System and method for navigating host vehicle

Abstract

Systems and methods for navigating a host vehicle are provided. In one embodiment, a system includes a processor programmed to: receive an image representing an environment of a host vehicle; determining a planned navigation action for completing a navigation target of the host vehicle based on the driving strategy; analyzing the image to identify a target vehicle in the environment of the host vehicle; determining a next state distance between the host vehicle and the target vehicle that would be generated with the planned navigation action taken; determining the maximum braking capacity, the maximum acceleration capacity and the speed of the host vehicle; determining a stop distance of the host vehicle based on the maximum braking capability, the maximum acceleration capability, and the speed of the host vehicle; determining a speed of the target vehicle based on the identified characteristics of the target vehicle and assuming a maximum braking capability of the target vehicle; and performing a planned navigation action when the determined stop distance of the host vehicle is less than the sum of the determined next state distance and a target vehicle travel distance determined based on the speed of the target vehicle and the assumed maximum braking capability of the target vehicle.

Description

[0001] This invention is a divisional application of the invention patent application with application date of December 21, 2017, application number 201780084515.6, and invention name “Navigation system with imposed liability constraints”.

[0002] CROSS-REFERENCE TO RELATED APPLICATIONS

[0003] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 438,563, filed December 23, 2016, U.S. Provisional Patent Application No. 62 / 546,343, filed August 16, 2017, U.S. Provisional Patent Application No. 62 / 565,244, filed September 29, 2017, and U.S. Provisional Patent Application No. 62 / 582,687, filed November 7, 2017. All of the foregoing applications are incorporated herein by reference in their entirety. Technical Field

[0004] The present disclosure generally relates to autonomous vehicle navigation. In addition, the present disclosure relates to systems and methods for navigating according to potential accident liability constraints. Background Art

[0005] As technology continues to advance, the goal of fully autonomous vehicles that can navigate on roadways is imminent. Autonomous vehicles may need to consider a variety of factors and make appropriate decisions based on those factors to safely and accurately reach the desired destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured from a camera), information from radar or lidar, and may also use information obtained from other sources (e.g., from GPS devices, speed sensors, accelerometers, suspension sensors, etc.). At the same time, in order to navigate to the destination, the autonomous vehicle may also need to identify its location in a specific roadway (e.g., a specific lane in a multi-lane road), navigate along other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, travel from one road to another at appropriate intersections or junctions, and respond to any other situations that occur or progress during vehicle operation. In addition, the navigation system may need to comply with certain imposed constraints. In some cases, these constraints may involve interactions between the main vehicle and one or more other objects (such as other vehicles, pedestrians, etc.). In other cases, constraints may involve responsibility rules to be followed when implementing one or more navigation actions for the main vehicle.

[0006] In the field of autonomous driving, there are two important considerations for viable autonomous vehicle systems. The first is the standardization of safety assurance, including the requirements that each self-driving car must meet to ensure safety, and how to verify these requirements. The second is scalability, because engineering solutions that incur release costs will not scale to millions of cars and may prevent widespread adoption of autonomous cars or even less widespread adoption. Therefore, there is a need for an interpretable mathematical model for safety assurance, and a system design that adheres to safety assurance requirements while scalable to millions of cars. Summary of the invention

[0007] Embodiments consistent with the present disclosure provide systems and methods for autonomous vehicle navigation. The disclosed embodiments may use cameras to provide autonomous vehicle navigation features. For example, consistent with the disclosed embodiments, the disclosed system may include one, two or more cameras that monitor the vehicle environment. The disclosed system may provide a navigation response based on, for example, analysis of images captured by one or more cameras. The navigation response may also take into account other data, including, for example, global positioning system (GPS) data, sensor data (e.g., from accelerometers, velocity sensors, suspension sensors, etc.), and / or other map data.

[0008] At least one embodiment of the present disclosure provides a system for navigating a main vehicle, the system comprising: at least one processor programmed to: receive at least one image representing the environment of the main vehicle from an image capture device; determine a planned navigation action for completing a navigation goal of the main vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the main vehicle; determine a next-state distance between the main vehicle and the target vehicle that would result if the planned navigation action were taken; determine a maximum braking capacity of the main vehicle, a maximum acceleration capacity of the main vehicle, and a speed of the main vehicle; determine a stopping distance of the main vehicle based on the maximum braking capacity of the main vehicle, the maximum acceleration capacity of the main vehicle, and the speed of the main vehicle; determine the speed of the target vehicle based on at least one identified characteristic of the target vehicle and assume a maximum braking capacity of the target vehicle; and implement the planned navigation action when the determined stopping distance of the main vehicle is less than the sum of the determined next-state distance and a travel distance of the target vehicle determined based on the speed of the target vehicle and the assumed maximum braking capacity of the target vehicle.

[0009] At least one embodiment of the present disclosure provides a method for navigating a main vehicle, comprising: receiving at least one image representing the environment of the main vehicle from an image capture device; determining a planned navigation action for completing a navigation goal of the main vehicle based on at least one driving strategy; analyzing at least one image to identify a target vehicle in the environment of the main vehicle; determining a next-state distance between the main vehicle and the target vehicle that will result if the planned navigation action is taken; determining a maximum braking capacity of the main vehicle, a maximum acceleration capacity of the main vehicle, and a speed of the main vehicle; determining a stopping distance of the main vehicle based on the maximum braking capacity of the main vehicle, the maximum acceleration capacity of the main vehicle, and the speed of the main vehicle; determining the speed of the target vehicle based on at least one identified characteristic of the target vehicle and assuming a maximum braking capacity of the target vehicle; and implementing the planned navigation action when the determined stopping distance of the main vehicle is less than the sum of the determined next-state distance and a target vehicle travel distance determined based on the speed of the target vehicle and the assumed maximum braking capacity of the target vehicle.

[0010] A system and method for navigating a host vehicle are provided. In some embodiments, the system may include at least one processing device programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; determine a planned navigation action for achieving a navigation goal of the host vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the host vehicle; test the planned navigation action against at least one accident liability rule to determine the potential accident liability of the host vehicle relative to the identified target vehicle; if the test of the planned navigation action against at least one accident liability rule indicates that there is potential accident liability for the host vehicle if the planned navigation action is taken, then cause the host vehicle to not implement the planned navigation action; and if the test of the planned navigation action against at least one accident liability rule indicates that there is no accident liability for the host vehicle if the planned navigation action is taken, then cause the host vehicle to implement the planned navigation action.

[0011] In some embodiments, a navigation system for a host vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; determine a plurality of potential navigation actions for the host vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the host vehicle; test a plurality of potential navigation actions against at least one accident liability rule to determine the potential accident liability of the host vehicle relative to the identified target vehicle; select one of the potential navigation actions for which a test indicates that no accident liability would result for the host vehicle if the selected potential navigation action were taken; and cause the host vehicle to implement the selected potential navigation action.

[0012] In some embodiments, a system for navigating a main vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the main vehicle from an image capture device; determine two or more planned navigation actions for achieving a navigation goal of the main vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the main vehicle; test each of the two or more planned navigation actions against at least one accident liability rule to determine potential accident liability; for each of the two or more planned navigation actions, if the test indicates that if a particular one of the two or more planned navigation actions is taken, there is potential accident liability for the main vehicle, causing the main vehicle not to implement the particular one of the planned navigation actions; and for each of the two or more planned navigation actions, if the test indicates that if a particular one of the two or more planned navigation actions is taken, no accident liability for the main vehicle will be incurred, identifying the particular one of the two or more planned navigation actions as a feasible candidate for implementation; select a navigation action to be taken from the feasible candidates for implementation based on at least one cost function; and causing the main vehicle to implement the selected navigation action.

[0013] In some embodiments, an accident liability tracking system for a host vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; determine one or more characteristics of a navigation state of the identified target vehicle based on the analysis of the at least one image; compare the determined one or more characteristics of the navigation state of the identified target vehicle with at least one accident liability rule; store at least one value indicating potential accident liability of the identified target vehicle based on the comparison of the determined one or more characteristics of the navigation state of the identified target vehicle with at least one accident liability rule; and, after an accident occurs between the host vehicle and at least one target vehicle, output the stored at least one value for determining liability for the accident.

[0014] In some embodiments, a system for navigating a host vehicle may include at least one processing device, the at least one processing device being programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; determine a planned navigation action for achieving a navigation goal of the host vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the host vehicle; test the planned navigation action against at least one accident liability rule to determine potential accident liability; if the test of the planned navigation action against at least one accident liability rule indicates that there is potential accident liability for the host vehicle if the planned navigation action is taken, then cause the host vehicle to not implement the planned navigation action; and if the test of the planned navigation action against at least one accident liability rule indicates that there will be no accident liability for the host vehicle if the planned navigation action is taken, then cause the host vehicle to implement the planned navigation action; and wherein the at least one processing device is further programmed to: determine one or more characteristics of a navigation state of the identified target vehicle based on analysis of the at least one image; compare the determined one or more characteristics of the navigation state of the identified target vehicle with at least one accident liability rule; and store at least one value indicating potential accident liability of the identified target vehicle based on the comparison of the determined one or more characteristics of the navigation state of the identified target vehicle with at least one accident liability rule.

[0015] In some embodiments, a system for navigating a host vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; determine a planned navigation action for achieving a navigation goal of the host vehicle based on at least one driving strategy; analyze at least one image to identify a target vehicle in the environment of the host vehicle; determine a next-state distance between the host vehicle and the target vehicle that would result if the planned navigation action were taken; determine a current maximum braking capacity of the host vehicle and a current speed of the host vehicle; determine a current speed of the target vehicle and assume a maximum braking capacity of the target vehicle based on at least one identified characteristic of the target vehicle; and implement the planned navigation action if, given the maximum braking capacity of the host vehicle and the current speed of the host vehicle, the host vehicle can stop within a stopping distance that is less than the sum of the determined next-state distance and a distance traveled by the target vehicle determined based on the current speed of the target vehicle and the assumed maximum braking capacity of the target vehicle.

[0016] In some embodiments, a system for navigating a main vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the main vehicle from an image capture device; determine a planned navigation action for achieving a navigation goal of the main vehicle based on at least one driving strategy; analyze at least one image to identify a first target vehicle in front of the main vehicle and a second target vehicle in front of the first target vehicle; determine a next-state distance between the main vehicle and the second target vehicle that would result if the planned navigation action were taken; determine a current maximum braking capacity of the main vehicle and a current speed of the main vehicle; and implement the planned navigation action if, given the maximum braking capacity of the main vehicle and the current speed of the main vehicle, the main vehicle can stop within a stopping distance that is less than the determined next-state distance between the main vehicle and the second target vehicle.

[0017] In some embodiments, a system for navigating a host vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the host vehicle from an image capture device; analyze the at least one image to identify a target vehicle in the environment of the host vehicle; determine two or more potential navigation actions for achieving a navigation goal of the host vehicle; test each of the two or more potential navigation actions against at least one accident liability rule to determine, for each of the two or more potential navigation actions, an indicator of potential accident liability between the host vehicle and the identified target vehicle; and select one of the two or more potential navigation actions to implement only when the indicator of potential accident liability associated with the selected action indicates that no potential accident liability will be attributed to the host vehicle as a result of implementing the selected action.

[0018] In some embodiments, a system for navigating a main vehicle may include at least one processing device programmed to: receive at least one image representing an environment of the main vehicle from an image capture device; receive an indicator of a current navigation state of the main vehicle from at least one sensor; determine that a collision between the main vehicle and one or more objects is inevitable based on an analysis of the at least one image and based on the indicator of the current navigation state of the main vehicle; determine, based on at least one driving strategy, a first planned navigation action of the main vehicle involving an expected collision with a first object and a second planned navigation action of the main vehicle involving an expected collision with a second object; test the first and second planned navigation actions against at least one accident liability rule to determine potential accident liability; if the test of the first planned navigation action against at least one accident liability rule indicates that there is potential accident liability for the main vehicle if the first planned navigation action is taken, then cause the main vehicle to not implement the first planned navigation action; and if the test of the second planned navigation action against at least one accident liability rule indicates that there will be no accident liability for the main vehicle if the second planned navigation action is taken, then cause the main vehicle to implement the second planned navigation action.

[0019] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that are executable by at least one processing device and perform any of the steps and / or methods described herein.

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

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

[0022] In the attached picture:

[0023] Figure 1 is a pictorial representation of an example system consistent with the disclosed embodiments.

[0024] Figure 2A is a diagrammatic side view representation of an example vehicle including systems consistent with the disclosed embodiments.

[0025] Figure 2B is consistent with the disclosed embodiments Figure 2A A diagrammatic top view representation of the vehicle and systems shown in .

[0026] Figure 2C is a diagrammatic top view representation of another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0027] Figure 2Dis a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0028] Figure 2E is a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0029] Figure 2F is a pictorial representation of an example vehicle control system consistent with the disclosed embodiments.

[0030] Figure 3A is a pictorial representation of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with the disclosed embodiments.

[0031] Figure 3B is an illustration of an example of a camera installation configured to be positioned behind a rearview mirror and against a vehicle windshield, consistent with the disclosed embodiments.

[0032] Figure 3C is consistent with the disclosed embodiments Figure 3B Illustration of the camera installation from different viewing angles shown in FIG.

[0033] Figure 3D is an illustration of an example of a camera mounting configured to be located behind a rearview mirror and against a vehicle windshield, consistent with the disclosed embodiments.

[0034] Figure 4 is an example block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0035] Figure 5A is a flow chart illustrating an example process for eliciting one or more navigation responses based on monocular image analysis, consistent with the disclosed embodiments.

[0036] Figure 5B is a flow chart illustrating an example process for detecting one or more vehicles and / or pedestrians in a set of images, consistent with the disclosed embodiments.

[0037] Figure 5C is a flow chart illustrating an example process for detecting road markings and / or lane geometry information in a set of images consistent with the disclosed embodiments.

[0038] Figure 5D is a flow chart illustrating an example process for detecting traffic lights in a set of images, consistent with the disclosed embodiments.

[0039] Figure 5Eis a flow chart illustrating an example process for eliciting one or more navigation responses based on a vehicle path, consistent with the disclosed embodiments.

[0040] Fig. 5F is a flow chart illustrating an example process for determining whether a leading vehicle is changing lanes, consistent with the disclosed embodiments.

[0041] Figure 6 is a flow chart illustrating an example process for eliciting one or more navigation responses based on stereoscopic image analysis, consistent with the disclosed embodiments.

[0042] Figure 7 is a flow chart illustrating an example process for eliciting one or more navigation responses based on analysis of three sets of images, consistent with the disclosed embodiments.

[0043] Figure 8 is a block diagram representation of modules that may be implemented by one or more specially programmed processing devices of a navigation system of an autonomous vehicle, consistent with the disclosed embodiments.

[0044] Fig. 9 is a diagram of navigation options consistent with the disclosed embodiments.

[0045] Fig.10 is a diagram of navigation options consistent with the disclosed embodiments.

[0046] Fig.11A , Fig. 11B and Fig. 11C A schematic representation of navigation options for a host vehicle in a merge zone consistent with the disclosed embodiments is provided.

[0047] Fig.11D An illustrative description of a dual-lane merging scenario consistent with the disclosed embodiments is provided.

[0048] Fig.11E A diagram of options that are potentially useful in a double-merge scenario consistent with the disclosed embodiments is provided.

[0049] Fig.12 A diagram capturing a representative image of a host vehicle's environment and potential navigation constraints is provided consistent with the disclosed embodiments.

[0050] Fig.13 A flow chart of an algorithm for navigating a vehicle consistent with the disclosed embodiments is provided.

[0051] Fig.14 A flow chart of an algorithm for navigating a vehicle consistent with the disclosed embodiments is provided.

[0052] Fig.15A flow chart of an algorithm for navigating a vehicle consistent with the disclosed embodiments is provided.

[0053] Fig.16 A flow chart of an algorithm for navigating a vehicle consistent with the disclosed embodiments is provided.

[0054] Fig.17A and 17B An illustrative illustration of a host vehicle navigating into a roundabout is provided consistent with the disclosed embodiments.

[0055] Fig.18 A flow chart of an algorithm for navigating a vehicle consistent with the disclosed embodiments is provided.

[0056] Fig.19 An example of a host vehicle traveling on a multi-lane highway is shown consistent with the disclosed embodiments.

[0057] Fig. 20A and 20B An example of a vehicle cutting in front of another vehicle is shown, consistent with the disclosed embodiments.

[0058] Fig.21 An example of a vehicle following another vehicle is shown, consistent with the disclosed embodiments.

[0059] Fig. 22 An example of a vehicle exiting a parking lot and merging onto a potentially busy roadway is shown, consistent with the disclosed embodiments.

[0060] Fig.23 A vehicle is shown traveling on a road consistent with the disclosed embodiments.

[0061] Fig.24 Four example scenarios consistent with the disclosed embodiments are shown.

[0062] Fig.25 An example scenario consistent with the disclosed embodiments is shown.

[0063] Fig.26 An example scenario consistent with the disclosed embodiments is shown.

[0064] Fig. 27 An example scenario consistent with the disclosed embodiments is shown.

[0065] Fig.28A and 28B An example of a scenario in which a vehicle is following another vehicle is shown, consistent with the disclosed embodiments.

[0066] Fig.29A and 29BExample blame in a cut-in scenario consistent with disclosed embodiments is shown.

[0067] Fig. 30A and 30B Example attribution in a cut-in scenario consistent with the disclosed embodiments is shown.

[0068] Figures 31A-31D Example attribution in a drift scenario consistent with disclosed embodiments is shown.

[0069] Fig.32A and 32B Example attribution in a two-way traffic scenario consistent with the disclosed embodiments is shown.

[0070] Fig.33A and 33B Example attribution in a two-way traffic scenario consistent with the disclosed embodiments is shown.

[0071] Fig.34A and 34B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0072] Fig.35A and 35B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0073] Fig.36A and 36B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0074] Fig.37A and 37B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0075] Fig.38A and 38B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0076] Fig.39A and 39B Example attribution in a route priority scenario consistent with the disclosed embodiments is shown.

[0077] Fig.40A and 40B Example attribution in a traffic light scenario consistent with disclosed embodiments is shown.

[0078] Fig.41A and 41B Example attribution in a traffic light scenario consistent with disclosed embodiments is shown.

[0079] Fig.42A and 42B Example attribution in a traffic light scenario consistent with disclosed embodiments is shown.

[0080] Figures 43A-43C An example vulnerable road user (VRU) scenario consistent with the disclosed embodiments is shown.

[0081] Figures 44A-44C An example vulnerable road user (VRU) scenario consistent with the disclosed embodiments is shown.

[0082] Figures 45A-45C An example vulnerable road user (VRU) scenario consistent with the disclosed embodiments is shown.

[0083] Figures 46A-46D An example vulnerable road user (VRU) scenario consistent with the disclosed embodiments is shown. DETAILED DESCRIPTION

[0084] The following detailed description refers to the accompanying drawings. Whenever possible, the same reference numerals are used in the drawings and the following description to refer to the same or similar parts. Although several exemplary embodiments are described herein, modifications, adjustments, and other implementations are possible. For example, the components shown in the drawings may be replaced, added, or modified, and the exemplary methods described herein may be modified by replacing, reordering, removing, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0085] Autonomous Vehicle Overview

[0086] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that can implement at least one navigation change without driver input. "Navigation change" refers to one or more of the steering, braking, or acceleration / deceleration of the vehicle. By autonomous, it is meant that the vehicle does not need to be fully automatic (e.g., fully operable without a driver or without driver input). In contrast, autonomous vehicles include those vehicles that can operate under the control of a driver during certain time periods and can operate without driver control during other time periods. Autonomous vehicles may also include vehicles that only control certain aspects of vehicle navigation (such as steering (e.g., maintaining a vehicle route between vehicle lane constraints) or certain steering operations in certain situations (but not in all situations)), but other aspects may be handed over to the driver (e.g., braking or braking in certain situations). In some cases, an autonomous vehicle may handle some or all aspects of braking, rate control, and / or steering of the vehicle.

[0087] Because human drivers often rely on visual cues and observations in order to control vehicles, traffic infrastructure has been built with lane markings, traffic signs, and traffic lights designed to provide visual information to drivers. In view of these design characteristics of the traffic infrastructure, autonomous vehicles can include cameras and processing units that analyze visual information captured from the vehicle's environment. Visual information can include, for example, images representing components of the traffic infrastructure that can be observed by the driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). In addition, autonomous vehicles can also use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, a vehicle can use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.) and / or other map data to provide information about its environment while the vehicle is traveling, and the vehicle (and other vehicles) can use this information to locate itself on the model. Some vehicles are also able to communicate between vehicles, share information, change the dangers of companion vehicles or changes around the vehicle, etc.

[0088] System Overview

[0089] Figure 11 is a block diagram representation of a system 100 consistent with the disclosed example embodiments. Depending on the requirements of a particular implementation, the system 100 may include various components. In some embodiments, the system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. The processing unit 110 may include one or more processing devices. In some embodiments, the processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, depending on the requirements of a particular application, the image acquisition unit 120 may include any number of image acquisition devices and components. In some embodiments, the image acquisition unit 120 may include one or more image capture devices (e.g., a camera, a charge coupled device (CCD), or any other type of image sensor), such as an image capture device 122, an image capture device 124, and an image capture device 126. The system 100 may also include a data interface 128 that communicatively connects the processing unit 110 to the image acquisition unit 120. For example, the data interface 128 may include any wired and / or wireless one or more links for transmitting image data acquired by the image acquisition unit 120 to the processing unit 110 .

[0090] The wireless transceiver 172 may include one or more devices configured to exchange transmissions over an air interface to one or more networks (e.g., cellular, Internet, etc.) by using radio frequencies, infrared frequencies, magnetic fields, or electric fields. The wireless transceiver 172 may send and / or receive data using any well-known standard (e.g., Wi-Fi, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications from the host vehicle to one or more remotely located servers. Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to facilitate coordination of the host vehicle's navigation with respect to or in conjunction with target vehicles in the host vehicle's environment), or even broadcast transmissions to unspecified recipients in the vicinity of the sending vehicle.

[0091] Both application processor 180 and image processor 190 may include various types of hardware-based processing devices. For example, either or both of application processor 180 and image processor 190 may include a microprocessor, a preprocessor (such as an image preprocessor), a graphics processor, a central processing unit (CPU), auxiliary circuits, a digital signal processor, an integrated circuit, a memory, or any other type of device suitable for running applications and suitable for image processing and analysis. In some embodiments, application processor 180 and / or image processor 190 may include any type of single-core or multi-core processor, a mobile device microcontroller, a central processing unit, etc. Various processing devices may be used, including, for example, those available from, for example, a processor such as a processor. processors from manufacturers such as Intel and Intel and can include various architectures (e.g., x86 processors, wait).

[0092] In some embodiments, the application processor 180 and / or the image processor 190 may include a processor that can be Any of the EyeQ series processor chips available. These processor designs include multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors, and may also include video output capabilities. In one example, 90 nanometer-micrometer technology operating at 332 megahertz was used. The architecture consists of two floating-point hyperthreaded 32-bit RISC CPUs ( cores), five visual computing engines (VCEs), and three vector microcode processors Denali 64-bit mobile DDR controller, 128-bit internal Sonics Interconnect, dual 16-bit video input and 18-bit video output controllers, 16-channel DMA and several peripherals. The MIPS34K CPU manages these five VCEs, three VMPs TM and DMA, a second MIPS34KCPU and multi-channel DMA and other peripherals. These five VCEs, three and MIPS34K CPUs can perform the intensive visual calculations required for multi-function bundled applications. Six times stronger can be used in the disclosed embodiments. In other examples, can be used in the disclosed embodiments and / or Of course, any newer or future EyeQ processing devices may also be used with the disclosed embodiments.

[0093] Any processing device disclosed herein may be configured to perform certain functions. Configuring a processing device (such as any described EyeQ processor or other controller or microprocessor) to perform certain functions may include programming computer executable instructions and making these instructions available to the processing device during its operation for execution. In some embodiments, configuring the processing device may include programming the processing device directly with architectural instructions. In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible to the processing device during operation. For example, the processing device may access the memory during operation to obtain and execute the stored instructions. In either case, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system that controls multiple hardware-based components of a host vehicle.

[0094] although Figure 1 Two separate processing devices included in processing unit 110 are depicted, but more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to complete the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by more than two processing devices. Additionally, in some embodiments, system 100 may include one or more processing units 110 without including other components such as image acquisition unit 120.

[0095] The processing unit 110 may include various types of devices. For example, the processing unit 110 may include various devices, such as a controller, an image preprocessor, a central processing unit (CPU), an auxiliary circuit, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image preprocessor may include a video processor for capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The auxiliary circuit may be any number of circuits known in the art, including cache, power supply, clock, and input-output circuits. The memory may store software that controls the operation of the system when executed by the processor. The memory may include a database and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage, tape storage, removable storage, and other types of storage. In one example, the memory may be separated from the processing unit 110. In another example, the memory may be integrated into the processing unit 110.

[0096] Each memory 140, 150 may include software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. For example, these memory units may include various databases and image processing software, as well as trained systems such as neural networks and deep neural networks. The memory units may include random access memory, read-only memory, flash memory, disk drives, optical storage, tape storage, removable storage, and / or any other type of storage. In some embodiments, memory units 140, 150 may be separate from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

[0097] Position sensor 130 may include any type of device suitable for determining a location associated with at least one component of system 100. In some embodiments, position sensor 130 may include a GPS receiver. Such a receiver may determine user location and velocity by processing signals broadcast by global positioning system satellites. Position information from position sensor 130 may be made available to application processor 180 and / or image processor 190.

[0098] In some embodiments, system 100 may include components such as a speed sensor (e.g., a speedometer) for measuring the velocity of vehicle 200. System 100 may also include one or more accelerometers (single-axis or multi-axis) for measuring the acceleration of vehicle 200 along one or more axes.

[0099] The memory units 140, 150 may include a database, or data organized in any other form indicating the locations of known landmarks. Sensor information of the environment (such as images from LiDAR or stereo processing of two or more images, radar signals, depth information) may be processed together with position information (such as GPS coordinates, vehicle ego motion, etc.) to determine the current location of the vehicle relative to known landmarks and to improve the vehicle position. Certain aspects of this technology are included in what is known as REM. TM Positioning technology sold by the assignee of this application.

[0100] The user interface 170 may 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 may include a user input device including, for example, a touch screen, a microphone, a keyboard, a pointing device, a tracking wheel, a camera, knobs, buttons, etc. Using such input devices, a user can provide information input or commands to the system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, a pointer or eye tracking capabilities, or by any other suitable technique for communicating information to the system 100.

[0101] The user interface 170 may be provided with one or more processing devices configured to provide and receive information to and from a user, and to process the information for use by, for example, the application processor 180. In some embodiments, such processing devices may execute instructions to recognize and track eye movements, receive and interpret voice commands, recognize and interpret touches and / or gestures made on a touch screen, respond to keyboard input or menu selections, etc. In some embodiments, the user interface 170 may include a display, a speaker, a haptic device, and / or any other device for providing output information to a user.

[0102] The map database 160 may include any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 may include data related to the location of various items in a reference coordinate system, including roads, water features, geographic features, commercial areas, points of interest, restaurants, gas stations, etc. The map database 160 may store not only the locations of these items, but also descriptors related to these items, including, for example, names associated with any stored features. In some embodiments, the map database 160 may be physically located with other components of the system 100. Alternatively or additionally, the map database 160 or a portion thereof may be remotely located relative to other components of the system 100 (e.g., the processing unit 110). In such embodiments, information from the map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, the map database 160 may store a sparse data model that includes a polynomial representation of certain road features (e.g., lane markings) or a target trajectory of the host vehicle. The map database 160 may also include stored representations of various recognized landmarks that may be used to determine or update the known position of the host vehicle relative to the target track. The landmark representation may include data fields such as landmark type, landmark location, and other potential identifiers.

[0103] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from an environment. Furthermore, any number of image capture devices may be used to acquire images for input to an image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four, or more image capture devices. FIG. 2B to FIG. 2E Image capture devices 122, 124, and 126 are further described.

[0104] One or more cameras (e.g., image capture devices 122, 124, and 126) may be part of a sensing block included on the vehicle. Various other sensors may be included in the sensing block, and any or all of these sensors may be relied upon to form a sensed navigation state of the vehicle. In addition to cameras (front, side, rear, etc.), other sensors (such as radar, lidar, and acoustic sensors) may be included in the sensing block. In addition, the sensing block may include one or more components configured to transmit and send / receive information related to the environment of the vehicle. For example, such a component may include a wireless transceiver (RF, etc.) that can receive sensor-based information or any other type of information related to the environment of the main vehicle from a source located far away from the main vehicle. This information may include sensor output information or related information received from a vehicle system other than the main vehicle. In some embodiments, this information may include information received from a remote computing device, a central server, etc. In addition, the camera may be configured in many different configurations: a single camera unit, multiple cameras, a camera group, a long FOV, a short FOV, a wide angle, a fisheye, etc.

[0105] The system 100 or its various components may be incorporated into a variety of different platforms. In some embodiments, the system 100 may be included in a vehicle 200, such as Figure 2A For example, vehicle 200 may be equipped with Figure 1 In some embodiments, the vehicle 200 may be equipped with only a single image capture device (e.g., a camera), while in other embodiments, such as a combination of FIG. 2B to FIG. 2E For those embodiments discussed, multiple image capture devices may be used. For example, Figure 2A Either of the image capture devices 122 and 124 of the vehicle 200 shown in FIG. 2 may be part of an ADAS (Advanced Driver Assistance System) imaging set.

[0106] The image capture device included on the vehicle 200 as part of the image acquisition unit 120 may be placed in any suitable location. FIG. 2A to FIG. 2E ,as well as FIG. 3A to FIG. 3C As shown in , the image capture device 122 can be located near the rearview mirror. This location can provide a line of sight similar to the line of sight of the driver of the vehicle 200, which can assist in determining what is visible and invisible to the driver. The image capture device 122 can be placed anywhere near the rearview mirror, and placing the image capture device 122 on the driver's side of the mirror can also assist in obtaining an image representing the driver's field of view and / or line of sight.

[0107] Other positions of the image capture device of the image acquisition unit 120 can also be used. For example, the image capture device 124 can be located on or in the bumper of the vehicle 200. This position can be particularly suitable for image capture devices with a wide field of view. The line of sight of the image capture device located at the bumper can be different from the line of sight of the driver, and therefore, the bumper image capture device and the driver may not always see the same object. The image capture device (e.g., image capture devices 122, 124 and 126) can also be located in other positions. For example, the image capture device can be located on or in one or both of the side mirrors of the vehicle 200, on the roof of the vehicle 200, on the hood of the vehicle 200, on the trunk of the vehicle 200, on the side of the vehicle 200, installed on any window of the vehicle 200, placed behind any window of the vehicle 200, or placed in front of any window, and installed in or near the lighting device on the front and / or rear of the vehicle 200.

[0108] In addition to the image capture device, the vehicle 200 may also include various other components of the system 100. For example, the processing unit 110 may be included on the vehicle 200, integrated with or separate from the vehicle's engine control unit (ECU). The vehicle 200 may also be equipped with a location sensor 130 such as a GPS receiver, and may also include a map database 160 and memory units 140 and 150.

[0109] As discussed earlier, the wireless transceiver 172 can transmit and / or receive data via one or more networks (e.g., a cellular network, the Internet, etc.). For example, the wireless transceiver 172 can upload data collected by the system 100 to one or more servers and download data from one or more servers. Via the wireless transceiver 172, the system 100 can receive, for example, periodic updates or on-demand updates to data stored in the map database 160, the memory 140, and / or the storage 150. Similarly, the wireless transceiver 172 can upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, the vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0110] The system 100 can upload data to a server (e.g., to the cloud) based on the privacy level settings. For example, the system 100 can implement privacy level settings to specify or limit the types of data (including metadata) sent to the server that can uniquely identify the vehicle and / or the driver / owner of the vehicle. These settings can be set by a user via, for example, the wireless transceiver 172, can be initialized by factory default settings, or by data received by the wireless transceiver 172.

[0111] In some embodiments, the system 100 may upload data according to a "high" privacy level, and if the setting is set, the system 100 may transmit data (e.g., location information related to the route, captured images, etc.) without any details about the specific vehicle and / or driver / owner. For example, when uploading data according to the "high" privacy setting, the system 100 may not include the vehicle identification number (VIN) or the name of the driver or owner of the vehicle, and may instead transmit data (such as captured images and / or limited location information related to the route).

[0112] Other privacy levels may also be considered. For example, the system 100 may transmit data to the server according to a "medium" privacy level and may include additional information that is not included at a "high" privacy level, such as the make and / or model of the vehicle and / or the type of vehicle (e.g., a passenger vehicle, a sport utility vehicle, a truck, etc.). In some embodiments, the system 100 may upload data according to a "low" privacy level. Under the "low" privacy level setting, the system 100 may upload data and include information sufficient to uniquely identify a specific vehicle, owner / driver, and / or a portion of the route or the entire route traveled by the vehicle. For example, such "low" privacy level data may include one or more of the following: VIN, driver / owner name, the source point of the vehicle before departure, the vehicle's desired destination, the make and / or model of the vehicle, the vehicle type, etc.

[0113] Figure 2A is a diagrammatic side view representation of an example vehicle imaging system consistent with the disclosed embodiments. Figure 2B yes Figure 2A A diagrammatic top view illustration of the embodiment shown in FIG. Figure 2B As shown, the disclosed embodiments may include a vehicle 200 including a system 100 in its body with a first image capture device 122 located near a rearview mirror of the vehicle 200 and / or near a driver, a second image capture device 124 located on or in a bumper area (e.g., one of the bumper areas 210) of the vehicle 200, and a processing unit 110.

[0114] like Figure 2C As shown, both image capture devices 122 and 124 may be located near a rearview mirror of vehicle 200 and / or near the driver. Figure 2B and Figure 2C Two image capture devices 122 and 124 are shown, it should be understood that other embodiments may include more than two image capture devices. Figure 2D and Figure 2E In the embodiment shown in , a first image capture device 122 , a second image capture device 124 , and a third image capture device 126 are included in the system 100 of a vehicle 200 .

[0115] like Figure 2D As shown, image capture device 122 may be located near a rearview mirror of vehicle 200 and / or near the driver, and image capture devices 124 and 126 may be located on or in a bumper area (e.g., one of bumper areas 210) of vehicle 200. Figure 2EAs shown, image capture devices 122, 124, and 126 may be located near rearview mirrors and / or near the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices may be located in any suitable location within or on vehicle 200.

[0116] It should be understood that the disclosed embodiments are not limited to vehicles and can be applied in other scenarios. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200 and can be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0117] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280×960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included, for example, to provide a desired focal length and field of view for the image capture device. In some embodiments, the image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, such as Figure 2D As shown, the image capture device 122 can be configured to capture an image with a desired field of view (FOV) 202. For example, the image capture device 122 can be configured to have a conventional FOV, such as in the range of 40 degrees to 56 degrees, including a 46 degree FOV, a 50 degree FOV, a 52 degree FOV, or a larger FOV. Alternatively, the image capture device 122 can be configured to have a narrow FOV in the range of 23 to 40 degrees, such as a 28 degree FOV or a 36 degree FOV. In addition, the image capture device 122 can be configured to have a wide FOV in the range of 100 to 180 degrees. In some embodiments, the image capture device 122 may include a wide-angle bumper camera or a camera with a FOV of up to 180 degrees. In some embodiments, the image capture device 122 may be a 7.2M (million) pixel image capture device with an aspect ratio of approximately 2:1 (e.g., H×V=3800×1900 pixels) and a horizontal FOV of approximately 100 degrees. Such an image capture device can be used to replace the three image capture device configurations. Due to significant lens distortion, in embodiments where the image capture device uses a radially symmetric lens, the vertical FOV of such an image capture device may be significantly less than 50 degrees. For example, such a lens may not be radially symmetric, which would allow a vertical FOV greater than 50 degrees with a 100 degree horizontal FOV.

[0118] The first image capture device 122 may acquire a plurality of first images of a scene associated with the vehicle 200. Each of the plurality of first images may be acquired as a series of image scan lines, which may be captured using a rolling shutter. Each scan line may include a plurality of pixels.

[0119] The first image capture device 122 may have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate may refer to the scan rate at which the image sensor may acquire image data associated with each pixel contained in a particular scan line.

[0120] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, including, for example, CCD sensors or CMOS sensors, etc. In one embodiment, a CMOS image sensor and a rolling shutter may be employed so that each pixel in a row is read one at a time, and scanning of the rows continues on a row-by-row basis until the entire image frame has been captured. In some embodiments, the rows may be captured sequentially from top to bottom relative to the frame.

[0121] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) may constitute a high-resolution imager and may have a resolution greater than 5M pixels, 7M pixels, 10M pixels, or more.

[0122] The use of a rolling shutter may cause pixels in different rows to be exposed and captured at different times, which may cause distortions and other image artifacts in the captured image frame. On the other hand, when the image capture device 122 is configured to operate with a global or synchronized shutter, all pixels may be exposed for the same amount of time and during a common exposure period. As a result, the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a particular time. In contrast, in a rolling shutter application, each row in the frame is exposed and data is captured at a different time. As a result, moving objects may appear distorted in an image capture device with a rolling shutter. This phenomenon will be described in more detail below.

[0123] The second image capture device 124 and the third image capture device 126 may be any type of image capture device. Similar to the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image capture devices 124 and 126 may provide a FOV (such as FOV 204 and 206) that is equal to or narrower than the FOV (such as FOV 202) associated with the image capture device 122. For example, the image capture devices 124 and 126 may have a FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0124] Image capture devices 124 and 126 may acquire a plurality of second and third images of a scene associated with vehicle 200. Each of the plurality of second and third images may be acquired as a second series of image scan lines and a third series of image scan lines, which may be captured using a rolling shutter. Each scan line or row may have a plurality of pixels. Image capture devices 124 and 126 may have a second scan rate and a third scan rate associated with the acquisition of each image scan line included in the second series and the third series.

[0125] Each image capture device 122, 124, and 126 may be placed at any suitable position and orientation relative to vehicle 200. The relative positions of image capture devices 122, 124, and 126 may be selected to help fuse together information obtained from the image capture devices. For example, in some embodiments, a FOV associated with image capture device 124 (such as FOV 204) may partially or completely overlap with a FOV associated with image capture device 122 (such as FOV 202) and a FOV associated with image capture device 126 (such as FOV 206).

[0126] Image capture devices 122, 124, and 126 may be located at any suitable relative heights on vehicle 200. In one example, there may be height differences between image capture devices 122, 124, and 126 that may provide sufficient parallax information to enable stereo analysis. Figure 2AAs shown, the two image capture devices 122 and 124 are at different heights. For example, there may also be lateral displacement differences between the image capture devices 122, 124, and 126, providing additional parallax information for the stereo analysis of the processing unit 110. Figure 2C and Figure 2D As shown, the difference in lateral displacement can be expressed by d x In some embodiments, there may be a forward or backward displacement (e.g., a range displacement) between image capture devices 122, 124, and 126. For example, image capture device 122 may be located 0.5 to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of displacement may enable one of the image capture devices to cover a potential blind spot of the other (one or more) image capture devices.

[0127] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with image capture device 122 may be higher, lower, or the same as the resolution of the image sensor(s) associated with image capture devices 124 and 126. In some embodiments, the image sensor(s) associated with image capture device 122 and / or image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0128] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame and then proceeds to capture pixel data associated with the next image frame) may be controllable. The frame rate associated with image capture device 122 may be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame rate associated with image capture devices 122, 124, and 126 may depend on various factors that may affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 may include a selectable pixel delay period that is applied before or after acquiring image data associated with one or more pixels of an image sensor in image capture devices 122, 124, and / or 126. Typically, image data corresponding to each pixel may be acquired based on a clock rate for the device (e.g., one pixel per clock cycle). Additionally, in embodiments including a rolling shutter, one or more of image capture devices 122, 124, and 126 may include a selectable horizontal blanking period that is applied before or after acquiring image data associated with a row of pixels of an image sensor in image capture devices 122, 124, and / or 126. Additionally, one or more of image capture devices 122, 124, and 126 may include a selectable vertical blanking period that is applied before or after acquiring image data associated with an image frame of image capture devices 122, 124, and 126.

[0129] These timing controls can enable synchronization of frame rates associated with image capture devices 122, 124, and 126, even if the line scan rates of each are different. In addition, as will be discussed in more detail below, these selectable timing controls, as well as other factors (e.g., image sensor resolution, maximum line scan rate, etc.), can enable synchronization of image capture from areas where the FOV of image capture device 122 overlaps with one or more FOVs of image capture devices 124 and 126, even if the field of view of image capture device 122 is different from the FOVs of image capture devices 124 and 126.

[0130] The frame rate timing in image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, assuming that the line scan rates are similar for both devices, if one device includes an image sensor with a resolution of 640×480 and the other device includes an image sensor with a resolution of 1280×960, more time will be required to acquire a frame of image data from the sensor with the higher resolution.

[0131] Another factor that may affect the timing of image data acquisition in image capture devices 122, 124, and 126 is the maximum line scan rate. For example, it will take a certain minimum amount of time to acquire a row of image data from the image sensors included in image capture devices 122, 124, and 126. Assuming that no pixel delay period is added, this minimum amount of time for acquiring a row of image data will be related to the maximum line scan rate for a particular device. Devices that provide a higher maximum line scan rate have the potential to provide a higher frame rate than devices with a lower maximum line scan rate. In some embodiments, one or more of image capture devices 124 and 126 may have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more of the maximum line scan rate of image capture device 122.

[0132] In another embodiment, image capture devices 122, 124, and 126 may have the same maximum line scan rate, but image capture device 122 may operate at a scan rate less than or equal to its maximum scan rate. The system may be configured such that one or more of image capture devices 124 and 126 operate at a line scan rate equal to the line scan rate of image capture device 122. In other examples, the system may be configured such that the line scan rate of image capture device 124 and / or image capture device 126 may be 1.25, 1.5, 1.75, or 2 or more times the line scan rate of image capture device 122.

[0133] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric. That is, they may include cameras with different fields of view (FOV) and focal lengths. For example, the fields of view of image capture devices 122, 124, and 126 may include any desired area of ​​the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, behind vehicle 200, to the side of vehicle 200, or a combination thereof.

[0134] In addition, the focal length associated with each image capture device 122, 124, and / or 126 may be selectable (e.g., by including an appropriate lens, etc.) so that each device acquires images of objects at a desired range of distances relative to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 may acquire images of objects that are within a few meters of the vehicle. The image capture devices 122, 124, and 126 may also be configured to acquire images of objects at a greater range from the vehicle (e.g., 25 meters, 50 meters, 100 meters, 150 meters, or more). In addition, the focal lengths of image capture devices 122, 124, and 126 may be selected so that one image capture device (e.g., image capture device 122) may capture images of objects that are relatively close to the vehicle (e.g., within 10 meters or within 20 meters), while other image capture devices (e.g., image capture devices 124 and 126) may capture images of objects that are farther away from the vehicle 200 (e.g., greater than 20 meters, 50 meters, 100 meters, 150 meters, etc.).

[0135] According to some embodiments, the FOV of one or more image capture devices 122, 124, and 126 may have a wide angle. For example, having a FOV of 140 degrees may be advantageous, especially for image capture devices 122, 124, and 126 that may be used to capture images of areas near vehicle 200. For example, image capture device 122 may be used to capture images of areas to the right or left of vehicle 200, and in these embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0136] The field of view associated with each of the image capture devices 122, 124, and 126 may depend on the respective focal lengths. For example, as the focal length increases, the corresponding field of view decreases.

[0137] Image capture devices 122, 124, and 126 may be configured to have any suitable field of view. In one particular example, image capture device 122 may have a horizontal FOV of 46 degrees, image capture device 124 may have a horizontal FOV of 23 degrees, and image capture device 126 may have a horizontal FOV between 23 degrees and 46 degrees. In another example, image capture device 122 may have a horizontal FOV of 52 degrees, image capture device 124 may have a horizontal FOV of 26 degrees, and image capture device 126 may have a horizontal FOV between 26 degrees and 52 degrees. In some embodiments, the ratio of the FOV of image capture device 122 to the FOV of image capture device 124 and / or image capture device 126 may vary from 1.5 to 2.0. In other embodiments, the ratio may vary between 1.25 and 2.25.

[0138] System 100 may be configured such that the field of view of image capture device 122 at least partially or completely overlaps the field of view of image capture device 124 and / or image capture device 126. In some embodiments, system 100 may be configured such that the fields of view of image capture devices 124 and 126, for example, fall within (e.g., are narrower than) the field of view of image capture device 122 and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs, or may have partial overlap in their FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 may be aligned such that the center of the narrower FOV image capture device 124 and / or 126 may be located in the lower half of the field of view of the wider FOV device 122.

[0139] Figure 2F is a pictorial representation of an example vehicle control system consistent with the disclosed embodiments. Figure 2F As indicated, the vehicle 200 may include a throttle adjustment system 220, a braking system 230, and a steering system 240. The system 100 may provide input (e.g., control signals) to one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 via one or more data links (e.g., any wired and / or wireless links for transmitting data). For example, based on an analysis of images acquired by the image capture devices 122, 124, and / or 126, the system 100 may provide control signals to one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 to navigate the vehicle 200 (e.g., by causing acceleration, steering, lane changes, etc.). In addition, the system 100 may receive input from one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 indicating operating conditions of the vehicle 200 (e.g., speed, whether the vehicle 200 is braking and / or steering, etc.). The following is combined with Figures 4 to 7 Provide further details.

[0140] like Figure 3AAs shown, the vehicle 200 may also include a user interface 170 for interacting with a driver or passenger of the vehicle 200. For example, the user interface 170 in a vehicle application may include a touch screen 320, a knob 330, a button 340, and a microphone 350. The driver or passenger of the vehicle 200 may also interact with the system 100 using a handle (e.g., located on or near the steering column of the vehicle 200, including, for example, a turn signal handle), a button (e.g., located on the steering wheel of the vehicle 200), etc. In some embodiments, the microphone 350 may be located adjacent to the rearview mirror 310. Similarly, in some embodiments, the image capture device 122 may be located near the rearview mirror 310. In some embodiments, the user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, the system 100 may provide various notifications (e.g., alarms) via the speaker 360.

[0141] FIG. 3B to FIG. 3D is an illustration of an example camera mount 370 configured to be located behind a rearview mirror (e.g., rearview mirror 310) and opposite a vehicle windshield consistent with the disclosed embodiments. Figure 3B As shown, camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be located behind visor 380, where visor 380 may be flush with the vehicle windshield and include a film and / or a composite of anti-reflective materials. For example, visor 380 may be positioned so that it is aligned with the windshield of the vehicle with a matching bevel. In some embodiments, each of image capture devices 122, 124, and 126 may be located behind visor 380, such as at Figure 3D The disclosed embodiments are not limited to any particular configuration of image capture devices 122 , 124 , and 126 , camera mount 370 , and visor 380 . Figure 3C yes Figure 3B The camera mount 370 is shown as an illustration from a front perspective.

[0142] As will be appreciated by those skilled in the art having the benefit of this disclosure, many variations and / or modifications may be made to the foregoing disclosed embodiments. For example, not all components are necessary for the operation of the system 100. In addition, any component may be located in any appropriate part of the system 100 and the components may be rearranged into various configurations while providing the functionality of the disclosed embodiments. Therefore, the foregoing configurations are exemplary, and regardless of the configurations discussed above, the system 100 may provide a wide range of functionality to analyze the surroundings of the vehicle 200 and navigate the vehicle 200 in response to the analysis.

[0143] As discussed in more detail below and in accordance with various disclosed embodiments, the system 100 can provide various features related to autonomous driving and / or driver assistance technology. For example, the system 100 can analyze image data, location 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 data for analysis from, for example, the image acquisition unit 120, the location sensor 130, and other sensors. In addition, the system 100 can analyze the collected data to determine whether the vehicle 200 should take a certain action, and then automatically take the determined action without human intervention. For example, when the vehicle 200 navigates 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 the throttle adjustment system 220, the braking system 230, and the steering system 240). In addition, the system 100 can analyze the collected data and issue warnings and / or alarms to the vehicle occupants based on the analysis of the collected data. Additional details of various embodiments provided by the system 100 are provided below.

[0144] Forward multi-imaging system

[0145] As discussed above, the system 100 can provide driving assistance functions using a multi-camera system. The multi-camera system can use one or more cameras facing the front of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side of the vehicle or facing the rear of the vehicle. In one embodiment, for example, the system 100 can use a dual-camera imaging system, wherein the first camera and the second camera (e.g., image capture devices 122 and 124) can be located in front of and / or on the side of the vehicle (e.g., vehicle 200). Other camera configurations are consistent with the disclosed embodiments, and the configurations disclosed herein are exemplary. For example, the system 100 can include a configuration of any number of cameras (e.g., one, two, three, four, five, six, seven, eight, etc.). In addition, the system 100 can include a camera "cluster". For example, a camera cluster (including any appropriate number of cameras, such as one, four, eight, etc.) can be forward relative to the vehicle, or can face any other direction (e.g., backward, sideways, angled, etc.). Therefore, the system 100 can include multiple camera clusters, each of which is oriented in a specific direction to capture images from a specific area of ​​the vehicle environment.

[0146] The first camera may have a field of view that is larger than, smaller than, or partially overlaps the field of view of the second camera. In addition, the first camera may be connected to a first image processor to perform monocular image analysis of the image provided by the first camera, and the second camera may be connected to a second image processor to perform monocular image analysis of the image provided by the second camera. The outputs (e.g., processed information) of the first and second image processors may be combined. In some embodiments, the second image processor may receive images from both the first camera and the second camera to perform stereo analysis. In another embodiment, the system 100 may use a three-camera imaging system, each of which has a different field of view. Thus, such a system may make decisions based on information obtained from objects at varying distances in front of and to the side of the vehicle. References to monocular image analysis may refer to instances of performing image analysis based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may refer to instances of performing image analysis based on two or more images captured using one or more changes in image capture parameters. For example, images captured that are 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, together with parallax information, etc.

[0147] For example, in one embodiment, the system 100 can implement a three-camera configuration using image capture devices 122 to 126. In this configuration, image capture device 122 can provide a narrow field of view (e.g., 34 degrees or other values ​​selected from a range of about 20 degrees to 45 degrees, etc.), image capture device 124 can provide a wide field of view (e.g., 150 degrees or other values ​​selected from a range of about 100 degrees to about 180 degrees), and image capture device 126 can provide an intermediate field of view (e.g., 46 degrees or other values ​​selected from a range of about 35 degrees to about 60 degrees). In some embodiments, image capture device 126 can serve as a primary camera or base camera. Image capture devices 122 to 126 can be located behind rearview mirror 310 and are substantially side by side (e.g., 6 centimeters apart). In addition, in some embodiments, as discussed above, one or more of image capture devices 122 to 126 can be mounted behind a sun visor 380 flush with the windshield of vehicle 200. Such shielding may act to reduce the effect of any reflections from within the vehicle on the image capture devices 122 - 126 .

[0148] In another embodiment, as above combined Figure 3B and 3CAs discussed, the wide field of view camera (e.g., image capture device 124 in the above example) can be mounted lower than the narrow field of view camera and the main field of view camera (e.g., image capture devices 122 and 126 in the above example). This configuration can provide a free line of sight from the wide field of view camera. To reduce reflections, the camera can be mounted close to the windshield of the vehicle 200, and a polarizer can be included on the camera to dampen reflected light.

[0149] The three-camera system may provide certain performance characteristics. For example, some embodiments may include the ability to verify the detection of an object by one camera based on the detection results from another camera. In the three-camera configuration discussed above, the processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), where each processing device is dedicated to processing images captured by one or more of the image capture devices 122 to 126.

[0150] In a three-camera system, the first processing device can receive images from both the main camera and the narrow field of view camera and perform visual processing on the narrow FOV camera to, for example, detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. In addition, the first processing device can calculate the disparity of pixels between the images from the main camera and the narrow camera and create a 3D reconstruction of the environment of the vehicle 200. The first processing device can then combine the 3D reconstruction with 3D map data, or combine the 3D reconstruction with 3D information calculated based on information from another camera.

[0151] The second processing device can receive images from the main camera and perform visual processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. In addition, the second processing device can calculate the camera displacement, and based on the displacement, calculate the disparity of pixels between consecutive images and create a 3D reconstruction of the scene (e.g., structure from motion). The second processing device can send the structure from motion based on the 3D reconstruction to the first processing device to be combined with the stereoscopic 3D image.

[0152] The third processing device can receive images from the wide FOV camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device can also execute additional processing instructions to analyze the images to identify moving objects in the images, such as vehicles changing lanes, pedestrians, etc.

[0153] In some embodiments, having the streams of image-based information captured and processed independently can provide an opportunity to provide redundancy in the system. Such redundancy can include, for example, using a first image capture device and images processed from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0154] In some embodiments, system 100 uses two image capture devices (e.g., image capture devices 122 and 124) in providing navigation assistance to vehicle 200, and uses a third image capture device (e.g., image capture device 126) to provide redundancy and verify the analysis of data received from the other two image capture devices. For example, in such a configuration, image capture devices 122 and 124 may provide images for stereo analysis by system 100 to navigate vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of information obtained based on images captured from image capture device 122 and / or image capture device 124. That is, image capture device 126 (and corresponding processing device) may be viewed as providing a redundant subsystem for providing a check on the analysis obtained from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). In addition, in some embodiments, redundancy and verification 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 the vehicle, etc.).

[0155] Those skilled in the art will recognize that the above-described camera configurations, camera placements, number of cameras, camera positions, etc. are merely examples. These components and other components described with respect to the overall system may be assembled and used in a variety of different configurations without departing 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 are as follows.

[0156] Figure 4 1 is an exemplary functional block diagram of memory 140 and / or storage 150 that may be stored / programmed with instructions for performing one or more operations consistent with embodiments of the present disclosure. Although memory 140 is referred to below, those skilled in the art will recognize that instructions may be stored in memory 140 and / or storage 150.

[0157] like Figure 4As shown, the memory 140 may 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 any particular configuration of the memory 140. In addition, the application processor 180 and / or the image processor 190 may execute instructions stored in any module 402 to 408 contained in the memory 140. Those skilled in the art will appreciate that in the following discussion, references to the processing unit 110 may refer individually or collectively to the application processor 180 and the image processor 190. Therefore, any of the following processing steps may be performed by one or more processing devices.

[0158] In one embodiment, monocular image analysis module 402 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform monocular image analysis on a set of images acquired by one of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from a set of images with additional sensory information (e.g., information from radar) to perform monocular image analysis. FIG. 5A to FIG. 5D As described, the monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other features associated with the vehicle's environment. Based on the analysis, the system 100 (e.g., via the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in conjunction with the navigation response module 408.

[0159] In one embodiment, monocular image analysis module 402 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform monocular image analysis on a set of images acquired by one of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from a set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. FIG. 5A to FIG. 5D As described, the monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other features associated with the vehicle's environment. Based on the analysis, the system 100 (e.g., via the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in conjunction with determining navigation responses.

[0160] In one embodiment, stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform stereo image analysis on a first set of second sets of images acquired by a combination of image capture devices selected from any of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from the first set of second sets of images with additional sensor information (e.g., information from radar) to perform stereo image analysis. For example, stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. As described below in conjunction with Figure 6 As described, stereo image analysis module 404 may include instructions for detecting 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, etc. Based on the analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in conjunction with navigation response module 408. Furthermore, in some embodiments, stereo image analysis module 404 may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.

[0161] In one embodiment, the speed and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in the vehicle 200 configured to cause changes in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 may execute instructions associated with the speed and acceleration module 406 to calculate a target velocity of the vehicle 200 based on data resulting from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, velocity and / or acceleration, position and / or velocity of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, position information of the vehicle 200 relative to lane markings of the road, etc. In addition, the processing unit 110 may calculate the target velocity of the vehicle 200 based on sensory input (e.g., information from a radar) and input from other systems of the vehicle 200, such as the throttle adjustment system 220, the braking system 230, and / or the steering system 240. Based on the calculated target rate, the processing unit 110 can transmit electronic signals to the throttle regulation system 220, the braking system 230 and / or the steering system 240 of the vehicle 200, for example by physically pressing the brake or releasing the accelerator of the vehicle 200, to trigger a change in speed and / or acceleration.

[0162] In one embodiment, the navigation response module 408 may store software that is executable by the processing unit 110 to determine a desired navigation response based on data resulting from execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may 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 may be based (partially or entirely) on map data, a predetermined position of the vehicle 200, and / or a relative velocity or relative acceleration between the vehicle 200 and one or more objects detected from execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine a desired navigation response based on sensory input (e.g., information from a radar) and input from other systems of the vehicle 200, such as the throttle adjustment 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 may transmit electronic signals to the throttle adjustment system 220, the braking system 230, and the steering system 240 of the vehicle 200 to trigger the desired navigation response, such as by turning the steering wheel of the vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as an input to the execution of the speed and acceleration module 406 for calculating the change in the velocity of the vehicle 200.

[0163] Furthermore, any modules disclosed herein (eg, modules 402, 404, and 406) may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.

[0164] Figure 5A is a flow chart illustrating an example process 500A for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via a data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera (such as an image capture device 122 having a field of view 202) included in the image acquisition unit 120 may capture a plurality of images of an area in front of the vehicle 200 (e.g., or to the side or rear of the vehicle) and transmit them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). At step 520, the processing unit 110 may execute the monocular image analysis module 402 to analyze the plurality of images, as described below in conjunction with the processing unit 110. Figures 5B to 5D By performing this analysis, processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0165] In step 520, the processing unit 110 may also execute the monocular image analysis module 402 to detect various road hazards, such as, for example, parts of a truck tire, fallen road signs, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of these hazards more difficult. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on the multiple images to detect road hazards. For example, the processing unit 110 may estimate the camera motion between consecutive image frames and calculate the parallax in the pixels between the frames to build a 3D map of the road. The processing unit 110 can then use the 3D map to detect the road surface and the hazards present on the road surface.

[0166] At step 530, the processing unit 110 may execute the navigation response module 408 to perform the navigation response based on the analysis performed at step 520 and the above combination. Figure 4 The described techniques cause one or more navigation responses. The navigation responses may include, for example, steering, lane changes, acceleration changes, etc. In some embodiments, the processing unit 110 may use data obtained from the execution of the speed and acceleration module 406 to cause one or more navigation responses. In addition, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 may cause the vehicle 200 to change a lane and then accelerate by, for example, sequentially transmitting control signals to the steering system 240 and the throttle adjustment system 220 of the vehicle 200. Alternatively, the processing unit 110 may cause the vehicle 200 to brake and change lanes simultaneously by, for example, simultaneously transmitting control signals to the braking system 230 and the steering system 240 of the vehicle 200.

[0167] Figure 5B is a flowchart showing an example process 500B for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500B. At step 540, the processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, the processing unit 110 may scan one or more images, compare the images to one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or parts thereof). The predetermined patterns may be designed in such a way as to achieve a high "false hit" rate and a low "miss" rate. For example, the processing unit 110 may use a low similarity threshold on the predetermined pattern to identify the candidate object as a possible vehicle or pedestrian. Doing so may allow the processing unit 110 to reduce the likelihood of missing (e.g., not identifying) a candidate object representing a vehicle or pedestrian.

[0168] At step 542, processing unit 110 may filter the set of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria may be derived from various attributes associated with object types stored in a database (e.g., a database stored in memory 140). Attributes may include object shape, size, texture, location (e.g., relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to reject pseudo candidates from the set of candidate objects.

[0169] At step 544, processing unit 110 may analyze multiple frames of images to determine whether an object in the set of candidate objects represents a vehicle and / or a pedestrian. For example, processing unit 110 may track detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to vehicle 200, etc.). In addition, processing unit 110 may estimate parameters of the detected object and compare the frame-by-frame position data of the object with the predicted position.

[0170] At step 546, the processing unit 110 may construct a set of measurements for the detected object. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to the vehicle 200) associated with the detected object. In some embodiments, the processing unit 110 may construct the measurements based on estimation techniques such as a Kalman filter or linear quadratic estimation (LQE) using a series of time-based observations and / or based on modeling data available for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter may be based on a measurement of the scale of the object, where the scale measurement is proportional to the time to collision (e.g., the amount of time it takes the vehicle 200 to reach the object). Thus, by executing steps 540 to 546, the processing unit 110 may identify vehicles and pedestrians that appear within the set of captured images and obtain information associated with the vehicles and pedestrians (e.g., position, velocity, size). Based on the identification and the information obtained, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as in combination with the above. Figure 5A as described.

[0171] In step 548, the processing unit 110 may perform an optical flow analysis on one or more images to reduce the likelihood of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing motion patterns relative to the vehicle 200, associated with other vehicles and pedestrians, and distinct from road motion in one or more images. The processing unit 110 may calculate the motion of the candidate objects by observing different positions of the objects across multiple image frames captured at different times. The processing unit 110 may use the position and time values ​​as input to a mathematical model for calculating the motion of the candidate objects. Therefore, optical flow analysis may provide another method for detecting vehicles and pedestrians near the vehicle 200. The processing unit 110 may perform optical flow analysis in conjunction with steps 540 to 546 to provide redundancy in detecting vehicles and pedestrians and improve the reliability of the system 100.

[0172] Figure 5C is a flow chart illustrating an example process 500C for detecting road markings and / or lane geometry information in a set of images consistent with the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to implement process 500C. At step 550, processing unit 110 may detect a set of objects by scanning one or more images. In order to detect segments of lane markings, lane geometry information, and other relevant road markings, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., small potholes, small rocks, etc.). At step 552, processing unit 110 may group together the segments detected in step 550 that belong to the same road marking or lane marking. Based on the grouping, processing unit 110 may generate a model, such as a mathematical model, representing the detected segments.

[0173] At step 554, the processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, the processing unit 110 may create a projection of the detected segment from the image plane onto the real world plane. The projection may be characterized using a cubic polynomial having coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivative of the detected road. In generating the projection, the processing unit 110 may take into account changes in the road surface, as well as the pitch and roll rates associated with the vehicle 200. In addition, the processing unit 110 may model the road elevation by analyzing the position and motion cues that appear on the road surface. In addition, the processing unit 110 may estimate the pitch and roll rates associated with the vehicle 200 by tracking a set of feature points in one or more images.

[0174] At step 556, processing unit 110 may perform a multi-frame analysis by, for example, tracking the detected segments across consecutive image frames and accumulating frame-by-frame data associated with the detected segments. As processing unit 110 performs multi-frame analysis, the set of measurements constructed in step 554 may become more reliable and associated with increasingly higher confidence levels. Thus, by performing steps 550 to 556, processing unit 110 may identify road markings present in the set of captured images and derive lane geometry information. Based on this identification and the derived information, processing unit 110 may cause one or more navigation responses in vehicle 200, such as those described above in conjunction with Figure 5A as described.

[0175] At step 558, processing unit 110 may consider additional information sources to further generate a safety model of vehicle 200 in its surrounding environment. Processing unit 110 may use the safety model to define an environment in which system 100 may perform autonomous control of vehicle 200 in a safe manner. To generate the safety model, in some embodiments, processing unit 110 may consider the positions and motions of other vehicles, detected curbs and guardrails, and / or general road shape descriptions extracted from map data (such as data from map database 160). By considering additional information sources, processing unit 110 may provide redundancy for detecting road markings and lane geometry and increase the reliability of system 100.

[0176] Figure 5D 5 is a flow chart showing an example process 500D for detecting a traffic light in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500D. At step 560, the processing unit 110 may scan the set of images and identify objects that appear in the image at locations that may contain traffic lights. For example, the processing unit 110 may filter the identified objects to construct a set of candidate objects, excluding those objects that are unlikely to correspond to traffic lights. The filtering may be based on various attributes associated with traffic lights, such as shape, size, texture, position (e.g., relative to the vehicle 200), etc. Such attributes may be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, the processing unit 110 may perform a multi-frame analysis on the set of candidate objects reflecting possible traffic lights. For example, the processing unit 110 may track the candidate objects across consecutive image frames, estimate the real-world position of the candidate objects, and filter out those moving objects (which are unlikely to be traffic lights). In some embodiments, the processing unit 110 may perform a color analysis on the candidate objects and identify the relative position of the detected colors that appear within the possible traffic lights.

[0177] At step 562, processing unit 110 may analyze the geometry of the intersection. The analysis may be based on any combination of: (i) the number of lanes detected on either side of vehicle 200, (ii) markings detected on the road (e.g., arrow markings), and (iii) a description of the intersection extracted from map data (e.g., data from map database 160). Processing unit 110 may use information obtained from execution of monocular analysis module 402 to perform the analysis. In addition, processing unit 110 may determine the correspondence between the traffic lights detected in step 560 and the lanes present near vehicle 200.

[0178] In step 564, as the vehicle 200 approaches the intersection, the processing unit 110 may update the confidence level associated with the analyzed intersection geometry and the detected traffic lights. For example, the number of traffic lights estimated to be present at the intersection compared to the number of traffic lights actually present at the intersection may affect the confidence level. Therefore, based on the confidence level, the processing unit 110 may delegate control to the driver of the vehicle 200 in order to improve safety conditions. By executing steps 560 to 564, the processing unit 110 may identify the traffic lights that appear within the set of captured images and analyze the intersection geometry information. Based on the identification and analysis, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as those described above in conjunction with Figure 5A As described.

[0179] Figure 5E 5 is a flow chart showing an example process 500E for causing one or more navigation responses in a vehicle based on a vehicle path consistent with the disclosed embodiments. At step 570, the processing unit 110 may construct an initial vehicle path associated with the vehicle 200. The vehicle path may be represented by a set of points expressed in coordinates (x, z), and the distance d between two points in the set of points may be i Can fall within the range of 1 to 5 meters. In one embodiment, the processing unit 110 can use two polynomials, such as a left road polynomial and a right road polynomial, to construct an initial vehicle path. The processing unit 110 can calculate the geometric midpoint between the two polynomials and offset each point included in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset), if any (a zero offset can correspond to driving in the middle of the lane). The offset can be in a direction perpendicular to the line segment between any two points in 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., a smart lane offset).

[0180] At step 572, the processing unit 110 may update the vehicle path constructed at step 570. The processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution so that the distance d between two points in the set of points representing the vehicle path is k Smaller than the above distance d i For example, the distance d k It may fall within the range of 0.1 to 0.3 meters. The processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may produce a cumulative distance vector S corresponding to the total length of the vehicle path (ie, based on the set of points representing the vehicle path).

[0181] At step 574, the processing unit 110 may determine a look-ahead point (expressed in coordinates (x l ,z l )). The processing unit 110 can extract a foresight point from the accumulated distance vector S, and the foresight point can be associated with a foresight distance and a foresight time. The foresight distance can have a lower limit ranging from 10 meters to 20 meters and can be calculated as the product of the velocity of the vehicle 200 and the foresight time. For example, as the velocity of the vehicle 200 decreases, the foresight distance can also decrease (e.g., until it reaches the lower limit). The foresight time can range from 0.5 to 1.5 seconds and can be inversely proportional to the gain of one or more control loops such as a heading error tracking control loop associated with causing a navigation response in the vehicle 200. For example, the gain of the heading error tracking control loop can depend on the bandwidth of the yaw rate loop, the steering actuator loop, the lateral dynamics of the vehicle, etc. Therefore, the higher the gain of the heading error tracking control loop, the shorter the foresight time.

[0182] At step 576, the processing unit 110 may determine the heading error and the yaw rate command based on the foresight point determined in step 574. The processing unit 110 may calculate the arc tangent of the foresight point, such as arctan(x l ,z l ) to determine the heading error. The processing unit 110 may determine the yaw rate command as the product of the heading error and the high level control gain. If the look ahead distance is not at the lower limit, the high level control gain may be equal to: (2 / look ahead time). Otherwise, the high level control gain may be equal to: (2×velocity of the vehicle 200 / look ahead distance).

[0183] Fig. 5Fis a flow chart illustrating an example process 500F for determining whether a leading vehicle is changing lanes consistent with the disclosed embodiments. In step 580, processing unit 110 may determine navigation information associated with a leading vehicle (e.g., a vehicle traveling in front of vehicle 200). For example, processing unit 110 may use the above combined Figure 5A and Figure 5B The described techniques can be used to determine the position, speed (e.g., direction and velocity), and / or acceleration of the vehicle ahead. The processing unit 110 can also use the above combined Figure 5E The described techniques determine one or more road polynomials, forward-looking points (associated with vehicle 200), and / or a snail trail (eg, a set of points describing a path taken by a leading vehicle).

[0184] In step 582, processing unit 110 may analyze the navigation information determined in step 580. In one embodiment, processing unit 110 may calculate the distance between the tracking trajectory and the road polynomial (e.g., along the trajectory). If the variance of this distance along the trajectory exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a sharp curve road), processing unit 110 may determine that the leading vehicle is likely to be changing lanes. In the case where multiple vehicles are detected traveling in front of vehicle 200, processing unit 110 may compare the tracking trajectories associated with each vehicle. Based on the comparison, processing unit 110 may determine that the vehicle whose tracking trajectory does not match the tracking trajectories of other vehicles is likely to be changing lanes. Processing unit 110 may additionally compare the curvature of the tracking trajectory (associated with the leading vehicle) with the expected curvature of the road segment in which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., data from map database 160), from a road polynomial, from tracking trajectories of other vehicles, from prior knowledge about the road, etc. If the difference between the curvature of the tracking trajectory and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely to be changing lanes.

[0185] In another embodiment, the processing unit 110 may compare the instantaneous position of the leading vehicle with the forward view point (associated with the vehicle 200) over a specific time period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the leading vehicle and the forward view point changes during the specific time period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a sharp curve road), the processing unit 110 may determine that the leading vehicle is likely to be changing lanes. In another embodiment, the processing unit 110 may analyze the geometry of the tracking track by comparing the lateral distance traveled along the tracking track with the expected curvature of the tracking track. The expected radius of curvature may be determined according to the formula: (δ z 2 +δ x 2 ) / 2 / (δ x ), where δ x represents the lateral distance traveled and δ z The longitudinal distance traveled is represented by the curvature. 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 leading vehicle is likely to be changing lanes. In another embodiment, the processing unit 110 can analyze the position of the leading vehicle. If the position of the leading vehicle obscures the road polynomial (e.g., the leading vehicle covers the top of the road polynomial), the processing unit 110 can determine that the leading vehicle is likely to be changing lanes. In the case where the position of the leading vehicle is such that another vehicle is detected in front of the leading vehicle and the tracking trajectories of the two vehicles are not parallel, the processing unit 110 can determine that the (closer) leading vehicle is likely to be changing lanes.

[0186] In step 584, the processing unit 110 may determine whether the leading vehicle 200 is changing lanes based on the analysis performed in step 582. For example, the processing unit 110 may make this determination based on a weighted average of the individual analyses performed in step 582. Under such an approach, for example, a determination made by the processing unit 110 that the leading vehicle is likely to be changing lanes based on a particular type of analysis may be assigned a value of "1" (and "0" used to represent a determination that the leading vehicle is unlikely to be changing lanes). Different analyses performed in step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights. In addition, in some embodiments, the analysis may utilize a trained system (e.g., a machine learning or deep learning system) that may, for example, estimate a future path ahead of the vehicle's current location based on images captured at the current location.

[0187] Figure 66 is a flow chart illustrating an example process 600 for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments. At step 610, the processing unit 110 may receive the first and second pluralities of images via the data interface 128. For example, a camera included in the image acquisition unit 120 (such as the image capture devices 122 and 124 having the fields of view 202 and 204) may capture the first and second pluralities of images of the area in front of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first and second pluralities of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0188] At step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis on the first and second plurality of images to create a 3D map of the road ahead of the vehicle and detect features within the image, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. The stereo image analysis may be performed in a manner similar to the above combined Figure 5A-5D The processing unit 110 may perform the steps described above in the manner described above. For example, the processing unit 110 may execute the stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) within the first and second multiple images, filter out a subset of the candidate objects based on various criteria, and perform multi-frame analysis, build measurements, and determine confidence levels for the remaining candidate objects. In performing the above steps, the processing unit 110 may consider information from both the first and second multiple images, rather than information from a single set of images. For example, the processing unit 110 may analyze the differences in pixel-level data (or other subsets of data from two streams of captured images) of candidate objects that appear in both the first and second multiple images. As another example, the processing unit 110 may estimate the position and / or speed of the candidate object (e.g., relative to the vehicle 200) by observing that the candidate object appears in one of the multiple images but not in the other, or with respect to other differences that may exist relative to the objects that appear in the two image streams. For example, the position, speed, and / or acceleration relative to the vehicle 200 may be determined based on features such as trajectories, positions, movement characteristics, etc. associated with objects that appear in one or both of the image streams.

[0189] In step 630, the processing unit 110 may execute the navigation response module 408 to respond to the navigation request based on the analysis performed in step 620 and the above combination. Figure 4The described techniques may cause one or more navigation responses in the vehicle 200. The navigation responses may include, for example, steering, lane changes, changes in acceleration, changes in speed, braking, etc. In some embodiments, the processing unit 110 may cause the one or more navigation responses using data obtained from the execution of the speed and acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0190] Figure 7 is a flow chart showing an example process 700 for causing one or more navigation responses based on analysis of three sets of images consistent with the disclosed embodiments. In step 710, the processing unit 110 may receive the first, second, and third plurality of images via the data interface 128. For example, a camera included in the image acquisition unit 120 (such as the image capture devices 122, 124, and 126 having the fields of view 202, 204, and 206) may capture the first, second, and third plurality of images of the area in front of and / or to the side of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first, second, and third plurality of images via three or more data interfaces. For example, each of the image capture devices 122, 124, 126 may have an associated data interface for transmitting data to the processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0191] At step 720, processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. This analysis may be performed in a manner similar to the above combined Figure 5A-5D and Figure 6 For example, the processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., via execution of the monocular image analysis module 402 and based on the above combination Figure 5A-5D Alternatively, the processing unit 110 may perform stereoscopic image analysis on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images (e.g., via execution of the stereoscopic image analysis module 404 and based on the above combined Figure 64 and 5. The processing unit 110 may perform a combination of monocular and stereo image analysis. For example, the processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via execution by the monocular image analysis module 402) and perform stereo image analysis on the second and third plurality of images (e.g., via execution by the stereo image analysis module 404). The configuration of the image capture devices 122, 124, and 126—including their respective positions and fields of view 202, 204, and 206—may affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a particular configuration of the image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0192] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed at steps 710 and 720. Such tests may provide indicators of the overall performance of system 100 for certain configurations of image acquisition devices 122, 124, and 126. For example, processing unit 110 may determine the proportion of "false hits" (e.g., instances where system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses."

[0193] At step 730, the processing unit 110 may cause one or more navigation responses in the vehicle 200 based on information obtained from two of the first, second, and third plurality of images. The selection of two of the first, second, and third plurality of images may depend on various factors, such as, for example, the number, type, and size of objects detected in each of the plurality of images. The processing unit 110 may also make a selection based on image quality and resolution, the effective field of view reflected in the image, the number of frames captured, the degree to which one or more objects of interest actually appear in the frame (e.g., the percentage of frames in which an object appears, the proportion of objects appearing in each such frame), etc.

[0194] In some embodiments, processing unit 110 may select information obtained from two of the first, second, and third pluralities of images by determining the degree to which information obtained from one image source is consistent with information obtained from other image sources. For example, processing unit 110 may combine processed information obtained from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.) that are consistent between each captured image from image capture devices 122, 124, and 126. Processing unit 110 may also exclude information that is inconsistent between captured images (e.g., vehicles changing lanes, lane models indicating that vehicles are too close to vehicle 200, etc.). Thus, processing unit 110 may select information obtained from two of the first, second, and third pluralities of images based on the determination of consistent and inconsistent information.

[0195] The navigation response may include, for example, steering, lane change, change of acceleration, etc. The processing unit 110 may be based on the analysis performed in step 720 and the above combination Figure 4 The described techniques cause one or more navigation responses. Processing unit 110 may also cause one or more navigation responses using data resulting from execution of velocity and acceleration module 406. In some embodiments, processing unit 110 may cause one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration between vehicle 200 and an object detected within any of the first, second, and third pluralities of images. Multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0196] Reinforcement Learning and Trained Navigation Systems

[0197] The following section discusses autonomous driving and systems and methods for accomplishing autonomous control of a vehicle, whether that control is fully autonomous (a self-driving vehicle) or partially autonomous (e.g., one or more driver assistance systems or functions). Figure 8As shown, the autonomous driving task can be divided into three main modules, including a sensing module 801, a driving strategy module 803, and a control module 805. In some embodiments, modules 801, 803, and 805 can be stored in the memory unit 140 and / or the memory unit 150 of the system 100, or modules 801, 803, and 805 (or parts thereof) can be stored away from the system 100 (e.g., stored in a server accessible to the system 100 via, for example, the wireless transceiver 172). In addition, any module disclosed herein (e.g., modules 801, 803, and 805) can implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.

[0198] The sensing module 801, which can be implemented using the processing unit 110, can handle various tasks related to sensing the navigation state in the environment of the main vehicle. These tasks can rely on inputs from various sensors and sensing systems associated with the main vehicle. These inputs can include images or image streams from one or more on-board cameras, GPS location information, accelerometer output, user feedback or user input to one or more user interface devices, radar, lidar, etc. The sensing, which can include data from cameras and / or any other available sensors and map information, can be collected, analyzed and formulated into a "sensed state", which describes the information extracted from the scene in the environment of the main vehicle. The sensed state can include sensed information related to target vehicles, lane markings, pedestrians, traffic lights, road geometry, lane shape, obstacles, distances to other objects / vehicles, relative speeds, relative accelerations, and any other potential sensed information. Supervised machine learning can be implemented to generate a sensed state output based on the sensed data provided to the sensing module 801. The output of the sensing module can represent the sensed navigation "state" of the main vehicle, which can be passed to the driving strategy module 803.

[0199] Although the sensed state can be generated based on image data received from one or more cameras or image sensors associated with the main vehicle, any suitable sensor or sensor combination can also be used to generate the sensed state used in navigation. In some embodiments, the sensed state can be generated without relying on captured image data. In fact, any navigation principle described herein can be applied to sensed states generated based on captured image data and sensed states generated using other non-image-based sensors. The sensed state can also be determined via a source outside the main vehicle. For example, the sensed state can be generated in whole or in part based on information received from a source away from the main vehicle (e.g., based on sensor information shared from other vehicles, shared from a central server, or from any other information source related to the navigation state of the main vehicle, processed state information, etc.).

[0200] The driving strategy module 803 (discussed in more detail below and may be implemented using the processing unit 110) may implement a desired driving strategy to determine one or more navigation actions to be taken by the host vehicle in response to the sensed navigation state. If there are no other agents (e.g., target vehicles or pedestrians) in the environment of the host vehicle, the sensed state input to the driving strategy module 803 may be processed in a relatively straightforward manner. The task becomes more complex when the sensed state requires negotiation with one or more other agents. Techniques for generating the output of the driving strategy module 803 may include reinforcement learning (discussed in more detail below). The output of the driving strategy module 803 may include at least one navigation action for the host vehicle, and may include a desired acceleration (which may be converted into an updated velocity of the host vehicle), a desired yaw rate of the host vehicle, a desired trajectory, and other potential desired navigation actions.

[0201] Based on the output from the driving strategy module 803, the control module 805, which may also be implemented using the processing unit 110, may generate control instructions for one or more actuators or controlled devices associated with the host vehicle. Such actuators and devices may include an accelerator, one or more steering controllers, brakes, signal transmitters, displays, or any other actuators or devices that may be controlled as part of a navigation operation associated with the host vehicle. Aspects of control theory may be used to generate the output of the control module 805. The control module 805 may be responsible for generating and outputting instructions to the controllable components of the host vehicle in order to implement the desired navigation goals or requirements of the driving strategy module 803.

[0202] Returning to the driving policy module 803, in some embodiments, the driving policy module 803 can be implemented using a trained system trained by reinforcement learning. In other embodiments, the driving policy module 803 can be implemented without machine learning methods by using a specified algorithm to "manually" solve various scenarios that may arise during autonomous navigation. However, this approach, while feasible, may result in oversimplification of driving policies and may lack the flexibility of a trained system based on machine learning. For example, a trained system may be better equipped to handle complex navigation states and may better determine whether a taxi is stopping or stopping to pick up / drop off passengers; determine whether a pedestrian intends to cross the street in front of the host vehicle; defensively balance unexpected behavior of other drivers; negotiate in dense traffic involving target vehicles and / or pedestrians; decide when to suspend certain navigation rules or augment other rules; anticipate unsensed but expected conditions (e.g., whether a pedestrian will emerge from behind a car or obstacle); and so on. A trained system based on reinforcement learning may also be better equipped to solve continuous and high-dimensional state spaces and continuous action spaces.

[0203] Training the system using reinforcement learning can involve learning a driving policy to map from sensed states to navigation actions. The driving policy is a function π: S→A, where S is a set of states and is the action space (e.g., desired velocity, acceleration, yaw command, etc.). The state space is S = S s ×S p , where S s is the sensing state, and S p is additional information about the state saved by the strategy. Working in discrete time intervals, at time t, the current state s can be observed t ∈S, and the policy can be applied to obtain the desired action a t =π(s t ).

[0204] The system can be trained by exposing it to various navigation states, causing it to apply the policy, and providing rewards (based on a reward function designed to reward the desired navigation behavior). Based on the reward feedback, the system can "learn" the policy and become trained in producing the desired navigation actions. For example, the learning system can observe the current state s t ∈S, and based on the strategy To decide action a t ∈A. Based on the action decided (and the execution of that action), the environment moves to the next state s t+1∈S, to be observed by the learning system. For each action taken in response to the observed state, the feedback to the learning system is a reward signal r1, r2, ...

[0205] The goal of reinforcement learning (RL) is to find a policy π. It is usually assumed that at time t, there exists a reward function r t , whose measurement is in state s t and take action a t However, taking action a at time t t affects the environment and therefore the value of future states. Therefore, when deciding which action to take, not only the current reward should be considered, but also the future reward. In some cases, when the system determines that a higher reward may be achieved in the future if a lower reward option is taken now, then the system should take an action even if that action is associated with a lower reward than another available option. To formalize this, observe that the policy π and the initial state s are summarized in distribution over , where if the agent starts at state s0 = s and follows policy π from there, then the vector (r1, …, r T ) is the probability of observing rewards r1,…,r T The probability of the initial state s can be defined as:

[0206]

[0207] Instead of limiting the time horizon to T, one can discount future rewards to define, for some fixed γ∈(0,1),

[0208]

[0209] In any case, the best strategy is the solution to:

[0210]

[0211] Among them, the expectation is above the initial state s.

[0212] There are several possible approaches for training a driving policy system. For example, one can use imitation methods (e.g., behavioral cloning), in which the system learns from state / action pairs, where the actions are those that a good actor (e.g., a human) would choose in response to a particular observed state. Suppose that human drivers are observed. From this observation, many forms of (s t ,a t ) (where s t is the state, and a tis the action of a human driver) can be obtained, observed, and used as the basis for training a driving policy system. For example, supervised learning can be used to learn a policy π such that π(s t )≈a t This approach has many potential advantages. First, it does not require the definition of a reward function. Second, the learning is supervised and occurs offline (no actor needs to be applied during the learning process). A disadvantage of this approach is that different human drivers, or even the same human driver, are not deterministic in their choice of strategy. Therefore, for ||π(s t )-a t ||Learning of very small functions is usually not feasible. Moreover, even small errors may accumulate to produce larger errors over time.

[0213] Another technique that can be used is policy-based learning. Here, the policy can be expressed in parameterized form and optimized directly using a suitable optimization technique (e.g., stochastic gradient descent). There are many other ways to solve this problem. One advantage of this approach is that it solves the problem directly, so it often leads to good practical results. A potential disadvantage is that it often requires "online policy" training, that is, the learning of π is an iterative process, where at iteration j, there is a non-perfect policy π j , and in order to construct the next strategy π j , must be based on π j Interact with the environment while performing actions.

[0214] The system can also be trained by value-based learning (learning Q or V functions). Assume that a good approximation can be learned to the optimal value function V*. The optimal policy can be constructed (e.g., relying on the Bellman equation). Some versions of value-based learning can be implemented offline (called "off-policy" training). Some disadvantages of value-based methods may be due to their strong reliance on Markovian assumptions and the need to approximate complex functions (which may be more difficult to approximate the value function than to directly approximate the policy).

[0215] Another technique can include model-based learning and planning (learning the probabilities of state transitions and solving the optimization problem of finding the optimal V). A combination of these techniques can also be used to train a learning system. In this approach, the dynamics of the process can be learned, i.e., taking (s t ,a t ) and in the next state s t+1Once this function is learned, the optimization problem can be solved to find the policy π whose value is optimal. This is called "planning". One advantage of this approach may be that the learning is partially supervised and can be obtained by observing the triples (s t ,a t ,s t+1 ) and are applied offline. Similar to the “imitation” approach, a drawback of this approach may be that small errors in the learning process may accumulate and produce an underperforming strategy.

[0216] Another method for training the driving strategy module 803 may include decomposing the driving strategy function into semantically meaningful components. This allows manual implementation of certain parts of the strategy, which can ensure the safety of the strategy; and other parts of the strategy can be implemented using reinforcement learning techniques, which can be adaptively implemented in many scenarios, a human-like balance between defensive / aggressive behavior, and human-like consultation with other drivers. From a technical perspective, reinforcement learning methods can combine several methods and provide an easy-to-operate training program, most of which can be performed using recorded data or self-built simulators.

[0217] In some embodiments, the training of the driving policy module 803 may rely on an "option" mechanism. To illustrate, consider a simple scenario of a driving policy on a two-lane highway. In a direct RL approach, policy π maps states to , where the first component of π(s) is the desired acceleration command and the second component of π(s) is the yaw rate. In the modified approach, the following strategy can be constructed:

[0218] Automatic Cruise Control (ACC) strategy, o ACC : S → A: This strategy always outputs a yaw rate of 0 and only changes the rate to achieve smooth and accident-free driving.

[0219] ACC+left strategy, o L : S → A: The longitudinal commands for this strategy are the same as the ACC commands. The yaw rate is a direct implementation of centering the vehicle towards the middle of the left lane while ensuring safe lateral movement (e.g., not moving to the left if there is a car on the left).

[0220] ACC+Right Strategy, o R :S→A:with o L Same, but the vehicle may center toward the center of the right lane.

[0221] These strategies can be called "options". Based on these "options", we can learn a strategy π that selects the option o: S→O, where O is a set of available options. In one case, O={o ACC , o L , o R}. Option selector strategy π o By setting To define the actual policy π: S→A.

[0222] In practice, the policy function can be decomposed into an option graph 901, such as Fig. 9 shown. Fig.10 Another example option graph 1000 is shown in FIG. An option graph can represent a hierarchical decision set organized as a directed acyclic graph (DAG). There is a special node called the root node 903 of the graph. This node has no incoming nodes. The decision process starts at the root node and traverses the entire graph until it reaches a "leaf" node, which is a node with no outgoing decision lines. Fig. 9 As shown, the leaf nodes may include, for example, nodes 905, 907, and 909. Upon encountering a leaf node, the driving strategy module 803 may output acceleration and steering commands associated with the desired navigation action associated with the leaf node.

[0223] Internal nodes, such as nodes 911, 913, and 915, for example, may cause the implementation of a policy that selects children among its available options. The set of available children of an internal node includes all nodes associated with the particular internal node via a decision line. For example, Fig. 9 The internal node 913 designated as "merge" in FIG. 9 includes three child nodes 909, 915 and 917 ("keep", "pass right" and "pass left", respectively) each connected to the node 913 via a decision line.

[0224] Flexibility in the decision-making system can be achieved by enabling nodes to adjust their positions in the hierarchy of the option graph. For example, any node can be allowed to declare itself as "critical". Each node can implement an "is critical" function that outputs "true" if the node is in a critical part of its policy implementation. For example, a node responsible for overtaking can declare itself as critical in the middle of a maneuver. This can impose constraints on the set of available children of node u, which can include all nodes v that are children of node u, and there is a path from v to a leaf node that passes through all nodes designated as critical. On the one hand, this approach can allow the expected path to be declared on the graph at each time step, while on the other hand, the stability of the policy can be retained, especially when the critical part of the policy is being implemented.

[0225] By defining an option graph, the problem of learning a driving policy π: S→A can be decomposed into the problem of defining a policy for each node in the graph, where the policy at the internal node should be selected from the available child nodes. For some nodes, the corresponding policy can be implemented manually (for example, by specifying a set of actions in response to the observed state through an if-then type algorithm), while for other policies, a trained system built by reinforcement learning can be used for implementation. The choice between manual or trained / learned methods can depend on the safety aspects associated with the task and on its relative simplicity. The option graph can be constructed in such a way that some nodes are implemented directly, while other nodes can rely on trained models. This approach can ensure the safe operation of the system.

[0226] The following discussion provides information about how to use the driving strategy module 803. Fig. 9 As described above, the input to the driving strategy module is a "sensed state" that summarizes the environment map, for example, obtained from available sensors. The output of the driving strategy module 803 is a set of expectations (optionally together with a set of hard constraints) that define the trajectory as a solution to the optimization problem.

[0227] As described above, the option graph represents a hierarchical decision set organized as a DAG. There is a special node called the "root" of the graph. The root node is the only node with no incoming edges (e.g., decision lines). The decision process traverses the graph starting from the root node until it reaches a "leaf" node, i.e., a node with no outgoing edges. Each internal node should implement a strategy of selecting a child from its available children. Each leaf node should implement a strategy that defines a set of expectations (e.g., a set of navigation goals for the main vehicle) based on the entire path from the root to the leaf. This set of expectations directly defined based on the sensed state together with a set of hard constraints establishes an optimization problem, the solution of which is the trajectory of the vehicle. Hard constraints can be used to further improve the safety of the system, and the expectation can be used to provide the system with driving comfort and human-like driving behavior. The trajectory provided as a solution to the optimization problem further defines the commands that should be provided to the steering, braking and / or engine actuators in order to complete the trajectory.

[0228] return Fig. 9, option graph 901 represents an option graph for a two-lane highway, including merging lanes (meaning that at some point, the third lane merges into the right lane or left lane of the highway). The root node 903 first decides whether the host vehicle is in a normal road scenario or is close to a merging scenario. This is an example of a decision that can be implemented based on the sensing state. The normal road node 911 includes three child nodes: a hold node 909, a left overtaking node 917, and a right overtaking node 915. Hold refers to a situation where the host vehicle wants to continue driving in the same lane. The hold node is a leaf node (no outgoing edges / lines). Therefore, the hold node defines a set of expectations. The first expectation it defines can include a desired lateral position - for example, as close to the center of the current driving lane as possible. It can also be expected to navigate smoothly (for example, within a predetermined or allowed acceleration maximum value). The hold node can also define how the host vehicle reacts to other vehicles. For example, the hold node can view the sensed target vehicles and assign semantic meanings to each vehicle, which can be converted into components of the trajectory.

[0229] Various semantic meanings may be assigned to target vehicles in the host vehicle's environment. For example, in some embodiments, the semantic meaning may include any of the following designations: 1) Not relevant: indicates that the sensed vehicle in the scene is currently not relevant; 2) Next lane: indicates that the sensed vehicle is in an adjacent lane and should maintain an appropriate offset relative to the vehicle (the exact offset may be calculated in an optimization problem that constructs a trajectory given a desired and hard constraint, and the exact offset may potentially be vehicle-dependent - the holding leaf of the option graph sets the semantic type of the target vehicle, which defines the desired relative to the target vehicle); 3) Give way: the host vehicle will attempt to give way to the sensed target vehicle by, for example, reducing speed (especially if the host vehicle determines that the target vehicle may cut into the host vehicle's lane); 4) Takeway: the host vehicle will attempt to take the right of way by, for example, increasing speed; 5) Follow: the host vehicle expects to follow the target vehicle and maintain a smooth drive; 6) Left / right overtaking: this means that the host vehicle wants to initiate a lane change to the left or right lane. Left overtaking node 917 and left overtaking node 915 are internal nodes where the desired is not yet defined.

[0230] The next node in the option graph 901 is the select gap node 919. This node may be responsible for selecting a gap between two target vehicles in a particular target lane that the host vehicle desires to enter. By selecting a node of the form IDj, for some value of j, the host vehicle arrives at a leaf that specifies a desire for the trajectory optimization problem - for example, the host vehicle desires to maneuver in order to reach the selected gap. This maneuver may involve first accelerating / braking in the current lane, then heading to the target lane at an appropriate time to enter the selected gap. If the select gap node 919 cannot find a suitable gap, it moves to the abort node 921, which defines the desire to return to the center of the current lane and cancel the overtaking.

[0231] Returning to the merge node 913, when the host vehicle approaches the merge, it has several options that may depend on the specific situation. Fig.11A As shown, the host vehicle 1105 is traveling along a two-lane road, where no other target vehicles are detected in the main lane or merging lane 1111 of the two-lane road. In this case, the driving strategy module 803 may select the stay node 909 upon reaching the merge node 913. That is, it may be desirable to stay in its current lane without a target vehicle being sensed to merge onto the road.

[0232] exist Fig. 11B Here, the host vehicle 1105 senses one or more target vehicles 1107 entering the main road 1112 from the merging lane 1111. In this case, once the driving strategy module 803 encounters the merging node 913, it can choose to initiate a left passing maneuver to avoid the merging situation.

[0233] exist Fig. 11C , the host vehicle 1105 encounters one or more target vehicles 1107 entering the main road 1112 from the merging lane 1111. The host vehicle 1105 also detects a target vehicle 1109 traveling in a lane adjacent to the host vehicle's lane. The host vehicle also detects one or more target vehicles 1110 traveling in the same lane as the host vehicle 1105. In this case, the driving strategy module 803 can decide to adjust the speed of the host vehicle 1105 to make way for the target vehicle 1107 and travel in front of the target vehicle 1115. This can be achieved, for example, by proceeding to select the gap node 919, which in turn selects the gap between ID0 (vehicle 1107) and ID1 (vehicle 1115) as the appropriate merging gap. In this case, the appropriate gap for the merging situation defines the objective of the trajectory planner optimization problem.

[0234] As described above, nodes of the option graph can declare themselves as "critical", which can ensure that the selected option passes through critical nodes. Formally, each node can implement an IsCritical function. After performing a forward pass from root to leaf on the option graph, and solving the trajectory planner's optimization problem, a reverse pass can be performed from leaf back to root. Along this reverse pass, the IsCritical function of all nodes in the pass can be called, and a list of all critical nodes can be saved. In the forward path corresponding to the next time frame, the driving strategy module 803 may be required to select a path from the root node to the leaf that passes through all critical nodes.

[0235] FIG. 11A to FIG. 11C Can be used to show the potential benefits of this method. For example, in the case where an overtaking action is initiated and the driving strategy module 803 reaches the leaf corresponding to IDk, such as when the main vehicle is in the middle of an overtaking maneuver, it would be undesirable to select the hold node 909. In order to avoid this jump, the IDj node can designate itself as critical. During the maneuver, the success of the trajectory planner can be monitored, and if the overtaking maneuver is performed as expected, the function IsCritical will return a "true" value. This method can ensure that in the next time frame, the overtaking maneuver will continue (rather than jumping to another potentially inconsistent maneuver before completing the initially selected maneuver). On the other hand, if the monitoring of the maneuver indicates that the selected maneuver is not performed as expected, or if the maneuver becomes unnecessary or impossible, the IsCritical function can return a "false" value. This can allow the selection gap node to select a different gap in the next time frame, or to completely terminate the overtaking maneuver. This method can allow the desired path to be declared on the option graph at each time step on the one hand, while on the other hand, it can help improve the stability of the strategy during the critical part of the execution.

[0236] Hard constraints may differ from navigation expectations, which will be discussed in more detail below. For example, hard constraints may ensure safe driving by applying an additional layer of filtering to planned navigation actions. The hard constraints involved may be determined based on the sensed state, and the hard constraints may be manually programmed and defined, rather than by using a trained system based on reinforcement learning. However, in some embodiments, the trained system may learn applicable hard constraints to be applied and followed. This approach may cause the driving strategy module 803 to arrive at a selected action that already complies with the applicable hard constraints, which may reduce or eliminate the selected action that may need to be modified later to comply with the applicable hard constraints. Nevertheless, as a redundant safety measure, hard constraints may be applied to the output of the driving strategy module 803 even when the driving strategy module 803 has been trained to cope with predetermined hard constraints.

[0237] There are many potential examples of hard constraints. For example, a hard constraint may be defined in conjunction with a guardrail at the edge of the road. The host vehicle is not allowed to pass the guardrail under any circumstances. Such a rule creates a hard lateral constraint on the trajectory of the host vehicle. Another example of a hard constraint may include a road bump (e.g., a rate control bump), which may cause a hard constraint on the driving speed before the bump and while traversing the bump. Hard constraints may be considered safety critical and therefore may be defined manually rather than relying solely on a trained system that learns the constraints during training.

[0238] In contrast to hard constraints, a desired goal may be to achieve or attain comfortable driving. As discussed above, an example of a desire may include a goal to place the host vehicle within a lane at a lateral position corresponding to the center of the host vehicle's lane. Another desire may include an ID of a gap that is suitable for entry. Note that the host vehicle need not be exactly in the center of the lane, but rather, a desire to be as close to it as possible may ensure that the host vehicle tends to migrate to the center of the lane even when off-center. Expectations may not be safety critical. In some embodiments, expectations may require negotiation with other drivers and pedestrians. One method of constructing expectations may rely on an option graph, and the policies implemented in at least some nodes of the graph may be based on reinforcement learning.

[0239] For nodes of the option graph 901 or 1000 implemented as nodes based on learning training, the training process may include decomposing the problem into a supervised learning phase and a reinforcement learning phase. In the supervised learning phase, it is possible to learn from (s t ,a t )arrive A differentiable map of This can be similar to "model-based" reinforcement learning. However, in the forward loop of the network, s t+1 The actual value is replaced by This eliminates the problem of error accumulation. The role of prediction is to propagate messages from the future back to past actions. In this sense, the algorithm can be a combination of "model-based" reinforcement learning and "policy-based learning".

[0240] An important element that can be provided in some scenarios is a differentiable path from future loss / reward back to the decision on the action. With the option graph structure, the implementation of options involving safety constraints is usually not differentiable. To overcome this problem, the selection of children in the learned policy node can be random. That is, the node can output a probability vector p that assigns the probability of each child for selecting a particular node. Suppose the node has k children, and let a (1) , ..., a (k)is the action of the path from each child to the leaf. The resulting predicted action is thus This may lead to a differentiable path from that action to p. In practice, action a can be chosen to be a for i~p (i) , and a and The difference between can be called additive noise.

[0241] For a given s t ,a t Down For training, supervised learning can be used with real data. For training of node policies, a simulator can be used. Afterwards, fine-tuning of the policy can be done using real data. Two concepts can make simulation more realistic. First, using imitation, an initial policy can be built using a large real-world dataset using the "behavioral cloning" paradigm. In some cases, the resulting actor can be suitable. In other cases, the resulting actor forms at least a very good initial policy for other actors on the road. Second, using self-play, our own policy can be used to reinforce training. For example, given an initial implementation of other actors (cars / pedestrians) that can be experienced, the policy can be trained based on a simulator. Some other actors can be replaced by new policies, and the process can be repeated. Therefore, the policy can continue to improve because it should respond to a wider variety of other actors with different levels of complexity.

[0242] Furthermore, in some embodiments, the system may implement a multi-actor approach. For example, the system may consider data from various sources and / or images captured from multiple angles. Furthermore, some disclosed embodiments may provide energy economy because anticipation of events that do not directly involve the host vehicle but may have an impact on the host vehicle may be considered, or even anticipation of events that may lead to unpredictable situations involving other vehicles may be a consideration (e.g., radar may "see through" the vehicle ahead and unavoidably anticipate, or even have a high probability of an event that will affect the host vehicle).

[0243] Trained system with imposed navigation constraints

[0244] In the case of autonomous driving, an important concern is how to ensure that the learned policy of the trained navigation network is safe. In some embodiments, the driving policy system can be trained using constraints so that the actions selected by the trained system can already account for the applicable safety constraints. In addition, in some embodiments, an additional layer of safety can be provided by passing the selected actions of the trained system through one or more hard constraints involved in a specific sensed scenario in the environment of the host vehicle. This approach can ensure that the actions taken by the host vehicle are limited to those actions that are confirmed to satisfy the applicable safety constraints.

[0245] At its core, the navigation system may include a learning algorithm based on a policy function that maps observed states to one or more desired actions. In some embodiments, the learning algorithm is a deep learning algorithm. The desired action may include at least one action that is expected to maximize the expected reward of the vehicle. While in some cases, the actual action taken by the vehicle may correspond to one of the desired actions, in other cases, the actual action taken may be determined based on the observed state, one or more desired actions, and non-learned hard constraints (e.g., safety constraints) imposed on the learning navigation engine. These constraints may include a prohibited driving zone around various types of detected objects (e.g., target vehicles, pedestrians, stationary objects on the side of the road or on the road, moving objects on the side of the road or on the road, guardrails, etc.). In some cases, the size of the zone may vary based on the detected motion (e.g., rate and / or direction) of the detected object. Other constraints may include a maximum driving speed when traveling within the influence zone of a pedestrian, a maximum deceleration rate (to cope with the target vehicle spacing behind the main vehicle), a mandatory stop at a sensed crosswalk or railway crossing, and the like.

[0246] Hard constraints used in conjunction with systems trained via machine learning can provide a degree of safety in autonomous driving that may exceed the degree of safety that can be achieved based solely on the output of the trained system. For example, a machine learning system may be trained using a desired set of constraints as a training guide, and thus, the trained system may select an action in response to a sensed navigation state that addresses and complies with the limitations of the applicable navigation constraints. However, the trained system still has some flexibility in selecting navigation actions, and thus, at least in some cases, the actions selected by the trained system may not strictly comply with the relevant navigation constraints. Therefore, in order to require that the selected actions strictly comply with the relevant navigation constraints, the output of the trained system may be combined, compared, filtered, adjusted, modified, etc. using non-machine learning components outside the learning / trained framework that ensure the strict application of the relevant navigation constraints.

[0247] The following discussion provides additional details about the trained system and the potential benefits (particularly from a safety perspective) gleaned from combining the trained system with algorithmic components outside the trained / learning framework. As previously mentioned, the reinforcement learning objective of the policy can be optimized via stochastic gradient ascent. The objective (e.g., expected reward) can be defined as

[0248] Goals involving expectations can be used in machine learning contexts. However, such goals, when not constrained by navigation constraints, may not return actions that are strictly constrained by those constraints. For example, consider a reward function where represents trajectories of rare “corner” events (e.g., such as accidents) to be avoided, while represents the rest of the trajectories, and one goal of the learning system can be to learn to perform overtaking maneuvers. Typically, in accident-free trajectories, will reward successful, smooth overtakes and penalize staying in the lane without completing the overtake - hence the range [-1,1]. represents an accident, then the reward -r should provide a high enough penalty to discourage such an event. The question is what value r should be to ensure accident-free driving.

[0249] Observed that the accident The effect of is an additional term -pr, where p is the probability mass of trajectories with accident events. If this term is negligible, i.e., p<<1 / r, then the learning system can more often prefer a strategy that resulted in an accident (or generally a reckless driving strategy) in order to successfully perform an overtaking maneuver, rather than a more defensive strategy at the expense of some overtaking maneuvers not being successfully completed. In other words, if the probability of an accident is at most p, then r must be set so that r>>1 / p. It may be desirable to make p very small (e.g., at p=10 -9 of the order of magnitude). Therefore, r should be large. In the policy gradient, it can be estimated The following lemma shows that the random variable The variance of pr 2 The variance is larger for r>>1 / p than for r. Therefore, estimating the target may be difficult, and estimating its gradient may be even more difficult.

[0250] Lemma: Let π o Let p and r be scalars, so that with probability p we get And with probability 1-p we get So,

[0251]

[0252] Here, the final approximation applies to the case r ≥ 1 / p.

[0253] This discussion shows that the form The goal may not ensure functional safety without causing variance problems. Baseline subtraction methods for reducing variance may not provide an adequate remedy for this problem because the problem will be The high variance of is transferred to the equally high variance of the baseline constant, whose estimate is also subject to numerical instability. Furthermore, if the probability of an accident is p, then on average at least 1 / p sequences should be sampled before an accident event is obtained. This means that the The minimum number of samples in the learning algorithm sequence is lower bounded by 1 / p. The solution to this problem can be found in the architectural design described in this paper, rather than through numerical tuning techniques. The approach here is based on the idea that hard constraints should be injected outside the learning framework. In other words, the policy function can be decomposed into a learnable part and a non-learnable part. Formally, the policy function can be constructed as in maps the (unknowable) state space to a set of expectations (e.g., desired navigation goals, etc.), and π (T) Map this expectation to a trajectory (which determines how the car should move over short distances). Function π (T) Responsible for driving comfort and making strategic decisions, such as which other cars should be overtaken or given way, and what is the desired position of the host vehicle within its lane. The mapping from the sensed navigation state to the desired is the policy It can learn from experience by maximizing expected reward. The generated expectation can be transformed into a cost function for the driving trajectory. Function π (T) Rather than learning a function, it can be achieved by finding a trajectory that minimizes the cost subject to hard constraints on functional safety. This decomposition can ensure functional safety while providing a comfortable ride.

[0254] like Fig.11D As shown, the double merge navigation situation provides an example that further illustrates these concepts. In a double merge, vehicles approach the merge area 1130 from both the left and right sides. And, vehicles from each side (such as vehicle 1133 or vehicle 1135) can decide whether to merge into the lane on the other side of the merge area 1130. Successfully executing a double merge in heavy traffic may require significant negotiation skills and experience, and may be difficult to perform with a heuristic or brute force approach by enumerating all possible trajectories that all actors in the scene may take. In this double merge example, a set of expected paths suitable for a double merge maneuver can be defined. can be the Cartesian product of the following sets:

[0255] Among them, [0,v max ] is the desired target velocity of the host vehicle, L = {1, 1.5, 2, 2.5, 3, 3.5, 4} is the desired lateral position in lanes, where integers represent lane centers and fractions represent lane boundaries, and {g, t, o} is the classification label assigned to each of the n other vehicles. The other vehicle may be assigned "g" if the host vehicle is to yield to the other vehicle, "t" if the host vehicle is to occupy the lane relative to the other vehicle, or "o" if the host vehicle is to maintain an offset distance relative to the other vehicle.

[0256] The following set of expectations is described How can it be transformed into a cost function for the driving trajectory? The driving trajectory can be (x1, y1),..., (x k ,y k ) means, where (x i ,y i ) is the (lateral, longitudinal) position (in egocentric units) of the subject vehicle at time τ·i, in some experiments τ = 0.1 seconds and k = 10. Of course, other values ​​may also be chosen. The cost assigned to the trajectory may include a weighted sum of the individual costs assigned to the desired velocity, lateral position, and label assigned to each of the other n vehicles.

[0257] Given a desired rate v∈[0,v max ], the cost of the trajectory associated with the rate is

[0258]

[0259] Given a desired lateral position l∈L, the cost associated with the desired lateral position is

[0260]

[0261] where dist(x,y,l) is the distance from point (x,y) to lane position l. Regarding the cost due to other vehicles, for any other vehicle, (x′1, y′1), ..., (x′ k , y′ k ) may represent other vehicles in the egocentric unit of the host vehicle, and i may be the earliest point for which there exists j such that (x i ,y i ) and (x' j ,y' j) is small. If there is no such point, i can be set to i=∞. If the other vehicle is classified as "give way", it can be expected that τi>τj+0.5, which means that the host vehicle will arrive at the trajectory intersection point at least 0.5 seconds after the other vehicle arrives at the same point. The formula used to convert the above constraints into costs can be [τ(ji)+0.5] + .

[0262] Likewise, if another car is classified as “occupying the lane”, we can expect τj>τi+0.5, which can be converted into a cost [τ(ij)+0.5] + If the other car is classified as "offset", then we can expect i = ∞, which means that the trajectory of the host vehicle and the trajectory of the offset car do not intersect. This situation can be converted into a cost by penalizing relative to the distance between the trajectories.

[0263] Assigning weights to each of these costs provides a single objective function π for the trajectory planner (T) A cost to encourage smooth driving can be added to this objective. Furthermore, to ensure the functional safety of the trajectory, hard constraints can be added to this objective. For example, it can be forbidden to i, y i ) leaves the road, and if |i–j| is small, then for any trajectory point (x' j ,y' j ), prohibit (x i, y i ) is close to (x' j ,y' j ).

[0264] In summary, strategy π θ can be decomposed into a mapping from an unknown state to a set of expectations and a mapping from expectations to actual trajectories. The latter mapping is not based on learning and can be achieved by solving an optimization problem whose cost depends on the expectations and whose hard constraints guarantee the functional safety of the policy.

[0265] The following discussion describes the mapping from unknowable states to this set of expectations. As mentioned above, in order to comply with functional safety, a system that relies solely on reinforcement learning may suffer from This result can be avoided by using policy gradients to iteratively decompose the problem into a mapping from an (unknowable) state space to a set of desired trajectories, followed by a mapping to actual trajectories without involving a machine learning-based trained system.

[0266] Decision making can be further broken down into semantically meaningful components for a variety of reasons. For example, The size of may be large or even continuous. Fig.11D In the double lane merging scenario described above, Additionally, the gradient estimator may involve the term In such an expression, the variance may grow with the time range T. In some cases, the value of T may be approximately 250, which may be sufficient to produce significant variance. Assuming the sampling rate is in the range of 10 Hz, and the merge area 1130 is 100 meters, the preparation for the merge may begin approximately 300 meters before the merge area. If the host vehicle is traveling at a speed of 16 meters per second (approximately 60 kilometers per hour), the value of T for the episode may be approximately 250.

[0267] Back to the concept of option map, Fig.11E It is shown that it can be expressed Fig.11D As previously described, the option graph may represent a hierarchical set of decisions organized as a directed acyclic graph (DAG). There may be a special node in the graph called a "root" node 1140, which may be the only node with no incoming edges (e.g., decision lines). The decision process may traverse the graph starting from the root node until it reaches a "leaf" node, i.e., a node with no outgoing edges. Each internal node may implement a policy function that selects a child from its available children. There may be a set of desired choices that are traversed from the option graph to a set of desired choices. In other words, traversals on the option graph can be automatically converted to Given a node v in the graph, the parameter vector θ v A strategy for selecting the children of v can be specified. If θ is all θ v The concatenation of , then, can be defined by traversing from the root of the graph to the leaves At the same time, at each node v, the v Defines the strategy to select child nodes.

[0268] exist Fig.11E In the double merging option diagram 1139, the root node 1140 may first determine whether the host vehicle is in the merging area (e.g., Fig.11D1130), or whether the host vehicle is approaching a merging area and needs to prepare for a possible merge. In both cases, the host vehicle may need to decide whether to change lanes (e.g., to the left or right) or whether to remain in the current lane. If the host vehicle has decided to change lanes, the host vehicle may need to decide whether conditions are suitable to continue and execute the lane change maneuver (e.g., at a “continue” node 1142). If a lane change is not possible, the host vehicle may attempt to “advance” toward the desired lane by aiming to be on the lane markings (e.g., at node 1144 as part of a negotiation with vehicles in the desired lane). Alternatively, the host vehicle may choose to “stay” in the same lane (e.g., at node 1146). This process can determine the lateral position of the host vehicle in a natural manner. For example,

[0269] This allows for determining the desired lateral position in a natural way. For example, if the host vehicle changes lanes from lane 2 to lane 3, the "continue" node can set the desired lateral position to 3, the "hold" node can set the desired lateral position to 2, and the "advance" node can set the desired lateral position to 2.5. Next, the host vehicle can decide whether to maintain the "same" rate (node ​​1148), "speed up" (node ​​1150), or "slow down" (node ​​1152). Next, the host vehicle can enter a "chain-like" structure 1154 of overtaking other vehicles and setting their semantic meaning to values ​​in the set {g, t, o}. This process can set expectations relative to other vehicles. The parameters of all nodes in the chain can be shared (similar to a recurrent neural network).

[0270] A potential benefit of this option is the interpretability of the results. Another potential benefit is that you can rely on the collection The decomposable structure of , and therefore, the policy at each node can be selected from a small number of probabilities. In addition, this structure can allow reducing the variance of the policy gradient estimator.

[0271] As described above, the length of the segments in the double merging scenario may be approximately T = 250 steps. Such a value (or any other suitable value depending on the specific navigation scenario) may provide sufficient time to see the consequences of the host vehicle's actions (e.g., if the host vehicle decides to change lanes as a preparation for a merge, the host vehicle can only see the benefit after successfully completing the merge). On the other hand, due to the dynamics of driving, the host vehicle must make decisions at a sufficiently fast frequency (e.g., 10 Hz in the above case).

[0272] The option graph can achieve a lower effective value of T in at least two ways. First, given higher-level decisions, rewards can be defined for lower-level decisions while considering shorter segments. For example, when the host vehicle has selected the "lane change" and "continue" nodes, a policy for assigning semantic meaning to the vehicle can be learned by watching 2 to 3 seconds of segments (meaning that T becomes 20-30 instead of 250). Second, for high-level decisions (such as whether to change lanes or stay in the same lane), the host vehicle may not need to make a decision every 0.1 seconds. Alternatively, the host vehicle can make decisions at a lower frequency (e.g., every second), or implement an "option termination" function, and then the gradient can be calculated only after each option termination. In both cases, the effective value of T may be an order of magnitude smaller than its original value. In summary, the estimator of each node can depend on a value of T that is an order of magnitude smaller than the original 250 steps, which may immediately turn into a smaller variance.

[0273] As described above, hard constraints can promote safer driving, and there can be several different types of constraints. For example, static hard constraints can be defined directly based on the sensed state. These hard constraints may include speed bumps, rate limits, road bends, intersections, etc. within the environment of the host vehicle, which may involve one or more constraints on vehicle speed, heading, acceleration, braking (deceleration), etc. Static hard constraints may also include semantic free space, where, for example, the host vehicle is prohibited from driving outside the free space and is prohibited from driving too close to physical obstacles. Static hard constraints can also limit (e.g., prohibit) manipulations that do not conform to various aspects of the vehicle's kinematic motion. For example, static hard constraints can be used to prohibit manipulations that may cause the host vehicle to flip, slide, or otherwise lose control.

[0274] Hard constraints may also be associated with the vehicle. For example, a constraint may be employed that requires the vehicle to maintain a longitudinal distance of at least one meter to other vehicles and a lateral distance of at least 0.5 meters to other vehicles. Constraints may also be applied such that the host vehicle will avoid maintaining a collision course with one or more other vehicles. For example, time τ may be a time metric based on a particular scenario. The predicted trajectories of the host vehicle and one or more other vehicles may be considered from the current time to time τ. In the event that the two trajectories intersect, We can denote the time it takes for vehicle i to arrive at and leave an intersection. That is, each car will arrive at the intersection when the first part of the car passes through it, and it will take a certain amount of time before the last part of the car passes through it. This amount of time separates the arrival time from the departure time. Assume (i.e., the arrival time of vehicle 1 is less than the arrival time of vehicle 2), then we will want to ensure that vehicle 1 has left the intersection before vehicle 2 arrives. Otherwise, a collision will result. Therefore, we can implement Furthermore, to ensure that vehicle 1 and vehicle 2 miss each other by a minimum amount, an additional safety margin can be obtained by including a buffer time (e.g., 0.5 seconds or another appropriate value) in the constraint. The hard constraint related to the predicted intersection trajectory of the two vehicles can be expressed as

[0275] The amount of time τ that the trajectories of the host vehicle and one or more other vehicles are tracked may vary. However, in an intersection scenario, the rate may be lower, τ may be longer, and τ may be defined so that the host vehicle will enter and leave the intersection in less than τ seconds.

[0276] Of course, applying hard constraints to vehicle trajectories requires predicting the trajectories of those vehicles. For the host vehicle, trajectory prediction may be relatively straightforward because the host vehicle generally already understands and is in fact planning the expected trajectory at any given time. Relative to other vehicles, predicting their trajectories may be less straightforward. For other vehicles, the baseline calculation used to determine the predicted trajectory may rely on the current speed and heading of the other vehicles, for example, as determined based on analysis of image streams captured by one or more cameras and / or other sensors (radar, lidar, acoustics, etc.) on the host vehicle.

[0277] However, there may be some exceptions that may simplify the problem or at least provide increased confidence in the trajectory predicted for another vehicle. For example, for structured roads where there are lane indications and where there may be give-way rules, the trajectory of the other vehicle may be based at least in part on the position of the other vehicle relative to the lane and on applicable give-way rules. Thus, in some cases, when the lane structure is observed, it may be assumed that the vehicle in the next lane will respect the lane boundaries. That is, the host vehicle may assume that the vehicle in the next lane will remain in its lane unless evidence is observed indicating that the vehicle in the next lane will cut into the host vehicle's lane (e.g., a signal light, strong lateral motion, movement across a lane boundary).

[0278] Other situations may also provide clues about the expected trajectory of other vehicles. For example, at stop signs, traffic lights, roundabouts, etc. where the host vehicle may have the right of way, it can be assumed that other vehicles will obey that right of way. Therefore, unless evidence of a violation is observed, it can be assumed that other vehicles will continue along a trajectory that obeys the right of way held by the host vehicle.

[0279] Hard constraints may also be applied relative to pedestrians in the host vehicle's environment. For example, a buffer distance may be established relative to pedestrians such that the host vehicle is prohibited from traveling closer than a specified buffer distance relative to any observed pedestrian. The pedestrian buffer distance may be any suitable distance. In some embodiments, the buffer distance may be at least one meter relative to an observed pedestrian.

[0280] Similar to the case with vehicles, hard constraints can also be applied relative to the relative motion between pedestrians and the host vehicle. For example, the trajectory of a pedestrian (based on heading and velocity) can be monitored relative to the predicted trajectory of the host vehicle. Given a specific pedestrian trajectory, where for each point p on the trajectory, t(p) can represent the time required for the pedestrian to reach point p. In order to maintain the required buffer distance of at least 1 meter from the pedestrian, t(p) must be greater than the time the host vehicle will arrive at point p (with enough time difference so that the host vehicle passes at least one meter in front of the pedestrian), or t(p) must be less than the time the host vehicle will arrive at point p (for example, if the host vehicle brakes to make way for the pedestrian). Nevertheless, in the latter example, the hard constraint may require the host vehicle to arrive at point p enough later than the pedestrian so that the host vehicle can pass behind the pedestrian and maintain the required buffer distance of at least one meter. Of course, there may be exceptions to the hard constraints for pedestrians. For example, in situations where the host vehicle has the right of way or is moving very slowly, and no evidence is observed that the pedestrian will refuse to yield to the host vehicle or will otherwise navigate toward the host vehicle, the hard pedestrian constraint can be relaxed (e.g., to a smaller buffer of at least 0.75 meters or 0.50 meters).

[0281] In some examples, in the case where it is determined that not all constraints can be satisfied, the constraints can be relaxed. For example, in the case where the road is too narrow to leave two curbs or the required spacing (e.g., 0.5 meters) between the curb and the parked vehicle, if there is a mitigating situation, one or more constraints can be relaxed. For example, if there are no pedestrians (or other objects) on the sidewalk, you can drive slowly at 0.1 meters from the curb. In some embodiments, if relaxing the constraints will improve the user experience, the constraints can be relaxed. For example, to avoid potholes, constraints can be relaxed to allow vehicles to get closer to the edge of the lane, the curb, or pedestrians than they might normally allow. In addition, when determining which constraints to relax, in some embodiments, one or more constraints to be relaxed are selected to be those that are considered to have the smallest available negative impact on safety. For example, before relaxing a constraint involving proximity to other vehicles, constraints on how close a vehicle can travel to a curb or concrete barrier can be relaxed. In some embodiments, pedestrian constraints may be the last to be relaxed, or in some cases may never be relaxed.

[0282] Fig.12 Examples of scenes that may be captured and analyzed during navigation of a host vehicle are shown. For example, the host vehicle may include a navigation system as described above (e.g., system 100), which may receive a plurality of images representing an environment of the host vehicle from a camera associated with the host vehicle (e.g., at least one of image capture device 122, image capture device 124, and image capture device 126). Fig.12The scene shown in is an example of one of the images that may be captured at time t from the environment of a host vehicle traveling in lane 1210 along predicted trajectory 1212. The navigation system may include at least one processing device (e.g., including any EyeQ processor or other device described above) that is specifically programmed to receive multiple images and analyze the images to determine an action in response to the scene. Specifically, as Figure 8 As shown, at least one processing device may implement a sensing module 801, a driving strategy module 803, and a control module 805. The sensing module 801 may be responsible for collecting and outputting image information collected from a camera, and providing the information to the driving strategy module 803 in the form of an identified navigation state, which may constitute a trained navigation system that has been trained by machine learning techniques (such as supervised learning, reinforcement learning, etc.). Based on the navigation state information provided by the sensing module 801 to the driving strategy module 803, the driving strategy module 803 (e.g., by implementing the option map method described above) may generate a desired navigation action for execution by the host vehicle in response to the identified navigation state.

[0283] In some embodiments, at least one processing device may use, for example, a control module 805 to directly convert the desired navigation action into a navigation command. However, in other embodiments, hard constraints may be applied so that the desired navigation action provided by the driving strategy module 803 is tested for various predetermined navigation constraints that may be involved in the scene and the desired navigation action. For example, in the case where the driving strategy module 803 outputs a desired navigation action that will cause the main vehicle to follow the trajectory 1212, the navigation action may be tested relative to one or more hard constraints associated with various aspects of the environment of the main vehicle. For example, the captured image 1201 may show a curb 1213, a pedestrian 1215, a target vehicle 1217, and a stationary object (e.g., an overturned box) present in the scene. Each of these may be associated with one or more hard constraints. For example, the curb 1213 may be associated with a static constraint that prohibits the main vehicle from navigating into the curb or past the curb and onto the sidewalk 1214. The curb 1213 may also be associated with a barrier envelope that defines a distance (e.g., a buffer zone) away from and extending along the curb (e.g., 0.1 m, 0.25 m, 0.5 m, 1 m, etc.) that defines a prohibited navigation zone for the host vehicle. Of course, static constraints may also be associated with other types of roadside boundaries (e.g., guardrails, concrete columns, traffic cones, bridge pylons, or any other type of roadside obstacle).

[0284] It should be noted that the distance and range can be determined by any suitable method. For example, in some embodiments, the distance information can be provided by an onboard radar and / or lidar system. Alternatively or additionally, the distance information can be derived from an analysis of one or more images captured from the environment of the host vehicle. For example, a number of pixels of the identified object represented in the image can be determined and compared with the known field of view and focal length geometry of the image capture device to determine the scale and distance. For example, the speed and acceleration can be determined by observing the change in scale between objects from image to image within a known time interval. The analysis can indicate the direction of movement of the object toward or away from the host vehicle, and how fast the object is moving away from or toward the host vehicle. The crossing speed can be determined by analyzing the change in the X-coordinate position of the object from one image to another within a known time period.

[0285] Pedestrian 1215 may be associated with a pedestrian envelope defining a buffer zone 1216. In some cases, the imposed hard constraints may prohibit the host vehicle from navigating within a distance of one meter from pedestrian 1215 (in any direction relative to pedestrian 1215). Pedestrian 1215 may also define the location of pedestrian impact zone 1220. Such an impact zone may be associated with a constraint that limits the speed of the host vehicle within the impact zone. The impact zone may extend 5 meters, 10 meters, 20 meters, etc. from pedestrian 1215. Each graduation of the impact zone may be associated with a different rate limit. For example, in an area from one meter to five meters from pedestrian 1215, the host vehicle may be limited to a first rate (e.g., 10 mph (miles per hour), 20 mph, etc.), which may be less than the rate limit in the pedestrian impact zone extending from 5 meters to 10 meters. Any graduation may be used for each level of the impact zone. In some embodiments, the first level may be narrower than from one meter to five meters, and may extend only from one meter to two meters. In other embodiments, the first level of influence zone may extend from one meter (the boundary of the no-navigation zone around pedestrians) to a distance of at least 10 meters. The second level may extend from ten meters to at least about twenty meters. The second level may be associated with a maximum travel speed of the host vehicle that is greater than the maximum travel speed associated with the first level of pedestrian influence zone.

[0286] One or more stationary object constraints may also be associated with a scene detected in the environment of the host vehicle. For example, in image 1201, at least one processing device may detect a stationary object, such as a box 1219 present in a road. The detected stationary object may include various objects, such as at least one of a tree, a pole, a road sign, or an object in a road. One or more predetermined navigation constraints may be associated with the detected stationary object. For example, such a constraint may include a stationary object envelope, wherein the stationary object envelope defines a buffer zone about the object, and the host vehicle may be prohibited from navigating into the buffer zone. At least a portion of the buffer zone may extend a predetermined distance from the edge of the detected stationary object. For example, in the scene represented by image 1201, a buffer zone of at least 0.1 meters, 0.25 meters, 0.5 meters, or more may be associated with box 1219, so that the host vehicle will pass through the right or left side of the box at least a distance (e.g., a buffer zone distance) to avoid collision with the detected stationary object.

[0287] The predetermined hard constraints may also include one or more target vehicle constraints. For example, a target vehicle 1217 may be detected in image 1201. To ensure that the host vehicle does not collide with the target vehicle 1217, one or more hard constraints may be employed. In some cases, the target vehicle envelope may be associated with a single buffer distance. For example, a buffer may be defined by a distance of 1 meter around the target vehicle in all directions. The buffer may define an area extending at least one meter from the target vehicle into which the host vehicle is prohibited from navigating.

[0288] However, the envelope around the target vehicle 1217 need not be defined by a fixed buffer distance. In some cases, the predetermined hard constraints associated with the target vehicle (or any other movable object detected in the environment of the host vehicle) may depend on the orientation of the host vehicle relative to the detected target vehicle. For example, in some cases, the longitudinal buffer distance (e.g., the distance extending from the target vehicle to the front or rear of the host vehicle - such as when the host vehicle is traveling toward the target vehicle) can be at least one meter. The lateral buffer distance (e.g., the distance extending from the target vehicle to either side of the host vehicle - such as when the host vehicle is traveling in the same or opposite direction as the target vehicle so that one side of the host vehicle will pass adjacent to one side of the target vehicle) can be at least 0.5 meters.

[0289] As described above, other constraints may also be involved through the detection of target vehicles or pedestrians in the host vehicle's environment. For example, the predicted trajectories of the host vehicle and the target vehicle 1217 may be considered, and in the event that the two trajectories intersect (e.g., at the intersection point 1230), a hard constraint may be required. or The host vehicle is vehicle 1 and the target vehicle 1217 is vehicle 2. Similarly, the trajectory of pedestrian 1215 (based on heading and velocity) can be monitored relative to the predicted trajectory of the host vehicle. Given a particular pedestrian trajectory, for each point p on the trajectory, t(p) will represent the pedestrian's arrival at point p (i.e., Fig.12 In order to maintain the required buffer distance of at least 1 meter from the pedestrian, t(p) must be greater than the time the host vehicle will arrive at point p (with enough time difference so that the host vehicle passes at least one meter in front of the pedestrian), or t(p) must be less than the time the host vehicle will arrive at point p (for example, if the host vehicle brakes to make way for the pedestrian). Nevertheless, in the latter example, the hard constraint will require the host vehicle to arrive at point p enough later than the pedestrian so that the host vehicle can pass behind the pedestrian and maintain the required buffer distance of at least one meter.

[0290] Other hard constraints may also be employed. For example, at least in some cases, a maximum deceleration rate for the host vehicle may be employed. Such a maximum deceleration rate may be determined based on a detected distance to a target vehicle following the host vehicle (e.g., using images collected from a rear-facing camera). Hard constraints may include mandatory stops at sensed crosswalks or railroad crossings, or other applicable constraints.

[0291] In the case where the analysis of the scene in the environment of the host vehicle indicates that one or more predetermined navigation constraints may be involved, these constraints may be imposed relative to one or more planned navigation actions of the host vehicle. For example, in the case where the analysis of the scene causes the driving strategy module 803 to return an expected navigation action, the expected navigation action may be tested against one or more involved constraints. If the expected navigation action is determined to violate any aspect of the constraints involved (e.g., if the expected navigation action will drive the host vehicle within 0.7 meters of the pedestrian 1215, where the predetermined hard constraint requires the host vehicle to maintain a distance of at least 1.0 meters from the pedestrian 1215), at least one modification may be made to the expected navigation action based on one or more predetermined navigation constraints. Adjusting the expected navigation action in this manner may provide actual navigation actions for the host vehicle in accordance with the constraints involved in the specific scene detected in the environment of the host vehicle.

[0292] After determining the actual navigation action of the host vehicle, the navigation action can be implemented by causing at least one adjustment of a navigation actuator of the host vehicle in response to the determined actual navigation action of the host vehicle. Such a navigation actuator can include at least one of a steering mechanism, a brake, or an accelerator of the host vehicle.

[0293] Precedence Constraints

[0294] As described above, the navigation system may employ various hard constraints to ensure safe operation of the host vehicle. Constraints may include a minimum safe driving distance relative to pedestrians, target vehicles, roadblocks, or detected objects, a maximum travel speed when passing within the influence zone of a detected pedestrian, or a maximum deceleration rate of the host vehicle, etc. These constraints may be imposed on trained systems based on machine learning (supervised, reinforcement, or combination) training, but they may also be useful for untrained systems (e.g., those systems that employ algorithms to directly process expected situations occurring in scenes from the host vehicle environment).

[0295] In either case, there may be a hierarchy of constraints. In other words, some navigation constraints take precedence over other constraints. Thus, if a situation arises where no navigation action is available that would result in all relevant constraints being satisfied, the navigation system may first determine an available navigation action that implements the highest priority constraint. For example, the system may also cause the vehicle to avoid the pedestrian first, even if navigation to avoid the pedestrian would result in a collision with another vehicle or object detected in the road. In another example, the system may cause the vehicle to ride on a curb to avoid the pedestrian.

[0296] Fig.13 A flow chart illustrating an algorithm for implementing a hierarchy of associated constraints determined based on an analysis of a scene in the environment of a host vehicle is provided. For example, at step 1301, at least one processing device associated with a navigation system (e.g., an EyeQ processor, etc.) may receive a plurality of images representing the environment of the host vehicle from a camera mounted on the host vehicle. By analyzing the images representing the scene in the environment of the host vehicle at step 1303, a navigation state associated with the host vehicle may be identified. For example, the navigation state may indicate that the host vehicle is traveling along a two-lane road 1210, such as Fig.12 12, wherein a target vehicle 1217 is moving through an intersection in front of the host vehicle, a pedestrian 1215 is waiting to cross the path of the host vehicle, an object 1219 exists in front of the host vehicle's lane, and various other attributes of the scene.

[0297] In step 1305, one or more navigation constraints related to the navigation state of the host vehicle may be determined. For example, after analyzing a scene in the environment of the host vehicle represented by one or more captured images, at least one processing device may determine one or more navigation constraints related to objects, vehicles, pedestrians, etc. identified by image analysis of the captured images. In some embodiments, at least one processing device may determine at least a first predetermined navigation constraint and a second predetermined navigation constraint related to the navigation state, and the first predetermined navigation constraint may be different from the second predetermined navigation constraint. For example, the first navigation constraint may relate to one or more target vehicles detected in the environment of the host vehicle, and the second navigation constraint may relate to pedestrians detected in the environment of the host vehicle.

[0298] In step 1307, at least one processing device may determine a priority associated with the constraint identified in step 1305. In the described example, a second predetermined navigation constraint involving a pedestrian may have a higher priority than a first predetermined navigation constraint involving a target vehicle. Although the priority associated with a navigation constraint may be determined or assigned based on various factors, in some embodiments, the priority of a navigation constraint may be related to its relative importance from a safety perspective. For example, while it may be important to comply with or meet all implemented navigation constraints in as many cases as possible, some constraints may be associated with a higher safety risk than other constraints, and therefore, these constraints may be assigned a higher priority. For example, a navigation constraint requiring the host vehicle to maintain a spacing of at least 1 meter from a pedestrian may have a higher priority than a constraint requiring the host vehicle to maintain a spacing of at least 1 meter from a target vehicle. This may be because a collision with a pedestrian may have more serious consequences than a collision with another vehicle. Similarly, maintaining the spacing between the host vehicle and the target vehicle may have a higher priority than the following constraints: requiring the host vehicle to avoid boxes on the road, driving below a certain speed on a speed bump, or exposing the host vehicle occupant to no more than a maximum acceleration level.

[0299] Although the driving strategy module 803 is designed to maximize safety by satisfying the navigation constraints involved in a particular scenario or navigation state, in some cases, it is not actually possible to satisfy each involved constraint. In this case, as shown in step 1309, the priority of each involved constraint can be used to determine which involved constraint should be satisfied first. Continuing with the above example, in the case where it is not possible to satisfy both the pedestrian gap constraint and the target vehicle gap constraint at the same time, and only one of the constraints can be satisfied, the higher priority pedestrian gap constraint may cause the constraint to be satisfied before attempting to maintain a gap to the target vehicle. Therefore, under normal circumstances, as shown in step 1311, in the case where both the first predetermined navigation constraint and the second predetermined navigation constraint can be satisfied, at least one processing device can determine the first navigation action of the main vehicle that satisfies both the first predetermined navigation constraint and the second predetermined navigation constraint based on the identified navigation state of the main vehicle. However, in other cases, when not all involved constraints can be satisfied, as shown in step 1313, when the first predetermined navigation constraint and the second predetermined navigation constraint cannot be satisfied at the same time, at least one processing device can determine, based on the identified navigation state, a second navigation action of the main vehicle that satisfies the second predetermined navigation constraint (i.e., a higher priority constraint) but does not satisfy the first predetermined navigation constraint (having a lower priority than the second navigation constraint).

[0300] Next, in order to implement the determined navigation action of the host vehicle, at least one processing device may cause at least one adjustment of a navigation actuator of the host vehicle in response to the determined first navigation action of the host vehicle or the determined second navigation action of the host vehicle at step 1315. As described in the previous examples, the navigation actuator may include at least one of a steering mechanism, a brake, or an accelerator.

[0301] Constraint Relaxation

[0302] As described above, navigation constraints may be imposed for safety purposes. Constraints may include a minimum safe driving distance relative to a pedestrian, target vehicle, roadblock, or detected object, a maximum driving speed when passing within the impact zone of a detected pedestrian, or a maximum deceleration rate of the host vehicle, and the like. These constraints may be imposed on a learning or non-learning navigation system. In some cases, these constraints may be relaxed. For example, in the case where the host vehicle slows down or stops near a pedestrian and then moves slowly forward to convey the intention to pass the pedestrian, the response of the pedestrian may be detected from the acquired image. If the pedestrian's response is to remain still or stop moving (and / or if eye contact with the pedestrian is sensed), it may be understood that the pedestrian recognizes the intention of the navigation system to pass the pedestrian. In this case, the system may relax one or more predetermined constraints and implement less stringent constraints (e.g., allowing the vehicle to navigate within 0.5 meters of the pedestrian, rather than within a stricter 1-meter boundary).

[0303] Fig.14 A flow chart for implementing control of a host vehicle based on relaxation of one or more navigation constraints is provided. In step 1401, at least one processing device may receive a plurality of images representing an environment of the host vehicle from a camera associated with the host vehicle. Analysis of the images in step 1403 may enable identification of a navigation state associated with the host vehicle. In step 1405, at least one processor may determine a navigation constraint associated with the navigation state of the host vehicle. The navigation constraint may include a first predetermined navigation constraint related to at least one aspect of the navigation state. In step 1407, analysis of the plurality of images may reveal the presence of at least one navigation constraint relaxation factor.

[0304] Navigation constraint relaxation factors may include any suitable indicator that one or more navigation constraints may be suspended, changed, or otherwise relaxed in at least one aspect. In some embodiments, at least one navigation constraint relaxation factor may include a determination (based on image analysis) that the pedestrian's eyes are looking in the direction of the host vehicle. In this case, it can be more safely assumed that the pedestrian is aware of the host vehicle. Therefore, the confidence that the pedestrian will not engage in unexpected actions that cause the pedestrian to move into the path of the host vehicle may be higher. Other constraint relaxation factors may also be used. For example, at least one navigation constraint relaxation factor may include: a pedestrian determined to be not moving (e.g., a pedestrian assumed to be unlikely to enter the path of the host vehicle); or a pedestrian whose movement is determined to be slowing down. Navigation constraint relaxation factors may also include more complex actions, such as a pedestrian determined to be not moving after the host vehicle stops and then resumes moving. In this case, it can be assumed that the pedestrian is aware that the host vehicle has the right of way, and the pedestrian's stopping may indicate the pedestrian's intention to give way to the host vehicle. Other situations that may cause one or more constraints to be relaxed include the type of curb (e.g., a low curb or a curb with a gradual slope may allow a relaxed distance constraint), the lack of pedestrians or other objects on the sidewalk, vehicles with their engines not running may have a relaxed distance, or situations where pedestrians are moving away from and / or away from the area toward which the host vehicle is traveling.

[0305] In the case of identifying the presence of a navigation constraint relaxation factor (e.g., in step 1407), a second navigation constraint can be determined or generated in response to the detection of the constraint relaxation factor. The second navigation constraint can be different from the first navigation constraint, and the second navigation constraint can include at least one characteristic that is relaxed relative to the first navigation constraint. The second navigation constraint can include a newly generated constraint based on the first constraint, wherein the newly generated constraint includes at least one modification that relaxes the first constraint in at least one aspect. Alternatively, the second constraint can constitute a predetermined constraint that is less strict than the first navigation constraint in at least one aspect. In some embodiments, such a second constraint can be retained for use only in situations where a constraint relaxation factor is identified in the environment of the main vehicle. Whether the second constraint is newly generated or selected from a set of fully or partially available predetermined constraints, applying the second navigation constraint instead of the stricter first navigation constraint (which can be applied in situations where no relevant navigation constraint relaxation factor is detected) can be referred to as constraint relaxation and can be completed in step 1409.

[0306] In the event that at least one constraint relaxation factor is detected in step 1407 and at least one constraint has been relaxed in step 1409, a navigation action of the host vehicle may be determined in step 1411. The navigation action of the host vehicle may be based on the identified navigation state and may satisfy the second navigation constraint. The navigation action may be implemented in step 1413 by causing at least one adjustment of a navigation actuator of the host vehicle in response to the determined navigation action.

[0307] As described above, the use of navigation constraints and relaxed navigation constraints can be employed with either trained (e.g., through machine learning) or untrained (e.g., a navigation system that is programmed to respond with a predetermined action in response to a particular navigation state) navigation systems. In the case of using a trained navigation system, the availability of relaxed navigation constraints for certain navigation situations can represent a mode switch from a trained system response to an untrained system response. For example, a trained navigation network can determine an original navigation action for a host vehicle based on a first navigation constraint. However, the action taken by the vehicle can be a different action from the navigation action that satisfies the first navigation constraint. Instead, the action taken can satisfy a second, more relaxed navigation constraint and can be an action generated by an untrained system (e.g., as a response to detecting a particular condition in the host vehicle's environment, such as the presence of a navigation constraint relaxation factor).

[0308] There are many examples of navigation constraints that may be relaxed in response to detecting a constraint relaxation factor in the environment of the host vehicle. For example, where a predetermined navigation constraint includes a buffer zone associated with a detected pedestrian, and at least a portion of the buffer zone extends a certain distance from the detected pedestrian, the relaxed navigation constraint (newly generated, called from a memory from a predetermined set, or generated as a relaxed version of a previously existing constraint) may include a different or modified buffer zone. For example, the different or modified buffer zone may have a smaller distance relative to the pedestrian than the original or unmodified buffer zone relative to the detected pedestrian. Thus, where an appropriate constraint relaxation factor is detected in the environment of the host vehicle, the host vehicle may be allowed to navigate closer to the detected pedestrian in view of the relaxed constraint.

[0309] As described above, the relaxed characteristics of the navigation constraints may include a reduction in the width of a buffer zone associated with at least one pedestrian. However, the relaxed characteristics may also include a reduction in the width of a buffer zone associated with a target vehicle, a detected object, a roadside obstacle, or any other object detected in the environment of the host vehicle.

[0310] At least one relaxed characteristic may also include other types of modifications to navigation constraint characteristics. For example, a relaxed characteristic may include an increase in a rate associated with at least one predetermined navigation constraint. A relaxed characteristic may also include an increase in a maximum allowable deceleration / acceleration associated with at least one predetermined navigation constraint.

[0311] Although constraints may be relaxed in some cases as described above, in other cases, navigation constraints may be augmented. For example, in some cases, the navigation system may determine conditions that warrant an enhancement to a set of normal navigation constraints. Such an enhancement may include adding new constraints to a set of predetermined constraints or adjusting one or more aspects of the predetermined constraints. The addition or adjustment may result in more conservative navigation relative to the set of predetermined constraints that would be applicable under normal driving conditions. Conditions that may warrant constraint augmentation may include sensor failures, adverse environmental conditions (rain, snow, fog, or other situations associated with reduced visibility or reduced vehicle traction), etc.

[0312] Fig.15 A flow chart is provided for implementing control of a host vehicle based on enhancements to one or more navigation constraints. At step 1501, at least one processing device may receive a plurality of images representing an environment of the host vehicle from a camera associated with the host vehicle. At step 1503, analysis of the images may enable identification of a navigation state associated with the host vehicle. At step 1505, at least one processor may determine a navigation constraint associated with the navigation state of the host vehicle. The navigation constraint may include a first predetermined navigation constraint related to at least one aspect of the navigation state. At step 1507, analysis of the plurality of images may reveal the presence of at least one navigation constraint enhancement factor.

[0313] The navigation constraints involved may include those mentioned above (e.g., Fig.12) any navigation constraint or any other suitable navigation constraint. The navigation constraint enhancement factor may include any indicator that one or more navigation constraints may be supplemented / enhanced in at least one aspect. The supplementation or enhancement of navigation constraints may be performed on a per-group basis (e.g., by adding a new navigation constraint to a set of predetermined constraints) or on a per-constraint basis (e.g., modifying a particular constraint so that the modified constraint is more restrictive than the original constraint, or adding a new constraint corresponding to a predetermined constraint, wherein the new constraint is more restrictive than the corresponding constraint in at least one aspect). Additionally or alternatively, the supplementation or enhancement of navigation constraints may refer to selecting from a set of predetermined constraints based on a hierarchy. For example, a set of enhanced constraints may be used to select based on whether a navigation enhancement factor is detected in the environment of the host vehicle or relative to the host vehicle. In a normal situation where no enhancement factor is detected, the involved navigation constraints may be extracted from the constraints applicable to the normal situation. On the other hand, in the case where one or more constraint enhancement factors are detected, the involved constraints may be extracted from the enhanced constraints, which are generated or predetermined relative to the one or more enhancement factors. The enhanced constraints may be more restrictive in at least one aspect than the corresponding constraints applicable in the normal situation.

[0314] In some embodiments, at least one navigation constraint enhancing factor may include detecting (e.g., based on image analysis) the presence of ice, snow, or water on a road surface in the host vehicle's environment. For example, such a determination may be based on detecting: areas of higher reflectivity than expected for dry roads (e.g., indicating ice or water on the road); white areas on the road indicating the presence of snow; shadows on the road consistent with the presence of longitudinal grooves on the road (e.g., tire tracks in the snow); water droplets or ice / snow particles on the host vehicle's windshield; or any other suitable indicator of the presence of water or ice / snow on the road surface.

[0315] At least one navigation constraint enhancing factor may also include particles detected on an exterior surface of a windshield of the host vehicle. Such particles may impair image quality of one or more image capture devices associated with the host vehicle. Although described with respect to the windshield of the host vehicle, in relation to a camera mounted behind the windshield of the host vehicle, detection of particles on other surfaces (e.g., a lens or lens cover of a camera, a headlight lens, a rear windshield, a taillight lens, or any other surface of the host vehicle visible to (or detected by a sensor) an image capture device associated with the host vehicle) may also indicate the presence of a navigation constraint enhancing factor.

[0316] Navigation constraint enhancement factors may also be detected as properties of one or more image acquisition devices. For example, a detected degradation in image quality of one or more images captured by an image capture device (e.g., a camera) associated with a host vehicle may also constitute a navigation constraint enhancement factor. The degradation in image quality may be associated with a hardware failure or partial hardware failure associated with the image capture device or a component associated with the image capture device. Such degradation in image quality may also be caused by environmental conditions. For example, the presence of smoke, fog, rain, snow, etc. in the air surrounding the host vehicle may also result in reduced image quality relative to roads, pedestrians, target vehicles, etc. that may be present in the environment of the host vehicle.

[0317] The navigation constraint enhancing factor may also relate to other aspects of the host vehicle. For example, in some cases, the navigation constraint enhancing factor may include a detected failure or partial failure of a system or sensor associated with the host vehicle. Such enhancing factors may include, for example, the detection of a failure or partial failure of a speed sensor, a GPS receiver, an accelerometer, a camera, a radar, a lidar, a brake, a tire, or any other system associated with the host vehicle that may affect the host vehicle's ability to navigate relative to the navigation constraints associated with the navigation state of the host vehicle.

[0318] In the event that the presence of a navigation constraint enhancing factor is identified (e.g., in step 1507), a second navigation constraint may be determined or generated in response to detecting the constraint enhancing factor. The second navigation constraint may be different from the first navigation constraint, and the second navigation constraint may include at least one characteristic that is enhanced relative to the first navigation constraint. The second navigation constraint may be more restrictive than the first navigation constraint because the constraint enhancing factor detected in the environment of the host vehicle or associated with the host vehicle may indicate that the host vehicle may have at least one reduced navigation capability relative to normal operating conditions. Such reduced capability may include lower road traction (e.g., ice, snow, or water on the road; reduced tire pressure, etc.); impaired vision (e.g., rain, snow, dust, smoke, fog, etc. that reduces the quality of captured images); impaired detection capability (e.g., sensor failure or partial failure, reduced sensor performance, etc.), or any other reduction in the ability of the host vehicle to navigate in response to a detected navigation state.

[0319] Where at least one constraint enhancing factor is detected in step 1507 and at least one constraint is enhanced in step 1509, a navigation action for the host vehicle may be determined in step 1511. The navigation action for the host vehicle may be based on the identified navigation state and may satisfy the second navigation (i.e., enhanced) constraint. The navigation action may be implemented in step 1513 by causing at least one adjustment of a navigation actuator of the host vehicle in response to the determined navigation action.

[0320] As discussed, the use of navigation constraints and augmented navigation constraints can be employed with either trained (e.g., through machine learning) or untrained (e.g., a system programmed to respond with a predetermined action in response to a particular navigation state) navigation systems. In the case of using a trained navigation system, the availability of augmented navigation constraints for certain navigation situations may represent a mode switch from a trained system response to an untrained system response. For example, a trained navigation network may determine an original navigation action for a host vehicle based on a first navigation constraint. However, the action taken by the vehicle may be a different action from a navigation action that satisfies the first navigation constraint. Conversely, the action taken may satisfy an augmented second navigation constraint and may be an action generated by an untrained system (e.g., as a response to detecting a particular condition in the host vehicle's environment, such as the presence of a navigation constraint augmenting factor).

[0321] There are many examples of navigation constraints that may be generated, supplemented, or enhanced in response to detection of a constraint enhancing factor in the environment of the host vehicle. For example, where a predetermined navigation constraint includes a buffer zone associated with a detected pedestrian, object, vehicle, etc., and at least a portion of the buffer zone extends a certain distance from the detected pedestrian / object / vehicle, the enhanced navigation constraint (newly generated, called from a memory from a predetermined set, or generated as an enhanced version of a previously existing constraint) may include a different or modified buffer zone. For example, the different or modified buffer zone may have a greater distance relative to the pedestrian / object / vehicle than the original or unmodified buffer zone relative to the detected pedestrian / object / vehicle. Thus, where an appropriate constraint enhancing factor is detected in the environment of the host vehicle or relative to the host vehicle, the host vehicle may be forced to navigate further away from the detected pedestrian / object / vehicle in view of the enhanced constraint.

[0322] At least one enhanced characteristic may also include other types of modifications to navigation constraint characteristics. For example, the enhanced characteristic may include a reduction in speed associated with at least one predetermined navigation constraint. The enhanced characteristic may also include a reduction in the maximum allowable deceleration / acceleration associated with at least one predetermined navigation constraint.

[0323] Navigation based on long-term planning

[0324] In some embodiments, the disclosed navigation system may not only respond to the navigation state detected in the environment of the host vehicle, but may also determine one or more navigation actions based on long range planning. For example, the system may consider the potential impact of one or more navigation actions that can be used as options for navigation relative to the detected navigation state on the future navigation state. Considering the impact of the available actions on the future state may enable the navigation system to determine the navigation action not only based on the currently detected navigation state, but also based on long range planning. In the case where the navigation system adopts one or more reward functions as a technique for selecting navigation actions from available options, navigation using long range planning techniques may be particularly applicable. Potential rewards may be analyzed relative to available navigation actions that can be taken in response to the current navigation state detected by the host vehicle. However, further, potential rewards may also be analyzed relative to actions that can be taken in response to future navigation states, which are expected to be caused by available actions to the current navigation state. Therefore, the disclosed navigation system may select a navigation action from available actions that can be taken in response to the current navigation state in response to the detected navigation state in some cases, even in the case where the selected navigation action may not produce the highest reward. This is particularly true when the system determines that the selected action may result in a future navigation state that gives rise to one or more potential navigation actions that provide a higher reward than the selected action or, in some cases, than any action available relative to the current navigation state. This principle can be expressed more simply as taking a less favorable action now in order to produce a higher reward option in the future. Thus, the disclosed navigation system capable of long-term planning can select short-term non-optimal actions where the long-term prediction indicates that a short-term loss of reward will result in a long-term reward increase.

[0325] Typically, autonomous driving applications may involve a series of planning problems, in which the navigation system can decide on immediate actions in order to optimize longer-term goals. For example, when a vehicle encounters a merge situation at a roundabout, the navigation system may decide on an immediate acceleration or braking command in order to initiate navigation to the roundabout. Although the immediate action on the detected navigation state at the roundabout may involve an acceleration or braking command in response to the detected state, the long-term goal is to merge successfully, and the long-term impact of the selected command is the success / failure of the merge. The planning problem can be solved by decomposing the problem into two stages. First, supervised learning can be applied to predict the near future based on the present (assuming that the predictor will be differentiable relative to the present representation). Second, a recurrent neural network can be used to model the complete trajectory of the actor, in which unexplained factors are modeled as (additive) input nodes. This can allow the use of supervised learning techniques and direct optimization of recurrent neural networks to determine the solution to the long-term planning problem. This approach can also enable robust strategies to be learned by incorporating adversarial elements into the environment.

[0326] The two most fundamental elements of an autonomous driving system are sensing and planning. Sensing deals with finding a compact representation of the current state of the environment, while planning deals with deciding what actions to take to optimize future goals. Supervised machine learning techniques are useful for solving sensing problems. Machine learning algorithm frameworks can also be used for the planning portion, especially reinforcement learning (RL) frameworks such as those mentioned above.

[0327] RL can be performed in a sequence of consecutive rounds. In round t, the planner (also known as the actor or driving strategy module 803) can observe the state s t ∈S, which represents the actor and the environment. Then it should decide the action a t ∈A. After performing the action, the actor receives an immediate reward and move to the new state s t+1 As an example, the host vehicle may include an adaptive cruise control (ACC) system, where the vehicle should autonomously implement acceleration / braking to maintain an appropriate distance from the vehicle ahead while maintaining a smooth ride. This state can be modeled as a pair of where x t is the distance to the vehicle ahead, v t is the speed of the host vehicle relative to the speed of the preceding vehicle. will be an acceleration command (if a t <0, the host vehicle slows down). The reward can be determined by |a t | (reflects the smoothness of driving) and s t(reflecting the host vehicle maintaining a safe distance from the vehicle in front). The goal of the planner is to maximize the cumulative reward (which can be the time horizon of future rewards or the discounted sum). To do this, the planner can rely on a policy π: S→A, which maps states to actions.

[0328] Supervised learning (SL) can be viewed as a special case of RL, where s t is sampled from some distribution over S, and the reward function can have of the form, where is the loss function, and the learner observes y t The value of y t To view the status t The value of the best action to take when y is y (which may be noisy). There may be several differences between general RL models and special case SL, and these differences make the general RL problem more challenging.

[0329] In some SL situations, the actions (or predictions) taken by the learner may have no effect on the environment. In other words, s t+1 and a t are independent. This has two important implications. First, in SL, samples (s1, y1), ..., (s m ,y m ) can be collected in advance before starting to search for a policy (or predictor) with good accuracy relative to the sample. In contrast, in RL, the state s t+1 Usually depends on the action taken (and the previous state), which in turn depends on the policy used to generate that action. This will make the data generation process tethered to the policy learning process. Second, because in SL the action does not affect the environment, choosing a t The contribution to the performance of π is local. Specifically, a t Only affects the value of the immediate reward. In contrast, in RL, the action taken in round t may have a long-term impact on the value of rewards in future rounds.

[0330] In SL, knowledge of the “correct” answer t , together with rewards The shape together can provide for a t Full knowledge of the rewards of all possible choices of , which can make it possible to calculate the reward relative to a tIn contrast, in RL, the "one-time" value of the reward may be all that can be observed for the specific choice of action taken. This can be called "bandit" feedback. This is one of the most important reasons why "exploration" is needed as part of long-term navigation planning, because in RL-based systems, if only "bandit" feedback is available, the system may not always know whether the action taken is the best action to take.

[0331] Many RL algorithms rely at least in part on a mathematical optimization model called a Markov decision process (MDP). The Markov assumption is that given s t and a t ,s t+1 The distribution of is completely determined. It gives a closed-form expression for the cumulative reward of a given policy in terms of the stable distribution over the states of the MDP. The stable distribution of policies can be expressed as a solution to a linear programming problem. This gives rise to two classes of algorithms: 1) Optimization with respect to the original problem, which is called policy search; 2) Optimization with respect to the dual problem, whose variable is called the value function V π If the MDP starts with an initial state s, and from there actions are chosen according to π, then the value function determines the expected cumulative reward. The relevant quantity is the state-action value function Q π (s, a), given that we start in state s, action a is chosen instantaneously, and from there we choose actions according to π, then the state-action value function determines the cumulative reward. The Q function may give rise to a characterization of the optimal policy (using the Bellman equation). In particular, the Q function may indicate that the optimal policy is a deterministic function from S to A (indeed, it may be characterized as a "greedy" policy with respect to the optimal Q function).

[0332] One potential advantage of the MDP model is that it allows the future to be coupled to the present using a Q function. For example, suppose the host vehicle is now in state s, Q π The value of (s, a) can indicate the impact of performing action a on the future. Therefore, the Q function can provide a local measure of the quality of action a, making the RL problem more similar to the SL scenario.

[0333] Many RL algorithms approximate the V-function or Q-function in some way. Value iteration algorithms (such as Q-learning algorithms) can rely on the fact that the V and Q-functions of the optimal policy can be fixed points of some operators derived from the Bellman equation. Actor-critic policy iteration algorithms aim to learn a policy in an iterative manner, where at iteration t, the “critic” estimates And based on that estimate, the “actor” refines the strategy.

[0334] Despite the mathematical advantages of MDPs and the convenience of switching to a Q-function representation, the approach may have several limitations. For example, the approximate notion of a Markovian behavior state may be all that can be found in some cases. Furthermore, transitions to states depend not only on the behavior of the actor, but also on the behavior of other actors in the environment. For example, in the ACC example mentioned above, although the dynamics of the autonomous vehicle may be Markovian, the next state may depend on the behavior of the driver of another vehicle, which is not necessarily Markovian. A possible solution to this problem is to use a partially observed MDP, where it is assumed that: there are Markovian states, but what can be seen are observations distributed according to the hidden states.

[0335] A more direct approach might consider a game theoretic generalization of MDPs (e.g., a stochastic game framework). Indeed, algorithms for MDPs can be generalized to multi-actor games (e.g., min-max-Q learning or Nash-Q learning). Other approaches might include explicit modeling of other players and vanishing regret learning algorithms. Learning in a multi-actor setting might be more complex than in a single-actor setting.

[0336] The second limitation of the Q-function representation can arise by deviating from the tabular setting. The tabular setting is when the number of states and actions is small, so Q can be represented as a table with |S| rows and |A| columns. However, if the natural representation of S and A contains Euclidean space, and the state and action spaces are discrete, the number of states / actions may be exponential in dimension. In this case, it may not be practical to adopt a tabular setting. Instead, the Q-function can be approximated by a function from a class of parameter assumptions (e.g., a neural network of a certain architecture). For example, a deep Q-network (DQN) learning algorithm can be used. In DQN, the state space can be continuous, while the action space can still be a small discrete set. There may be ways to handle continuous action spaces, but they may rely on approximating the Q-function. In any case, the Q-function may be complex and sensitive to noise, and therefore may pose challenges to learning.

[0337] A different approach could be to use recurrent neural networks (RNNs) to solve RL problems. In some cases, RNNs can be combined with concepts from multi-actor games and robustness to adversarial environments from game theory. Furthermore, this approach may not explicitly rely on any Markov assumptions.

[0338] The following describes the method of navigating by prediction-based planning in more detail. In this method, it can be assumed that the state space S is A subset of , and the action space A is This may be a natural representation in many applications. As mentioned above, there may be two key differences between RL and SL: (1) because past actions affect future rewards, information from the future may need to be propagated back to the past; (2) the “bandit” nature of rewards may obscure the dependencies between (state, action) and rewards, which can complicate the learning process.

[0339] As a first step in this approach, it can be observed that there are interesting problems where the bandit nature of rewards is not a problem. For example, the reward values ​​applied by ACC (as discussed in more detail below) may be differentiable with respect to the current state and action. In fact, even if the rewards are given in a "bandit" fashion, learning a differentiable function Make The problem of can be a relatively straightforward SL problem (e.g., a one-dimensional regression problem). Therefore, the first step of the method can be to define the reward as a function The function is differentiable with respect to s and a, or the first step of the method may be to use a regression learning algorithm in order to learn a differentiable function This function minimizes at least some regression loss on at least one sample, where the instance vector is and the target scalar is r t In some cases, an element of exploration may be used in order to create a training set.

[0340] To solve the connection between the past and the future, similar ideas can be used. For example, suppose we can learn a differentiable function Make Learning such a function can be formulated as a SL problem. can be considered as a predictor of the near future. Next, we can use the parameter function π θ :S→A to describe the strategy of mapping from S to A. θ Expressing it as a neural network allows us to use a recurrent neural network (RNN) to express the fragment of running the actor for T rounds, where the next state is defined as Here, Can be defined by the environment and can express unpredictable aspects of the near future. t+1 Depends on s in a differentiable way t and a t The fact that π can make the connection between future reward values ​​and past actions. θ The parameter vector of can be learned by back-propagating through the resulting RNN. Note that there is no need to tIn particular, no explicit probabilistic assumptions are imposed on . In particular, no requirement for a Markov relation is required. Instead, the recurrent network can be relied upon to propagate “enough” information between the past and the future. Intuitively, can describe the predictable part of the near future, while ν t can express the unpredictable aspects that may arise due to the behavior of other actors in the environment. The learning system should learn policies that are robust to the behavior of other actors. If ‖v t ‖ is large, the connection between past actions and future reward values ​​may be too noisy to learn a meaningful policy. Explicitly expressing the dynamics of the system in a transparent way can make it easier to incorporate prior knowledge. For example, prior knowledge can simplify the definition of problem.

[0341] As described above, the learning system may benefit from robustness relative to an adversarial environment (such as the host vehicle's environment), which may include multiple other drivers that may behave in unexpected ways. t In the model that imposes probabilistic assumptions, we can consider the choice of ν in an adversarial manner. t In some cases, μ t impose constraints, otherwise the adversary may make the planning problem difficult or even impossible. A natural constraint might be to require that ||μ t ||.

[0342] Robustness against adversarial environments may be useful in autonomous driving applications. t It can even speed up the learning process because it allows the learning system to focus on the best strategy that is robust. This concept can be illustrated with a simple game. Action The instant loss function is 0.1|a t |+[|s t |-2] + , where [x] + =max{x, 0} is the ReLU (rectified linear unit) function. The next state is s t+1 =s t +a t +ν t , where ν t ∈[-0.5, 0.5] is chosen in an adversarial way for the environment. Here, the optimal strategy can be written as a two-layer network with ReLU: t =-[s t -1.5] + +[-s t -1.5] + . Observe that when |st |∈(1.5, 2], the optimal action may have a larger immediate loss than action a=0. Therefore, the system can plan for the future and can rely solely on the immediate loss. Observe that the loss is about a t The derivative is 0.1sign(a t ), and about s t The derivative of is 1[|s t |>2]sign(s t ). t ∈(1.5, 2], ν t The adversarial selection of t = 0.5, so whenever a t >1.5-s t , there can be non-zero loss at round t+1. In this case, the derivative of the loss can be directly back-propagated to a t Therefore, in a t When the choice is non-optimal, ν t Adversarial selection of can help the navigation system obtain non-zero back-propagation messages. This relationship can help the navigation system choose the current action based on the expectation that this current behavior (even if it leads to non-optimal rewards or even losses) will provide opportunities for more optimal actions that lead to higher rewards in the future.

[0343] This approach can be applied to virtually any navigation situation that may arise. The following description applies to the approach for one example: Adaptive Cruise Control (ACC). In the ACC problem, the host vehicle may attempt to maintain an appropriate distance to a target vehicle ahead (e.g., 1.5 seconds to the target vehicle). Another goal may be to drive as smoothly as possible while maintaining a desired gap. A model representing this situation can be defined as follows. The state space is The action space is The first coordinate of the state is the speed of the target car, the second coordinate is the speed of the host vehicle, and the last coordinate is the distance between the host vehicle and the target vehicle (e.g., the position of the host vehicle minus the position of the target vehicle along the curve of the road). The action taken by the host vehicle is to accelerate and can be expressed as a t The quantity τ may represent the time difference between successive rounds. Although τ may be set to any suitable quantity, in one example, τ may be 0.1 seconds. The position s t It can be expressed as And the (unknown) acceleration of the target vehicle can be expressed as

[0344] The complete dynamics of the system can be described by the following description:

[0345]

[0346] This can be described as the sum of two vectors:

[0347]

[0348] The first vector is the predictable part, while the second vector is the unpredictable part. The reward for round t is defined as follows:

[0349] in

[0350] The first term results in a penalty for non-zero acceleration, thus encouraging smooth driving. The second term depends on the distance x to the target car. t The distance from expectation The ratio between the desired distance is defined as the maximum between a 1-meter distance and a 1.5-second braking distance. In some cases, this ratio may be exactly 1, but as long as the ratio is in the range [0.7, 1.3], the policy may forgo any penalty, which may allow the host vehicle to relax a bit in navigation - a characteristic that may be important in achieving smooth driving.

[0351] Implementing the method outlined above, the navigation system of the host vehicle (e.g., through operation of the driving strategy module 803 within the processing unit 110 of the navigation system) can select an action in response to the observed state. The selected action can be based on an analysis of not only the rewards associated with the responsive actions available relative to the sensed navigation state, but also based on consideration and analysis of future states, potential actions in response to the future states, and rewards associated with the potential actions.

[0352] Fig.16 An algorithmic approach to navigation based on detection and long-term planning is shown. For example, at step 1601, at least one processing device 110 of a navigation system of a host vehicle may receive a plurality of images. These images may capture a scene representing an environment of the host vehicle and may be provided by any of the above-described image capture devices (e.g., a camera, a sensor, etc.). Analyzing one or more of these images at step 1603 may enable at least one processing device 110 to identify a current navigation state associated with the host vehicle (as described above).

[0353] Various potential navigation actions in response to the sensed navigation state may be determined in steps 1605, 1607, and 1609. These potential navigation actions (e.g., the first navigation action through the Nth available navigation action) may be determined based on the sensed state and the long-term goal of the navigation system (e.g., completing a merge, smoothly following a preceding vehicle, passing a target vehicle, avoiding an object in the road, slowing down for a detected stop sign, avoiding an oncoming target vehicle, or any other navigation action that may advance the navigation goal of the system).

[0354] For each of the potential navigation actions determined, the system can determine an expected reward. The expected reward can be determined according to any of the above techniques and can include an analysis of the particular potential action with respect to one or more reward functions. For each potential navigation action (e.g., the first, second, and Nth) determined in steps 1605, 1607, and 1609, an expected reward 1606, 1608, and 1610 can be determined, respectively.

[0355] In some cases, the navigation system of the host vehicle may select from the available potential actions based on the values ​​associated with expected rewards 1606, 1608, and 1610 (or any other type of indicator of expected reward). For example, in some cases, the action that yields the highest expected reward may be selected.

[0356] In other cases, particularly where the navigation system performs long-term planning to determine the navigation action of the host vehicle, the system may not select the potential action that produces the highest expected reward. Instead, the system may look into the future to analyze whether there is an opportunity to achieve a higher reward later if a lower reward action is selected in response to the current navigation state. For example, a future state may be determined for any or all of the potential actions determined at steps 1605, 1607, and 1609. Each future state determined at steps 1613, 1615, and 1617 may represent a future navigation state that is expected to be modified by a corresponding potential action (e.g., a potential action determined at steps 1605, 1607, and 1609) based on the current navigation state.

[0357] For each of the future states predicted at steps 1613, 1615, and 1617, one or more future actions (as navigation options available in response to the determined future states) may be determined and evaluated. At steps 1619, 1621, and 1623, for example, a value or any other type of indicator of an expected reward associated with the one or more future actions may be generated (e.g., based on one or more reward functions). The expected reward associated with the one or more future actions may be evaluated by comparing the value of the reward function associated with each future action or by comparing any other indicator associated with the expected reward.

[0358] At step 1625, the navigation system of the host vehicle may select a navigation action for the host vehicle based on a comparison of expected rewards based not only on potential actions identified relative to the current navigation state (e.g., in steps 1605, 1607, and 1609), but also based on expected rewards determined as a result of potential future actions available in response to the predicted future state (e.g., determined at steps 1613, 1615, and 1617). The selection at step 1625 may be based on the options and reward analysis performed at steps 1619, 1621, and 1623.

[0359] The selection of a navigation action at step 1625 may be based solely on a comparison of the expected rewards associated with future action options. In this case, the navigation system may select an action for the current state based solely on a comparison of the expected rewards resulting from actions for potential future navigation states. For example, the system may select the potential actions identified at steps 1650, 1610, and 1609 that are associated with the highest future reward value determined by the analysis at steps 1619, 1621, and 1623.

[0360] The selection of a navigation action at step 1625 may also be based solely on a comparison of current action options (as described above). In this case, the navigation system may select the potential action associated with the highest expected reward 1606, 1608, or 1610 identified at steps 1605, 1607, or 1609. This selection may be performed with little or no consideration of future navigation states or future expected rewards for available navigation actions in response to expected future navigation states.

[0361] On the other hand, in some cases, the selection of navigation action in step 1625 can be based on the comparison of the expected reward associated with both the future action option and the current action option. In fact, this may be one of the navigation principles based on long-term planning. For example, the expected reward for future action can be analyzed to determine whether there is any expected reward that can authorize the selection of the lower reward action in response to the current navigation state, so as to realize potential higher reward in response to subsequent navigation action, which is expected to be available in response to future navigation state. As an example, the value of expected reward 1606 or other indicators can indicate the highest expected reward among rewards 1606, 1608 and 1610. On the other hand, expected reward 1608 can indicate the lowest expected reward among rewards 1606, 1608 and 1610. Rather than simply selecting the potential action (that is, the action causing the highest expected reward 1606) determined in step 1605, the analysis of future state, potential future action, and future reward can be used to select navigation action in step 1625. In one example, it may be determined that the reward identified at step 1621 (in response to at least one future action for the future state determined at step 1615, which is based on the second potential action determined at step 1607) may be higher than the expected reward 1606. Based on this comparison, the second potential action determined at step 1607 may be selected instead of the first potential action determined at step 1605, even though the expected reward 1606 is higher than the expected reward 1608. In one example, the potential navigation actions determined at step 1605 may include a merge in front of a detected target vehicle, while the potential navigation actions determined at step 1607 may include a merge behind the target vehicle. Although the expected reward 1606 for merging in front of the target vehicle may be higher than the expected reward 1608 associated with merging behind the target vehicle, it may be determined that merging behind the target vehicle may result in a future state for which there may be action options that produce potential rewards that are even higher than the expected rewards 1606, 1608, or other rewards based on available actions responsive to the current, sensed navigation state.

[0362] The selection from among the potential actions at step 1625 can be based on any suitable comparison of expected rewards (or comparing any other measure or indicator of benefit associated with one potential action to another). In some cases, as described above, the second potential action can be selected over the first potential action if the second potential action is expected to provide at least one future action associated with an expected reward that is higher than the reward associated with the first potential action. In other cases, more complex comparisons can be employed. For example, a reward associated with an action option responsive to an expected future state can be compared to more than one expected reward associated with a determined potential action.

[0363] In some cases, if at least one future action is expected to produce a reward that is higher than any reward expected as a result of a potential action for the current state (e.g., expected rewards 1606, 1608, 1610, etc.), then the action based on the predicted future state and the expected reward can influence the selection of the potential action for the current state. In some cases, the future action option that produces the highest expected reward (e.g., from the expected rewards associated with the potential actions for the sensed current state, and from the expected rewards associated with the potential future action options relative to the potential future navigation state) can be used as a guide to select the potential action for the current navigation state. That is, after identifying the future action option that produces the highest expected reward (or a reward above a predetermined threshold, etc.), in step 1625, a potential action that will result in the future state associated with the identified future action that produces the highest expected reward can be selected.

[0364] In other cases, selection of available actions may be made based on the determined difference between the expected rewards. For example, if the difference between the expected reward associated with the future action determined at step 1621 and the expected reward 1606 is greater than the difference between the expected reward 1608 and the expected reward 1606 (assuming a positive-signed difference), then the second potential action determined at step 1607 may be selected. In another example, if the difference between the expected reward associated with the future action determined at step 1621 and the expected reward associated with the future action determined at step 1619 is greater than the difference between the expected reward 1608 and the expected reward 1606, then the second potential action determined at step 1607 may be selected.

[0365] Several examples have been described for selecting from among potential actions for the current navigation state. However, any other suitable comparison technique or criteria may be used for selecting available actions through long-term planning based on action and reward analysis extending into projected future states. Fig.16 Two layers in the long-term planning analysis are represented (e.g., the first layer considers rewards resulting from potential actions for the current state, and the second layer considers rewards resulting from future action options in response to the projected future state), however, analysis based on more layers may be possible. For example, rather than basing the long-term planning analysis on one or two layers, three, four, or more layers of analysis may be used to select from among the available potential actions in response to the current navigation state.

[0366] After selecting from among the potential actions in response to the sensed navigation state, at least one processor may cause at least one adjustment action of a navigation actuator of the host vehicle in response to the selected potential navigation, at step 1627. The navigation actuator may include any suitable device for controlling at least one aspect of the host vehicle. For example, the navigation actuator may include at least one of a steering mechanism, a brake, or an accelerator.

[0367] Navigation based on inferred aggression from others

[0368] The target vehicle can be monitored by analyzing the acquired image stream to determine indicators of driving aggression. Aggression is described herein as a qualitative or quantitative parameter, but other characteristics can be used: perceived level of attention (potential impairment of the driver, distraction caused by the mobile phone, falling asleep, etc.). In some cases, the target vehicle can be considered to have a defensive posture, and in some cases, the target vehicle can be determined to have a more aggressive posture. Navigation actions can be selected or generated based on the aggression indicator. For example, in some cases, the relative speed, relative acceleration, increase in relative acceleration, following distance, etc. relative to the host vehicle can be tracked to determine whether the target vehicle is aggressive or defensive. For example, if the target vehicle is determined to have an aggression level exceeding a threshold, the host vehicle may be inclined to give way to the target vehicle. The aggression level of the target vehicle can also be discerned based on the determined behavior of the target vehicle relative to one or more obstacles in or near the path of the target vehicle (e.g., a vehicle ahead, an obstacle on the road, a traffic light, etc.).

[0369] As an introduction to this concept, an exemplary experiment will be described with respect to a host vehicle merging into a roundabout, where the navigation goal is to pass through the roundabout and exit the roundabout. The situation may begin with the host vehicle approaching the entrance to the roundabout, and may end with the host vehicle reaching the exit (e.g., the second exit) of the roundabout. Success may be measured based on whether the host vehicle always maintains a safe distance from all other vehicles, whether the host vehicle completes the route as quickly as possible, and whether the host vehicle follows a smooth acceleration strategy. In this example, N T target vehicles can be randomly placed on the roundabout. To model a mixture of adversarial and typical behavior, with probability p, the target vehicle can be modeled by an "aggressive" driving strategy, such that the aggressive target vehicle speeds up when the host vehicle attempts to merge in front of the target vehicle. With probability 1-p, the target vehicle can be modeled by a "defensive" driving strategy, such that the target vehicle slows down and lets the host vehicle merge. In this experiment, p = 0.5, and the host vehicle's navigation system may not be provided with information about the type of other driver. The type of other driver may be randomly selected at the beginning of the segment.

[0370] The navigation state can be represented as the speed and position of the main vehicle (actor), and the position, speed and acceleration of the target vehicles. It may be important to keep an eye on the target acceleration in order to distinguish between aggressive and defensive drivers based on the current state. All target vehicles may move along a one-dimensional curve with a circular path as the outline. The main vehicle can move on its own one-dimensional curve, which intersects the curve of the target vehicle at the merge point, and this point is the starting point of the two curves. In order to model reasonable driving, the absolute value of the acceleration of all vehicles can be bounded by a constant. Because reverse driving is not allowed, the speed can also be passed through ReLU. Note that by not allowing reverse driving, long-term planning can become necessary because the actor will not regret its past behavior.

[0371] As mentioned above, the next state s t+1 Can be broken down into predictable parts and the unpredictable part ν t The sum of . The expression can represent the dynamics of the vehicle position and velocity (which can be well defined in a differentiable way), while ν t It can represent the acceleration of the target vehicle. It can be verified that It can be expressed as a combination of ReLU functions on affine transformations, so it is relatively t and a t is differentiable. The vector ν t can be defined by the simulator in a non-differentiable way and can behave aggressively towards some targets and defensively towards others. Fig.17A and 17B Two frames from such a simulator are shown in FIG. 17. In this exemplary experiment, the host vehicle 1701 learns to slow down as it approaches the entrance to the roundabout. It also learns to yield to aggressive vehicles (e.g., vehicles 1703 and 1705) and to safely continue driving when defensive vehicles (e.g., vehicles 1706, 1708, and 1710) merge in front of it. Fig.17A and 17B In the example shown, the type of target vehicle is not provided to the navigation system of the host vehicle 1701. Rather, whether a particular vehicle is determined to be aggressive or defensive is determined by inference based on the observed position and acceleration (e.g., of the target vehicle). Fig.17A In FIG. 1 , based on position, velocity, and / or relative acceleration, host vehicle 1701 may determine that vehicle 1703 has an aggressive tendency, and therefore host vehicle 1701 may stop and wait for target vehicle 1703 to pass rather than attempting to merge in front of target vehicle 1703. However, in Fig. 17B, target vehicle 1701 recognizes that target vehicle 1710 traveling behind vehicle 1703 is exhibiting a defensive tendency (also based on the observed position, speed and / or relative acceleration of vehicle 1710), and therefore completes a successful lane merge in front of target vehicle 1710 and behind target vehicle 1703.

[0372] Fig.18 A flow chart representing an exemplary algorithm for navigating a host vehicle based on predicted aggression of other vehicles is provided. Fig.18 In an example of FIG. 18 , an aggression level associated with at least one target vehicle may be inferred based on observed behavior of the target vehicle relative to objects in the target vehicle's environment. For example, at step 1801, at least one processing device (e.g., processing device 110) of a host vehicle navigation system may receive a plurality of images representing an environment of the host vehicle from a camera associated with the host vehicle. At step 1803, analysis of one or more of the received images may enable at least one processor to identify a target vehicle (e.g., vehicle 1703) in the environment of the host vehicle 1701. At step 1805, analysis of one or more of the received images may enable at least one processing device to identify at least one obstacle to the target vehicle in the environment of the host vehicle. The object may include debris in the road, a stop light / traffic light, a pedestrian, another vehicle (e.g., a vehicle traveling in front of the target vehicle, a parked vehicle, etc.), a box in the road, a roadblock, a curb, or any other type of object that may be encountered in the environment of the host vehicle. At step 1807, analysis of one or more of the received images may enable at least one processing device to determine at least one navigation characteristic of the target vehicle relative to at least one identified obstacle to the target vehicle.

[0373] Various navigation characteristics may be used to infer the aggression level of a detected target vehicle in order to generate an appropriate navigation response to the target vehicle. For example, such navigation characteristics may include a relative acceleration between the target vehicle and at least one identified obstacle, a distance of the target vehicle from the obstacle (e.g., a following distance of the target vehicle behind another vehicle), and / or a relative speed between the target vehicle and the obstacle, etc.

[0374] In some embodiments, the navigation characteristics of the target vehicle can be determined based on outputs from sensors associated with the host vehicle (e.g., radar, speed sensors, GPS, etc.). However, in some cases, the navigation characteristics of the target vehicle can be determined partially or entirely based on an analysis of an image of the host vehicle's environment. For example, the image analysis techniques described above and in, for example, U.S. Patent No. 9,168,868, incorporated by reference herein, can be used to identify a target vehicle within the host vehicle's environment. Furthermore, monitoring the position of the target vehicle in the captured image over time and / or monitoring the position of one or more features associated with the target vehicle (e.g., taillights, headlights, bumpers, wheels, etc.) in the captured image can enable determination of the relative distance, speed, and / or acceleration between the target vehicle and the host vehicle or between the target vehicle and one or more other objects in the host vehicle's environment.

[0375] The aggression level of the identified target vehicle may be inferred from any suitable observed navigation characteristic of the target vehicle or any combination of observed navigation characteristics. For example, a determination of aggression may be made based on any observed characteristic and one or more predetermined threshold levels or any other suitable qualitative or quantitative analysis. In some embodiments, a target vehicle may be considered aggressive if the target vehicle is observed to follow the host vehicle or another vehicle at a distance less than a predetermined aggressive distance threshold. On the other hand, a target vehicle observed to follow the host vehicle or another vehicle at a distance greater than a predetermined defensive distance threshold may be considered defensive. The predetermined aggressive distance threshold need not be the same as the predetermined defensive distance threshold. In addition, either or both of the predetermined aggressive distance threshold and the predetermined defensive distance threshold may include a range of values ​​rather than a bright line value. Furthermore, neither the predetermined aggressive distance threshold nor the predetermined defensive distance threshold need be fixed. Instead, these values ​​or ranges of values ​​may change over time, and different thresholds / ranges of thresholds may be applied based on the observed characteristics of the target vehicle. For example, the thresholds applied may depend on one or more other characteristics of the target vehicle. Higher observed relative speeds and / or accelerations may warrant the application of larger thresholds / ranges. Conversely, lower relative speeds and / or accelerations (including zero relative speed and / or acceleration) may authorize the application of smaller distance thresholds / ranges when making aggressive / defensive inferences.

[0376] Aggressive / defensive inferences may also be based on relative speed and / or relative acceleration thresholds. If the observed relative speed and / or relative acceleration of a target vehicle relative to another vehicle exceeds a predetermined level or range, the target vehicle may be considered aggressive. If the observed relative speed and / or relative acceleration of a target vehicle relative to another vehicle is below a predetermined level or range, the target vehicle may be considered defensive.

[0377] Although an aggressive / defensive determination may be made based solely on any observed navigation characteristic, the determination may also depend on any combination of observed characteristics. For example, as described above, in some cases, a target vehicle may be considered aggressive based solely on the observation that it is following another vehicle at a distance below a certain threshold or range. However, in other cases, a target vehicle may be considered aggressive if it is following another vehicle at less than a predetermined amount (which may be the same or different than the threshold applied when determining based solely on distance) and with a relative speed and / or relative acceleration greater than a predetermined amount or range. Similarly, a target vehicle may be considered defensive based solely on the observation that it is following another vehicle at a distance greater than a certain threshold or range. However, in other cases, a target vehicle may be considered defensive if it is following another vehicle at greater than a predetermined amount (which may be the same or different than the threshold applied when determining based solely on distance) and with a relative speed and / or relative acceleration less than a predetermined amount or range. System 100 may deduce aggressiveness / defensiveness if, for example, the vehicle exceeds 0.5G acceleration or deceleration (e.g., 5m / s3 jerk), the vehicle has 0.5G lateral acceleration in a lane change or curve, a vehicle causes another vehicle to do any of the above, a vehicle changes lanes and causes another vehicle to yield with 0.3G deceleration or more than 3m / s3 jerk, and / or the vehicle changes lanes without stopping.

[0378] It should be understood that a reference to a quantity exceeding a range may indicate that the quantity exceeds all values ​​associated with the range or falls within the range. Similarly, a reference to a quantity below a range may indicate that the quantity is below all values ​​associated with the range or falls within the range. In addition, although examples for making aggressive / defensive inferences are described with respect to distance, relative acceleration, and relative speed, any other suitable quantity may be used. For example, a calculation of the time to collision, or any indirect indicator of the distance, acceleration, and / or speed of the target vehicle may be used. It should also be noted that although the above examples focus on target vehicles relative to other vehicles, aggressive / defensive inferences may be made by observing the navigation characteristics of the target vehicle relative to any other type of obstacle (e.g., pedestrians, roadblocks, traffic lights, debris, etc.).

[0379] Back to Fig.17A and 17B In the example shown, when the host vehicle 1701 approaches the roundabout, the navigation system (including at least one of its processing devices) can receive an image stream from a camera associated with the host vehicle. Based on the analysis of one or more received images, any one of the target vehicles 1703, 1705, 1706, 1708, and 1710 can be identified. In addition, the navigation system can analyze the navigation characteristics of one or more identified target vehicles. The navigation system can recognize that the gap between the target vehicles 1703 and 1705 represents a potential first opportunity to merge into the roundabout. The navigation system can analyze the target vehicle 1703 to determine the aggressive indicator associated with the target vehicle 1703. If the target vehicle 1703 is considered aggressive, the host vehicle navigation system can choose to give way to the vehicle 1703 instead of merging in front of the vehicle 1703. On the other hand, if the target vehicle 1703 is considered defensive, the host vehicle navigation system can attempt to complete the merging action in front of the vehicle 1703.

[0380] As host vehicle 1701 approaches the roundabout, at least one processing device of the navigation system may analyze the captured images to determine navigation characteristics associated with target vehicle 1703. For example, based on the images, it may be determined that vehicle 1703 is following vehicle 1705 at a distance that provides sufficient clearance for host vehicle 1701 to enter safely. In fact, it may be determined that vehicle 1703 is following vehicle 1705 at a distance that exceeds an aggressive distance threshold, and thus based on this information, the host vehicle navigation system may be inclined to identify target vehicle 1703 as defensive. However, in some cases, as described above, more than one navigation characteristic of the target vehicle may be analyzed when making an aggressive / defensive determination. Further analyzing, the host vehicle navigation system may determine that when target vehicle 1703 is following behind target vehicle 1705 at a non-aggressive distance, vehicle 1703 has a relative speed and / or relative acceleration relative to vehicle 1705 that exceeds one or more thresholds associated with aggressive behavior. In practice, host vehicle 1701 may determine that target vehicle 1703 is accelerating relative to vehicle 1705 and is approaching a gap that exists between vehicles 1703 and 1705. Based on further analysis of relative speed, acceleration, and distance (and even the rate at which the gap between vehicles 1703 and 1705 is closing), host vehicle 1701 may determine that target vehicle 1703 is behaving aggressively. Thus, while there may be a sufficient gap that the host vehicle can safely navigate into, host vehicle 1701 may anticipate that a merge in front of target vehicle 1703 will result in an aggressively navigating vehicle immediately behind the host vehicle. Furthermore, based on the behavior observed through image analysis or other sensor outputs, target vehicle 1703 may be expected to continue to accelerate toward host vehicle 1701 or continue to travel toward host vehicle 1701 at a non-zero relative speed if host vehicle 1701 were to merge in front of vehicle 1703. This situation may be undesirable from a safety perspective and may also cause discomfort to the occupants of the host vehicle. For this reason, if host vehicle 1701 were to merge in front of vehicle 1703, target vehicle 1703 may continue to accelerate toward host vehicle 1701 or continue to travel toward host vehicle 1701 at a non-zero relative speed. This situation may be undesirable from a safety perspective and may also cause discomfort to the occupants of the host vehicle. For this reason, if Fig. 17B As shown, host vehicle 1701 may choose to yield to vehicle 1703 and merge onto the roundabout behind vehicle 1703 and in front of vehicle 1710, which is deemed to be defensive based on an analysis of one or more of its navigation characteristics.

[0381] Back to Fig.18At step 1809, at least one processing device of the navigation system of the host vehicle may determine a navigation action for the host vehicle (e.g., merging in front of vehicle 1710 and behind vehicle 1703) based on at least one navigation characteristic of the identified target vehicle relative to the identified obstacle. To implement the navigation action (at step 1811), at least one processing device may cause at least one adjustment of a navigation actuator of the host vehicle in response to the determined navigation action. For example, a brake may be applied to give way to the target vehicle. Fig.17A 1703 in the vehicle, and the accelerator can be applied together with the steering of the wheels of the host vehicle to make the host vehicle enter the roundabout behind vehicle 1703, such as Fig. 17B shown.

[0382] As described in the above examples, the navigation of the host vehicle may be based on the navigation characteristics of the target vehicle relative to another vehicle or object. In addition, the navigation of the host vehicle may be based only on the navigation characteristics of the target vehicle without specific reference to another vehicle or object. Fig.18 At step 1807 of , analysis of the plurality of images captured from the host vehicle's environment may enable determination of at least one navigation characteristic of the identified target vehicle that indicates a level of aggression associated with the target vehicle. The navigation characteristic may include speed, acceleration, and the like that do not require reference relative to another object or target vehicle in order to make an aggressive / defensive determination. For example, an observed acceleration and / or speed associated with the target vehicle that exceeds a predetermined threshold or falls within or exceeds a range of values ​​may indicate aggressive behavior. Conversely, an observed acceleration and / or speed associated with the target vehicle that falls below a predetermined threshold or falls within or exceeds a range of values ​​may indicate defensive behavior.

[0383] Of course, in some cases, observed navigational characteristics (e.g., position, distance, acceleration, etc.) may be referenced relative to the host vehicle for purposes of making an aggressive / defensive determination. For example, observed navigational characteristics of a target vehicle that indicate a level of aggression associated with the target vehicle may include an increase in relative acceleration between the target vehicle and the host vehicle, a following distance of the target vehicle behind the host vehicle, a relative speed between the target vehicle and the host vehicle, etc.

[0384] Navigation based on liability constraints

[0385] As described in the above sections, planned navigation actions can be tested against predetermined constraints to ensure that certain rules are met. In some embodiments, this concept can be extended to considerations of potential accident liability. As described below, a primary goal of autonomous navigation is safety. Since absolute safety may not be possible (e.g., at least because a particular host vehicle under autonomous control cannot control other vehicles around it - it can only control its own actions), using potential accident liability as a consideration in autonomous navigation, and indeed as a constraint on planned actions, can help ensure that a particular autonomous vehicle does not take any actions that are considered unsafe - for example, those actions for which potential accident liability may be attached to the host vehicle. If the host vehicle only takes actions that are safe and are determined not to result in an accident for which the host vehicle is itself at fault (fault) or responsible, then the desired level of accident avoidance (e.g., less than 10 accidents per hour of driving) can be achieved. -9 ).

[0386] Challenges posed by most current approaches to autonomous driving include a lack of safety guarantees (or at least an inability to provide the desired level of safety), as well as a lack of scalability. Consider the problem of ensuring multi-actor safety. As society is unlikely to tolerate machine-caused road fatalities, an acceptable level of safety is critical to the acceptance of autonomous vehicles. While the goal may be to provide zero accidents, this may not be possible, as multiple actors are often involved in an accident, and it is conceivable that an accident occurs solely due to the fault of other actors. For example, if Fig.19 As shown, host vehicle 1901 is driving on a multi-lane highway, and while host vehicle 1901 can control its own movements relative to target vehicles 1903, 1905, 1907, and 1909, it cannot control the movements of the target vehicles around it. As a result, if vehicle 1905, for example, suddenly cuts into the host vehicle's lane on a collision course with the host vehicle, host vehicle 1901 may be unable to avoid an accident with at least one of the target vehicles. To address this challenge, the typical response of autonomous vehicle practitioners is to adopt a statistical data-driven approach in which safety validation becomes more rigorous as more miles of data are collected.

[0387] However, to understand the nature of the problem with a data-driven approach to safety, first consider that the probability of death due to a (human) driving accident is known to be 10 per hour. -6 It is reasonable to assume that in order for society to accept machines replacing humans in driving tasks, the death rate should be reduced by three orders of magnitude, to 10 per hour. -9 This estimate is similar to the assumed air bag mortality rate and is derived from aviation standards. For example, 10 -9is the probability that the wing will spontaneously detach from the aircraft in midair. However, it is not practical to try to guarantee safety using data-driven statistical methods that provide additional confidence by accumulating driving miles. -9 The amount of data required to calculate the probability of death is its reciprocal (i.e. 10 9 hours of data), which is on the order of 30 billion miles. Furthermore, multi-actor systems interact with their environment and may not be validated offline (unless a realistic simulator is available that simulates real human driving (such as reckless driving) in all its richness and complexity - but the problem of validating such a simulator is even more difficult than creating a safe autonomous vehicle actor). Any change to the planning and control software will require the same amount of new data collection, which is clearly impractical and impractical. Furthermore, developing systems through data always suffers from a lack of interpretability and explainability of the actions taken - if an autonomous vehicle (AV) has an accident resulting in a fatality, we need to know why. Therefore, a model-based approach to safety is needed, but existing "functional safety" and ASIL requirements in the automotive industry are not designed to cope with multi-actor environments.

[0388] The second major challenge in developing safe driving models for autonomous vehicles is the need for scalability. The premise of AVs is not just about “building a better world”, but is based on the premise that mobility without drivers can be maintained at a lower cost than mobility with drivers. This premise is always coupled with the concept of scalability - that is, supporting mass production of AVs (in the millions) and, more importantly, supporting negligible incremental costs to be able to drive in new cities. So, while the cost of compute and sensing does matter, the cost of validation and the ability to drive “everywhere” rather than in a select few cities are also necessary requirements to sustain the business if AVs are to be manufactured at scale.

[0389] The problem with most current approaches is the “brute force” mentality along three axes: (i) the required “computation density”, (ii) the way HD maps are defined and created, and (iii) the required specifications of the sensors. The brute force approach runs counter to scalability and shifts the focus to a future of unconstrained onboard computing ubiquity, where the cost of building and maintaining HD maps becomes negligible and scalable, and exotic ultra-advanced sensors are developed, produced to automotive grade, and cost negligible. A future in which any of the above is achieved is indeed possible, but a future in which all of the above are achieved is likely to be a low probability event. Therefore, there is a need to provide a formal model that combines safety and scalability into an AV program that is socially acceptable and scalable in the sense of supporting millions of cars driving anywhere in the developed world.

[0390] The disclosed embodiments represent a solution that can provide the target safety level (or even exceed the safety goal) and can also be scaled to systems including millions (or more) of autonomous vehicles. On the safety side, a model called "Responsibility Sensitive Safety (RSS)" is introduced, which formalizes the concept of "accident attribution", is interpretable and explainable, and incorporates the concept of "responsibility" into the actions of robotic actors. The definition of RSS is agnostic to the way it is implemented - a key feature that facilitates the goal of creating a convincing global safety model. The motivation for RSS is that (e.g. Fig.19 (as shown) actors play asymmetric roles in accidents where typically only one of the actors is responsible and therefore liable for the accident. The RSS model also includes a formal treatment of "careful driving" under limited sensing conditions where not all actors are always visible (e.g., due to occlusion). A major goal of the RSS model is to guarantee that an actor never has an accident for which it is "attributed" or for which it is responsible. The model can only be useful if it comes with an effective policy that complies with RSS (e.g., a function that maps "sensing states" to actions). For example, actions that seem innocent at the moment may lead to catastrophic events (the "butterfly effect") in the distant future. RSS can help construct a set of local constraints in the short term future that can guarantee (or at least virtually guarantee) that no accidents will occur in the future due to the actions of the host vehicle.

[0391] Another contribution revolves around the introduction of a “semantic” language that includes units, measurements, and action spaces, and specifications for how to incorporate them into the planning, sensing, and actuation of an AV. To get a sense of semantics, in this context, consider how someone taking a driving course is instructed to think about “driving strategies.” These instructions are not geometric—they don’t say “drive 13.7 meters at your current speed, then drive at 0.8 m / s.” 2 Instead, the instructions are semantic in nature—“follow the car in front of you” or “pass that car on your left.” The typical language of human driving policy is in terms of longitudinal and lateral targets, not geometric units of acceleration vectors. Formal semantic languages ​​can be useful in a number of ways, including the computational complexity of planning that does not scale exponentially with time and the number of actors, the way safety and comfort interact, the way sensing computations are defined, the specification of sensor modalities and how they interact in fusion methods. Fusion methods (based on semantic languages) can ensure that the RSS model achieves the required 10 km / h per hour driven. -9 The probability of death is only 10 5 Offline validation was performed on a dataset of 150 hours of driving data.

[0392] For example, in a reinforcement learning setting, a Q function (e.g., a function that evaluates the long-term quality of performing an action a∈A when the agent is in state s∈S; given such a Q function, a natural choice of action would be to pick the action with the highest quality π(s) = argmax a Q(s,a)) can be defined on a semantic space where the number of trajectories to be examined at any given time is 10 4 bounded, regardless of the time horizon used for planning. The signal-to-noise ratio in this space can be high, allowing effective machine learning methods to successfully model the Q-function. In the case of computation on sensing, semantics can allow for the distinction between errors that affect safety and errors that affect driving comfort. We define a PAC model for sensing (Probably Approximate Correct (PAC), borrowing Valiant’s PAC learning terminology), fit this model to the Q-function, and show how measured errors can be incorporated into planning in a way that is consistent with RSS while allowing for optimization of driving comfort. The semantic language may be important to the success of certain aspects of the model, as other standard measures of error (such as error relative to a global coordinate system) may not conform to the PAC sensing model. Furthermore, the semantic language may be an important enabler for defining HD maps, which can be built using low-bandwidth sensing data, thereby being built through crowdsourcing and supporting scalability.

[0393] In summary, the disclosed embodiments may include a formal model covering the important components of an AV: sensing, planning, and action. The model may help ensure that from a planning perspective, no accidents occur for which the AV is itself responsible. And through the PAC sensing model, even in the presence of sensing errors, the described fusion approach may only require a very reasonable amount of offline data collection to comply with the described safety model. Furthermore, the model may bring safety and scalability together through a semantic language, thereby providing a complete approach for safe and scalable AVs. Finally, it is worth noting that developing an accepted safety model that will be adopted by industry and regulators may be a necessary condition for the success of AVs.

[0394] The RSS model generally follows the classic sense-plan-act robotic control approach. The sensing system can be responsible for understanding the current state of the host vehicle environment. The planning part can be called a "driving strategy" and can be implemented by a set of hard-coded instructions, through a trained system (e.g., a neural network), or a combination. The planning part can be responsible for determining the best next move based on the available options for achieving the driving goal (e.g., how to move from the left lane to the right lane to exit the highway). The action part is responsible for implementing the plan (e.g., a system of actuators and one or more controllers for steering, accelerating and / or braking the vehicle, etc. in order to implement the selected navigation action). The embodiments described below focus mainly on the sensing and planning parts.

[0395] Accidents can result from sensing errors or planning errors. Planning is a multi-actor effort because there are other road users (humans and machines) reacting to the AV's actions. The described RSS model is designed to address issues such as the safety of the planning part. This can be called multi-actor safety. In a statistical approach, the estimation of the probability of planning errors can be done "online". That is, after each update of the software, billions of miles must be driven with the new version to provide an acceptable level of estimation of the frequency of planning errors. This is obviously not feasible. As an alternative, the RSS model can provide 100% guarantee (or almost 100% guarantee) that the planning module will not make mistakes that are attributed to the AV (the concept of "attribution" is formally defined). The RSS model can also provide an efficient method for its verification that does not rely on online testing.

[0396] Errors in the sensing system may be easier to verify because sensing can be independent of vehicle motion, so we can verify the probability of severe sensing errors using “offline” data. However, even if more than 10 9 Hours of driving offline data is also challenging. As part of the description of the disclosed sensing system, a fusion method is described that can be validated using significantly smaller amounts of data.

[0397] The described RSS system can also scale to millions of cars. For example, the described semantic driving strategy and applied safety constraints can be consistent with sensing and mapping requirements that can scale to millions of cars even with today's technology.

[0398] The fundamental building block for such systems is a thorough safety definition, i.e., the minimum standards that an AV system may need to comply with. In the following technical lemma, statistical methods for validating AV systems are shown to be infeasible even for verifying simple statements such as “the system experiences N accidents per hour.” This means that a model-based safety definition is the only viable tool for validating AV systems.

[0399] Lemma 1 Let X be a probability space, and A be an event with Pr(A)=p1<0.1. Suppose we sample from X samples, and let So

[0400] Pr(z=0)≥e -2 .

[0401] Prove that we use the inequality 1-x ≥ e -2x (proven in Appendix A.1 for completeness), we get

[0402]

[0403] Corollary 1: Assume that AV system AV1 has an accident with a small yet insufficient probability p1. Any deterministic verification procedure given 1 / p1 samples will be unable to distinguish AV1 from a different AV system AV0 that never has an accident with constant probability.

[0404] To get some perspective on typical values ​​for these probabilities, suppose we expect the probability of an accident to be 10 per hour. -9 , while one AV system provides only 10 -8 Even if the system obtains 10 8 hours of driving, there is still a constant probability that the validation process will fail to indicate that the system is dangerous.

[0405] Finally, note that the difficulty lies in invalidating a single, specific, dangerous AV system. The complete solution cannot be viewed as a single system, as new versions, bug fixes, and updates are required. From the verifier's perspective, every change, even to a single line of code, generates a new system. Therefore, a statistically validated solution must be validated online with new samples after each small correction or change to account for shifts in the state distribution observed and derived by the new system. It is not feasible to repeatedly and systematically obtain such a large number of samples (and even then, fail to validate the system with constant probability).

[0406] Furthermore, any statistical claim must be formalized to be measurable. Claiming that a system has a statistical property about the number of accidents it has had is much weaker than claiming that it drives in a safe manner. To make this point, one must formally define what safety is.

[0407] Absolute safety is impossible

[0408] If no accident occurs at some time in the future following action a, then the action a taken by car c can be considered absolutely safe. Fig.19 From the simple driving scenario depicted, it can be seen that it is impossible to achieve absolute safety. From the perspective of vehicle 1901, there is no action that can ensure that surrounding vehicles will not hit it. It is also impossible to solve this problem by prohibiting autonomous cars from being in such situations. Since every highway with more than two lanes will lead to such a scenario at some point, prohibiting such scenarios is equivalent to requiring to stay in the garage. At first glance, this suggestion may seem disappointing. Nothing is absolutely safe. However, as mentioned above, such a requirement for absolute safety may be too demanding, and it is proven that human drivers do not adhere to the requirement of absolute safety. Instead, humans act according to a concept of safety that relies on responsibility.

[0409] Responsibility-sensitive safety

[0410] An important aspect missing from the concept of absolute safety is the asymmetry of most accidents - usually one of the drivers is responsible for the crash and is blamed. Fig.19 In the example of , if, for example, the left car 1909 suddenly drives into the center car 1901, the center car 1901 should not be blamed. In order to formalize the fact that it lacks responsibility, the behavior of AV 1901 staying in its own lane can be considered safe. For this purpose, a formal concept of "accident blame" or accident responsibility is described, which can be used as a premise for a safe driving method.

[0411] As an example, consider two cars c f 、cr A simple case of two cars traveling at the same speed, one behind the other, on a straight road. Assume that the car in front, c f Because of an obstacle in the road, he suddenly braked and tried to avoid it. Unfortunately, c r No with c f Keep enough distance to not be able to respond in time and hit c f Obviously, the responsibility lies with c r ; It is the responsibility of the following vehicle to maintain a safe distance from the vehicle in front and to be prepared for unexpected but reasonable braking.

[0412] Next, consider a wider range of scenarios: driving on a multi-lane road where cars are free to change lanes, cut into the path of other cars, travel at different speeds, and so on. To simplify the following discussion, assume that there is a straight road on a plane, where the lateral and longitudinal axes are the x-axis and y-axis, respectively. Under mild conditions, this can be achieved by defining a homomorphism between actual curves and straights. In addition, consider a discrete time space. The definition may help to distinguish two intuitively different groups of cases: simple cases where no significant lateral maneuvers are performed, and more complex cases involving lateral motion.

[0413] Definition 1 (Corridor): The corridor of car c is a range [c x,left, c x,right ]×[±∞], where c x,left, c x,right It is the position of the leftmost and rightmost corners of c.

[0414] Definition 2 (cut-in) If car c1( Fig. 20A and 20B The car in 2003) is not identical to the car c0( Fig. 20A and 20B If the corridor of car c1 intersects with the corridor of car c0 at time t, then car c1 cuts into the corridor of car c0 at time t.

[0415] A further distinction can be made between the front / rear part of the corridor. The term "cut-in direction" can describe ...

Claims

1. A system for navigating a host vehicle, the system comprising: At least one processor programmed to: receiving at least one image representing an environment of the host vehicle from an image capture device; Determining a planned navigation action for completing a navigation goal of the host vehicle based on at least one driving strategy; analyzing the at least one image to identify a target vehicle in an environment of the host vehicle; determining a next state distance between the host vehicle and the target vehicle that would result if the planned navigation action were taken; determining a maximum braking capability of the host vehicle, a maximum acceleration capability of the host vehicle, and a speed of the host vehicle; determining a stopping distance for the host vehicle based on a maximum braking capability of the host vehicle, a maximum acceleration capability of the host vehicle, and a speed of the host vehicle; determining a speed of the target vehicle based on at least one identified characteristic of the target vehicle and assuming a maximum braking capacity of the target vehicle; as well as The planned navigation action is implemented when the determined stopping distance of the host vehicle is less than the sum of the determined next state distance and a target vehicle travel distance determined based on the speed of the target vehicle and an assumed maximum braking capacity of the target vehicle.

2. The system according to claim 1, wherein: The stopping distance of the host vehicle includes an acceleration distance corresponding to a distance the host vehicle can travel at a maximum acceleration capability of the host vehicle within a predetermined period of time, wherein an initial speed corresponds to the determined speed of the host vehicle.

3. The system according to claim 2, wherein: The predetermined period of time is a reaction time associated with the host vehicle.

4. The system according to claim 1, wherein: The target vehicle speed is determined based on an analysis of the at least one image.

5. The system according to claim 1, wherein: The target vehicle speed is determined based on an analysis of output from at least one of a LIDAR system or a RADAR system associated with the host vehicle.

6. The system according to claim 1, wherein: The identified characteristics of the target vehicle include vehicle type.

7. The system according to claim 1, wherein: The identified characteristic of the target vehicle is vehicle size.

8. The system according to claim 1, wherein: The identified characteristics of the target vehicle include a vehicle model.

9. The system according to claim 1, wherein: The identified characteristic of the target vehicle is determined based on an analysis of the at least one image.

10. The system according to claim 1, wherein: At least one characteristic of the target vehicle is determined based on at least one of the LIDAR output or the RADAR output.

11. The system according to claim 1, wherein: The planned navigation maneuver includes at least one of a lane change maneuver, a lane merging maneuver, a passing maneuver, a following distance reduction maneuver, or a hold-throttle maneuver.

12. The system of claim 1, wherein: The at least one processor is configured to implement a planned navigation action if the determined stopping distance of the host vehicle is less than the sum of the determined next-state distance and a target vehicle travel distance by at least a predetermined minimum distance, wherein the target vehicle travel distance is determined based on a speed of the target vehicle and an assumed maximum braking capacity of the target vehicle.

13. The system according to claim 12, wherein: The predetermined minimum distance corresponds to a predetermined separation distance to be maintained between the host vehicle and other vehicles.

14. A method for navigating a host vehicle, comprising: receiving at least one image representing an environment of the host vehicle from an image capture device; Determining a planned navigation action for completing a navigation goal of the host vehicle based on at least one driving strategy; analyzing the at least one image to identify a target vehicle in an environment of the host vehicle; determining a next state distance between the host vehicle and the target vehicle that would result if the planned navigation action were taken; determining a maximum braking capability of the host vehicle, a maximum acceleration capability of the host vehicle, and a speed of the host vehicle; determining a stopping distance for the host vehicle based on a maximum braking capability of the host vehicle, a maximum acceleration capability of the host vehicle, and a speed of the host vehicle; determining a speed of the target vehicle based on at least one identified characteristic of the target vehicle and assuming a maximum braking capacity of the target vehicle; as well as The planned navigation action is implemented when the determined stopping distance of the host vehicle is less than the sum of the determined next state distance and a target vehicle travel distance determined based on the speed of the target vehicle and an assumed maximum braking capacity of the target vehicle.

15. The method according to claim 14, wherein: The stopping distance of the host vehicle includes an acceleration distance corresponding to a distance the host vehicle can travel at a maximum acceleration capability of the host vehicle within a predetermined period of time, wherein an initial speed corresponds to the determined speed of the host vehicle.

16. The method according to claim 15, wherein: The predetermined period of time is a reaction time associated with the host vehicle.

17. The method according to claim 14, wherein: The target vehicle speed is determined based on an analysis of the at least one image.

18. The method according to claim 14, wherein: The target vehicle speed is determined based on an analysis of output from at least one of a LIDAR system or a RADAR system associated with the host vehicle.

19. The method according to claim 14, wherein: The identified characteristics of the target vehicle include vehicle type.

20. The method according to claim 14, wherein: The identified characteristic of the target vehicle is vehicle size.

21. The method according to claim 14, wherein: The identified characteristics of the target vehicle include a vehicle model.

22. The method according to claim 14, wherein: The identified characteristic of the target vehicle is determined based on an analysis of the at least one image.

23. The method according to claim 14, wherein: At least one characteristic of the target vehicle is determined based on at least one of the LIDAR output or the RADAR output.

24. The method according to claim 14, wherein: The planned navigation maneuver includes at least one of a lane change maneuver, a lane merging maneuver, a passing maneuver, a following distance reduction maneuver, or a hold-throttle maneuver.

25. The method of claim 14, further comprising: The planned navigation action is implemented when the determined stopping distance of the host vehicle is less than the sum of the determined next-state distance and a target vehicle travel distance by at least a predetermined minimum distance, wherein the target vehicle travel distance is determined based on the speed of the target vehicle and an assumed maximum braking capacity of the target vehicle.

26. The method according to claim 25, wherein: The predetermined minimum distance corresponds to a predetermined separation distance to be maintained between the host vehicle and other vehicles.

Images