors. Furthermore, the system 100 can analyze the collected data to determine whether or not the vehicle 200 should perform a specific action and then automatically execute the specific action without human intervention.For example, if the vehicle 200 is navigating without human intervention, the system 100 can automatically control the braking, acceleration, and / or steering of the vehicle 200 (e.g., by sending control signals to one or more of a throttle system 220, a braking system 230, and a steering system 240). Furthermore, the system 100 can analyze the collected data and issue warnings and / or alarms to vehicle occupants based on this analysis. Additional details regarding the various embodiments provided by the system 100 are given below. Forward-facing multi-imaging system

[0079] As discussed above, the system 100 can provide driver assistance functionality that uses a multi-camera system. The multi-camera system can use one or more cameras facing forward in the direction of a vehicle. In other embodiments, the multi-camera system can include one or more cameras facing to the side or rear of a vehicle. In one embodiment, for example, the system 100 can use a two-camera imaging system, wherein a first camera and a second camera (e.g., image capture devices 122 and 124) can be positioned at the front and / or sides of a vehicle (e.g., vehicle 200). The first camera can have a field of view that is larger than, smaller 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 to perform monocular image analysis of images provided by the first camera, and the second camera can be connected to a second image processor to perform monocular image analysis of 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 and second cameras to perform stereo analysis. In another embodiment, the system 100 can use a three-camera imaging system, with each camera having a different field of view.Such a system can therefore make decisions based on information derived from objects located at varying distances both in front of and to the sides of the vehicle. References to monocular image analysis may refer to cases where image analysis is performed based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may refer to cases where image analysis is performed based on two or more images captured with one or more variations of an image capture parameter. For example, captured images suitable for performing stereo image analysis may include images captured from two or more different positions, from different fields of view, using different focal lengths, along with parallax information, and so on.

[0080] For example, in one embodiment, the system 100 can implement a three-camera configuration using the image capture devices 122, 124, and 126. In such a configuration, the image capture device 122 can provide a narrow field of view (e.g., 34 degrees or other values ​​selected from a range of approximately 20 to 45 degrees, etc.), the image capture device 124 can provide a wide field of view (e.g., 150 degrees or other values ​​selected from a range of approximately 100 to approximately 180 degrees), and the image capture device 126 can provide an intermediate field of view (e.g., 46 degrees or other values ​​selected from a range of approximately 35 to approximately 60 degrees). In some embodiments, the image capture device 126 can function as the main or primary camera.The image capture devices 122, 124, and 126 can be positioned behind the rearview mirror 310 and essentially side by side (e.g., 6 cm apart). Furthermore, in some embodiments as discussed above, one or more of the image capture devices 122, 124, and 126 can be mounted behind the glare shield 380, which is flush with the windshield of the vehicle 200. Such shielding can serve to minimize the influence of reflections from inside the car on the image capture devices 122, 124, and 126.

[0081] In a further embodiment, as above in conjunction with the Fig. 3B and Fig. As discussed in Section 3C, the wide-field camera (e.g., image capture device 124 in the preceding example) can be mounted lower than the narrow-field and main-field cameras (e.g., image capture devices 122 and 126 in the preceding example). This configuration can provide an unobstructed line of sight from the wide-field camera. To reduce reflections, the cameras can be mounted near the windshield of the vehicle 200 and include polarizers on the cameras to attenuate reflected light.

[0082] A three-camera system can provide certain performance characteristics. For example, some embodiments may include the ability to validate the detection of objects by one camera based on detection results from another camera. In the three-camera configuration discussed above, the processing unit 110 may, for example, include three processing devices (e.g., three EyeQ arrays of processor chips, as discussed above), each processing device dedicated to processing images captured by one or more of the image capture devices 122, 124, and 126.

[0083] In a three-camera system, a first processing unit can receive images from both the main camera and the narrow field-of-view camera and perform image processing from the narrow-field-view camera to detect, for example, other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Furthermore, the first processing unit can calculate pixel disparities between the images from the main camera and the narrow camera and create a 3D reconstruction of the vehicle's surroundings. The first processing unit can then combine this 3D reconstruction with 3D map data or with 3D information calculated based on information from another camera.

[0084] The second processing unit can receive images from the main camera and perform image processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the second processing unit can calculate camera displacement and, based on this displacement, determine pixel disparity between successive images and create a 3D reconstruction of the scene (e.g., a motion structure). The second processing unit can then send this motion-based 3D reconstruction structure to the first processing unit for merging with the stereo 3D images.

[0085] The third processing unit can receive images from the wide-field-of-view (FOV) camera and process them to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing unit can also execute additional processing instructions to analyze images and identify objects moving within the frame, such as vehicles changing lanes, pedestrians, etc.

[0086] In some embodiments, streams of image-based information that are independently acquired and processed can provide a means of providing redundancy in the system. Such redundancy can, for example, include using a first image acquisition device and the images processed by that device to validate and / or supplement information obtained by acquiring and processing image information from at least one second image acquisition device.

[0087] In some embodiments, the system 100 can use two image acquisition devices (e.g., image acquisition devices 122 and 124) to provide navigational support for the vehicle 200 and a third image acquisition device (e.g., image acquisition device 126) to provide redundancy and validate the analysis of the data received by the other two image acquisition devices. For example, in such a configuration, image acquisition devices 122 and 124 can provide images for stereo analysis by the system 100 to navigate the vehicle 200, while image acquisition device 126 can provide images for monocular analysis by the system 100 to provide redundancy and validation of information obtained based on images acquired by image acquisition device 122 and / or image acquisition device 124.This means that the image acquisition device 126 (and a corresponding processing device) can be considered a redundant subsystem that provides verification of the analysis derived from the image acquisition devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Furthermore, in some embodiments, the redundancy and validation of the received data can be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside a vehicle, etc.).

[0088] A person skilled in the art will recognize that the foregoing camera configurations, camera placements, number of cameras, camera locations, etc., are only examples. These components and others described in relation to the overall system can be combined and used in a multitude of different configurations without deviating from the scope of the disclosed embodiments. Further details regarding the use of a multi-camera system to provide driver assistance and / or autonomous vehicle functionality follow.

[0089] Fig. Figure 4 shows an exemplary functional block diagram of memory 140 and / or 150, which can be stored / programmed with instructions for performing one or more operations, in accordance with the disclosed embodiments. Although the following refers to memory 140, a person skilled in the art will recognize that instructions can be stored in memory 140 and / or 150.

[0090] As in Fig. As shown in Figure 4, the memory 140 can store a monocular image analysis module 402, a stereo image analysis module 404, a speed and acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to a specific configuration of the memory 140. Furthermore, the application processor 180 and / or the image processor 190 can execute the instructions stored in any one of the modules 402, 404, 406, and 408 included in the memory 140. A person skilled in the art will understand that references in the following discussion to the processing unit 110 may refer individually or jointly to the application processor 180 and the image processor 190. Accordingly, steps of any of the following processes can be performed by one or more processing units.

[0091] In one embodiment, the monocular image analysis module 402 can store instructions (such as computer vision software) which, when executed by the processing unit 110, perform monocular image analysis of a set of images captured by one of the image acquisition devices 122, 124, and 126. In some embodiments, the processing unit 110 can combine information from a set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform the monocular image analysis. As described in conjunction with the following Fig. As described in sections 5A to 5D, the monocular image analysis module 402 can include instructions for recognizing a set of features within the image series, such as lane markings, vehicles, pedestrians, road signs, highway exits, traffic lights, hazardous objects, and any other features related to the vehicle's surroundings. Based on the analysis, the system 100 (e.g., via the processing unit 110) can initiate one or more navigation responses in the vehicle 200, such as turning, changing lanes, altering acceleration, and the like, as discussed below in conjunction with the navigation response module 408.

[0092] In one embodiment, the stereo image analysis module 404 can store instructions (such as computer vision software) which, when executed by the processing unit 110, perform a stereo image analysis of a first and second set of images acquired by a combination of image acquisition devices selected from any one of the image acquisition devices 122, 124, and 126. In some embodiments, the processing unit 110 can combine information from the first and second sets of images with additional sensory information (e.g., information from radar) to perform the stereo image analysis.For example, the stereo image analysis module 404 can include instructions for performing a stereo image analysis based on a first set of images captured by the image acquisition device 124 and a second set of images captured by the image acquisition device 126. As in conjunction with the following. Fig. As described in Section 6, the stereo image analysis module 404 can include instructions for recognizing a set of features within the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and the like. Based on the analysis, the processing unit 110 can initiate one or more navigation responses in the vehicle 200, such as turning, changing lanes, changing acceleration, and the like, as discussed below in conjunction with the navigation response module 408.Furthermore, in some embodiments, the stereo image analysis module 404 can implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system, such as a system that may be configured to use computer vision algorithms to detect and / or label objects in an environment from which sensory information has been acquired 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 a trained and an untrained system.

[0093] In one embodiment, the speed and acceleration module 406 can store software configured to analyze data received from one or more computing devices and electromechanical devices in the vehicle 200, which are configured to cause a change in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 can execute instructions associated with the speed and acceleration module 406 to calculate a target speed for the vehicle 200 based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404.Such data can include, for example, a target position, speed, and / or acceleration; the position and / or speed of the vehicle 200 relative to a nearby vehicle, pedestrian, or road object; positional information for the vehicle 200 relative to lane markings; and the like. Additionally, the processing unit 110 can calculate a target speed for the vehicle 200 based on sensor inputs (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle system 220, the braking system 230, and / or the steering system 240.Based on the calculated target speed, the processing unit 110 can transmit electronic signals to the throttle system 220, the brake system 230 and / or the steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration, for example by physically pressing down the brake or releasing the accelerator pedal of the vehicle 200.

[0094] In one embodiment, the navigation response module 408 can store software that can be executed by the processing unit 110 to determine a desired navigation response based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data can include position and velocity information associated with nearby vehicles, pedestrians, and road objects, target position information for the vehicle 200, and the like.Additionally, in some embodiments, the navigation response can be based (partially or completely) on map data, a predetermined position of the vehicle 200, and / or a relative speed or acceleration between the vehicle 200 and one or more objects detected by the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 can also determine a desired navigation response based on sensor inputs (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle system 220, the braking system 230, and the steering system 240 of the vehicle 200.Based on the desired navigation response, the processing unit 110 can transmit electronic signals to the throttle system 220, the brake system 230, and the steering system 240 of the vehicle 200 to trigger a desired navigation response, for example, by turning the steering wheel of the vehicle 200 to achieve a rotation of a predetermined angle. In some embodiments, the processing unit 110 can use the output of the navigation response module 408 (e.g., the desired navigation response) as an input to execute the speed and acceleration module 406 to calculate a change in the speed of the vehicle 200.

[0095] Furthermore, each of the modules disclosed herein (e.g., modules 402, 404, and 406) can implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.

[0096] Fig. Figure 5A shows a flowchart illustrating an exemplary process 500A for initiating one or more navigation responses based on monocular image analysis, in accordance with the disclosed embodiments. In step 510, the processing unit 110 can receive a plurality of images via the data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera enclosed in the image acquisition unit 120 (such as the image capture device 122 with the field of view 202) can capture a plurality of images of an area in front of the vehicle 200 (or, for example, to the sides or rear of a vehicle) and transmit them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.).The processing unit 110 can execute the monocular image analysis module 402 to analyze the multitude of images in step 520, as described in the following. Fig. Sections 5B to 5D are described in more detail below. By performing the analysis, the processing unit 110 can recognize a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and the like.

[0097] The processing unit 110 can also execute the monocular image analysis module 402 to detect various road hazards at step 520, such as pieces of a truck tire, fallen road signs, loose cargo, small animals, and the like. Road hazards can vary in structure, shape, size, and color, which can make detection more difficult. In some embodiments, the processing unit 110 can execute the monocular image analysis module 402 to perform multi-frame analysis on the multitude of images to detect road hazards. For example, the processing unit 110 can estimate the camera movement between successive frames and calculate the pixel disparities between the frames to create a 3D map of the road.The processing unit 110 can then use the 3D map to detect the road surface as well as the hazards existing above the road surface.

[0098] At step 530, the processing unit 110 can execute the navigation response module 408 to initiate one or more navigation responses in the vehicle 200 based on the analysis performed at step 520 and the techniques described above in conjunction with Fig. 4. Navigation responses can include, for example, turning, changing lanes, changing acceleration, and the like. In some embodiments, the processing unit 110 can use data derived from the execution of the speed and acceleration module 406 to initiate 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 lanes laterally and then accelerate by, for example, sequentially transmitting control signals to the steering system 240 and the throttle system 220 of the vehicle 200.Alternatively, the processing unit 110 can cause the vehicle 200 to brake while simultaneously changing lanes, for example by simultaneously transmitting control signals to the braking system 230 and the steering system 240 of the vehicle 200.

[0099] Fig. Figure 5B shows a flowchart illustrating an exemplary process 500B for detecting one or more vehicles and / or pedestrians in a set of images, in accordance with the disclosed embodiments. The processing unit 110 can execute the monocular image analysis module 402 to implement 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 against one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or parts thereof). The predetermined patterns can be designed to achieve a high rate of "false hits" and a low rate of "missed hits."For example, processing unit 110 can use a low threshold of similarity to predetermined patterns to identify candidate objects as possible vehicles or pedestrians. This can allow processing unit 110 to reduce the probability that a candidate object representing a vehicle or pedestrian is missing (e.g., not identified).

[0100] In step 542, processing unit 110 can filter the set of candidate objects to exclude certain candidates (e.g., irrelevant or less relevant objects) based on classification criteria. Such criteria can be derived from various properties associated with object types stored in a database (e.g., a database stored in memory 140). Properties can include object shape, dimensions, texture, position (e.g., relative to vehicle 200), and the like. Thus, processing unit 110 can use one or more sets of criteria to exclude incorrect candidates from the set of candidate objects.

[0101] In step 544, processing unit 110 can analyze multiple frames of images to determine whether objects in the set of candidate objects represent vehicles and / or pedestrians. For example, processing unit 110 can track a detected candidate object across successive frames and accumulate frame-by-frame data associated with the detected object (e.g., size, position relative to vehicle 200, etc.). Additionally, processing unit 110 can estimate parameters for the detected object and compare the object's frame-by-frame position data with a predicted position.

[0102] In step 546, the processing unit 110 can generate a set of measurements for the detected objects. Such measurements can include, for example, position, velocity, and acceleration values ​​(relative to vehicle 200) associated with the detected objects. In some embodiments, the processing unit 110 can generate the measurements based on estimation techniques using a range of time-based observations, such as Kalman filters or linear quadratic estimation (LQE), and / or based on available modeling data for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filters can be based on a measurement of an object's scale, where the scale measurement is proportional to a time to collision (e.g., the time it takes vehicle 200 to reach the object).Thus, by performing steps 540-546, the processing unit 110 can identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, the processing unit 110 can initiate one or more navigation responses in the vehicle 200, as described above in conjunction with [the above]. Fig. 5A described.

[0103] In step 548, the processing unit 110 can perform an optical flow analysis of one or more images to reduce the probability of a "false hit" being detected and a candidate object representing a vehicle or pedestrian being missing. The optical flow analysis might involve, for example, analyzing movement patterns relative to vehicle 200 in one or more images that are associated with other vehicles and pedestrians and differ from the movement of the road surface. The processing unit 110 can calculate the movement of candidate objects by observing the different positions of the objects across multiple frames captured at different times. The processing unit 110 can use the position and time values ​​as inputs into mathematical models to calculate the movement of the candidate objects.Thus, optical flow analysis can provide an alternative method for detecting vehicles and pedestrians in the vicinity of vehicle 200. Processing unit 110 can perform optical flow analysis in combination with steps 540-546 to provide redundancy for detecting vehicles and pedestrians and to increase the reliability of system 100.

[0104] Fig. Figure 5C shows a flowchart illustrating an exemplary process 500C for detecting road markings and / or lane geometry information in a set of images, in accordance with the disclosed embodiments. The processing unit 110 can execute the monocular image analysis module 402 to implement process 500C. In step 550, the processing unit 110 can detect a set of objects by scanning one or more images. To detect segments of lane markings, lane geometry information, and other relevant road markings, the processing unit 110 can filter the set of objects to exclude those determined to be irrelevant (e.g., small potholes, small rocks, etc.). In step 552, the processing unit 110 can group together the segments detected in step 550 that belong to the same road marking or lane marking.Based on the grouping, the processing unit 110 can develop a model to represent the detected segments, such as a mathematical model.

[0105] In step 554, the processing unit 110 can construct a set of measurements associated with the detected segments. In some embodiments, the processing unit 110 can create a projection of the detected segments from the image plane onto the real plane. The projection can be characterized using a third-degree polynomial that has coefficients corresponding to physical properties such as the position, inclination, curvature, and curvature derivative of the detected road. When generating the projection, the processing unit 110 can take into account changes in the road surface as well as pitch and roll rates associated with the vehicle 200. Additionally, the processing unit 110 can model the road height by analyzing position and motion cues present on the road surface.Furthermore, the processing unit 110 can estimate the pitch and roll rates associated with the vehicle 200 by tracking a set of feature points in the one or more images.

[0106] In step 556, the processing unit 110 can perform a multi-frame analysis by, for example, tracking the detected segments across successive frames and accumulating frame data associated with detected segments. Because the processing unit 110 performs a multi-frame analysis, the set of measurements created in step 554 can become more reliable and associated with an increasingly higher level of confidence. Thus, by performing steps 550, 552, 554, and 556, the processing unit 110 can identify road markings appearing within the set of captured images and derive lane geometry information. Based on the identification and the derived information, the processing unit 110 can initiate one or more navigation responses in the vehicle 200, as described above in conjunction with Fig. 5A described.

[0107] In step 558, the processing unit 110 can consider additional information sources to further develop a safety model for the vehicle 200 within the context of its environment. The processing unit 110 can use the safety model to define a context in which the system 100 can safely perform autonomous control of the vehicle 200. To develop the safety model, the processing unit 110, in some embodiments, can consider the position and movement of other vehicles, detected road edges and barriers, and / or general road shape descriptions extracted from map data (such as data from the map database 160). By considering additional information sources, the processing unit 110 can provide redundancy for detecting road markings and lane geometry, thereby increasing the reliability of the system 100.

[0108] Fig. Figure 5D shows a flowchart illustrating an exemplary process 500D for detecting traffic lights in a set of images, in accordance with the disclosed embodiments. The processing unit 110 can execute the monocular image analysis module 402 to implement process 500D. At step 560, the processing unit 110 can scan the set of images and identify objects that appear in locations within the images likely to contain traffic lights. For example, the processing unit 110 can filter the identified objects to create a set of candidate objects, excluding those objects that are unlikely to be traffic lights. The filtering can be based on various properties associated with traffic lights, such as shape, dimensions, texture, position (e.g., relative to vehicle 200), and the like.Such properties can be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, the processing unit 110 can perform a multi-frame analysis on the set of candidate objects that reflect possible traffic lights. For example, the processing unit 110 can track the candidate objects across successive frames, estimate the actual position of the candidate objects, and filter out those objects that are moving (which are unlikely to be traffic lights). In some embodiments, the processing unit 110 can perform a color analysis on the candidate objects and identify the relative position of the detected colors that appear within possible traffic lights.

[0109] At step 562, the processing unit 110 can analyze the geometry of an intersection. The analysis can be based on any combination of the following factors: (i) the number of lanes detected on both sides of the vehicle 200, (ii) road markings detected (such as arrow markings), and (iii) descriptions of the intersection extracted from map data (e.g., data from the map database 160). The processing unit 110 can perform the analysis using information derived from the execution of the monocular analysis module 402. Additionally, the processing unit 110 can determine a match between the traffic lights detected at step 560 and the lanes appearing near the vehicle 200.

[0110] As vehicle 200 approaches the intersection, processing unit 110 can update the confidence level associated with the analyzed intersection geometry and the detected traffic lights at step 564. For example, the number of traffic lights estimated to appear at the intersection, compared to the number actually present, can affect the confidence level. Based on this confidence level, processing unit 110 can then delegate control to the driver of vehicle 200 to improve safety. By performing steps 560, 562, and 564, processing unit 110 can identify traffic lights appearing within the set of captured images and analyze intersection geometry information.Based on the identification and analysis, the processing unit 110 can initiate one or more navigation responses in the vehicle 200, as described above in conjunction with . Fig. 5A described.

[0111] Fig. Figure 5E shows a flowchart illustrating an exemplary process 500E for initiating one or more navigation responses in the vehicle 200 based on a vehicle path, in accordance with the disclosed embodiments. At step 570, the processing unit 110 can construct an initial vehicle path associated with the vehicle 200. The vehicle path can be represented using a set of points expressed in coordinates (x, z) and the distance d. iThe distance between any two points in the set of points can fall within the range of 1 to 5 meters. In one embodiment, the processing unit 110 can construct the initial vehicle path using two polynomials, such as left and right road polynomials. The processing unit 110 can compute the geometric midpoint between the two polynomials and offset each point enclosed in the resulting vehicle path by a predetermined offset (e.g., an offset of a smart lane), if any (an offset of zero can correspond to driving in the center of a lane). The offset can be in a direction perpendicular to any segment between any two points on the vehicle path.In another embodiment, the processing unit 110 can use a polynomial and an estimated lane width to offset each point of the vehicle path by half the estimated lane width plus a predetermined offset (e.g., an offset of a smart lane).

[0112] At step 572, processing unit 110 can update the vehicle path constructed at step 570. Processing unit 110 can reconstruct the vehicle path constructed at step 570 using a higher resolution, so that the distance d k The distance between two points in the set of points representing the vehicle path is smaller than the distance d described above. i For example, the distance d kthe distance falls within the range of 0.1 to 0.3 meters. The processing unit 110 can reconstruct the vehicle path using a parabolic spline algorithm, which can provide 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).

[0113] At step 574, the processing unit 110 can provide a foresight point (expressed in coordinates as (x)). l , z l)) based on the updated vehicle path constructed in step 572. Processing unit 110 can extract the lookout point from the cumulative distance vector S, and the lookout point can be associated with a lookout distance and a lookout time. The lookout distance, which can have a lower limit in the range of 10 to 20 meters, can be calculated as the product of the vehicle 200's speed and the lookout time. For example, if the vehicle 200's speed decreases, the lookout distance can also decrease (e.g., until it reaches the lower limit). The lookout time, which can be in the range of 0.5 to 1.5 seconds, can be inversely proportional to the gain of one or more control loops associated with initiating a navigation response in vehicle 200, such as the control loop for heading error tracking.For example, the gain of the control loop for tracking driving direction errors can depend on the bandwidth of a yaw rate loop, a steering actuator loop, the vehicle's lateral dynamics, and the like. Therefore, the higher the gain of the control loop for tracking driving direction errors, the shorter the predictive time.

[0114] At step 576, processing unit 110 can determine a direction error and a yaw rate command based on the lookout point determined at step 574. Processing unit 110 can determine the direction error by calculating the arctangent of the lookout point, e.g., arctan(x). l / z lThe processing unit 110 can determine the yaw rate command as the product of the direction error and a high control gain. The high control gain can be equal to: (2 / foresight time) if the foresight distance is not at the lower limit. Otherwise, the high control gain can be equal to: (2 * vehicle speed 200 / foresight distance).

[0115] Fig. Figure 5F shows a flowchart illustrating an exemplary process 500F for determining whether a vehicle ahead is changing lanes, in accordance with the disclosed embodiments. At step 580, the processing unit 110 can determine navigation information associated with a vehicle ahead (e.g., a vehicle traveling in front of vehicle 200). For example, the processing unit 110 can determine the position, speed (e.g., direction and velocity), and / or acceleration of the vehicle ahead using the information described above in conjunction with Fig. 5A and Fig. The processing unit 110 can also determine one or more road polynomials, a lookout point (associated with the vehicle 200) and / or a driven route (e.g., a set of points describing a path taken by the vehicle ahead) using the techniques described above in conjunction with Fig. Determine the techniques described in section 5E.

[0116] In step 582, the processing unit 110 can analyze the navigation information determined in step 580. In one embodiment, the processing unit 110 can calculate the distance between a driven route and a road polynomial (e.g., along the route). If the variance of this distance along the lane exceeds a predetermined threshold (for example, 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a road with sharp curves), the processing unit 110 can determine that the vehicle ahead is likely to change lanes. In the event that multiple vehicles are detected driving ahead of vehicle 200, the processing unit 110 can compare the driven routes associated with each vehicle.Based on this comparison, processing unit 110 can determine that a vehicle whose route does not match the routes of other vehicles is likely to change lanes. Processing unit 110 can additionally compare the curvature of the route traveled (associated with the vehicle ahead) with the expected curvature of the road segment in which the vehicle ahead is traveling. The expected curvature can be extracted from map data (e.g., data from map database 160), road polynomials, routes traveled by other vehicles, prior knowledge of the road, and the like. If the difference in curvature between the route traveled and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 can determine that the vehicle ahead is likely to change lanes.

[0117] In another embodiment, the processing unit 110 can compare the instantaneous position of the vehicle ahead with the look-ahead point (associated with vehicle 200) over a specific period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the vehicle ahead and the look-ahead point varies during the specific period, and the cumulative sum of the variation exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a road with sharp curves), the processing unit 110 can determine that the vehicle ahead is likely to change lanes.In another embodiment, the processing unit 110 can analyze the geometry of the driven route by comparing the lateral distance traveled along the track with the expected curvature of the driven route. The expected radius of curvature can be determined according to the following calculation: (δ. z 2 + δx 2 ) / 2 / (δ x ), where δ x for the lateral distance traveled and δ zThis represents the distance traveled in the longitudinal direction. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 can determine that the vehicle ahead is likely to change lanes. In another embodiment, the processing unit 110 can analyze the position of the vehicle ahead. If the position of the vehicle ahead obscures a road polynomial (e.g., the vehicle ahead is positioned over the road polynomial), then the processing unit 110 can determine that the vehicle ahead is likely to change lanes.In the event that the position of the vehicle ahead is such that another vehicle is detected in front of the vehicle ahead and the routes traveled by the two vehicles are not parallel, the processing unit 110 can determine that the (closer) vehicle ahead is likely to change lanes.

[0118] In step 584, the processing unit 110 can determine, based on the analysis performed in step 582, whether the vehicle 200 ahead is changing lanes or not. For example, the processing unit 110 can make the determination based on a weighted average of the individual analyses performed in step 582. Under such a scheme, for example, a decision by the processing unit 110 that the vehicle ahead is likely to change lanes, based on a specific type of analysis, can be assigned a value of "1" (and "0" to represent a determination that the vehicle ahead is unlikely to change lanes). Different analyses performed in step 582 can be assigned different weights, and the disclosed embodiments are not limited to a specific combination of analyses and weights.

[0119] Fig. Figure 6 shows a flowchart illustrating an exemplary process 600 for initiating one or more navigation responses based on stereo image analysis, in accordance with the disclosed embodiments. In step 610, the processing unit 110 can receive a first and second set of images via the data interface 128. For example, cameras enclosed in the image acquisition unit 120 (such as the image capture devices 122 and 124 with fields of view 202 and 204) can capture a first and second set of images of an 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 can receive the first and second sets of images via two or more data interfaces.The disclosed embodiments are not limited to specific data interface configurations or protocols.

[0120] At step 620, the processing unit 110 can execute the stereo image analysis module 404 to perform a stereo image analysis of the first and second sets of images to create a 3D map of the road in front of the vehicle and to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, and the like. The stereo image analysis can be performed similarly to the above in conjunction with the Fig. The steps described in sections 5A to 5D can be performed. For example, the Processing Unit 110 can execute the Stereo Image Analysis Module 404 to identify candidate objects (e.g., vehicles, pedestrians, road markings, traffic lights, road hazards, etc.) within the first and second sets of images, filter out a subset of the candidate objects based on various criteria, perform a multi-frame analysis, take measurements, and determine a confidence level for the remaining candidate objects. In performing the above steps, the Processing Unit 110 can consider information from both the first and second sets of images, as well as information from a single set of images.For example, processing unit 110 can analyze the differences in pixel-level data (or other data subsets from the two streams of captured images) for a candidate object that appears in both the first and second sets of images. As another example, processing unit 110 can estimate the position and / or velocity of a candidate object (e.g., relative to vehicle 200) by observing that the object appears in one of the sets of images but not in the other, or by considering other differences relative to objects that may exist when the two image streams are viewed. For example, position, velocity, and / or acceleration relative to vehicle 200 can be determined based on trajectories, positions, motion characteristics, etc., of features associated with an object that appears in one or both of the image streams.

[0121] At step 630, the processing unit 110 can execute the navigation response module 408 to initiate one or more navigation responses in the vehicle 200 based on the analysis performed at step 620 and the techniques described above in conjunction with Fig. 4. Navigation responses can include, for example, turning, changing lanes, changing acceleration, changing speed, braking, and the like. In some embodiments, the processing unit 110 can use data derived from the execution of the speed and acceleration module 406 to initiate one or more navigation responses. Additionally, multiple navigation responses can occur simultaneously, sequentially, or in any combination thereof.

[0122] Fig. Figure 7 shows a flowchart illustrating an exemplary process 700 for initiating one or more navigation responses based on an analysis of three sets of images, in accordance with disclosed embodiments. In step 710, the processing unit 110 can receive a first, second, and third plurality of images via the data interface 128. For example, cameras enclosed in the image acquisition unit 120 (such as the image capture devices 122, 124, and 126 with fields of view 202, 204, and 206) can capture a first, second, and third plurality of images of an area in front of and / or beside 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 can receive the first, second, and third plurality of images via three or more data interfaces.For example, each of the image acquisition devices 122, 124, 126 can have an associated data interface for communicating data to the processing unit 110. The disclosed embodiments are not limited to specific data interface configurations or protocols.

[0123] At step 720, the processing unit 110 can analyze the first, second, and third sets of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, and the like. The analysis can be performed similarly to the above in conjunction with the Fig. 5A to 5D and 6 described steps. For example, the Unit 110 can perform monocular image analysis (e.g., by running the monocular image analysis module 402 and based on the above in conjunction with the Fig. (Steps 5A to 5D described) on each of the images of the first, second, and third sets of images. Alternatively, the processing unit 110 can perform a stereo image analysis (e.g., by executing the stereo image analysis module 404 and based on the steps described above in conjunction with Fig. (6 described steps) on the first and second sets of images, the second and third sets of images, and / or the first and third sets of images. The processed information corresponding to the analysis of the first, second, and / or third sets of images can be combined. In some embodiments, the processing unit 110 can perform a combination of monocular image analysis and stereo image analysis. For example, the processing unit 110 can perform a monocular image analysis (e.g., by executing the monocular image analysis module 402) on the first set of images and a stereo image analysis (e.g., by executing the stereo image analysis module 404) on the second and third sets of images.The configuration of the image acquisition devices 122, 124, and 126—including their respective positions and fields of view 202, 204, and 206—can influence the types of analyses performed on the first, second, and third sets of images. The disclosed embodiments are not limited to a specific configuration of the image acquisition devices 122, 124, and 126 or to the types of analyses performed on the first, second, and third sets of images.

[0124] In some embodiments, the processing unit 110 can perform a check on the system 100 based on the images acquired and analyzed in steps 710 and 720. Such a check can 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 can determine the proportion of "false hits" (e.g., cases in which the system 100 incorrectly determined the presence of a vehicle or pedestrian) and "missed hits."

[0125] At step 730, the processing unit 110 can initiate one or more navigation responses in the vehicle 200 based on information derived from two of the first, second, and third sets of images. The selection of two of the first, second, and third sets of images can depend on various factors, such as the number, types, and sizes of the objects detected in each set of images. The processing unit 110 can 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 an object appears, the proportion of the object appearing in each of these frames, etc.), and the like.

[0126] In some embodiments, the processing unit 110 can select information derived from any two of the first, second, and third sets of images by determining the degree to which information derived from one image source is consistent with information derived from other image sources. For example, the processing unit 110 can combine the processed information derived from each of the image capture devices 122, 124, and 126 (whether by monocular analysis, stereo analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, a detected vehicle and its location and / or path, a detected traffic light, etc.) that are consistent across the images captured by each of the image capture devices 122, 124, and 126. The processing unit 110 can also exclude information that is inconsistent across the captured images (e.g.,(a vehicle changing lanes, a lane model indicating a vehicle too close to vehicle 200, etc.). Thus, the processing unit can select 110 pieces of information derived from two of the first, second, and third sets of images, based on the determination of consistent and inconsistent information.

[0127] Navigation responses can include, for example, turning, changing lanes, altering acceleration, and the like. The processing unit 110 can perform one or more navigation responses based on the analysis performed in step 720 and the techniques described above in conjunction with Fig. 4 described. The processing unit 110 can also use data derived from the execution of the velocity and acceleration module 406 to initiate one or more navigation responses. In some embodiments, the processing unit 110 can initiate one or more navigation responses based on a relative position, relative velocity, and / or relative acceleration between vehicle 200 and an object detected within any of the first, second, and third sets of images. Multiple navigation responses can occur simultaneously, sequentially, or in any combination thereof. Sparsely populated road model for autonomous vehicle navigation

[0128] In some embodiments, the disclosed systems and methods can use a sparse map for autonomous vehicle navigation. In particular, the sparse map can be used for autonomous vehicle navigation along a road segment. For example, the sparse map can provide sufficient information for an autonomous vehicle to navigate without storing and / or updating a large amount of data. As discussed in more detail below, an autonomous vehicle can use the sparse map to navigate one or more roads based on one or more stored trajectories. Sparsely populated map for autonomous vehicle navigation

[0129] In some embodiments, the disclosed systems and methods can generate a sparse map for autonomous vehicle navigation. For example, the sparse map can provide sufficient information for navigation without requiring excessive data storage or data transmission rates. As discussed in more detail below, a vehicle (which may be an autonomous vehicle) can use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map can include data relating to a road and potentially landmarks along the road, which may be sufficient for vehicle navigation but also have small data footprints.For example, the sparse data maps, which are described in more detail below, can require significantly less storage space and data transmission bandwidth compared to digital maps that include detailed map information, such as image data collected along a road.

[0130] Instead of storing, for example, detailed representations of a road segment, the sparse data map can store three-dimensional polynomial representations of preferred vehicle paths along a road. These paths can require very little data storage space. Furthermore, landmarks can be identified and included in the road model of the sparse data map described above to aid navigation. These landmarks can be placed at intervals suitable for vehicle navigation, but in some cases, it is not necessary to identify and include such landmarks in the model at high density and close intervals. Rather, in some cases, navigation may be possible based on landmarks that are at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart.As discussed in more detail in other sections, the sparse map can be generated based on data collected or measured by vehicles equipped with various sensors and devices, such as image capture devices, global positioning system sensors, motion sensors, etc., as the vehicles travel along roadways. In some cases, the sparse map can be generated based on data collected during multiple trips by one or more vehicles along a particular roadway. Generating a sparse map using multiple trips by one or more vehicles can be referred to as "crowdsourcing" a sparse map.

[0131] In accordance with the disclosed embodiments, an autonomous vehicle system can use a sparse map for navigation. For example, the disclosed systems and methods can distribute a sparse map to generate a road navigation model for an autonomous vehicle and can navigate an autonomous vehicle along a road segment using a sparse map and / or a generated road navigation model. Sparse maps in accordance with the present disclosure can include one or more three-dimensional contours that can represent predetermined trajectories that autonomous vehicles can traverse when moving along associated road segments.

[0132] Sparse maps according to the present disclosure may also include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and any other road-related features useful for navigating a vehicle. Sparse maps according to the present disclosure may enable autonomous navigation of a vehicle based on relatively small amounts of data included in the sparse map.Instead of including, for example, detailed representations of a road, such as road edges, road curvature, images associated with road segments, or data detailing other physical features associated with a road segment, the disclosed embodiments of the sparse map can require relatively little storage space (and relatively little bandwidth when portions of the sparse map are transmitted to a vehicle) while still adequately providing autonomous vehicle navigation. The small data footprint of the disclosed sparse maps, discussed in more detail below, can be achieved in some embodiments by storing representations of road-related elements that require small amounts of data but still enable autonomous navigation.

[0133] Instead of storing, for example, detailed representations of different viewpoints of a road, the disclosed sparse maps can store polynomial representations of one or more trajectories that a vehicle can follow along the road. Thus, instead of having to store (or transmit) details regarding the physical nature of the road to enable navigation along it, a vehicle can be navigated along a particular road segment using the disclosed sparse maps, in some cases without having to interpret physical viewpoints of the road, but rather by aligning its path with a trajectory (e.g., a polynomial spline) along the particular road segment. In this way, the vehicle can navigate primarily based on the stored trajectory (e.g.,a polynomial spline) which can be navigated using much less memory than an approach that involves storing road images, road parameters, road layout, etc.

[0134] In addition to the stored polynomial representations of trajectories along a road segment, the disclosed sparse maps can also include small data objects that can represent a road feature. In some embodiments, the small data objects can include digital signatures derived from a digital image (or digital signal) acquired by a sensor (e.g., a camera or other sensor, such as a suspension sensor) on board a vehicle traveling along the road segment. The digital signature can be of reduced size relative to the signal acquired by the sensor. In some embodiments, the digital signature can be generated to be compatible with a classifier function configured to detect and identify the road feature from the signal acquired by the sensor, for example, during a subsequent drive.In some embodiments, a digital signature can be generated such that the digital signature has a footprint that is as small as possible while retaining the ability to correlate or match the road feature with the stored signature based on an image (or a digital signal generated by a sensor if the stored signature is not based on an image and / or includes other data) of the road feature captured by a camera on board a vehicle traveling along the same road segment at a subsequent time.

[0135] In some embodiments, the size of the data objects can also be associated with the uniqueness of the road feature. For example, for a road feature detectable by a camera on board a vehicle, and if the camera system on board the vehicle is coupled with a classifier capable of distinguishing the image data corresponding to that road feature as associated with a specific type of road feature, such as a road sign, and if such a road sign is locally unique in that area (e.g., there is no identical road sign or road sign of the same type nearby), it may be sufficient to store data specifying the type of road feature and its location.

[0136] As discussed in more detail below, road features (e.g., landmarks along a road segment) can be stored as small data objects that can represent a road feature in relatively few bytes, while still providing sufficient information to recognize and use such a feature for navigation. For example, a road sign can be identified as a recognized landmark on which a vehicle's navigation can be based. A representation of the road sign can be stored in the sparse map to include, for example, a few bytes of data specifying a landmark type (e.g., a stop sign) and a few bytes of data specifying a location of the landmark (e.g., coordinates). Navigation based on such data-light representations of the landmarks (e.g.,Using representations sufficient for localization, recognition, and navigation based on landmarks, a desired level of navigation functionality associated with sparse maps can be provided without significantly increasing the data overhead associated with sparse maps. This streamlined representation of landmarks (and other road features) can leverage the sensors and processors included on board such vehicles, which are configured to detect, identify, and / or classify specific road features.

[0137] For example, if a character or even a specific type of character is locally unique in a given area (e.g., if there is no other character or character of the same type), the sparse map can use data specifying a type of landmark (a character or a specific type of character), and during navigation (e.g., autonomous navigation), when a camera on board an autonomous vehicle captures an image of the area that includes a character (or a specific type of character), the processor can process the image, detect the character (if it is indeed present in the image), classify the image as a character (or a specific type of character), and correlate the location of the image with the location of the character as stored in the sparse map.

[0138] The sparse map can include any suitable representation of the objects identified along a road segment. In some cases, the objects can be referred to as semantic or non-semantic objects. Semantic objects, for example, can include objects associated with a predefined type classification. This type classification can be useful for reducing the amount of data required to describe the semantic object detected in an environment, which is beneficial both during the data collection phase (e.g., to reduce costs associated with bandwidth usage for transmitting driving information from multiple collection vehicles to a server) and during the navigation phase (e.g.,Reducing map data can be advantageous, as it can speed up the transmission of map tiles from a server to a navigating vehicle and also reduce the costs associated with bandwidth usage for such transmissions. Semantic object classification types can be assigned to any type of object or feature encountered along a roadway.

[0139] Semantic objects can further be divided into two or more logical groups. For example, in some cases, a group of semantic object types can be associated with predetermined dimensions. Such semantic objects might include specific speed limit signs, yield signs, merge signs, stop signs, traffic lights, directional arrows on the road, manhole covers, or any other type of object that can be associated with a standardized size. One advantage of such semantic objects is that very little data is required to represent / fully define the objects.For example, if the standardized size of a speed limit sign is known, a data collection vehicle (by analyzing a captured image) only needs to identify the presence of a speed limit sign (of a recognized type) along with a location of the recognized speed limit sign (e.g., a 2D position in the captured image (or alternatively, a 3D position in real-world coordinates) of the sign's center point or a specific corner of the sign) to provide sufficient information for map generation on the server side. When 2D image positions are transmitted to the server, a location associated with the captured image where the sign was detected can also be transmitted so that the server can determine a real-world location of the sign (e.g., using structure-in-motion techniques with multiple captured images from one or more data collection vehicles).Even with this limited information (which requires only a few bytes to define each detected object), the server can create the map including a fully displayed speed limit sign based on the type classification (representative of a speed limit sign) received from one or more collection vehicles along with the position information for the detected sign.

[0140] Semantic objects can also include other detected object or feature types that are not associated with specific standardized features. Such objects or features can include potholes, tar seams, lampposts, non-standardized signs, curbs, trees, branches, or other detected object types with one or more variable features (e.g., variable dimensions). In such cases, in addition to transmitting an indication of the detected object or feature type (e.g., pothole, post, etc.) and the position information for the detected object or feature to a server, a collection vehicle can also transmit an indication of the object's or feature's size. The size can be expressed in 2D image dimensions (e.g.,with a bounding box or one or more dimensional values) or expressed in real dimensions (which are determined by structure-in-motion calculations, based on the results of LIDAR or RADAR systems, based on the outputs of trained neural networks, etc.).

[0141] Non-semantic objects or features can include any detectable objects or features that do not fall into a recognized category or type but can nevertheless provide valuable information for map generation. In some cases, such non-semantic features might include a detected corner of a building or the corner of a detected window of a building, a unique stone or object near a roadway, a concrete chip on a road edge, or any other detectable object or feature. Upon detecting such an object or feature, one or more collection vehicles can transmit the position of one or more points (2D pixels or 3D points in the real world) associated with the detected object / feature to a map generation server. Additionally, a compressed or simplified image segment (e.g.,An image hash can be generated for a region of the captured image that includes the detected object or feature. This image hash can be calculated based on a predetermined image processing algorithm and can form an effective signature for the detected non-semantic object or feature. Such a signature can be useful for navigation with respect to a sparse map that includes the non-semantic feature or object, as a vehicle crossing the roadway can apply an algorithm similar to the one used to generate the image hash to confirm / verify the presence of the mapped non-semantic feature or object in a captured image. Using this technique, non-semantic features can contribute to the richness of sparse maps (e.g.,(to improve their usefulness in navigation), without adding significant data overhead.

[0142] As noted, destination trajectories can be stored in the sparse map. These destination trajectories (e.g., 3D splines) can represent the preferred or recommended paths for each available lane of a roadway, each valid pedestrian path through an intersection, for merges and exits, etc. In addition to destination trajectories, other road features can also be detected, collected, and incorporated into the sparse maps as representative splines. Such features can include, for example, road edges, lane markings, curbs, guardrails, or other objects or features that extend along a roadway or road segment. Creating a sparsely populated map

[0143] In some embodiments, a sparse map may include at least one line representation of a road surface feature extending along a road segment and a multitude of landmarks associated with the road segment. In certain aspects, the sparse map may be generated through crowdsourcing, for example, by image analysis of a multitude of images captured when one or more vehicles cross the road segment.

[0144] Fig. Figure 8 shows a sparse map 800, which one or more vehicles, e.g., vehicle 200 (which may be an autonomous vehicle), can access to provide autonomous vehicle navigation. The sparse map 800 may be stored in a memory, such as memory 140 or 150. Such storage devices may include any type of non-volatile storage device or computer-readable media. For example, in some embodiments, memory 140 or 150 may include hard disks, compact discs, flash memory, magnetic-based storage devices, optical-based storage devices, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., the map database 160), which may be stored in memory 140 or 150 or in other types of storage devices.

[0145] In some embodiments, the sparse map 800 can be stored on a storage device or non-volatile, computer-readable medium provided on board the vehicle 200 (e.g., a storage device included in a navigation system on board the vehicle 200). A processor (e.g., processing unit 110) provided on the vehicle 200 can access the sparse map 800 stored on the storage device or computer-readable medium provided on board the vehicle 200 to generate navigation instructions for guiding the autonomous vehicle 200 as the vehicle crosses a road segment.

[0146] The thin map 800 need not be stored locally with respect to a vehicle. In some embodiments, the thin map 800 can be stored on a storage device or computer-readable medium provided on a remote server that communicates with the vehicle 200 or a device associated with the vehicle 200. A processor (e.g., processing unit 110) provided on the vehicle 200 can receive data contained in the thin map 800 from the remote server and can execute the data to guide the autonomous driving of the vehicle 200. In such embodiments, the remote server can store the entire thin map 800 or only a portion thereof.Accordingly, the storage device or computer-readable medium provided on board the vehicle 200 and / or on board one or more additional vehicles can store the remaining part(s) of the sparsely populated card 800.

[0147] Furthermore, in such embodiments, the sparse map 800 can be made accessible to a large number of vehicles crossing different road segments (e.g., dozens, hundreds, thousands, or millions of vehicles, etc.). It should also be noted that the sparse map 800 can include multiple submaps. For example, in some embodiments, the sparse map 800 can include hundreds, thousands, millions, or more submaps (e.g., map tiles) that can be used when a vehicle navigates. Such submaps can be referred to as local maps or map tiles, and a vehicle traveling along a roadway can access any number of local maps relevant to the location where the vehicle is traveling.The local map sections of the sparse map 800 can be stored with a Global Navigation Satellite System (GNSS) key as an index for the sparse map 800 database. While the calculation of steering angles for navigating a host vehicle in this system can be performed without dependence on a GNSS position of the host vehicle, road features, or landmarks, such GNSS information can be used to retrieve relevant local maps.

[0148] In general, the sparse map 800 can be generated based on data (e.g., driving information) collected by one or more vehicles as they travel along the roadway. For example, using sensors on board the one or more vehicles (e.g., cameras, speedometers, GPS, accelerometers, etc.), the trajectories traveled by the one or more vehicles along a roadway can be recorded, and the polynomial representations of a preferred trajectory for subsequent journeys along the roadway can be determined based on the collected trajectories traveled by the one or more vehicles. Similarly, data collected by the one or more vehicles can help identify potential landmarks along a given roadway.The data collected from crossing vehicles can also be used to identify road profile information, such as road width profiles, road roughness profiles, traffic line spacing profiles, road conditions, etc. Using the collected information, a sparse map 800 can be generated and distributed for use in navigating one or more autonomous vehicles (e.g., for local storage or via on-the-fly data transmission). In some embodiments, however, map generation may not end with the initial creation of the map. As discussed in more detail below, the sparse map 800 can be continuously or periodically updated based on data collected from vehicles as these vehicles continue to cross roadways included in the sparse map 800.

[0149] Data recorded in the sparse map 800 can include positional information based on Global Positioning System (GPS) data. For example, location information for various map elements can be included in the sparse map 800, including landmark locations, road profile information, and so on. The locations of the map elements included in the sparse map 800 can be determined using GPS data collected from vehicles crossing a roadway. For example, a vehicle passing an identified landmark can determine the location of the identified landmark using GPS positional information associated with the vehicle and a determination of the location of the identified landmark relative to the vehicle (e.g.,based on image analysis of data collected by one or more cameras on board the vehicle). Such location determinations of an identified landmark (or any other feature included in the sparse map 800) can be repeated as additional vehicles pass the location of the identified landmark. 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 position measurements relative to a particular feature stored in the sparse map 800 can be averaged together.However, any other mathematical operations can also be used to refine a stored location of a map element based on a multitude of specific locations for the map element.

[0150] In a specific example, the collection vehicles can traverse a particular road segment. Each collection vehicle captures images of its surroundings. The images can be collected at any suitable frame rate (e.g., 9 Hz, etc.). An image analysis processor (or processors) on board each collection vehicle analyzes the captured images to detect the presence of semantic and / or non-semantic features / objects. At a high level, the collection vehicles transmit information about the detections of the semantic and / or non-semantic objects / features, along with the positions associated with these objects / features, to a mapping server. More specifically, type indicators, dimension indicators, etc., can be transmitted along with the position information.The positional information can include any suitable information that allows the mapping server to aggregate the detected objects / features into a sparse map useful for navigation. In some cases, the positional information can include one or more 2D image positions (e.g., XY pixel positions) within a captured image where the semantic or non-semantic features / objects were detected. Such image positions can correspond to the center of the feature / object, a corner, etc. In this scenario, to assist the mapping server in reconstructing and aligning the driving information from multiple collection vehicles, each collection vehicle can also provide the server with a location (e.g., a GPS coordinate) where each image was captured.

[0151] In other cases, the collection vehicle can provide the server with one or more real 3D points associated with the detected objects / features. Such 3D points can be referenced to a predetermined origin (such as the origin of a journey segment) and can be determined using any suitable technique. In some cases, a structure-in-motion technique can be used to determine the real 3D position of a detected object / feature. For example, a specific object, such as a particular speed limit sign, can be detected in two or more captured images. Using information such as the known motion (speed, trajectory, GPS position, etc.) of the collection vehicle between the captured images, along with observed changes to the speed limit sign in the captured images (change in XY pixel position, change in size, etc.), the system can determine the object's position.The actual position of one or more points associated with the speed limit sign can be determined and forwarded to the mapping server. This approach is optional, as it requires more computational effort from the collection vehicle's systems. The sparse map of the disclosed embodiments can enable autonomous vehicle navigation using relatively small amounts of stored data. In some embodiments, the sparse map 800 can have a data density (e.g., including data representing the target trajectories, landmarks, and any other stored road features) 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.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 no more than 10 kB per kilometer of road, or no more than 20 kB per kilometer of road. In some embodiments, most, if not all, of the United States' roadways can be navigated autonomously using a sparse map containing a total of 4 GB or less of data. These data density values ​​can represent an average over an entire sparse map 800, over a local map within the sparse map 800, and / or over a specific road segment within the sparse map 800.

[0152] As noted, the sparse map can include representations of a variety of destination trajectories for guiding autonomous driving or navigation along a road segment. Such destination trajectories can be stored as three-dimensional splines. The destination trajectories stored in the sparse map can, for example, be determined based on two or more reconstructed trajectories of previous vehicle crossings along a particular road segment. A road segment can be associated with a single destination trajectory or multiple destination trajectories. For example, on a two-lane road, a first destination trajectory can be stored to represent an intended route along the road in a first direction, and a second destination trajectory can be stored to represent an intended route along the road in another direction (e.g.,to represent the opposite direction to the first direction). Additional destination trajectories can be stored with respect to a particular road segment. For example, on a multi-lane road, one or more destination trajectories can be stored, representing intended routes for vehicles in one or more lanes associated with the multi-lane road. In some embodiments, each lane of a multi-lane road can be associated with its own destination trajectory. In other embodiments, fewer destination trajectories can be stored than there are lanes on a multi-lane road. In such cases, a vehicle navigating the multi-lane road can use any of the stored destination trajectories to guide its navigation by taking into account a quantity of lane offset from a lane for which a destination trajectory is stored (e.g.,If a vehicle is traveling in the leftmost lane of a three-lane highway and a destination trajectory is stored only for the middle lane of the highway, the vehicle can navigate using the middle lane's destination trajectory by taking into account the amount of lane offset between the middle lane and the leftmost lane when generating navigation instructions.

[0153] In some embodiments, the target trajectory can represent an ideal path a vehicle should take while driving. For example, the target trajectory might be located in the approximate center of a lane. In other cases, the target trajectory might be located elsewhere with respect to a road segment. For example, a target trajectory might coincide approximately with the center of a road, the edge of a road, or the edge of a lane, etc. In such a case, navigation based on the target trajectory might include a specific amount of offset to be maintained relative to the location of the target trajectory. Furthermore, in some embodiments, the specific amount of offset to be maintained relative to the location of the target trajectory might differ based on vehicle type (e.g.,(a two-axle passenger car may have a different offset than a truck with more than two axles along at least one section of the target trajectory).

[0154] The sparsely populated map 800 can also include data relating to a variety of predetermined landmarks 820, which are associated with specific road segments, local maps, etc. As discussed in more detail below, these landmarks can be used for navigation by the autonomous vehicle. For example, in some embodiments, the landmarks can be used to determine the vehicle's current position relative to a stored target trajectory. With this positional information, the autonomous vehicle can adjust its direction of travel to match the direction of the target trajectory at a given location.

[0155] The multitude of landmarks 820 can be identified and stored in the sparsely populated map 800 at any suitable interval. In some embodiments, landmarks can be stored at relatively high densities (e.g., every few meters or more). However, in some embodiments, significantly larger distances between landmarks can be used. For example, in the sparsely populated map 800, identified (or recognized) landmarks can be 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, the identified landmarks can even be located at distances of more than 2 kilometers apart.

[0156] Between landmarks, and therefore between determinations of the vehicle's position relative to a target trajectory, the vehicle can navigate using dead reckoning, where the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Since errors can accumulate during dead reckoning, position determinations relative to the target trajectory can become increasingly inaccurate over time. The vehicle can use landmarks that appear on the sparsely populated Chart 800 (and their known locations) to eliminate dead reckoning-induced position determination errors. In this way, the identified landmarks included on the sparsely populated Chart 800 can serve as navigation anchors from which an accurate position of the vehicle relative to a target trajectory can be determined.Since a certain degree of error in the location of the position may be acceptable, an identified landmark need not always be available to an autonomous vehicle. Rather, suitable navigation may also be possible based on landmark spacings, as noted above, of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more. In some embodiments, a density of 1 identified landmark every 1 km of road may be sufficient to maintain longitudinal positioning accuracy within 1 m. Thus, it is not necessary to store every potential landmark that appears along a road segment in the sparsely populated map 800.

[0157] Furthermore, in some embodiments, lane markings can be used to locate the vehicle during reference point intervals. Using lane markings during reference point intervals can minimize the accumulation of errors caused by dead reckoning during navigation.

[0158] In addition to destination trajectories and identified landmarks, the sparsely populated map can include 800 pieces of information relating to various other road features. For example, Fig. Figure 9A illustrates a representation of curves along a given 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. Such polynomials representing the left and right sides of a single lane are shown in Fig. 9A is shown. Regardless of how many lanes a road may have, the road can be represented using polynomials in a way that is shown in Fig. 9A is similar to the one shown. For example, the left and right sides of a multi-lane road can be defined by polynomials similar to those in Fig. 9A, and intermediate lane markings included on a multi-lane road (e.g., dashed markings representing lane boundaries, solid yellow lines representing boundaries between lanes traveling in different directions, etc.) can also be represented using polynomials, such as those shown in Fig. 9A will be shown.

[0159] As in Fig. As shown in Figure 9A, a lane 900 can be represented using polynomials (e.g., first-order, second-order, third-order, or any suitable order). For illustration, lane 900 is shown as a two-dimensional lane, and the polynomials are shown as two-dimensional polynomials. As shown in Fig. As shown in Figure 9A, lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial can be used to represent a location on each side of the 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 may be approximately 100 m long, although other lengths greater or less than 100 m may also be used. Additionally, the polynomials may overlap to facilitate seamless transitions when navigating based on subsequently encountered polynomials as a host vehicle travels along a lane.For example, each of the left side 910 and the right side 920 can be represented by a plurality of third-order polynomials separated into segments of approximately 100 meters in length (an example of the first predetermined area) that overlap each other by approximately 50 meters. The polynomials representing the left side 910 and the right side 920 may or may not be of the same order. For example, in some embodiments, some polynomials may be second-order, some third-order, and some fourth-order.

[0160] In the Fig. In the example shown in Figure 9A, the left side 910 of lane 900 is represented by two groups of third-order polynomials. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. While essentially parallel to each other, the two groups follow the locations of their respective sides of the road. Polynomial segments 911, 912, 913, 914, 915, and 916 are approximately 100 meters long and overlap adjacent segments in the sequence by about 50 meters. However, as noted earlier, polynomials of different lengths and overlap amounts can also be used. For example, the polynomials can have lengths of 500 m, 1 km or more, and the amount of overlap can vary from 0 to 50 m, 50 m to 100 m, or more than 100 m. While Fig. Figure 9A shows polynomials extending in 2D space (e.g., on the surface of the paper). It is further understood that these polynomials can represent curves extending in three dimensions (e.g., including a height component) to depict changes in elevation in a road segment in addition to the XY curvature. In the figure shown in Fig. In the example shown in 9A, the right side 920 of lane 900 is further represented by a first group with polynomial segments 921, 922 and 923 and a second group with polynomial segments 924, 925 and 926.

[0161] Regarding the target trajectories of the sparsely populated map 800, it shows Fig. 9B is a three-dimensional polynomial representing a target trajectory for a vehicle moving along a given road segment. The target trajectory represents not only the XY path a host vehicle should travel along a given road segment, but also the change in elevation the host vehicle will experience while traveling along the road segment. Thus, any target trajectory in the sparsely populated map 800 can be represented by one or more three-dimensional polynomials, such as the one in Fig. Figure 9B shows a three-dimensional polynomial 950. The sparse map 800 can include a multitude of trajectories (e.g., millions or billions or more to represent trajectories of vehicles along different road segments along highways around the world). In some embodiments, each target trajectory can correspond to a spline connecting three-dimensional polynomial segments.

[0162] Regarding the data footprint of polynomial curves stored in the sparsely populated 800 card, in some embodiments each third-degree polynomial can be represented by four parameters, each requiring four bytes of data. Suitable representations can be obtained with third-degree polynomials requiring approximately 192 bytes of data per 100 m. For a host vehicle traveling at approximately 100 km / h, this equates to about 200 kB of data consumption / transmission requirement per hour.

[0163] The sparse map 800 can describe the lane network using a combination of geometry descriptors and metadata. The geometry can be described by polynomials or splines, as described above. The metadata can describe the number of lanes, special properties (such as a carpool lane), and possibly other sparse labels. The overall footprint of such indicators can be negligible.

[0164] Accordingly, a sparse map according to embodiments of the present disclosure can include at least one line representation of a road surface feature extending along the road segment, each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as discussed above, the at least one line representation of the road surface feature can include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature can include at least one of a road edge or lane marking.Furthermore, as discussed below in relation to “crowdsourcing”, the road surface feature can be identified by image analysis of a large number of images taken when one or more vehicles cross the road segment.

[0165] As previously noted, the sparse map 800 can include a large number of predefined landmarks associated with a road segment. Instead of storing actual images of the landmarks and relying, for example, on image recognition analysis based on captured and stored images, each landmark in the sparse map 800 can be represented and recognized using less data than a stored actual image would require. Data representing landmarks can still include sufficient information to describe or identify the landmarks along a road. Storing data describing landmark properties, rather than actual images of landmarks, can reduce the size of the sparse map 800.

[0166] Fig. Figure 10 illustrates examples of landmark types that can be represented on the sparse map 800. Landmarks can include any visible and identifiable objects along a road segment. Landmarks can be selected to be fixed and not change frequently in their location and / or content. Landmarks included on the sparse map 800 can be useful in determining the location of a vehicle 200 relative to a destination trajectory as the vehicle crosses a particular road segment. Examples of landmarks may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lampposts, reflectors, etc.), and any other suitable category.In some embodiments, lane markings on the road may also be included as orientation points in the sparsely populated map 800.

[0167] Examples of the in Fig. The 10 reference points shown include traffic signs, directional signs, roadside fortifications, and general signs. Traffic signs can include, for example, speed limit signs (e.g., Speed ​​Limit Sign 1000), priority signs (e.g., Priority Sign 1005), road number signs (e.g., Road Number Sign 1010), traffic light signs (e.g., Traffic Light Sign 1015), and stop signs (e.g., Stop Sign 1020). Directional signs can include a sign containing one or more arrows indicating one or more directions to different locations. For example, directional signs can include a motorway sign 1025, which has arrows directing vehicles to different roads or locations, an exit sign 1030, which has an arrow directing vehicles from a road, and so on. Accordingly, at least one of the multiple reference points can include a road sign.

[0168] General signs do not have to be related to traffic. For example, general signs can include billboards used for advertising or a welcome sign adjacent to a border between two countries, states, counties, cities, or municipalities. Fig. Figure 10 shows a generic sign 1040 (“Joe’s Restaurant”). Although the generic sign 1040 can have a rectangular shape, as in Fig. As shown in 10, the general symbol 1040 can also have other forms, for example square, circle, triangle, etc.

[0169] Orientation points can also include roadside fixtures. Roadside fixtures can be objects that are not signs and need not be related to traffic or directions. For example, roadside fixtures can include lampposts (e.g., lamppost 1035), power line poles, traffic light poles, etc.

[0170] Navigational aids can also include beacons specifically designed for use in an autonomous vehicle's navigation system. For example, such beacons can include stand-alone structures placed at predetermined intervals to assist a host vehicle in navigating. These beacons can also incorporate visual / graphical information added to existing road signs (e.g., icons, emblems, barcodes, etc.) that can be identified or recognized by a vehicle traveling along a road segment. Furthermore, such beacons can include electronic components. In these embodiments, electronic beacons (e.g., RFID tags, etc.) can be used to transmit non-visual information to a host vehicle.Such information may include, for example, landmark identification and / or landmark location information that a host vehicle can use to determine its position along a target trajectory.

[0171] In some embodiments, the landmarks included in the sparse map 800 can be represented by a data object of a predetermined size. The data representing a landmark can include any suitable parameters for identifying a particular landmark. For example, in some embodiments, landmarks stored in the sparse map 800 can include parameters such as the physical size of the landmark (e.g., to assist in estimating the distance to the landmark based on a known size / scale), a distance to a previous landmark, lateral offset, elevation, a type code (e.g., a landmark type—what type of directional marker, traffic sign, etc.), a GPS coordinate (e.g., to assist in global localization), and any other suitable parameters.Each parameter can be associated with a data size. For example, a landmark size can be stored using 8 bytes of data. Distance to a previous landmark, lateral offset, and elevation can be specified using 12 bytes of data. A type code associated with a landmark, such as a directional sign or traffic sign, might require approximately 2 bytes of data. For generic characters, an image signature that allows identification of the generic character can be stored using 50 bytes of data. The landmark GPS position can be associated with 16 bytes of data. These data sizes for each parameter are only examples, and other data sizes can also be used.Representing landmarks in the sparsely populated 800-scale map in this manner can provide a streamlined solution for efficiently displaying landmarks in the database. In some implementations, objects can be referred to as standard semantic objects and non-standard semantic objects. A standard semantic object can include any class of objects for which there is a standardized set of properties (e.g., speed limit signs, warning signs, directional signs, traffic lights, etc., with known dimensions or other properties). A non-standard semantic object can include any object that is not associated with a standardized set of properties (e.g., generic advertising signs, signs identifying business premises, potholes, trees, etc., which may have variable dimensions).Each non-standard semantic object can be represented with 38 bytes of data (e.g., 8 bytes for size; 12 bytes for distance to a previous landmark, lateral offset, and elevation; 2 bytes for a type code; and 16 bytes for positional coordinates). Standard semantic objects can be represented using even less data, as size information may not be required by the mapping server to fully represent the object on the sparsely populated map.

[0172] The sparsely populated Map 800 can use a marker system to represent landmark types. In some cases, each traffic sign or directional sign can be associated with its own marker, which can be stored in the database as part of the landmark identification. For example, the database can include on the order of 1,000 different markers to represent various traffic signs and on the order of about 10,000 different markers to represent directional signs. Of course, any suitable number of markers can be used, and additional markers can be generated as needed. Common characters can be represented in some embodiments using fewer than about 100 bytes (e.g.,approximately 86 bytes, including 8 bytes for size; 12 bytes for distance to a previous landmark, lateral offset and height; 50 bytes for an image signature; and 16 bytes for GPS coordinates).

[0173] Thus, for semantic road signs that do not require an image signature, the data density impact on the sparsely populated Map 800, even with relatively high landmark densities of about 1 per 50 m, can be on the order of about 760 bytes per kilometer (e.g., 20 landmarks per km x 38 bytes per landmark = 760 bytes). Even for general signs that include an image signature component, the data density impact is about 1.72 kB per km (e.g., 20 landmarks per km x 86 bytes per landmark = 1,720 bytes). For semantic road signs, this equates to about 76 kB per hour of data usage for a vehicle traveling at 100 km / h. For general signs, this equates to about 170 kB per hour for a vehicle traveling at 100 km / h. It should be noted that in some environments (e.g.,in urban environments) a much higher density of detected objects may be available for inclusion in the sparse map (perhaps more than one per meter). In some embodiments, a general rectangular object, such as a rectangular character, may be represented in the sparse map 800 by no more than 100 bytes of data. The representation of the general rectangular object (e.g., the general character 1040) in the sparse map 800 may include a condensed image signature or image hash (e.g., the condensed image signature 1045) associated with the general rectangular object. This condensed image signature / image hash may, for example, be used to aid in the identification of a general character, such as a recognized landmark. Such a condensed image signature (e.g.,Image information derived from actual image data representing an object can eliminate the need to store an actual image of an object or the need for comparative image analysis performed on actual images to identify reference points.

[0174] With reference to Fig. 10. The sparsely populated card 800 can include or store a condensed image signature 1045 associated with a generic character 1040, rather than an actual image of the generic character 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of the generic character 1040, a processor (e.g., image processor 190, or any other processor capable of processing images either onboard or remotely relative to a host vehicle) can perform image analysis to extract / generate the condensed image signature 1045, which includes a unique signature or pattern associated with the generic character 1040.In one embodiment, the condensed image signature 1045 may include a shape, a color pattern, a brightness pattern or any other feature that can be extracted from the image of the generic sign 1040 to describe the generic sign 1040.

[0175] For example, in Fig. 10. The circles, triangles, and stars shown in the condensed image signature 1045 represent areas of different colors. The pattern represented by the circles, triangles, and stars can be stored in the sparse map 800, for example, within the 50 bytes designated to enclose an image signature. Specifically, the circles, triangles, and stars are not necessarily intended to indicate that such shapes are stored as part of the image signature. Rather, these shapes are intended to conceptually represent recognizable areas with recognizable color differences, text areas, graphic shapes, or other variations of properties that may be associated with a generic sign. Such condensed image signatures can be used to identify a landmark in the form of a generic sign.For example, the condensed image signature can be used to perform an equal-not-equal analysis based on a comparison of a stored condensed image signature with image data captured, for example, using a camera on board an autonomous vehicle.

[0176] Accordingly, the multitude of landmarks can be identified by image analysis of the multitude of images captured when one or more vehicles cross the road segment. As explained below with regard to "crowdsourcing," in some embodiments, the image analysis for identifying the multitude of landmarks may include accepting potential landmarks if the ratio of images in which the landmark appears to images in which it does not appear exceeds a threshold. Furthermore, in some embodiments, the image analysis for identifying the multitude of landmarks may include rejecting potential landmarks if the ratio of images in which the landmark does not appear to images in which it does appear exceeds a threshold.

[0177] Regarding the target trajectories that a host vehicle can use to navigate on a particular road segment, it shows Fig. 11A Polynomial representations of trajectories recorded during a process for creating or maintaining a sparse map 800. A polynomial representation of a target trajectory included in the sparse map 800 may be determined based on two or more reconstructed trajectories of previous vehicle crossings along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be an aggregation of two or more reconstructed trajectories of previous vehicle crossings along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be an average of the two or more reconstructed trajectories of previous vehicle crossings along the same road segment.Other mathematical operations can also be used to construct a target trajectory along a road route based on reconstructed trajectories collected from vehicles crossing along a road segment.

[0178] As in Fig. As shown in Figure 11A, a road segment 1100 can be traversed by a number of vehicles 200 at different times. Each vehicle 200 can collect data relating to a path the vehicle has taken along the road segment. The path traveled by a particular vehicle can be determined, among other potential sources, based on camera data, accelerometer information, speed sensor information, and / or GPS information. Such data can be used to reconstruct trajectories of vehicles moving along the road segment, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) for the particular road segment can be determined. Such target trajectories can represent a preferred path for a host vehicle (e.g., guided by an autonomous navigation system) when the vehicle travels along the road segment.

[0179] In the Fig. In the example shown in Figure 11A, a first reconstructed trajectory 1101 can be determined based on data received from a first vehicle crossing road segment 1100 in a first period (e.g., day 1), a second reconstructed trajectory 1102 can be obtained from a second vehicle crossing road segment 1100 in a second period (e.g., day 2), and a third reconstructed trajectory 1103 can be obtained from a third vehicle crossing road segment 1100 in a third period (e.g., day 3). Each trajectory 1101, 1102, and 1103 can be represented by a polynomial, such as a three-dimensional polynomial. It should be noted that in some embodiments, each of the reconstructed trajectories can be assembled on board the vehicles crossing road segment 1100.

[0180] Additionally or alternatively, such reconstructed trajectories can be determined on a server-side based on information received from vehicles crossing road segment 1100. For example, in some embodiments, the vehicles 200 can transmit data to one or more servers relating to their movement along road segment 1100 (e.g., steering angle, direction of travel, time, position, speed, detected road geometry, and / or detected landmarks, among others). The server can reconstruct trajectories for the vehicles 200 based on the received data. The server can also generate a target trajectory to guide the navigation of the autonomous vehicle traveling along the same road segment 1100 at a later time, based on the first, second, and third trajectories 1101, 1102, and 1103.While a target trajectory may be associated with a single previous crossing of a road segment, in some embodiments each target trajectory enclosed in the sparsely populated map 800 can be determined based on two or more reconstructed trajectories of vehicles crossing the same road segment. Fig. 11A represents the target trajectory by 1110. In some embodiments, the target trajectory 1110 can be generated based on an average of the first, second, and third trajectories 1101, 1102, and 1103. In some embodiments, the target trajectory 1110, which is enclosed in the sparse map 800, can be an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories.

[0181] On the mapping server, the server can receive actual trajectories for a given road segment from multiple collection vehicles crossing the segment. To generate a target trajectory for each valid path along the road segment (e.g., each lane, each direction of travel, each pedestrian path through an intersection, etc.), the received actual trajectories can be aligned. The alignment process can involve using detected objects / features identified along the road segment, along with the collected positions of those detected objects / features, to correlate the collected actual trajectories. Once aligned, an average or "best-fit" target trajectory for each available lane, etc., can be determined based on the aggregated, correlated / aligned actual trajectories.

[0182] Fig. 11B and Fig. Figure 11C further illustrates the concept of destination trajectories associated with road segments that exist within a geographic area 1111. As in Fig. As shown in Figure 11B, a first road segment 1120 within the geographical area 1111 can include a multi-lane road comprising two lanes 1122 designated for vehicle travel in a first direction and two additional lanes 1124 designated for vehicle travel in a second direction opposite to the first. Lanes 1122 and 1124 can be separated by a double yellow line 1123. The geographical area 1111 can also include a branch road segment 1130 intersecting road segment 1120. Road segment 1130 can include a two-lane road, with each lane designated for a different direction of travel. 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 warning sign 1138.

[0183] As in Fig. As shown in Figure 11C, the sparse map 800 can include a local map 1140, which contains a road model to support autonomous vehicle navigation within the geographic area 1111. For example, the local map 1140 can include destination trajectories for one or more lanes associated with the road segments 1120 and / or 1130 within the geographic area 1111. For example, the local map 1140 can include destination trajectories 1141 and / or 1142 that an autonomous vehicle can access or rely on when crossing lanes 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that an autonomous vehicle can access or rely on when crossing lanes 1124.Furthermore, the local map 1140 may include destination trajectories 1145 and / or 1146 that an autonomous vehicle can access or rely on when crossing road segment 1130. Destination trajectory 1147 represents a preferred path that an autonomous vehicle should follow when transitioning from lanes 1120 (and specifically relative to destination trajectory 1141, which is associated with a rightmost lane of lanes 1120) to road segment 1130 (and specifically relative to destination trajectory 1145, which is associated with a first side of road segment 1130).Similarly, the destination trajectory 1148 represents a preferred path that an autonomous vehicle should follow when transitioning from road segment 1130 (and specifically relative to the destination trajectory 1146) to a section of road segment 1124 (and specifically, as shown, relative to a destination trajectory 1143 associated with a left lane of lanes 1124).

[0184] The sparse map 800 may also include representations of other road-related features associated with the geographic area 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in the geographic area 1111. Such landmarks may include a first landmark 1150 associated with the stop line 1132, a second landmark 1152 associated with the stop sign 1134, a third landmark associated with the speed limit sign 1154, and a fourth landmark 1156 associated with the warning sign 1138.Such reference points can be used, for example, to assist an autonomous vehicle in determining its current location in relation to one of the shown target trajectories, so that the vehicle can adjust its direction of travel to correspond to a direction of the target trajectory at the specified location.

[0185] In some embodiments, the sparsely populated map 800 may also include road signature profiles. Such road signature profiles may be associated with any detectable / measurable variation in at least one parameter associated with a road. For example, in some cases, such profiles may be associated with variations in road surface information, such as variations in the surface roughness of a particular road segment, variations in the road width across a particular road segment, variations in the distances between dashed lines painted along a particular road segment, variations in the road curvature along a particular road segment, and so on. Fig. Figure 11D shows an example of a road signature profile 1160. While profile 1160 can represent any of the parameters mentioned above or others, in one example, profile 1160 can represent a measure of road surface roughness, such as that obtained by monitoring one or more sensors that provide outputs indicating an amount of suspension displacement as a vehicle travels a particular road segment.

[0186] Alternatively or simultaneously, profile 1160 can represent a variation in road width as determined based on image data obtained from a camera on board a vehicle traveling a specific road segment. Such profiles can be useful, for example, in determining a specific location of an autonomous vehicle relative to a particular target trajectory. That is, as it crosses a road segment, an autonomous vehicle can measure a profile associated with one or more parameters related to that road segment. If the measured profile can be correlated / matched with a predetermined profile representing the parameter variation with respect to position along the road segment, the measured and predetermined profiles can be used (e.g.,(by superimposing corresponding sections of the measured and predetermined profiles) to determine a current position along the road segment and therefore a current position with respect to a target trajectory for the road segment.

[0187] In some embodiments, the sparse map 800 can include different trajectories based on various characteristics associated with a user of autonomous vehicles, environmental conditions, and / or other parameters related to the journey. For example, in some embodiments, different trajectories can be generated based on different user preferences and / or profiles. The sparse map 800, which 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 others prefer to take the shortest or fastest routes, regardless of whether a toll road is present on the route.The revealed systems can generate different sparsely populated maps with different trajectories based on such differing user preferences or profiles. As another example, some users may prefer to drive in a fast-moving lane, while others prefer to maintain a position in the center lane at all times.

[0188] Based on varying environmental conditions, such as day and night, snow, rain, fog, etc., different trajectories can be generated and included in the sparse map 800. For autonomous vehicles operating under these varying environmental conditions, a sparse map 800 generated based on these conditions can be provided. In some embodiments, cameras mounted on autonomous vehicles can detect environmental conditions and transmit this information back to a server that generates and provides sparse maps. For example, the server can generate or update an existing sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions.The update of the sparsely populated map 800 based on environmental conditions can be performed dynamically while the autonomous vehicles are driving on roads.

[0189] Other different parameters related to driving can also be used as a basis for generating and providing various sparse maps for different autonomous vehicles. For example, if an autonomous vehicle is traveling at high speed, turns may be tighter. Trajectories associated with specific lanes, rather than roads, can be included in the sparse map 800, allowing the autonomous vehicle to remain within a specific lane while following a specific trajectory. If an image captured by an onboard camera of the autonomous vehicle indicates that the vehicle has drifted out of its lane (e.g., crossed the lane marking), an action can be triggered within the vehicle to guide it back into the designated lane according to the specific trajectory. Crowdsourcing a sparsely populated map

[0190] The disclosed sparse maps can be efficiently (and passively) generated through the power of crowdsourcing. For example, any private or commercial vehicle equipped with a camera (e.g., a simple, low-resolution camera, often included as original equipment in modern vehicles) and a suitable image analysis processor can serve as a data collection vehicle. No specialized equipment (e.g., high-resolution imaging and / or positioning systems) is required. As a result of the disclosed crowdsourcing technique, the generated sparse maps can be extremely accurate and include highly refined positional information (enabling navigation error limits of 10 cm or less) without requiring any specialized imaging or scanning equipment as input for the map generation process.Crowdsourcing also enables much faster (and more cost-effective) updates to the generated maps, as the mapping server system constantly receives new driving data from all roads crossed by private or commercial vehicles that are minimally equipped to also serve as collection vehicles. There is no need for specialized vehicles equipped with high-resolution imaging and mapping sensors. Therefore, the costs associated with building such specialized vehicles can be avoided.Furthermore, updates to the sparsely populated maps disclosed herein can be carried out much faster than with systems that rely on dedicated, specialized mapping vehicles (which, due to their cost and specialized equipment, are typically limited to a fleet of specialized vehicles, the number of which is far below the number of private or commercial vehicles already available for carrying out the disclosed collection techniques).

[0191] The resulting sparsely populated maps, generated through crowdsourcing, can be extremely accurate because they are based on input from numerous (tens, hundreds, millions, etc.) collection vehicles that have gathered driving data along a specific road segment. For example, each collection vehicle traveling along a particular road segment can record its actual trajectory and determine positional information relative to detected objects / features along the road segment. This information is then relayed from multiple collection vehicles to a server. The actual trajectories are aggregated to generate a refined target trajectory for each valid route along the road segment.Additionally, the positional information collected by the multiple survey vehicles for each detected object / feature along the road segment (semantic or non-semantic) can also be aggregated. As a result, the mapped position of each detected object / feature can be an average of hundreds, thousands, or millions of individually determined positions for that object / feature. Such a technique can provide extremely accurate mapped positions for the detected objects / features.

[0192] In some embodiments, the disclosed systems and methods can generate a sparse map for autonomous vehicle navigation. For example, 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 a road segment at different times, and such data is used to generate and / or update the road model, including sparse map tiles. The model, or any of its sparse map tiles, can then be transmitted to the vehicles or other vehicles that subsequently travel along the road segment to assist autonomous vehicle navigation.The road model can include a variety of target trajectories, which represent preferred trajectories that autonomous vehicles should follow when crossing a road segment. The target trajectories can be the same as a reconstructed actual trajectory collected from a vehicle crossing a road segment, which the vehicle can transmit to a server. In some embodiments, the target trajectories can differ from actual trajectories taken by one or more vehicles previously crossing a road segment. The target trajectories can be generated based on actual trajectories (e.g., by averaging or any other suitable operation).

[0193] The vehicle trajectory data that a vehicle can upload to a server can correspond to the actual reconstructed trajectory for the vehicle, or it can correspond to a recommended trajectory, which may be based on or referencing the vehicle's actual reconstructed trajectory, but may differ from it. 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 then use the recommended modified trajectories as target trajectories for autonomous navigation by other vehicles.

[0194] In addition to trajectory information, other information for potential use in creating a sparse data map may include information relating to potential landmark candidates. For example, the disclosed systems and methods can identify potential landmarks in an environment and refine landmark positions by crowdsourcing information. The landmarks can be used by an autonomous vehicle navigation system to determine and / or adjust the vehicle's position along the target trajectories.

[0195] The reconstructed trajectories that a vehicle can generate while traveling along a road can be obtained by any suitable method. In some embodiments, the reconstructed trajectories can be developed by piecing together motion segments for the vehicle using, for example, self-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 the analysis of images acquired by one or more image acquisition devices, together with information from other sensors or devices, such as inertial and velocity sensors.For example, the inertial sensors may include an accelerometer or other suitable sensors configured to measure changes in the translation and / or rotation of the vehicle body. The vehicle may also include a speed sensor that measures the vehicle's speed.

[0196] In some embodiments, the camera's own motion (and thus the vehicle body's motion) can be estimated based on an optical flow analysis of the captured images. An optical flow analysis of an image sequence identifies the motion of pixels within the sequence and, based on this identified motion, determines the vehicle's movements. The camera's own motion can be integrated over time and along the road segment to reconstruct a trajectory associated with the road segment the vehicle followed.

[0197] Data (e.g., reconstructed trajectories) collected from multiple vehicles traveling along a road segment at different times over multiple trips can be used to construct the road model (e.g., including destination trajectories, etc.) contained in the sparse data map 800. Data collected from multiple vehicles traveling along a road segment at different times over multiple trips can also be averaged to improve model accuracy. In some embodiments, data relating to road geometry and / or landmarks can be received from multiple vehicles traveling through the common road segment at different times. Such data received from different vehicles can be combined to generate and / or update the road model.

[0198] The geometry of a reconstructed trajectory (and also a 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 from the analysis of a video stream or a multitude of images captured by a camera mounted on the vehicle. In some embodiments, a location a few meters ahead of the vehicle's current position is identified in each frame or image. This location is where the vehicle is expected to travel within a predetermined timeframe. This operation can be repeated frame by frame, and simultaneously, the vehicle can calculate the camera's own motion (rotation and translation).For each individual frame or image, a close-range model of the desired path from the vehicle is generated within a reference frame attached to the camera. These close-range models can be combined to obtain a three-dimensional model of the road within a coordinate frame, which can be any or a predefined coordinate frame. The three-dimensional road model can then be fitted by a spline, which can enclose or connect one or more polynomials of suitable orders.

[0199] To complete the near-field road model for each frame, one or more detection modules can be used. For example, a ground-to-top lane detection module can be employed. This module is useful when lane markings are drawn on the road. It can search for edges in the image and join them together to form the lane markings. A second module can be used in conjunction with the ground-to-top lane detection module. This second module is a deep end-to-end neural network that can be trained to predict the correct near-field path from an 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.

[0200] Although the reconstructed trajectory modeling method may introduce an accumulation of errors due to the integration of self-motion over a long period, which may include a noise component, such errors may be insignificant because the generated model can provide sufficient accuracy for navigation over a local scale. Additionally, it is possible to eliminate the integrated error by using external information sources, such as satellite imagery or geodetic measurements. For example, the disclosed systems and methods can use a GNSS receiver to eliminate accumulated errors. However, GNSS positioning signals may not always be available or accurate. The disclosed systems and methods can enable a steering application that is weakly dependent on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be limited.For example, in some embodiments of the disclosed systems, the GNSS signals can be used only for database indexing purposes.

[0201] In some embodiments, the range scale (e.g., local scale) relevant for autonomous vehicle navigation may be on the order of 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances can be used because the geometric road model is primarily used for two purposes: planning the ahead trajectory and locating the vehicle on the road model. In some embodiments, the planning task may utilize the model over a typical range of 40 meters ahead (or another suitable distance, such as 20 meters, 30 meters, 50 meters) when the control algorithm steers the vehicle toward a target point located 1.3 seconds ahead (or another time interval, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.).The localization task uses the road model over a typical range of 60 meters behind the car (or any other suitable distances, such as 50 meters, 100 meters, 150 meters, etc.) according to a procedure called "tail alignment," which is described in more detail in another section. The disclosed systems and methods can generate a geometric model that has sufficient accuracy over a given range, such as 100 meters, so that a planned trajectory does not deviate from the lane centerline by more than, for example, 30 cm.

[0202] As explained above, a three-dimensional road model can be constructed from detecting short-range segments and stitching them together. Stitching can be achieved by calculating a six-degree self-motion model using the video and / or image data captured by the camera, data from the inertial sensors reflecting the vehicle's movements, and the host vehicle's velocity signal. The accumulated error can be scaled up over a local range, on the order of… 100 meters, small enough. All this can be completed in a single trip over a specific road segment.

[0203] In some embodiments, multiple trips can be used to average the resulting model and further increase its accuracy. The same car can drive the same route multiple times, or multiple cars can send their collected model data to a central server. In either case, a matching process can be performed to identify overlapping models and allow averaging to generate target trajectories. The constructed model (e.g., including the target trajectories) can be used for steering once a convergence criterion is met. Subsequent trips can be used for further model improvements and to adapt to infrastructure changes.

[0204] Sharing driving experience (such as captured data) between multiple cars becomes feasible when they are connected to a central server. Each vehicle client can store a partial copy of a universal road model that may be relevant to its current position. A bidirectional update process between the vehicles and the server can be performed by both the vehicles and the server. The small footprint concept discussed above enables the disclosed systems and methods to perform the bidirectional updates using very little bandwidth.

[0205] Information relating to potential landmarks can also be determined and forwarded to a central server. For example, the disclosed systems and methods can determine one or more physical properties of a potential landmark based on one or more images that include the landmark. The physical properties can include the landmark's physical size (e.g., height, width), the distance from a vehicle to the landmark, the distance between the landmark and a previous landmark, the landmark's lateral position (e.g., the landmark's position relative to the lane), the landmark's GPS coordinates, the landmark's type, identification of text on the landmark, and so on.For example, a vehicle can analyze one or more images captured by a camera to detect a potential landmark, such as a speed limit sign.

[0206] The vehicle can determine a distance from the vehicle to the landmark or a position associated with the landmark (e.g., any semantic or non-semantic object or feature along a road segment) based on the analysis of one or more images. In some embodiments, the distance can be determined based on the analysis of images of the landmark using a suitable image analysis technique, such as a scaling technique and / or an optical flow technique. As noted previously, the position of the object / feature can include a 2D image position (e.g., an XY pixel position in one or more captured images) of one or more points associated with the object / feature, or it can include a real 3D position of one or more points (e.g., determined by structure-in-motion techniques / optical flow techniques, LiDAR or radar information, etc.).) include. In some embodiments, the disclosed systems and methods can be configured to determine a type or classification of a potential landmark. If the vehicle determines that a particular potential landmark corresponds to a predetermined type or classification stored in a sparse map, it may be sufficient for the vehicle to communicate an indication of the landmark's type or classification, along with its location, to the server. The server can store such information. At a later time, during navigation, a navigating vehicle can acquire an image that includes a representation of the landmark, process the image (e.g.,(using a classifier) ​​and compare the resulting landmark to confirm the detection of the mapped landmark and use the mapped landmark in locating the navigating vehicle relative to the sparsely populated map.

[0207] 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 journey (e.g., through self-motion integration) within any given coordinate frame. The vehicles can detect landmarks and locate them within the same frame. The vehicles can upload the curve and the landmarks to the server. The server can collect data from vehicles across multiple journeys and generate a unified road model. For example, as described below with respect to Fig. As discussed in section 19, the server can generate a sparsely populated map using the uniform road model and the uploaded curves and landmarks.

[0208] The server can also distribute the model to clients (e.g., vehicles). For example, the server can distribute the sparsely populated map to one or more vehicles. The server can continuously or periodically update the model when it receives new data from the vehicles. For example, the server can process the new data to assess whether the data includes information that should trigger an update or the creation of new data on the server. The server can then distribute the updated model or updates to the vehicles to provide autonomous vehicle navigation.

[0209] The server can use one or more criteria to determine whether new data received from vehicles should trigger a model update or the creation of new data. For example, if the new data indicates that a previously recognized landmark at a particular location no longer exists or has been replaced by another landmark, the server can determine that the new data should trigger a model update. As another example, if the new data indicates that a road segment has been closed, and this is confirmed by data received from other vehicles, the server can determine that the new data should trigger a model update.

[0210] The server can distribute the updated model (or the updated portion of the model) to one or more vehicles traveling on the road segment associated with the model updates. The server can also distribute the updated model to vehicles about to travel on the road segment, or to vehicles whose planned route includes the road segment associated with the model updates. For example, while an autonomous vehicle is traveling along another road segment before reaching the road segment associated with an update, the server can distribute the updates or the updated model to the autonomous vehicle before it reaches the road segment.

[0211] In some embodiments, the remote server can collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a shared road segment). The server can match curves using landmarks and create an average road model based on the trajectories collected from the multiple vehicles. The server can also compute a graphic of roads and the most probable path at each node or in conjunction with the road segment. For example, the remote server can align the trajectories to generate a sparsely populated crowdsourced map from the collected trajectories.

[0212] The server can average landmark properties received from multiple vehicles traveling along the shared road segment, such as the distances between one landmark and another (e.g., a previous one along the road segment), as measured by multiple vehicles, to determine an arc length parameter and support path localization and speed calibration for each client vehicle. The server can average the physical dimensions of a landmark, measured by multiple vehicles traveling along the shared road segment, and recognize the same landmark. The averaged physical dimensions can be used to support distance estimation, such as the distance from the vehicle to the landmark. The server can also determine the lateral position of a landmark (e.g.,The server can average the GPS coordinates of the landmark (measured by multiple vehicles traveling along the same road segment) from the lane in which vehicles are traveling to the landmark, and identify the same landmark. The averaged lateral position can be used to assist with lane assignment. The server can also average the GPS coordinates of the landmark, measured by multiple vehicles traveling along the same road segment, and identify the same landmark. The averaged GPS coordinates of the landmark can be used to assist with global localization or positioning of the landmark in the road model.

[0213] In some embodiments, the server can identify model changes, such as constructions, detours, new characters, character removals, etc., based on data received from the vehicles. The server can update the model continuously, periodically, or immediately upon receiving new data from the vehicles. The server can distribute updates to the model, or the updated model, to vehicles to provide autonomous navigation. For example, as discussed further below, the server can use crowdsourced data to filter out "ghost" waypoints that are detected by vehicles.

[0214] In some embodiments, the server can analyze driver interventions during autonomous driving. The server can analyze data received from the vehicle at the time and location of the intervention, and / or data received prior to the intervention. The server can identify specific parts of the data that caused the intervention or are closely related to it, for example, data indicating a temporary lane closure device or data indicating a pedestrian 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.

[0215] Fig. Figure 12 shows a schematic illustration of a system that uses crowdsourcing to generate a sparse map (as well as to distribute and navigate using a sparse crowdsourcing map). Fig. Figure 12 shows a road segment 1200 that includes one or more lanes. A variety of vehicles 1205, 1210, 1215, 1220, and 1225 can travel on road segment 1200 simultaneously or at different times (although in Fig. Figure 12 shows that they appear simultaneously on road segment 1200. At least one of the vehicles 1205, 1210, 1215, 1220, and 1225 can be an autonomous vehicle. For the sake of simplicity, it is assumed that all vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0216] Each vehicle can be similar to vehicles disclosed in other embodiments (e.g., vehicle 200) and can include components or devices that are included in or associated with 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 over one or more networks (e.g., over a cellular network and / or the Internet, etc.) via wireless communication paths 1235, as indicated by the dashed lines. Each vehicle can transmit data to and receive data from the server 1230.For example, Server 1230 can collect data from multiple vehicles traveling on road segment 1200 at different times and process the collected data to generate a road navigation model of the autonomous vehicle or an update to the model. Server 1230 can transmit the road navigation model of the autonomous vehicle or the model update to the vehicles that transmitted data to Server 1230. Server 1230 can also transmit the road navigation model of the autonomous vehicle or the model update to other vehicles traveling on road segment 1200 at later times.

[0217] When vehicles 1205, 1210, 1215, 1220, and 1225 are traveling on road segment 1200, navigation information collected (e.g., detected, captured, 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 a trajectory associated with each of vehicles 1205, 1210, 1215, 1220, and 1225 as each vehicle travels along road segment 1200. In some embodiments, the trajectory can be reconstructed based on data acquired by various sensors and devices provided on vehicle 1205.For example, the trajectory can be reconstructed based on at least one of the following: accelerometer data, velocity data, landmark data, road geometry or profile data, vehicle positioning data, and self-motion data. In some embodiments, the trajectory can be reconstructed based on data from inertial sensors, such as accelerometers, and the vehicle's velocity 1205, as detected by a velocity sensor. Additionally, in some embodiments, the trajectory can be determined based on detected self-motion of the camera (e.g., by a processor on board each of the vehicles 1205, 1210, 1215, 1220, and 1225), which can indicate three-dimensional translation and / or three-dimensional rotations (or rotational movements). The self-motion of the camera (and thus the vehicle body) can be determined from the analysis of one or more images captured by the camera.

[0218] In some embodiments, the trajectory of the vehicle 1205 can be determined by a processor provided on board the vehicle 1205 and transmitted to the server 1230. In other embodiments, the server 1230 can receive data acquired by the various sensors and devices provided in the vehicle 1205 and determine the trajectory based on the data received from the vehicle 1205.

[0219] In some embodiments, the navigation information transmitted by vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 may include data relating to the road surface, road geometry, or road profile. The geometry of road segment 1200 may include a lane structure and / or landmarks. The lane structure may include the total number of lanes in road segment 1200, the type of lanes (e.g., one-way, two-way, lane, passing lane, etc.), lane markings, lane width, and so on. In some embodiments, the navigation information may include a lane assignment, such as which lane a vehicle is traveling in out of a number of lanes. For example, the lane assignment may be associated with a numerical value "3," indicating that the vehicle is traveling in the third lane from the left or right.As another example, the lane assignment can be associated with a text value "middle lane", indicating that the vehicle is driving in the middle lane.

[0220] The Server 1230 can store the navigation information on a non-volatile, computer-readable medium, such as a hard disk, a compact disc, a tape, a memory, etc. The Server 1230 can (e.g., through a processor enclosed within the Server 1230) generate at least one section of a road navigation model of the autonomous vehicle for the common road segment 1200 based on the navigation information received from the multitude of vehicles 1205, 1210, 1215, 1220, and 1225, and can store the model as a section of a sparse map. Server 1230 can 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 on a lane of the road segment at different times.Server 1230 can generate the autonomous vehicle's road navigation model, or a portion thereof (e.g., an updated portion), based on a variety of trajectories determined from crowdsourced navigation data. Server 1230 can then transmit the model, or the updated portion thereof, to one or more autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or to any other autonomous vehicles traveling on the road segment at a later time, to update an existing autonomous vehicle road navigation model stored in the vehicles' navigation systems. The autonomous vehicle's road navigation model can then be used by the autonomous vehicles while navigating autonomously along the shared road segment 1200.

[0221] As explained above, the autonomous vehicle's road navigation model can be used in a sparsely populated map (e.g., the one in Fig. The sparse map 800 shown in Figure 8 may be included. The sparse map 800 may include a sparse record of data relating to road geometry and / or landmarks along a road, which can provide sufficient information to guide the autonomous navigation of an autonomous vehicle, but does not require excessive data storage. In some embodiments, the autonomous vehicle's road navigation model may be stored separately from the sparse map 800 and may use map data from the sparse map 800 when the model is executed for navigation.In some embodiments, the autonomous vehicle's road navigation model can use map data included in the sparse map 800 to determine target trajectories along road segment 1200 to guide the autonomous navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles, subsequently traveling along road segment 1200. For example, if the autonomous vehicle's road navigation model is executed by a processor included in a navigation system of vehicle 1205, the model can cause the processor to compare the trajectories determined based on navigation information received from vehicle 1205 with predetermined trajectories contained in the sparse map 800 to validate and / or correct the current driving path of vehicle 1205.

[0222] In the autonomous vehicle's road navigation model, the geometry of a road feature or destination 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 connecting three-dimensional polynomials. As a person skilled in the art would understand, a spline can be a numerical function defined piecewise by a series of polynomials for fitting data. A spline for fitting the three-dimensional geometry data of the road can include a linear spline (first order), a quadratic spline (second order), a cubic spline (third order), or any other splines (other orders), or a combination thereof. The spline can include one or more three-dimensional polynomials of different orders that connect (e.g., fit) data points of the three-dimensional geometry data of the road.In some embodiments, the autonomous vehicle's road navigation model may 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.

[0223] As explained above, the autonomous vehicle's road navigation model, contained 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) installed on each of the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 can capture an image of a 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 identification information for the landmark. The landmark identification information can be stored in the sparse map 800 instead of an actual image of the landmark.The landmark identification information can require far less storage space than an actual image. Other sensors or systems (e.g., a GPS system) can also provide certain landmark identification information (e.g., the landmark's position). The landmark can include at least one traffic sign, arrow marking, lane marking, dashed lane marking, traffic light, stop line, directional sign (e.g., a highway exit sign with an arrow indicating a direction, a highway sign with arrows pointing in different directions or locations), a landmark beacon, or a lamppost. A landmark beacon refers to a device (e.g., a marker or signpost) that is positioned to indicate the direction of travel.an RFID device) installed along a road segment that transmits or reflects a signal to a receiver installed on a vehicle, so that when the vehicle passes the device, the beacon received by the vehicle and the location of the device (e.g. determined from the GPS location of the device) can be used as a reference point to be included in the autonomous vehicle's road navigation model and / or the sparse map 800.

[0224] The identification of at least one landmark can include the position of that landmark. The position of the landmark can be determined based on position measurements taken using sensor systems (e.g., global positioning systems, inertial positioning systems, landmark beacons, etc.) associated with the plurality of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the position of the landmark can be determined by averaging the position measurements detected, collected, or received by sensor systems on various vehicles 1205, 1210, 1215, 1220, and 1225 over multiple journeys.For example, vehicles 1205, 1210, 1215, 1220, and 1225 can transmit position measurement data to server 1230, which can average the position measurements and use the averaged position measurement as the position of the reference point. The position of the reference point can be continuously refined by measurements received from vehicles on subsequent journeys.

[0225] The identification of a landmark can include its size. The processor deployed on a vehicle (e.g., 1205) can estimate the physical size of the landmark based on image analysis. Server 1230 can receive multiple estimates of the physical size of the same landmark from different vehicles over different trips. Server 1230 can average these estimates to arrive at a physical size for the landmark and store this landmark size in the road model. This physical size estimate can then be used to determine or estimate the distance from the vehicle to the landmark.The distance to the landmark can be estimated based on the current speed of the vehicle and an extension scale based on the position of the landmark as it appears in the images, relative to the camera's extension focus. For example, the distance to the landmark can be estimated by Z = V*dt*R / D, where V is the speed of the vehicle, R is the distance in the image from the landmark at time t1 to the extension focus, and D is the change in distance for the landmark in the image from t1 to t2, where dt represents (t2-t1). Alternatively, the distance to the landmark can be estimated by Z = V*dt*R / D, where V is the speed of the vehicle, R is the distance in the image between the landmark and the extension focus, dt is a time interval, and D is the image shift of the landmark along the epipolar line.Other equations analogous to the one above, such as Z = V * w / Aw, can be used to estimate the distance to the reference point. Here, V is the vehicle speed, ω is an image length (like the object width), and Δω is the change in this image length per unit of time.

[0226] If the physical size of the reference point is known, the distance to the reference point can also be determined based on the following equation: Z = f * W / ω, where f is the focal length, W is the size of the reference point (e.g., height or width), and ω is the number of pixels when the reference point leaves the image. From the above equation, a change in the distance Z can be calculated using ΔZ = f * W * Δω / ω² + f * ΔW / ω, where ΔW decays to zero by averaging and Δω is the number of pixels representing a bounding frame accuracy in the image. A value that estimates the physical size of the reference point can be calculated by averaging multiple observations on the server side. The resulting error in the distance estimation can be very small. There are two sources of error that can occur when using the above formula: ΔW and Δω.Their contribution to the distance error is given by ΔZ = f * W * Δω / ω² + f * ΔW / ω. However, ΔW averages out to zero; therefore, ΔZ is determined by Δω (e.g., the inaccuracy of the bounding frame in the image).

[0227] For landmarks of unknown dimensions, the distance to the landmark can be estimated by tracking feature points on the landmark between successive frames. For example, certain features appearing on a speed limit sign can be tracked between two or more frames. Based on these tracked features, a distance distribution per feature point can be generated. The distance estimate can then be extracted from this distance distribution. For example, the most frequent distance appearing in the distance distribution can be used as the distance estimate. Alternatively, the average of the distance distribution can be used as the distance estimate.

[0228] Fig. Figure 13 illustrates an exemplary road navigation model of the autonomous vehicle, represented by a multitude of three-dimensional splines 1301, 1302, and 1303. The in Fig. The curves 1301, 1302, and 1303 shown in Figure 13 are for illustrative purposes only. Each spline can enclose one or more three-dimensional polynomials connecting a plurality of 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 by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 can be associated with data relating to landmarks (e.g., size, location, and identification information of landmarks) and / or road signature profiles (e.g., road geometry, road roughness profile, road curvature profile, road width profile).In some embodiments, some data points 1310 may be associated with data relating to landmarks, and others may be associated with data relating to road signature profiles.

[0229] Fig. Figure 14 illustrates raw location data 1410 (e.g., GPS data) received from five separate journeys. A journey can be considered separate from another journey if it was traversed simultaneously by separate vehicles, at separate times by the same vehicle, or at separate times by separate vehicles. To account for errors in the location data 1410 and for different locations of vehicles within the same lane (e.g., one vehicle may be closer to the left side of a lane than another), the server 1230 can generate a map skeleton 1420 using one or more statistical techniques to determine whether variations in the raw location data 1410 represent actual discrepancies or statistical errors. Each path within the skeleton 1420 can be linked back to the raw data 1410 that formed the path.For example, the path between A and B within skeleton 1420 is linked to the raw data 1410 from trips 2, 3, 4, and 5, but not from trip 1. Skeleton 1420 may not be detailed enough to be used to navigate a vehicle (e.g., because it combines trips from multiple lanes on the same road, unlike the splines described above), but it can provide useful topological information and can be used to define intersections.

[0230] Fig. Figure 15 illustrates an example by which additional details can be generated for a sparsely populated map within a segment of a map skeleton (e.g., segment A to B within skeleton 1420). As in Fig. As shown in Figure 15, the data (e.g., self-motion data, road marking data, and the like) can be shown as a function of position S (or S1 or S2) along the trip. Server 1230 can identify landmarks for the sparsely populated map by identifying unique matches between landmarks 1501, 1503, and 1505 of trip 1510 and landmarks 1507 and 1509 of trip 1520. Such a matching algorithm can lead to the identification of landmarks 1511, 1513, and 1515. However, a person skilled in the art would recognize that other matching algorithms can be used. For example, probability optimization can be used instead of, or in combination with, a unique match. Server 1230 can align the trips longitudinally to align the matched landmarks. For example, Server 1230 can align a trip (e.g.,Select ride 1520) as a reference ride and then move and / or elastically stretch the other ride(s) (e.g. ride 1510) for alignment.

[0231] Fig. Figure 16 shows an example of aligned landmark data for use in a sparsely populated map. In the example of Fig. The landmark 1610 includes a street sign. The example of Fig. Item 16 also presents data from a large number of journeys: 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the example of Fig. 16. The data from trip 1613 consists of a "ghost" landmark, and Server 1230 can identify it as such because none of trips 1601, 1603, 1605, 1607, 1609, and 1611 include an identification of a landmark near the identified landmark in trip 1613. Accordingly, Server 1230 can accept potential landmarks if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or reject potential landmarks if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0232] Fig. 17 presents a System 1700 for generating travel data, which can be used to crowdsource a sparsely populated map. As in Fig. As shown in Figure 17, the system 1700 can include a camera 1701 and a localization device 1703 (e.g., a GPS position transmitter). The camera 1701 and the localization device 1703 can be mounted on a vehicle (e.g., one of the vehicles 1205, 1210, 1215, 1220, and 1225). The camera 1701 can generate a variety of data of several types, such as self-motion data, traffic sign data, road data, or the like. The camera data and location data can be segmented into trip segments 1705. For example, each trip segment 1705 can contain camera data and location data for a trip of less than 1 km.

[0233] In some embodiments, the system 1700 can eliminate redundancies in the driving segments 1705. For example, if a landmark appears in multiple images from camera 1701, the system 1700 can remove the redundant data so that the driving segments 1705 contain only one copy of the location and any metadata relating to the landmark. As another example, if a lane marking appears in multiple images from camera 1701, the system 1700 can remove the redundant data so that the driving segments 1705 contain only one copy of the location and any metadata relating to the lane marking.

[0234] System 1700 also includes a server (e.g., server 1230). Server 1230 can receive trip segments 1705 from the vehicle and recombine these segments into a single trip 1707. This arrangement can reduce bandwidth requirements when transferring data between the vehicle and the server, while also allowing the server to store data relating to an entire trip.

[0235] Fig. 18 represents the system 1700 from Fig. 17, which is further configured for crowdsourcing a sparsely populated map. As in Fig. 17. System 1700 includes vehicle 1810, which records driving data, for example, using a camera (which produces, for example, self-motion data, traffic sign data, road data, or the like) and a localization device (e.g., a GPS position transmitter). As in Fig. 17. The vehicle 1810 segments the collected data into journey segments (represented as “DS1 1”, “DS2 1”, “DSN 1” in Fig. 18.) Server 1230 then receives the trip segments and reconstructs a trip (represented as "Trip 1" in Fig. 18) from the received segments.

[0236] As further in Fig. As shown in Figure 18, the system 1700 also receives data from additional vehicles. For example, vehicle 1820 also collects driving data, for instance, using a camera (which generates, for example, self-motion data, traffic sign data, road data, or the like) and a localization device (e.g., a GPS position transmitter). Similar to vehicle 1810, vehicle 1820 segments the collected data into driving segments (represented as "DS1 2", "DS2 2", "DSN 2" in Figure 18). Fig. 18). Server 1230 then receives the trip segments and reconstructs a trip (represented as "Trip 2" in Fig. 18) from the received segments. Any number of additional vehicles can be used. For example, includes Fig. 18 also “AUTO N”, which records journey data and segments it into journey segments (represented as “DS1 N”, “DS2 N”, “DSN N” in Fig. 18) and sends it to server 1230 for reconstruction into a drive (represented as "drive N" in Fig. 18).

[0237] As in Fig. As shown in 18, server 1230 can construct a sparsely populated map (represented as "MAP") using the reconstructed journeys (e.g., "Journey 1", "Journey 2", and "Journey N") collected by a variety of vehicles (e.g., "CAR 1" (also referred to as Vehicle 1810), "CAR 2" (also referred to as Vehicle 1820), and "CAR N").

[0238] Fig. Figure 19 shows a flowchart illustrating an example of Process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 can be performed by one or more processing devices enclosed in Server 1230.

[0239] Process 1900 can include receiving a multitude of images captured as one or more vehicles cross the road segment (step 1905). Server 1230 can receive images from cameras located in one or more of the vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 can capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 can also receive remote image data that exhibits redundancies eliminated by a processor on vehicle 1205, as described above in relation to Fig. 17 described.

[0240] Process 1900 can further include identifying, based on the plurality of images, at least one line representation of a road surface feature extending along the road segment (step 1910). Each line representation can represent a path along the road segment that substantially corresponds to the road surface feature. For example, Server 1230 can analyze the environmental images received from Camera 122 to identify a road edge or lane marking and determine a driving trajectory along the road segment 1200 associated with the road edge or lane marking. In some embodiments, the trajectory (or line representation) can include a spline, a polynomial representation, or a curve. Server 1230 can determine the driving trajectory of the vehicle 1205 based on camera intrinsic movements (e.g.,three-dimensional translation and / or three-dimensional rotational movements) are determined, which are received at step 1905.

[0241] Process 1900 can also include identifying, based on the multitude of images, a multitude of landmarks associated with the road segment (step 1910). For example, server 1230 can analyze the environmental images received from camera 122 to identify one or more landmarks, such as the road sign along road segment 1200. Server 1230 can identify the landmarks using the analysis of the multitude of images captured when one or more vehicles cross the road segment. To enable crowdsourcing, the analysis can include rules regarding the acceptance and rejection of potential landmarks associated with the road segment.For example, the analysis may include accepting potential landmarks if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting potential landmarks if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0242] Process 1900 may include other operations or steps performed by Server 1230. For example, the navigation information may include a destination trajectory for vehicles to travel along a road segment, and Process 1900 may include Server 1230 clustering vehicle trajectories relating to multiple vehicles traveling on the road segment and determining the destination trajectory based on the clustered vehicle trajectories, as discussed in more detail below. Vehicle trajectory clustering may involve Server 1230 grouping multiple trajectories relating to vehicles traveling on the road segment into a multitude of clusters based on at least one of the vehicles' absolute direction of travel or their lane assignment.Generating the target trajectory can include averaging the clustered trajectories by server 1230. As another example, process 1900 can include aligning data received in step 1905. Other processes or steps performed by server 1230, as described above, can also be included in process 1900.

[0243] 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, latitude and longitude coordinates on the Earth's surface may be used. To use the map for steering, the host vehicle may determine its position and orientation relative to the map. It seems natural to use an onboard GPS device to position the vehicle on the map and to find the rotational transformation between the vehicle's body reference frame and the world reference frame (e.g., north, east, and down). Once the vehicle's body reference frame is aligned with the map reference frame, the desired route can be expressed in the vehicle's body reference frame, and the steering commands can be calculated or generated.

[0244] The disclosed systems and methods can enable autonomous vehicle navigation (e.g., steering control) using low-footprint models that can be collected by the autonomous vehicles themselves without the need for expensive surveying equipment. To support autonomous navigation (e.g., steering applications), the road model can include a sparse map containing the road geometry, its lane structure, and landmarks, which can be used to determine the location or position of vehicles along a trajectory contained in the model. As discussed above, the generation of the sparse map can be performed by a remote server that communicates with and receives data from vehicles traveling on the road.The data can include captured data, trajectories reconstructed based on the captured data, and / or recommended trajectories, which may represent modified reconstructed trajectories. As discussed below, the server can transmit the model back to the vehicles or other vehicles later driving on the road to support autonomous navigation.

[0245] Fig. Figure 20 illustrates a block diagram of Server 1230. Server 1230 can include a Communication Unit 2005, which can include both hardware components (e.g., communication control circuits, switches, and antenna) and software components (e.g., communication protocols, computer code). For example, Communication Unit 2005 can include at least one network interface. Server 1230 can communicate with Vehicles 1205, 1210, 1215, 1220, and 1225 via Communication Unit 2005. For example, Server 1230 can receive navigation information transmitted by Vehicles 1205, 1210, 1215, 1220, and 1225 via Communication Unit 2005. Server 1230 can distribute the autonomous vehicle's road navigation model to one or more autonomous vehicles via Communication Unit 2005.

[0246] The Server 1230 can include at least one non-volatile storage medium 2010, such as a hard disk, a compact disc, a tape, etc. The storage device 1410 can be configured to store data such as navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225 and / or the autonomous vehicle's road navigation model, which the Server 1230 generates based on the navigation information. The storage device 2010 can be configured to store any other information, such as a sparse map (e.g., the sparse map 800 described above in relation to Fig. 8 was discussed).

[0247] In addition to or instead of the storage device 2010, the server 1230 may include a memory 2015. The memory 2015 may be similar to or different from the memory 140 or 150. The memory 2015 may be non-volatile memory, such as flash memory, random access memory, etc. The memory 2015 may be configured to store data such as computer code or instructions executable by a processor (e.g., the processor 2020), map data (e.g., data from the sparse map 800), the autonomous vehicle's road navigation model, and / or navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225.

[0248] Server 1230 can include at least one Processing Device 2020 configured to execute computer code or instructions stored in Memory 2015 to perform various functions. For example, Processing Device 2020 can analyze the navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and generate the autonomous vehicle's road navigation model based on this analysis. Processing Device 2020 can control Communication Unit 1405 to distribute the autonomous vehicle's 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 traveling on road segment 1200 at a later time). The processing device 2020 may be similar to or different from the processor 180, 190 or the processing unit 110.

[0249] Fig. Figure 21 illustrates a block diagram of memory 2015, which can store computer code or instructions for performing one or more operations to generate a road navigation model for use in autonomous vehicle navigation. As shown in Fig. As shown in Figure 21, memory 2015 can store one or more modules for performing operations to process vehicle navigation information. For example, memory 2015 can include a model generation module 2105 and a model distribution module 2110. Processor 2020 can execute the instructions stored in either of the modules 2105 and 2110 contained in memory 2015.

[0250] The model generation module 2105 can store instructions that, when executed by the processor 2020, can generate at least one section of an autonomous vehicle's road navigation model for a shared 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's road navigation model, the processor 2020 can cluster vehicle trajectories along the shared road segment 1200 into different clusters. The processor 2020 can determine a destination trajectory along the shared road segment 1200 based on the clustered vehicle trajectories for each of the different clusters. Such an operation can involve finding a mean or average trajectory of the clustered vehicle trajectories (e.g.,by means of data representing the clustered vehicle trajectories) included in each cluster. In some embodiments, the target trajectory may be associated with a single lane of the common road segment 1200.

[0251] The road model and / or the sparse map can store trajectories associated with a road segment. These trajectories can be referred to as target trajectories, which are provided to autonomous vehicles for autonomous navigation. The target trajectories can be received by multiple vehicles or can be generated based on actual trajectories or recommended trajectories (actual trajectories with some modifications) received by multiple vehicles. The target trajectories contained in the road model or the sparse map can be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0252] Vehicles traveling on a road segment can collect data from various sensors. This data can include landmarks, road signature profile, vehicle motion (e.g., accelerometer data, velocity data), and vehicle position (e.g., GPS data). The vehicles can either reconstruct the actual trajectories themselves or transmit the data to a server that reconstructs the actual trajectories for the vehicles. In some embodiments, the vehicles can transmit data relating to a trajectory (e.g., a curve in any reference frame), landmark data, and lane assignment along the route to Server 1230. Different vehicles traveling along the same road segment on multiple trips can exhibit different trajectories.Server 1230 can identify routes or trajectories associated with each lane from the trajectories received from vehicles through a clustering process.

[0253] Fig. Figure 22 illustrates a process for clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine a destination trajectory for the common road segment (e.g., road segment 1200). The destination trajectory, or a plurality of destination trajectories, determined from the clustering process can be included in the road navigation model or sparse map 800 of the autonomous vehicle. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 can transmit a plurality of trajectories 2200 to server 1230. In some embodiments, the server 1230 can generate trajectories based on landmark, road geometry and vehicle movement information received by vehicles 1205, 1210, 1215, 1220 and 1225.To generate the road navigation model of the autonomous vehicle, the server can cluster 1230 vehicle trajectories 1600 into a variety of clusters 2205, 2210, 2215, 2220, 2225 and 2230, as shown in . Fig. 22 shown.

[0254] Clustering can be performed using various criteria. In some embodiments, all journeys in a cluster can be similar with respect to the absolute direction of travel along road segment 1200. The absolute direction of travel can be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the absolute direction of travel can be obtained using dead reckoning. As a person skilled in the art would understand, dead reckoning can be used to determine the current position, and thus the direction of travel, of vehicles 1205, 1210, 1215, 1220, and 1225 by using previously determined position, estimated speed, etc. Trajectories clustered by the absolute direction of travel can be useful for identifying routes along the roadway.

[0255] In some embodiments, all journeys in a cluster may be similar with respect to lane assignment (e.g., in the same lane before and after an intersection) along the journey on road segment 1200. Trajectories clustered by lane assignment can be useful for identifying lanes along the roadway. In some embodiments, both criteria (e.g., absolute direction of travel and lane assignment) can be used for clustering.

[0256] In each cluster 2205, 2210, 2215, 2220, 2225, and 2230, trajectories can be averaged to obtain a target trajectory associated with that specific cluster. For example, the trajectories of multiple trips associated with the same lane cluster can be averaged. The averaged trajectory can be a target trajectory associated with a specific lane. To average a cluster of trajectories, server 1230 can select a reference frame of any trajectory C0. For all other trajectories (C1, ..., Cn), server 1230 can find a rigid transformation that maps C1 to C0, where i = 1, 2, ..., n, and n is a positive integer corresponding to the total number of trajectories included in the cluster. Server 1230 can calculate a mean curve or trajectory in the C0 reference frame.

[0257] In some embodiments, the reference points can define an arc length alignment between different journeys, which can be used to align trajectories with lanes. In some embodiments, lane markings before and after an intersection can be used to align trajectories with lanes.

[0258] To assemble lanes from trajectories, Server 1230 can select a reference frame of any lane. Server 1230 can map partially overlapping lanes onto the selected reference frame. Server 1230 can continue mapping until all lanes are within the same reference frame. Adjacent lanes can be aligned as if they were the same lane and can later be shifted laterally.

[0259] Landmarks detected along the road segment can be mapped onto the common reference frame, first at the lane level, then at the intersection level. For example, the same landmarks may be detected multiple times by several vehicles in multiple trips. The data for the same landmarks received in different trips may vary slightly. Such data can be averaged and mapped onto the same reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of the data for the same landmark received in multiple trips can be calculated.

[0260] In some embodiments, each lane of road segment 120 can be associated with a destination trajectory and specific landmarks. The destination trajectory, or a plurality of such destination trajectories, can be included in the autonomous vehicle's road navigation model, which can later be used by other autonomous vehicles traveling along the same road segment 1200. Landmarks identified by vehicles 1205, 1210, 1215, 1220, and 1225 as they travel along road segment 1200 can be recorded in association with the destination trajectory. The destination trajectory and landmark data can be continuously or periodically updated with new data received from other vehicles during subsequent journeys.

[0261] To localize an autonomous vehicle, the disclosed systems and methods can use an extended Kalman filter. The vehicle's location can be determined based on three-dimensional position data and / or three-dimensional orientation data, predicting the future location prior to the vehicle's current location by integrating its own motion. The vehicle's localization can be corrected or adjusted by image observations of landmarks. For example, if the vehicle detects a landmark within an image captured by the camera, the landmark can be compared to a known landmark stored within the road model or the sparse map 800. The known landmark may have a known location (e.g., GPS data) along a target trajectory stored in the road model and / or the sparse map 800.Based on the current speed and the landmark images, the distance from the vehicle to the landmark can be estimated. The vehicle's position along a target trajectory can be adjusted based on the distance to the landmark and the known location of the landmark (stored in the road model or the sparse map 800). It can be assumed that the landmark position / location data (e.g., averages from multiple trips) stored in the road model and / or the sparse map 800 are accurate.

[0262] In some embodiments, the disclosed system can form a closed-loop subsystem in which the six-degrees-of-freedom estimate of the vehicle's location (e.g., three-dimensional position data plus three-dimensional orientation data) can be used to navigate the autonomous vehicle (e.g., to steer the wheel) to reach a desired point (e.g., 1.3 seconds prior in the stored data). Conversely, data measured by the steering and actual navigation can be used to estimate the location with six degrees of freedom.

[0263] In some embodiments, poles along a road, such as lampposts and power or cable line poles, can be used as landmarks for locating vehicles. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of an object along the road segment, can also be used as landmarks for locating the vehicle. When poles are used for locating, the x-observation of the poles (i.e., the angle of view from the vehicle) can be used instead of the y-observation (i.e., the distance to the pole), because the bases of the poles may be obscured and they are sometimes not at the road plane.

[0264] Fig. Figure 23 illustrates a navigation system for a vehicle that can be used for autonomous navigation using a sparsely populated crowdsourced map. For illustrative purposes, the vehicle is referenced as vehicle 1205. The in Fig. The vehicle shown in Figure 23 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 in Fig. As shown in Figure 12, the vehicle 1205 can communicate with the server 1230. The vehicle 1205 can include an image acquisition device 122 (e.g., camera 122). The vehicle 1205 can include a navigation system 2300 configured to provide navigation guidance for the vehicle 1205 to drive on a road (e.g., road segment 1200). The 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 the vehicle 1205. The accelerometer 2325 can be configured to detect acceleration or deceleration of the vehicle 1205. The in Fig. The vehicle 1205 shown in Figure 23 can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, the vehicle 1205 can also be a non-autonomous, human-driven vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0265] The navigation system 2300 can include a communication unit 2305 configured to communicate with the server 1230 via the communication path 1235. The navigation system 2300 can also include a GPS unit 2310 configured to receive and process GPS signals. The navigation system 2300 can further include at least one processor 2315 configured to process data such as GPS signals, map data from the sparse map 800 (which may be stored on a storage device provided on board the vehicle 1205 and / or received by the server 1230), road geometry captured by a road profile sensor 2330, images captured by the camera 122, and / or a road navigation model of the autonomous vehicle received by the server 1230.The road profile sensor 2330 can 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 can include a device that measures the movement of a suspension of the vehicle 2305 to derive the road roughness profile. In some embodiments, the road profile sensor 2330 can include radar sensors to measure the distance from the vehicle 1205 to the sides of the road (e.g., a barrier on the sides of the road), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 can include a device configured to measure the height of the road upwards and downwards. In some embodiments, the road profile sensor 2330 can include a device configured to measure the curvature of the road.For example, a camera (e.g., camera 122 or another camera) can be used to capture images of the road showing curves. Vehicle 1205 can use such images to detect road curves.

[0266] The at least one processor 2315 can be programmed to receive at least one environmental image associated with the vehicle 1205 from the camera 122. The at least one processor 2315 can analyze the at least one environmental image to determine navigation information relating to the vehicle 1205. The navigation information can include a trajectory relating to the journey of the vehicle 1205 along the road segment 1200. The at least one processor 2315 can determine the trajectory based on movements of the camera 122 (and thus of the vehicle), such as three-dimensional translation and three-dimensional rotation. In some embodiments, the at least one processor 2315 can determine the translation and rotation movements of the camera 122 based on the analysis of a plurality of images captured by the camera 122.In some embodiments, the navigation information can include lane assignment information (e.g., which lane vehicle 1205 is traveling in along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 can be used by server 1230 to generate and / or update a road navigation model of the autonomous vehicle, which can be transmitted back from server 1230 to vehicle 1205 to provide autonomous navigation guidance for vehicle 1205.

[0267] The at least one processor 2315 can also be programmed to transmit navigation information from the vehicle 1205 to the server 1230. In some embodiments, the navigation information can be transmitted to the server 1230 along with the road information. The road location information can include at least one of the GPS signals received by the GPS unit 2310, landmark information, road geometry, lane information, etc. The at least one processor 2315 can receive the autonomous vehicle's road navigation model, or a portion thereof, from the server 1230. The autonomous vehicle's road navigation model received by the server 1230 can include at least one update based on the navigation information transmitted from the vehicle 1205 to the server 1230.The section of the model transmitted from server 1230 to vehicle 1205 may include an updated section of the model. The at least one processor 2315 can perform at least one navigation maneuver (e.g., steering, such as turning, braking, accelerating, overtaking another vehicle, etc.) by vehicle 1205 based on the received road navigation model of the autonomous vehicle or the updated section of the model.

[0268] The at least one processor 2315 can be configured to communicate with various sensors and components contained in the vehicle 1205, including the communication unit 2305, the GPS unit 2310, the camera 122, the speed sensor 2320, the accelerometer 2325, and the road profile sensor 2330. The at least one processor 2315 can collect information or data from various sensors and components and transmit this information or data to the server 1230 via the communication unit 2305. Alternatively or additionally, various sensors or components of the vehicle 1205 can also communicate with the server 1230 and transmit data or information collected by the sensors or components to the server 1230.

[0269] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can communicate with each other and share navigation information, such that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 can generate the autonomous vehicle's road navigation model using crowdsourcing, for example, based on information shared by other vehicles. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can share navigation information, and each vehicle can update its own road navigation model of the autonomous vehicle, which is provided in the vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) can act as a hub vehicle. The hub vehicle's at least one 2315 processor (e.g., vehicle 1205) can perform some or all of the functions carried out by server 1230.For example, the hub vehicle's at least one 2315 processor can communicate with other vehicles and receive navigation information from them. The hub vehicle's at least one 2315 processor can generate the autonomous vehicle's road navigation model, or an update to the model, based on the shared information received from other vehicles. The hub vehicle's at least one 2315 processor can transmit the autonomous vehicle's road navigation model, or the model update, to other vehicles to provide autonomous navigation guidance. Navigation based on sparsely populated maps

[0270] As previously discussed, the autonomous vehicle's road navigation model, which includes the sparse map 800, can include a variety of mapped lane markings and a variety of mapped objects / features associated with a road segment. As discussed in more detail below, these mapped lane markings, objects, and features can be used when the autonomous vehicle navigates. For example, in some embodiments, the mapped objects and features can be used to locate a host vehicle relative to the map (e.g., relative to a mapped destination trajectory). The mapped lane markings can be used (e.g., as a check) to determine a lateral position and / or orientation with respect to a planned or destination trajectory.With this position information, the autonomous vehicle can adjust its direction of travel to correspond to the direction of a target trajectory at the specified position.

[0271] The Vehicle 200 can be configured to detect lane markings in a given road segment. The road segment can include any markings on a road used to guide traffic in a lane. For example, lane markings can be solid or dashed lines indicating the edge of a lane. Lane markings can also include dual lines, such as double solid lines, double dashed lines, or a combination of solid and dashed lines, indicating, for example, whether overtaking is permitted in an adjacent lane. Lane markings can also include highway entrance and exit markings, indicating, for example, a deceleration lane for an exit ramp, or dotted lines indicating that a lane is for turning only or that the lane ends.The markings may also indicate a work zone, a temporary lane change, a route through an intersection, a median, a special lane (e.g. a bicycle lane, a HOV lane, etc.) or other various markings (e.g. pedestrian crossing, a speed ramp, a level crossing, a stop line, etc.).

[0272] The vehicle 200 can use cameras, such as the image capture devices 122 and 124 enclosed in the image acquisition unit 120, to capture images of the surrounding lane markings. The vehicle 200 can analyze the images to capture point locations associated with the lane markings, based on features identified within one or more of the captured images. These point locations can be uploaded to a server to display the lane markings on the sparse map 800. Depending on the camera's position and field of view, lane markings for both sides of the vehicle can be captured 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 actual images of the lane markings, the markings in the sparse map 800 can be stored as a spline or a series of points, thereby reducing the size of the sparse map 800 and / or the data that needs to be uploaded remotely by the vehicle.

[0273] Fig. Figures 24A to 24D illustrate example point locations that can be detected by the Vehicle 200 to represent specific lane markings. Similar to the landmarks described above, the Vehicle 200 can use various image recognition algorithms or software to identify point locations within a captured image. For example, the Vehicle 200 can detect a series of edge points, corner points, or various other point locations associated with a particular lane marking. Fig. Figure 24A shows a continuous lane marking 2410 that can be detected by vehicle 200. The lane marking 2410 can represent the outer edge of a roadway, depicted by a continuous white line. As shown in Fig. As shown in Figure 24A, the vehicle 200 can be configured to detect a multitude of edge location points 2411 along the lane marking. The location points 2411 can be collected to represent the lane marking at intervals sufficient to create a mapped lane marking on the sparse map. For example, the lane marking can be represented by one point per meter of the detected edge, one point every five meters of the detected edge, or at other suitable intervals. In some embodiments, the spacing can be determined by factors other than fixed intervals, such as, for example, based on points where the vehicle 200 has the highest confidence rating of the location of the detected points. Although Fig. 24A Edge location points are shown on an inner edge of the lane marking 2410; points can be collected on the outer edge of the line or along both edges. Furthermore, while a single line in Fig. As shown in Figure 24A, similar edge points can be detected for a double continuous line. For example, points 2411 can be detected along an edge of one or both of the continuous lines.

[0274] The vehicle 200 can also display lane markings differently depending on the type or shape of the lane marking. Fig. Figure 24B shows an example of a dashed lane marking 2420 that can be detected by vehicle 200. Instead of detecting edge points, as in Fig. 24A, the vehicle can detect a series of vertices 2421 representing the corners of the lane lines to define the complete boundary of the line. While Fig. Figure 24B shows how each corner of a given line marking is determined. Vehicle 200 can detect or upload a subset of the points shown in the figure. For example, Vehicle 200 can detect the leading edge or the leading corner of a given line marking, or it can detect the two corner points closest to the interior of the lane. Furthermore, it is not necessary to detect every line marking; for example, Vehicle 200 can detect and / or record points representing a sample of line markings (e.g., every second, every third, every fifth, etc.) or line markings at a predefined interval (e.g., every meter, every five meters, every ten meters, etc.).Corner points can also be detected for similar lane markings, such as markings indicating that a lane is for an exit ramp, that a particular lane ends, or other various lane markings that may have detectable corner points. Corner points can also be detected for lane markings consisting of double-dashed lines or a combination of solid and dashed lines.

[0275] In some embodiments, the points uploaded to the server to generate the mapped lane markings can represent other points besides the detected boundary points or corner points. Fig. Figure 24C illustrates a series of points that can represent a centerline of a given lane marking. For example, the continuous lane 2410 can be represented by centerline points 2441 along a centerline 2440 of the lane marking. In some embodiments, the vehicle 200 can be configured to detect these centerlines using various image recognition techniques, such as convolutional neural networks (CNNs), scale-invariant feature transform (SIFT), histogram of oriented gradients (HOG) features, or other techniques. Alternatively, the vehicle 200 can detect other points, such as the edge points 2411 shown in Figure 24C. Fig. 24A, and can calculate centerline points 2441, for example by detecting points along each edge and determining a midpoint between the edge points. Similarly, the dashed lane marking 2420 can be represented by centerline points 2451 along a centerline 2450 of the lane marking. The centerline points can be located at the edge of a dash, as in Fig. 24C, or at various other locations along the centerline. For example, each dash can be represented by a single point at the geometric center of the dash. The points can also be spaced at a predetermined interval along the centerline (e.g., every meter, 5 meters, 10 meters, etc.). The centerline points 2451 can be detected directly by the vehicle 200 or can be calculated based on other detected reference points, such as corner points 2421, as shown in Fig. Figure 24B shows that a center line can also be used to represent other lane marking types, such as a double line, using similar techniques as above.

[0276] In some embodiments, the vehicle can identify 200 points representing other features, such as a vertex between two intersecting lane markings. Fig. Figure 24D shows example points representing an intersection between two lane markings 2460 and 2465. Vehicle 200 can calculate a vertex 2466, which represents an intersection between the two lane markings. For example, one of the lane markings 2460 or 2465 may represent a level crossing area or another transition area in the road segment. While lane markings 2460 and 2465 are shown as intersecting perpendicularly, various other configurations can be detected. For example, lane markings 2460 and 2465 may intersect at other angles, or one or both of the lane markings may terminate at vertex 2466. Similar techniques can also be applied for intersections between dashed or other lane marking types.In addition to the vertex 2466, various other points 2467 can also be detected, which provide further information about the alignment of the lane markings 2460 and 2465.

[0277] The Vehicle 200 can associate real-world coordinates with each detected point of the lane marking. For example, location identifiers, including coordinates for each point, can be generated and uploaded to a server for mapping the lane marking. These location identifiers can also include other identifying information about the points, such as whether the point is a vertex, edge point, midpoint, etc. The Vehicle 200 can therefore be configured to determine the real-world position of each point based on image analysis. For instance, the Vehicle 200 can detect other features in the image, such as the various reference points described above, to pinpoint the real-world location of the lane markings.This can involve determining the location of the lane markings in the image relative to the detected landmark, or determining the vehicle's position based on the detected landmark and then calculating a distance from the vehicle (or the vehicle's target trajectory) to the lane marking. If no landmark is available, the location of the lane marking points can be determined relative to a vehicle position determined using dead reckoning. The real-world coordinates included in the location identifiers can be represented as absolute coordinates (e.g., latitude / longitude coordinates) or relative to other features, such as a longitudinal position along a target trajectory and a lateral distance from the target trajectory.The location identifiers can then be uploaded to a server to generate the mapped lane markings in the navigation model (such as the sparse map 800). In some embodiments, the server can construct a spline representing the lane markings of a road segment. Alternatively, the vehicle 200 can generate the spline and upload it to the server to be recorded in the navigation model.

[0278] Fig. Figure 24E shows an exemplary navigation model or sparse map for a corresponding road segment, including mapped lane markings. The sparse map may include a target trajectory 2475 that a vehicle is to follow along a road segment. As described above, the target trajectory 2475 may represent an ideal path that a vehicle should take when traveling along the corresponding road segment, or it may be located elsewhere on the road (e.g., a center line of the road, etc.). The target trajectory 2475 may be computed using the various methods described above, for example, based on an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories of vehicles crossing the same road segment.

[0279] In some embodiments, the target trajectory can be generated equally for all vehicle types and for all road, vehicle, and / or environmental conditions. In other embodiments, however, various other factors or variables can also be taken into account when generating the target trajectory. A different target trajectory can be generated for different vehicle types (e.g., a private vehicle, a light truck, and a full trailer). For example, a target trajectory with relatively tighter turning radii can be generated for a small private vehicle than for a larger semi-trailer truck. In some embodiments, road, vehicle, and environmental conditions can also be taken into account. For example, a different target trajectory can be generated for different road conditions (e.g., wet, snowy, icy, dry, etc.), vehicle conditions (e.g.,The target trajectory can be generated based on factors such as tire condition (or estimated tire condition), brake condition (or estimated brake condition), remaining fuel level, etc., or environmental factors (e.g., time of day, visibility, weather, etc.). The target trajectory can also depend on one or more aspects or characteristics of a particular road segment (e.g., speed limit, frequency and size of curves, gradient, etc.). In some embodiments, various user settings, such as a predefined driving mode (e.g., desired driving aggressiveness, economy mode, etc.), can also be used to determine the target trajectory.

[0280] The sparse map can also include mapped lane markings 2470 and 2480, which represent lane markings along the road segment. The mapped lane markings can be represented by a variety of location identifiers 2471 and 2481. As described above, the location identifiers can include locations in real-world coordinates of points associated with a detected lane marking. Similar to the target trajectory in the model, the lane markings can also include elevation data and can be represented as a curve in three-dimensional space. For example, the curve can be a spline connecting three-dimensional polynomials of suitable order, with the curve being computable based on the location identifiers. The mapped lane markings can also include other information or metadata about the lane marking, such as an identifier of the lane marking type (e.g.,(between two lanes traveling in the same direction, between two lanes traveling in opposite directions, the edge of a roadway, etc.) and / or other lane marking characteristics (e.g., solid, dashed, single line, double line, yellow, white, etc.). In some embodiments, the mapped lane markings within the model can be continuously updated, for example, using crowdsourcing techniques. The same vehicle can upload location identifiers during multiple trips on the same road segment, or data can be selected from a variety of 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 location identifiers received from the vehicles and stored in the system.When the mapped lane markings are updated and refined, the updated road navigation model and / or the sparsely populated map can be distributed to a large number of autonomous vehicles.

[0281] Generating the mapped lane markings in the sparse map may also include detecting and / or mitigating errors based on anomalies in the images or in the actual lane markings themselves. Fig. Figure 24F shows an example of anomaly 2495, which is associated with the detection of a lane marking 2490. The anomaly 2495 may appear in the image captured by the vehicle 200, for example, due to an object obstructing the camera's view of the lane marking, dirt on the lens, etc. In some cases, the anomaly may be due to the lane marking itself, which may be damaged, worn, or partially covered, for example, by dirt, debris, water, snow, or other materials on the road. The anomaly 2495 may cause a faulty point 2491 to be detected by the vehicle 200. The sparsely populated map 800 can provide the correct mapped lane marking and eliminate the error.In some embodiments, the vehicle 200 can detect a faulty point 2491, for example, by detecting the anomaly 2495 in the image or by identifying the fault based on detected lane marking points before and after the anomaly. Based on the detection of the anomaly, the vehicle can omit point 2491 or adjust it to match other detected points. In other embodiments, the fault can be corrected after the point has been uploaded, for example, 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.

[0282] The mapped lane markings in the navigation model and / or the sparse map can also be used for navigation by an autonomous vehicle crossing the corresponding roadway. For example, a vehicle navigating along a target trajectory can periodically use the mapped lane markings in the sparse map to align itself with the target trajectory. As mentioned above, the vehicle can navigate between landmarks based on dead reckoning, where the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Errors can accumulate over time, and the vehicle's position estimates relative to the target trajectory can become increasingly inaccurate.Accordingly, the vehicle can use lane markings that appear in the sparsely populated map 800 (and their known locations) to reduce the position determination errors induced by coupled navigation. In this way, the identified lane markings included in the sparsely populated map 800 can serve as navigation anchors from which an accurate position of the vehicle relative to a target trajectory can be determined.

[0283] Fig. Figure 25A shows an exemplary image 2500 of a vehicle's surroundings that can be used for navigation based on the mapped lane markings. The image 2500 can be acquired, for example, by the vehicle 200 via the image acquisition devices 122 and 124, which are enclosed in the image acquisition unit 120. The image 2500 can include an image of at least one lane marking 2510, as shown in Fig. 25A shown. The image 2500 may also include one or more landmarks 2521, such as a road sign, which are used for navigation as described above. Some in Fig. Elements shown in 25A, such as elements 2511, 2530 and 2520, which do not appear in the captured image 2500 but are detected and / or determined by the vehicle 200, are also shown for reference.

[0284] Using the various techniques described above with regard to the Fig. As described in sections 24A to D and 24F, a vehicle can analyze image 2500 to identify lane marking 2510. Various points 2511 can be detected according to features of the lane marking in the image. For example, the points 2511 can correspond to an edge of the lane marking, a corner of the lane marking, a midpoint of the lane marking, a vertex between two intersecting lane markings, or various other features or locations. The points 2511 can be detected to correspond to a location of points stored in a navigation model received from a server. For example, if a sparse map is received containing points representing the centerline of a mapped lane marking, the points 2511 can also be detected based on a centerline of the lane marking 2510.

[0285] The vehicle can also determine a longitudinal position, represented by element 2520, along a target trajectory. The longitudinal position 2520 can be determined from image 2500, for example, by detecting landmark 2521 within image 2500 and comparing a measured location with a known landmark location stored in the road model or sparse map 800. The vehicle's location along a target trajectory can then 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 those used to determine the position of a lane marking.For example, the longitudinal position 2520 can be determined by detecting landmarks in images from other cameras within the image acquisition unit 120, which are captured simultaneously or nearly simultaneously with image 2500. In some cases, the vehicle may not be near arbitrary landmarks or other reference points for determining the longitudinal position 2520. In such cases, the vehicle can navigate using dead reckoning and can thus use sensors to determine its own motion and estimate a longitudinal position 2520 relative to the target trajectory. The vehicle can also determine a distance 2530, which represents the actual distance between the vehicle and the lane marking 2510 observed in the captured image(s).The camera angle, the speed of the vehicle, the width of the vehicle, or various other factors can be taken into account when determining the distance 2530.

[0286] Fig. Figure 25B illustrates a lateral localization correction of the vehicle based on the mapped lane markings in a road navigation model. As described above, the vehicle 200 can determine a distance 2530 between itself and a lane marking 2510 using one or more images captured by the vehicle 200. The vehicle 200 may also have access to a road navigation model, such as the sparse map 800, which may include a mapped lane marking 2550 and a destination trajectory 2555. The mapped lane marking 2550 can be modeled using the techniques described above, for example, using crowdsourced location identifiers captured by a variety of vehicles. The destination trajectory 2555 can also be generated using the various techniques described above.The vehicle 200 can also determine or estimate a longitudinal position 2520 along the target trajectory 2555, as described above in relation to . Fig. 25A described. The vehicle 200 can then determine an expected distance 2540 based on a lateral distance between the target trajectory 2555 and the mapped lane marking 2550, which corresponds to the longitudinal position 2520. The lateral localization of the 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.

[0287] Fig. 25°C and Fig. 25D provides illustrations associated with another example of locating a host vehicle during navigation based on mapped landmarks / objects / features on a sparsely populated map. Fig. Figure 25C conceptually represents a series of images captured by a vehicle navigating along a road segment 2560. In this example, the road segment 2560 comprises a straight section of a two-lane, divided highway, bounded by the road edges 2561 and 2562 and the center lane marking 2563. As shown, the host vehicle navigates along a lane 2564 associated with a mapped target trajectory 2565. Therefore, in an ideal situation (and without influencing factors such as the presence of target vehicles or objects on the roadway, etc.), the host vehicle should follow the mapped target trajectory 2565 precisely while navigating along lane 2564 of the road segment 2560. In reality, the host vehicle may experience drift while navigating along the mapped target trajectory 2565.For effective and safe navigation, this drift should be kept within acceptable limits (e.g., + / - 10 cm lateral displacement from the target trajectory 2565 or any other suitable threshold). To periodically account for the drift and make all necessary course corrections to ensure that the host vessel follows the target trajectory 2565, the disclosed navigation systems may be able to locate the host vessel along the target trajectory 2565 (e.g., determine a lateral and longitudinal position of the host vessel relative to the target trajectory 2565) by using one or more mapped features / objects included in the sparsely populated map.

[0288] As a simple example, it shows Fig. 25C shows a speed limit sign 2566 as it can appear in five different, sequentially captured images while the host vehicle navigates along road segment 2560. For example, at an initial time point, t0, sign 2566 may appear near the horizon in a captured image. As the host vehicle approaches sign 2566, in subsequent captured images at times t1, t2, t3, and t4, sign 2566 appears at different 2D-XY pixel positions within the captured images. For example, sign 2566 moves down and to the right in the space of the captured images along curve 2567 (e.g., a curve that extends through the center of the sign in each of the five captured images). Sign 2566 also appears to increase in size as the host vehicle approaches it (i.e., it occupies a large number of pixels in the subsequently captured images).

[0289] These changes in the image space representations of an object, such as sign 2566, can be exploited to determine the local position of the host vehicle along a target trajectory. For example, as described in the present disclosure, any detectable object or feature, such as a semantic feature like sign 2566 or a detectable non-semantic feature, can be identified by one or more collection vehicles that have previously crossed a road segment (e.g., road segment 2560). A mapping server can collect the driving information gathered from a multitude of vehicles, aggregate and correlate this information, and generate a sparse map that includes, for example, a target trajectory 2565 for lane 2564 of road segment 2560. The sparse map can also store the location of sign 2566 (along with type information, etc.). During navigation (e.g.,Before entering road segment 2560, a host vehicle can be provided with a map tile that includes a sparse map for road segment 2560. To navigate on lane 2564 of road segment 2560, the host vehicle can follow the mapped target trajectory 2565.

[0290] The mapped representation of sign 2566 can be used by the host vehicle to locate itself relative to the target trajectory. For example, a camera on the host vehicle captures an image 2570 of the host vehicle's surroundings, and this captured image 2570 can include an image representation of sign 2566 with a specific size and XY image position, as shown in Fig. 25D is shown. This size and XY image position can be used to determine the host vehicle's position relative to the target trajectory 2565. For example, based on the sparse map that includes a representation of sign 2566, a host vehicle's navigation processor can determine that, in response to the host vehicle's travel along the target trajectory 2565, a representation of sign 2566 should appear in the captured images, such that the center of sign 2566 (in image space) moves along line 2567. If a captured image, such as image 2570, shows that the center (or some other reference point) is shifted from line 2567 (e.g., the expected image space trajectory), the host vehicle's navigation system can determine that it was not on the target trajectory 2565 at the time the image was captured.From the image, the navigation processor can determine an appropriate navigation correction to guide the host vehicle back to the target trajectory 2565. For example, if the analysis shows an image position of sign 2566 that is shifted a distance 2572 to the left of the expected image space position on line 2567, the navigation processor can initiate a change in the host vehicle's direction of travel (e.g., by changing the steering angle of the wheels) to move the host vehicle a distance 2573 to the left. In this way, each captured image can be used as part of a feedback loop, minimizing any difference between an observed image position of sign 2566 and the expected image trajectory 2567 to ensure that the host vehicle continues along the target trajectory 2565 with little or no deviation.Naturally, the more mapped objects are available, the more frequently the described localization technique can be used, thereby reducing or eliminating drift-related deviations from the target trajectory 2565.

[0291] The process described above can be useful for detecting a lateral orientation or displacement of the host vehicle relative to a target trajectory. Localizing the host vehicle relative to the target trajectory 2565 can also include determining the longitudinal position of the target vehicle along the target trajectory. For example, the captured image 2570 includes a representation of the sign 2566 with a specific image size (e.g., a 2D XY pixel area). This size can be compared to an expected image size of the mapped sign 2566 as it moves along the line 2567 through image space (e.g., as the size of the sign progressively increases, as in Fig. (25C shown). Based on the image size of sign 2566 in image 2570 and the expected size profile in image space relative to the mapped target trajectory 2565, the host vehicle can determine its longitudinal position (at the time of image 2570 acquisition) relative to the target trajectory 2565. This longitudinal position, coupled with any lateral displacement relative to the target trajectory 2565 as described above, allows for complete localization of the host vehicle relative to the target trajectory 2565 as the host vehicle navigates along road 2560.

[0292] Fig. 25°C and Fig. Figure 25D presents only one example of the disclosed localization technique using a single mapped object and a single target trajectory. In other examples, there may be many more target trajectories (e.g., one target trajectory for each usable lane of a multi-lane highway, urban street, complex intersection, etc.) and many more mapped objects available for localization. For example, a sparsely populated map representative of an urban environment may include many objects per meter available for localization.

[0293] Fig. Figure 26A shows a flowchart illustrating an exemplary process 2600A for mapping a lane marking for use in autonomous vehicle navigation, in accordance with the disclosed embodiments. In step 2610, process 2600A may include receiving two or more location identifiers associated with a detected lane marking. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifiers may include locations in real-world coordinates of points associated with the detected lane marking, as described above with respect to Fig. 24E described. In some embodiments, the location identifiers may also contain other data, such as additional information about the road segment or lane markings. Additional data may also be received during step 2610, such as accelerometer data, velocity data, landmark data, road geometry or profile data, vehicle positioning data, self-motion data, or various other forms of data described above. The location identifiers may be generated by a vehicle, such as vehicles 1205, 1210, 1215, 1220, and 1225, based on images captured by the vehicle.For example, the identifiers can be determined based on capturing at least one image representing the environment of the host vehicle from a camera associated with the host vehicle, analyzing that image to detect the lane marking in the environment of the host vehicle, and analyzing that image to determine the position of the detected lane marking relative to a location associated with the host vehicle. As described above, the lane marking can include a variety of different marking types, and the location identifiers can correspond to a variety of points relative to the lane marking. For example, if the detected lane marking is part of a dashed line marking a lane boundary, the points can correspond to detected corners of the lane marking.If the detected lane marking is part of a continuous line that defines a lane boundary, the points can correspond to a detected edge of the lane marking, with varying distances as described above. In some embodiments, the points can correspond to the centerline of the detected lane marking, as shown in [reference]. Fig. 24C shown, or can correspond to a vertex between two intersecting lane markings and at least two other points associated with the intersecting lane markings, as in Fig. 24D shown.

[0294] In step 2612, process 2600A can include associating the detected lane marking with a corresponding road segment. For example, server 1230 can analyze the real-world coordinates or other information received during step 2610 and compare that coordinates or other information with location information stored in the autonomous vehicle's road navigation model. Server 1230 can then determine a road segment in the model that corresponds to the real-world road segment where the lane marking was detected.

[0295] In step 2614, process 2600A may include updating an autonomous vehicle's road navigation model relative to the relevant road segment based on the two or more location identifiers associated with the detected lane marking. For example, the autonomous road navigation model may be a sparse map 800, and server 1230 may update the sparse map to include or adjust a mapped lane marking in the model. Server 1230 may update the model based on the various procedures or processes described above with respect to Fig. 24E. In some embodiments, updating the autonomous vehicle's road navigation model may include storing one or more position indicator(s) in real-world coordinates of the detected lane marking. The autonomous vehicle's road navigation model may also include at least one target trajectory that the vehicle is to follow along the corresponding road segment, as described in Fig. 24E shown.

[0296] In step 2616, process 2600A can include distributing the updated autonomous vehicle road navigation model to a large number of autonomous vehicles. For example, server 1230 can distribute the updated autonomous vehicle road navigation model to vehicles 1205, 1210, 1215, 1220, and 1225, which can then use the model for navigation. The autonomous vehicle road navigation model can be distributed over one or more networks (e.g., a cellular network and / or the internet, etc.) via wireless communication paths 1235, as shown in Fig. 12 shown.

[0297] In some embodiments, the lane markings can be mapped using data received from a large number of vehicles, such as through a crowdsourcing technique, as described above in relation to Fig. 24E described. For example, process 2600A can include receiving an initial communication from a first host vehicle, including location identifiers associated with a detected lane marking, and receiving a second communication from a second host vehicle, including additional location identifiers associated with the detected lane marking. For example, the second communication can be received from a following vehicle traveling on the same road segment or from the same vehicle on a subsequent journey along the same road segment. Process 2600A can further include refining a determination of at least one position associated with the detected lane marking based on the location identifiers received in the first communication and based on the additional location identifiers received in the second communication.This may include using an average of several location identifiers and / or filtering out “ghost” identifiers that may not reflect the actual position of the lane marking.

[0298] Fig. Figure 26B shows a flowchart illustrating an exemplary process 2600B for autonomously navigating a host vehicle along a road segment using mapped lane markings. Process 2600B can be performed, for example, by the processing unit 110 of the autonomous vehicle 200. At step 2620, process 2600B can include receiving a road navigation model of the autonomous vehicle from a server-based system. In some embodiments, the autonomous vehicle's road navigation model can include a destination trajectory for the host vehicle along the road segment and location identifiers associated with one or more lane markings associated with the road segment. For example, the vehicle 200 can receive a sparse map 800 or another road navigation model developed using process 2600A.In some embodiments, the target trajectory can be represented as a three-dimensional spline, as in . Fig. 9B shown. As above in relation to the Fig. As described in sections 24A to F, the location identifiers can include locations in real coordinates of points associated with the lane marking (e.g., corner points of a dashed lane marking, edge points of a solid lane marking, a vertex between two intersecting lane markings and other points associated with the intersecting lane markings, a center line associated with the lane marking, etc.).

[0299] In step 2621, process 2600B may include receiving at least one image depicting the vehicle's surroundings. The image may be received by an image capture device of the vehicle, such as the image capture devices 122 and 124 enclosed in the image acquisition unit 120. The image may include an image of one or more lane markings, similar to image 2500 described above.

[0300] In step 2622, process 2600B may include determining a longitudinal position of the host vehicle along the target trajectory. As above in relation to Fig. As described in 25A, this can be based on other information in the captured image (e.g. landmarks, etc.) or by dead reckoning of the vehicle between detected landmarks.

[0301] In step 2623, process 2600B may include determining an expected lateral distance to the lane marking based on the determined longitudinal position of the host vehicle along the target trajectory and based on the two or more location identifiers associated with the at least one lane marking. For example, vehicle 200 may use the sparsely populated map 800 to determine an expected lateral distance to the lane marking. As in Fig. As shown in Figure 25B, the longitudinal position 2520 along a target trajectory 2555 can be determined in step 2622. Using the substitute map 800, the vehicle 200 can determine an expected distance 2540 to the mapped lane marking 2550, which corresponds to the longitudinal position 2520.

[0302] In step 2624, process 2600B may include analyzing the at least one image to identify the at least one lane marking. For example, vehicle 200 may use various image recognition techniques or algorithms to identify the lane marking within the image, as described above. For instance, lane marking 2510 may be detected by image analysis of image 2500, as shown in Fig. 25A shown.

[0303] In step 2625, process 2600B may include determining an actual lateral distance to the at least one lane marking based on the analysis of the at least one image. For example, the vehicle may determine a distance of 2530, as shown in Fig. Figure 25A shows the actual distance between the vehicle and the lane marking 2510. The camera angle, the vehicle's speed, the vehicle's width, the camera's position relative to the vehicle, or various other factors may be taken into account when determining the distance 2530.

[0304] In step 2626, process 2600B may include determining an autonomous steering action for the host vehicle based on a difference between the expected lateral distance to the at least one lane marking and the determined actual lateral distance to the at least one lane marking. For example, as above regarding Fig. As described in 25B, vehicle 200 compares the actual distance 2530 with an expected distance 2540. The difference between the actual and expected distances can indicate an error (and its magnitude) between the vehicle's actual position and the target trajectory it is following. Accordingly, the vehicle can determine an autonomous steering action or other autonomous action based on this difference. For example, if the actual distance 2530 is less than the expected distance 2540, as described in 25B, the vehicle can... Fig. As shown in Figure 25B, the vehicle determines an autonomous steering action to steer the vehicle to the left, away from the lane marking 2510. Thus, the vehicle's position relative to the target trajectory can be corrected. Process 2600B can be used, for example, to improve the vehicle's navigation between landmarks.

[0305] Processes 2600A and 2600B provide only examples of techniques that can be used to navigate a host vehicle using the disclosed sparsely populated maps. Other examples may also involve those relating to the Fig. 25°C and Fig. The consistent processes described in 25D are used.

[0306] In some embodiments, the disclosed systems, methods, and non-volatile, computer-readable media can use one or more AV maps. An autonomous vehicle (AV) map (or AV card) can include information that supports and / or implements one or more functions of an autonomous vehicle (AV) in such a way that the vehicle operates safely and / or navigates precisely. The AV functions supported and / or implemented by an autonomous vehicle (or a semi-autonomous vehicle) can include one or more autonomously controlled functions (e.g., functions that are determined, selected, and / or implemented based on instructions executed by at least one processor), such as steering, accelerating, and / or braking the vehicle.AV functions can be part of a driving strategy, such as RSS, which was developed and implemented by Mobileye, Jerusalem, Israel. Information for the safe operation of the vehicle can include, but is not limited to, information relating to one or more regulations applicable to a location of the vehicle or a jurisdiction (e.g., right-hand or left-hand traffic jurisdiction), information relating to the environment in which the vehicle is located (e.g., information relating to a drivable road, a stop sign, a traffic light, a speed limit, lane markings, landmarks, clear space, virtual or physical stop lines, relevance information from traffic lights, etc.), and / or information relating to the setting and / or adjustment of the vehicle's navigation to one or more objects (e.g.,to take into account other vehicles, pedestrians, objects, obstacles, obstructions, hazards, construction zones, traffic cones, etc.) in the vicinity of the vehicle. The vehicle can detect objects in its vicinity using one or more sensors (e.g., cameras, radar, lidar), as described herein. The AV map can serve as a redundant source of information for the detected information and, in some cases, supplement the detected information (e.g., provide the location of a virtual stop line when no stop line is marked on the road). In some embodiments, the safe operation of the vehicle may further include operating the vehicle to maintain a comfort level for one or more passengers in the vehicle. The comfort level may be defined by one or more predetermined criteria (e.g.,(with regard to speed, acceleration, and / or cornering) that are selected to operate the vehicle in a manner that meets or exceeds a designated or selected level of passenger comfort. The level of comfort may be formalized and expressed in appropriate mathematical formulas. For example, mathematical formulas may be used that limit the magnitude of jerk or acceleration experienced by a passenger in various directions. The information required for precise vehicle operation may include, among other things, information about a planned or predetermined navigation path (e.g., a trajectory, as discussed herein) or a route (e.g., from a specific location, such as a starting point, to a destination).In some embodiments, the information included in an AV card may further include information that efficiently supports and / or implements one or more AV functions. The information for efficient vehicle operation may include information relating to speed, acceleration, lane changes and / or lane positioning, and / or driving, and / or the selection of a path or route based on traffic conditions (e.g., taking a longer route than a shorter one where traffic conditions prevail), and / or other factors or characteristics related to possible routes (e.g., weather conditions, road conditions, or other route characteristics, such as taking a highway without traffic lights instead of a road with traffic lights).In some embodiments, the AV card may further include at least some information from a high-resolution (HD) card. In some embodiments, the AV card may be a sparsely populated card, as described above. In some embodiments, the AV card, as described herein, may be created by a group of people. In this disclosure, the terms "AV card" and "sparsely populated card" are used synonymously. Systems and procedures for determining the relevance of traffic signs

[0307] In certain situations, an autonomous (or semi-autonomous) vehicle may need to determine whether a traffic sign is relevant to it. Existing solutions can make a decision about the relevance of the traffic sign by analyzing an image captured by a front-facing camera on the vehicle. However, a single camera (e.g., a front-facing or front-facing camera) may not provide enough information to definitively determine whether the traffic sign is relevant to the vehicle. This can be particularly true if the question of relevance is decided before the vehicle passes the traffic sign. For example, in some situations, the relevance of a particular traffic sign depends on the path the vehicle takes (e.g., when changing lanes regulated by a specific traffic sign).In some cases, the path taken by the vehicle may change after passing a particular traffic sign, so that it moves from a position or lane for which the traffic sign is not relevant to a position or lane for which the traffic sign just passed is relevant.

[0308] In some situations, traffic signs may be relevant for a specific lane or group of lanes. In other situations, a traffic sign may be positioned before an exit and apply only to that exit. Therefore, a relevance decision based on an image captured by the vehicle before passing the traffic sign may be incorrect if the vehicle ultimately does not travel on a road segment associated with the traffic sign. Furthermore, a forward-facing image may include representations of other objects (e.g., trees, other vehicles, pedestrians, etc.) that are not relevant to the relevance decision and could lead to an incorrect one. In other situations, a relevance decision may be necessary if the traffic sign is at least partially obscured. The obscuration may be caused by a permanent object (e.g., a road sign).The impact could be caused by a tree or a temporary object (e.g., a parked car or truck). Therefore, in these and other situations, relying on an image captured by a vehicle's front camera and making a relevance decision before passing the traffic sign can lead to incorrect relevance decisions.

[0309] The disclosed systems and methods can use images captured by a camera on a host vehicle to determine whether a traffic sign within the host vehicle's field of vision is relevant to the host vehicle's movement. In some embodiments, the camera is a front-facing camera on the host vehicle. In other embodiments, the camera can be mounted on the side (e.g., the left or right side) of the host vehicle or otherwise positioned.

[0310] For example, in some embodiments, a system for navigating a host vehicle may include at least one processor, which includes switching logic and memory, wherein the memory contains instructions which, when executed by the switching logic, cause the at least one processor to: receive at least one image captured by a camera of the host vehicle; analyze the at least one image to recognize a representation of a traffic sign in an environment of the host vehicle; determine a relevance of the traffic sign to the host vehicle, wherein the relevance of the traffic sign to the host vehicle is determined based on a trajectory of the host vehicle relative to a location of the traffic sign; and cause the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle.

[0311] In some embodiments, a top-down image can be used to further contribute to the relevance decision of a traffic sign. For example, if a decision on the relevance of a traffic sign is made solely by analyzing an image captured by a front-facing camera of the vehicle, such a front-facing image alone may not provide sufficient information to definitively determine whether the traffic sign is relevant to the vehicle. This may be particularly true if the question of relevance is decided before the vehicle passes the traffic sign. For instance, in some situations, the relevance of a particular traffic sign to a vehicle depends on the path it takes (i.e., whether it is relevant to the vehicle).Some lanes at an intersection are regulated by a specific traffic sign, while other lanes do not need to observe that particular traffic sign when passing through. In some cases, the path followed by a vehicle may change after passing a specific traffic sign, from a position or lane for which the traffic sign is not relevant to a position or lane for which the just-passed traffic sign is relevant.

[0312] In some embodiments, a traffic sign can be relevant to a host vehicle if the traffic sign provides an instruction or indication intended to control the host vehicle in some way. In some embodiments, the control of the host vehicle can include keeping the host vehicle within a specific lane associated with the host vehicle's position or trajectory. In some embodiments, a traffic sign can be relevant to a host vehicle if the traffic sign provides an instruction or indication used by a driving strategy implemented by the host vehicle in the embodiment to control the...

Claims

[1] System for navigating a host vehicle, the system comprising: at least one processor, comprising a circuit and a memory, the memory including instructions which, when executed by the circuit, cause the at least one processor to: Receiving at least one image captured by a front camera of the host vehicle; Analyzing the at least one image to identify a representation of a traffic sign in the vicinity of the host vehicle; Determining the relevance of the traffic sign for the host vehicle, wherein the relevance of the traffic sign for the host vehicle is determined based on a trajectory of the host vehicle relative to a location of the traffic sign; and Causing the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle. [2] System according to claim 1, wherein the trajectory of the host vehicle traverses at least one road segment and wherein a first section of the at least one road segment is in front of a front of the traffic sign and a second section of the at least one road segment is behind a rear of the traffic sign. [3] System according to claim 2, wherein the host vehicle travels the first section of the at least one road segment before traveling the second section of the at least one road segment. [4] System according to claim 2, wherein the determination of the relevance of the traffic sign for the host vehicle is carried out while the host vehicle is navigating in the environment. [5] System according to claim 1, wherein the relevance of the traffic sign for the host vehicle is further determined on the basis of at least one lane marking in the vicinity of the host vehicle. [6] System according to claim 1, wherein the relevance of the traffic sign for the host vehicle is further determined on the basis of at least one roadside in the vicinity of the host vehicle. [7] System according to claim 1, wherein the relevance of the traffic sign for the host vehicle is further determined on the basis of an analysis of a top-view image, wherein the top-view image includes a first indicator for the trajectory of the host vehicle and a second indicator for the position of the traffic sign. [8] System according to claim 7, wherein the top view image is generated on the basis of an analysis of a plurality of images captured by the front camera of the host vehicle. [9] System according to claim 7, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to provide the top-view image to a trained system, and wherein the trained system is configured to determine the relevance of the traffic sign to the host vehicle. [10] System according to claim 9, wherein the trained system includes a neural network. [11] System according to claim 7, wherein the top view image further includes an indicator for at least one lane of a road segment in the vicinity of the host vehicle. [12] System according to claim 7, wherein the top view image further includes an indicator for at least one road edge of a road segment in the vicinity of the host vehicle. [13] System according to claim 7, wherein the top view image is linked to information indicating an orientation of the traffic sign. [14] System according to claim 7, wherein the top view image further includes an indicator for the traffic sign at an origin of a coordinate system connected with the top view image. [15] System according to claim 1, wherein the traffic sign is a speed limit sign. [16] System according to claim 15, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to determine a speed limit associated with the speed limit sign. [17] System according to claim 16, wherein the speed limit associated with the speed limit sign is determined by analysis of the at least one image. [18] System according to claim 16, wherein the memory further contains instructions which, when executed by the switching logic, cause the at least one processor to determine the at least one navigation action based on the speed limit. [19] System according to claim 1, wherein the traffic sign is determined to be irrelevant for the host vehicle. [20] System according to claim 19, wherein the traffic sign is determined to be irrelevant to the host vehicle after the host vehicle has passed the traffic sign by a predetermined distance. [21] System according to claim 19, wherein the traffic sign is a speed limit sign. [22] System according to claim 21, wherein the memory further contains instructions which, when executed by the switching logic, cause the at least one processor to determine a speed limit associated with the speed limit sign. [23] System according to claim 22, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to determine a different speed limit for the host vehicle. [24] System according to claim 1, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to send an indicator of the relevance of the traffic sign from the host vehicle to a server. [25] System according to claim 24, wherein the server is configured to store the indicator in a navigation map. [26] System according to claim 25, wherein the indicator is stored in connection with a drivable path. [27] System according to claim 1, wherein the at least one navigation action includes braking, steering or accelerating the host vehicle. [28] System for navigating a host vehicle, which includes the system: at least one processor, comprising a circuit and a memory, wherein the memory includes instructions which, when executed by the circuit, cause the at least one processor to: Receiving at least one image captured by a front camera of the host vehicle; Analyzing the at least one image to detect a representation of a speed limit sign in the vicinity of the host vehicle; Determining an initial speed limit that is associated with the speed limit sign; Determining the relevance of the speed limit sign for the host vehicle, wherein the relevance of the speed limit sign for the host vehicle is determined based on a trajectory of the host vehicle relative to a location of the speed limit sign, wherein the speed limit sign is determined to be irrelevant for the host vehicle after the host vehicle has passed the speed limit sign by a predetermined distance; After determining that the speed limit sign is not relevant for the host vehicle, determine a second speed limit for the host vehicle, wherein the second speed limit differs from the first speed limit; and Causing the host vehicle to perform at least one navigation action based on the second speed limit. [29] System according to claim 28, wherein the first speed limit associated with the speed limit sign is determined by analysis of the at least one image. [30] System for navigating a host vehicle, the system comprising: at least one processor, comprising a circuit and a memory, wherein the memory includes instructions which, when executed by the circuit, cause the at least one processor to: Receiving at least one image captured by a front camera of the host vehicle; Analyzing the at least one image to detect a representation of a traffic sign in an environment of the host vehicle, wherein the representation of the traffic sign is at least partially obscured by an object; Determining the relevance of the traffic sign for the host vehicle, wherein the relevance of the traffic sign for the host vehicle is determined based on a trajectory of the host vehicle relative to a location of the traffic sign; and Causing the host vehicle to perform at least one navigation action based on the relevance of the traffic sign to the host vehicle. [31] System according to claim 30, wherein the object includes a tree. [32] System according to claim 30, wherein the object includes a parked vehicle. [33] System for navigating a host vehicle, the system comprising: at least one processor, comprising a circuit and a memory, wherein the memory includes instructions which, when executed by the circuit, cause the at least one processor to: Receiving at least one image captured by a front camera of the host vehicle; Analyzing the at least one image to identify a representation of a traffic sign in the vicinity of the host vehicle; Generating a top-down image based on the analysis of a large number of images captured by the host vehicle's front camera; Providing the top-down image to a trained system configured to determine the relevance of the traffic sign to the host vehicle based on a trajectory of the host vehicle relative to a location of the traffic sign, wherein the trained system is further configured to output an indicator of the relevance of the traffic sign to the host vehicle based on an analysis of the top-down image; Receiving the indicator for the relevance of the traffic sign to the host vehicle from the trained system; and Causing the host vehicle to perform at least one navigation action based on the traffic sign relevance indicator for the host vehicle in the embodiment. [34] System according to claim 33, wherein the top view image includes a first indicator for the trajectory of the host vehicle and a second indicator for the position of the traffic sign. [35] System according to claim 34, wherein the top view image further includes an indicator for at least one lane of a road segment in the vicinity of the host vehicle. [36] System according to claim 34, wherein the top view image further includes an indicator for at least one edge of a road segment in the vicinity of the host vehicle. [37] System according to claim 34, wherein the top view image is linked to information indicating an orientation of the traffic sign. [38] System according to claim 34, wherein the top view image further includes an indicator for the traffic sign at an origin of a coordinate system connected with the top view image. [39] System according to claim 34, wherein the trajectory of the host vehicle includes at least one road segment and wherein a first section of the at least one road segment is in front of a front of the traffic sign and a second section of the at least one road segment is behind a rear of the traffic sign. [40] System according to claim 39, wherein the host vehicle travels the first section of the at least one road segment before traveling the second section of the at least one road segment. [41] System according to claim 33, wherein the traffic sign is a speed limit sign. [42] System according to claim 41, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to determine a speed limit associated with the speed limit sign. [43] System according to claim 42, wherein the speed limit associated with the speed limit sign is determined by analysis of the at least one image. [44] System according to claim 42, wherein the memory further includes instructions which, when executed by the switching logic, cause the at least one processor to determine the at least one navigation action based on the speed limit. [45] System according to claim 33, wherein the trained system includes a neural network. [46] System according to claim 33, wherein the memory further contains instructions which, when executed by the switching logic, cause the at least one processor to send an indicator of the relevance of the traffic sign to the host vehicle to a server. [47] System according to claim 46, wherein the server is configured to store the indicator in a navigation map. [48] ​​System according to claim 47, wherein the indicator is stored in connection with a drivable path. [49] System according to claim 33, wherein the at least one navigation action includes braking, steering or accelerating the host vehicle.

Images