A method, system, and computer readable medium for generating a road navigation model

Abstract

The present disclosure provides a method, system and computer readable medium of generating a road navigation model. The method generates a road navigation model for autonomous vehicle navigation and includes receiving, by a server, navigation information from a plurality of vehicles, storing, by the server, the navigation information associated with the common road segment, generating, by the server, at least a portion of an autonomous vehicle road navigation model for the common road segment based on the navigation information from a plurality of vehicles, the autonomous vehicle road navigation model for the common road segment including at least one line representation of a road surface feature extending along the common road segment, and distributing, by the server, the autonomous vehicle road navigation model to one or more autonomous vehicles for use in autonomously navigating the one or more autonomous vehicles along the common road segment.

Description

[0001] This application is a divisional application of the invention patent application filed on July 21, 2017, with application number 201780051420.4 (international application number PCT / IB2017 / 001058) entitled "Method, system and readable medium for crowdsourcing and distributing sparse maps and lane measurement for autonomous vehicle navigation".

[0002] Cross-reference to related applications

[0003] This application claims priority to U.S. Provisional Patent Application No. 62 / 365,188, filed July 21, 2016; U.S. Provisional Patent Application No. 62 / 365,192, filed July 21, 2016; and U.S. Provisional Patent Application No. 62 / 373,153, filed August 10, 2016. The entire contents of the above applications are incorporated herein by reference. Technical Field

[0004] This disclosure generally relates to autonomous vehicle navigation and sparse maps for autonomous vehicle navigation. In particular, this disclosure relates to systems and methods for crowdsourcing sparse maps for autonomous vehicle navigation, systems and methods for distributing crowdsourced sparse maps for autonomous vehicle navigation, systems and methods for navigating vehicles using crowdsourced sparse maps, systems and methods for aligning crowdsourced map data, systems and methods for crowdsourcing road surface information collection, and systems and methods for vehicle localization using lane measurements. Background Technology

[0005] With continuous technological advancements, the goal of fully autonomous vehicles capable of navigating on roads is emerging. Autonomous vehicles may need to consider a wide variety of factors and make appropriate decisions based on those factors to safely and accurately reach their desired destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured from cameras) and may also use information from other sources (e.g., from GPS devices, speed sensors, accelerometers, suspension sensors, etc.). Simultaneously, to navigate to their destination, autonomous vehicles may also need to identify their position within a specific roadway (e.g., a specific lane in a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and move from one road to another at appropriate intersections or junctions. Utilizing and interpreting the vast amounts of information collected by the autonomous vehicle as it reaches its destination presents numerous design challenges. The large amounts of data that autonomous vehicles may need to analyze, access, and / or store (e.g., captured image data, map data, GPS data, sensor data, etc.) present challenges that can actually limit or even adversely affect autonomous navigation. Furthermore, if autonomous vehicles rely on traditional mapping technologies for navigation, the large amount of data required to store and update maps will pose a significant challenge.

[0006] In addition to data collection for map updates, autonomous vehicles must be able to use maps for navigation. Therefore, the size and detail of the maps, as well as their construction and transmission, must be optimized. Summary of the Invention

[0007] Embodiments consistent with this 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 systems may include one, two, or more cameras monitoring the vehicle's environment. The disclosed systems may provide navigation responses based, for example, analysis of images captured by one or more cameras. The disclosed systems may also provide navigation constructed from crowdsourced sparse maps. Other disclosed systems may use correlation analysis of images to perform localization that can be supplemented by sparse maps. The navigation response may also take into account other data, including, for example, global positioning system (GPS) data, sensor data (from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data.

[0008] As described above, in some embodiments, the disclosed systems and methods can use sparse maps for autonomous vehicle navigation. For example, sparse maps can provide sufficient information for navigation without requiring excessive data storage.

[0009] In other embodiments, the disclosed systems and methods can construct road models for autonomous vehicle navigation. For example, the disclosed systems and methods can allow crowdsourcing of sparse maps for autonomous vehicle navigation, distribution of crowdsourced sparse maps for autonomous vehicle navigation, and alignment of crowdsourced map data. Some disclosed systems and methods can additionally or alternatively crowdsource road surface information collection.

[0010] In another embodiment, the disclosed systems and methods can be used for autonomous vehicle navigation using sparse road models. For example, the disclosed systems and methods can provide vehicle navigation using crowdsourced sparse maps.

[0011] In yet another embodiment, the disclosed systems and methods can provide adaptive autonomous navigation. For example, the disclosed systems and methods can provide vehicle positioning using lane measurements.

[0012] In some embodiments, a non-transitory computer-readable medium may include a sparse map for autonomous vehicle navigation along a road segment. The sparse map may include at least one line representation of road surface features extending along the road segment and multiple landmarks associated with the road segment. Each line representation may represent a path along the road segment substantially corresponding to the road surface features, and the road surface features may be identified through image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0013] In other embodiments, a system for generating a sparse map for autonomous vehicle navigation along a road segment may include at least one processing device. The at least one processing device may be configured to receive multiple images acquired as one or more vehicles traverse the road segment; based on the multiple images, identify at least one line representation of road surface features extending along the road segment; and based on the multiple images, identify multiple landmarks associated with the road segment. Each line representation may represent a path along the road segment that substantially corresponds to the road surface features.

[0014] In another embodiment, a method for autonomous vehicle navigation to generate sparse maps along a road segment may include receiving multiple images acquired as one or more vehicles traverse the road segment; identifying at least one line representation of road surface features extending along the road segment based on the multiple images; and identifying multiple landmarks associated with the road segment based on the multiple images. Each line representation may represent a path along the road segment that substantially corresponds to the road surface features.

[0015] In some embodiments, a method for generating a road navigation model for use in autonomous vehicle navigation may include receiving navigation information from multiple vehicles by a server. The navigation information from the multiple vehicles may be associated with a common road segment. The method may further include storing the navigation information associated with the common road segment by the server, and generating at least a portion of the autonomous vehicle road navigation model for the common road segment based on the navigation information from the multiple vehicles. The autonomous vehicle road navigation model for the common road segment may include at least one line representation of road surface features extending along the common road segment, and each line representation may represent a path along the common road segment substantially corresponding to the road surface features. Furthermore, road surface features may be identified through image analysis of multiple images acquired as the multiple vehicles traverse the common road segment. The method may further include distributing the autonomous vehicle road navigation model by the server to one or more autonomous vehicles for autonomous navigation along the common road segment.

[0016] In other embodiments, a system for generating a road navigation model for use in autonomous vehicle navigation may include at least one network interface, at least one non-transitory storage medium, and at least one processing device. The at least one processing device may be configured to receive navigation information from multiple vehicles using the network interface. The navigation information from the multiple vehicles may be associated with a common road segment. The at least one processing device may also be configured to store the navigation information associated with the common road segment on the non-transitory storage medium and generate at least a portion of the autonomous vehicle road navigation model for the common road segment based on the navigation information from the multiple vehicles. The autonomous vehicle road navigation model for the common road segment may include at least one line representation of road surface features extending along the common road segment, and each line representation may represent a path along the common road segment substantially corresponding to the road surface features. Furthermore, road surface features may be identified through image analysis of multiple images acquired as the multiple vehicles traverse the common road segment. The at least one processing device may also be configured to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles using the network interface for autonomous navigation along the common road segment.

[0017] In some embodiments, a system for autonomously navigating a vehicle along a road segment may include at least one processing device. The at least one processing device may be configured to receive a sparse map model. The sparse map model may include at least one line representation of road surface features extending along the road segment, and each line representation may represent a path along the road segment substantially corresponding to the road surface features. The at least one processing device may also be configured to receive at least one image representing the vehicle's environment from a camera, analyze the sparse map model and the at least one image received from the camera, and determine an autonomous navigation response for the vehicle based on the analysis of the sparse map model and the at least one image received from the camera.

[0018] In other embodiments, a method for autonomously navigating a vehicle along a road segment may include receiving a sparse map model. The sparse map model may include at least one line representation of road surface features extending along the road segment, and each line representation may represent a path along a road segment substantially corresponding to the road surface features. The method may further include receiving at least one image representing the vehicle's environment from a camera, analyzing the sparse map model and the at least one image received from the camera, and determining an autonomous navigation response for the vehicle based on the analysis of the sparse map model and the at least one image received from the camera.

[0019] In some embodiments, a method for determining a line representation of road surface features extending along a road segment, wherein the line representation of the road surface features is configured for use in autonomous vehicle navigation, may include receiving, from a server, a first set of travel data including location information associated with the road surface features, and receiving, from a server, a second set of travel data including location information associated with the road surface features. The location information may be determined based on analysis of images of the road segment. The method may further include segmenting the first set of travel data into first travel segments and segmenting the second set of travel data into second travel segments; longitudinally aligning the first set of travel data with the second set of travel data within the corresponding segments; and determining the line representation of the road surface features based on the longitudinally aligned first and second travel data in the first and second draft segments.

[0020] In other embodiments, a system for determining a line representation of road surface features extending along a road segment, wherein the line representation of the road surface features is configured for use in autonomous vehicle navigation, may include at least one processing device. The at least one processing device may be configured to receive a first set of travel data including location information associated with the road surface features, and to receive a second set of travel data including location information associated with the road surface features. The location information may be determined based on analysis of images of the road segment. The at least one processing device may also be configured to segment the first set of travel data into first travel segments and the second set of travel data into second travel segments; to longitudinally align the first set of travel data with the second set of travel data within the corresponding segments; and to determine the line representation of the road surface features based on the longitudinally aligned first and second travel data in the first and second draft segments.

[0021] In some embodiments, a system for collecting road surface information of a road segment may include at least one processing device. The at least one processing device may be configured to receive at least one image representing a portion of the road segment from a camera, and to identify at least one road surface feature along said portion of the road segment in said at least one image. The at least one processing device may also be configured to determine a plurality of locations associated with the road surface features according to a vehicle's local coordinate system, and to transmit the determined plurality of locations from the vehicle to a server. The determined locations may be configured such that the server can determine a line representation of the road surface features extending along the road segment, and the line representation may represent a path along the road segment substantially corresponding to the road surface features.

[0022] In other embodiments, a method for collecting road surface information of a road segment may include receiving at least one image representing a portion of the road segment from a camera, and identifying at least one road surface feature along said portion of the road segment in the at least one image. The method may further include determining a plurality of locations associated with the road surface features according to a vehicle's local coordinate system, and sending the determined plurality of locations from the vehicle to a server. The determined locations may be configured such that the server can determine a line representation of the road surface features extending along the road segment, and the line representation may represent a path along the road segment substantially corresponding to the road surface features.

[0023] In some embodiments, a system for correcting the vehicle position on a navigation segment may include at least one processing device. The at least one processing device may be configured to determine the measured position of the vehicle along a predetermined road model trajectory based on the output of at least one navigation sensor. The predetermined road model trajectory may be associated with a road segment. The at least one processing device may also be configured to receive at least one image representing the vehicle's environment from an image capture device and analyze the at least one image to identify at least one lane marking. The at least one lane marking may be associated with a driving lane along the road segment. The at least one processing device may also be configured to determine, based on the at least one image, the distance from the vehicle to the at least one lane marking, determine an estimated offset of the vehicle from the predetermined road model trajectory based on the measured position of the vehicle and the determined distance, and determine autonomous maneuvering actions of the vehicle based on the estimated offset to correct the vehicle's position.

[0024] In other embodiments, a method for correcting the vehicle position on a navigation segment may include determining a measured position of the vehicle along a predetermined road model trajectory based on the output of at least one navigation sensor. The predetermined road model trajectory may be associated with a road segment. The method may further include receiving at least one image representing the vehicle's environment from an image capture device and analyzing the at least one image to identify at least one lane marking. The at least one lane marking may be associated with a driving lane along the road segment. The method may further include determining a distance from the vehicle to the at least one lane marking based on the at least one image, determining an estimated offset of the vehicle from the predetermined road model trajectory based on the measured vehicle position and the determined distance, and determining an autonomous maneuvering action of the vehicle based on the estimated offset to correct the vehicle's position.

[0025] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store any program instructions that are executed by at least one processing device and perform any of the methods described herein.

[0026] The foregoing general description and the following detailed description are merely exemplary and illustrative, and do not limit the scope of the claims. Attached Figure Description

[0027] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various embodiments disclosed.

[0028] In the attached diagram:

[0029] Figure 1 It is a schematic representation of an example system consistent with the disclosed embodiments.

[0030] Figure 2A It is an illustrative side view representation of an example vehicle that includes a system consistent with the disclosed embodiments.

[0031] Figure 2B It is consistent with the disclosed embodiments. Figure 2A The illustration shows a top view of the vehicle and system.

[0032] Figure 2C This is an illustrative top view representation of another embodiment of a vehicle that includes a system consistent with the disclosed embodiments.

[0033] Figure 2D This is an illustrative top view representation of yet another embodiment of a vehicle that includes a system consistent with the disclosed embodiments.

[0034] Figure 2E This is an illustrative top view representation of yet another embodiment of a vehicle that includes a system consistent with the disclosed embodiments.

[0035] Figure 2FThis is a schematic representation of an example vehicle control system consistent with the disclosed embodiments.

[0036] Figure 3A It is an illustrative representation of the interior of a vehicle, including a rearview mirror and a user interface for a vehicle imaging system, consistent with the disclosed embodiments.

[0037] Figure 3B This is an illustration of an example of a camera mounted behind the rearview mirror and against the vehicle's windshield, consistent with the disclosed embodiments.

[0038] Figure 3C It is consistent with the disclosed embodiments. Figure 3B The diagram shows the camera installation from different perspectives.

[0039] Figure 3D This is an illustration of an example of a camera mounted behind the rearview mirror and against the vehicle's windshield, consistent with the disclosed embodiments.

[0040] Figure 4 This is an example block diagram of a memory configured to store instructions for performing one or more operations, consistent with the disclosed embodiments.

[0041] Figure 5A This is a flowchart illustrating an example process for causing one or more navigation responses based on monocular image analysis, consistent with the disclosed embodiments.

[0042] Figure 5B This is a flowchart illustrating an example process for detecting one or more vehicles and / or pedestrians in a set of images, consistent with the disclosed embodiments.

[0043] Figure 5C This is a flowchart illustrating an example process for detecting road markings and / or lane geometry information in a set of images, consistent with the disclosed embodiments.

[0044] Figure 5D This is a flowchart illustrating an example process for detecting traffic lights in a set of images, consistent with the disclosed embodiments.

[0045] Figure 5E This is a flowchart illustrating an example process for generating one or more navigation responses based on a vehicle path, consistent with the disclosed embodiments.

[0046] Figure 5F This is a flowchart illustrating an example process for determining whether a vehicle ahead is changing lanes, consistent with the disclosed embodiments.

[0047] Figure 6This is a flowchart illustrating an example process for causing one or more navigation responses based on stereo image analysis, consistent with the disclosed embodiments.

[0048] Figure 7 This is a flowchart illustrating an example process consistent with the disclosed embodiments for causing one or more navigation responses based on the analysis of three sets of images.

[0049] Figure 8 A sparse map for providing autonomous vehicle navigation is shown, consistent with the disclosed embodiments.

[0050] Figure 9A A polynomial representation of a section of road consistent with the disclosed embodiments is shown.

[0051] Figure 9B The diagram shows a curve in three-dimensional space, representing the target trajectory of a vehicle included in a sparse map consistent with the disclosed embodiments.

[0052] Figure 10 Example landmarks that may be included in a sparse map consistent with the disclosed embodiments are shown.

[0053] Figure 11A A polynomial representation of the trajectory consistent with the disclosed embodiments is shown.

[0054] Figure 11B and 11C The target trajectory along a multi-lane road is shown, consistent with the disclosed embodiments.

[0055] Figure 11D An example road signature profile consistent with the disclosed embodiments is shown.

[0056] Figure 12 This is a schematic diagram of a system for autonomous vehicle navigation using crowdsourced data received from multiple vehicles, consistent with the disclosed embodiments.

[0057] Figure 13 An example autonomous vehicle road navigation model, represented by multiple three-dimensional splines, is shown, consistent with the disclosed embodiments.

[0058] Figure 14 A map skeleton, consistent with the disclosed embodiments, is shown, generated by combining location information from a number of trips.

[0059] Figure 15 An example of two vertically aligned strokes is shown, consistent with the disclosed embodiments, and used as a landmark to identify examples.

[0060] Figure 16An example is shown that uses example markers as landmarks to vertically align multiple runs, consistent with the disclosed embodiments.

[0061] Figure 17 This is a schematic diagram of a system for generating trip data using a camera, vehicle, and server, consistent with the disclosed embodiments.

[0062] Figure 18 This is a schematic diagram of a system for crowdsourced sparse maps, consistent with the disclosed embodiments.

[0063] Figure 19 This is a flowchart illustrating an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment, consistent with the disclosed embodiments.

[0064] Figure 20 A block diagram of a server consistent with the disclosed embodiments is shown.

[0065] Figure 21 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0066] Figure 22 The process of clustering vehicle trajectories associated with vehicles, consistent with the disclosed embodiments, is illustrated.

[0067] Figure 23 A navigation system for a vehicle, consistent with the disclosed embodiments, is shown, which can be used for autonomous navigation.

[0068] Figure 24 This is a flowchart illustrating an example process for generating a road navigation model for autonomous vehicle navigation, consistent with the disclosed embodiments.

[0069] Figure 25 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0070] Figure 26 This is a flowchart illustrating an example process for autonomously navigating a vehicle along a road segment, consistent with the disclosed embodiments.

[0071] Figure 27 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0072] Figure 28A An example of trip data from four separate trips, consistent with the disclosed embodiments, is shown.

[0073] Figure 28B An example of trip data from five individual trips, consistent with the disclosed embodiments, is shown.

[0074] Figure 28CAn example of a vehicle route determined based on trip data from five separate trips, consistent with the disclosed embodiments, is shown.

[0075] Figure 29 This is a flowchart illustrating an example process for determining line representations of road surface features extending along a road segment, consistent with the disclosed embodiments.

[0076] Figure 30 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0077] Figure 31 This is a flowchart illustrating an example process for collecting road surface information for a road segment, consistent with the disclosed embodiments.

[0078] Figure 32 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0079] Figure 33A This shows an example of a vehicle crossing a lane without using lane markings.

[0080] Figure 33B This shows the situation after the vehicle's position and heading have drifted. Figure 33A Examples.

[0081] Figure 33C This illustrates the situation after further drift in position and heading, and when the expected location of a landmark differs significantly from its actual location. Figure 33B Examples.

[0082] Figure 34A An example of a vehicle crossing a lane without using lane markings, consistent with the disclosed embodiments, is shown.

[0083] Figure 34B This illustrates a reduced position and heading drift consistent with the disclosed embodiments. Figure 34A Examples.

[0084] Figure 34C The embodiments shown are consistent with those disclosed. Figure 34B The example shows a landmark whose expected location is significantly aligned with its actual location.

[0085] Figure 35 This is a flowchart illustrating an example process for correcting the vehicle position on a navigation segment, consistent with the disclosed embodiments. Detailed Implementation

[0086] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numerals are used in the drawings and the following description to refer to the same or similar parts. While several illustrative embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, components illustrated in the drawings may be replaced, added, or modified, and the illustrative methods described herein may be modified by replacing, reordering, removing, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0087] Overview of autonomous vehicles

[0088] As used throughout this disclosure, the term "autonomous vehicle" means a vehicle capable of implementing at least one navigation change without driver input. "Navigation change" refers to one or more of the vehicle's handling, braking, or acceleration. "Autonomous" means that the vehicle does not need to be fully automatic (e.g., fully operational without a driver or driver input). Rather, autonomous vehicles include those capable of operating under driver control during certain time periods and operating without driver control during other time periods. Autonomous vehicles may also include those that control only some aspects of vehicle navigation, such as handling (e.g., maintaining vehicle alignment between lane constraints), but can delegate other aspects to the driver (e.g., braking). In some cases, an autonomous vehicle may handle some or all aspects of the vehicle's braking, speed control, and / or handling.

[0089] Traffic infrastructure has been built to provide drivers with visual information, including lane markings, traffic signs, and traffic lights, because human drivers typically rely on visual cues and observation to control vehicles. Given these design characteristics of 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, components of traffic infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) that can be observed by the driver, as well as other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Furthermore, autonomous vehicles can use stored information, such as information that provides a model of the vehicle's environment during navigation. For example, a vehicle can use GPS data, sensor data (e.g., from accelerometers, rate sensors, suspension sensors, etc.), and / or other map data to provide information about its environment while the vehicle is in motion, and the vehicle (and other vehicles) can use this information to locate itself on the model.

[0090] In some embodiments of this disclosure, the autonomous vehicle may use information acquired during navigation (e.g., from cameras, GPS devices, accelerometers, speed sensors, suspension sensors, etc.). In other embodiments, the autonomous vehicle may use information acquired by the vehicle (or by other vehicles) from past navigation during navigation. In yet another embodiment, the autonomous vehicle may use a combination of information acquired during navigation and information acquired from past navigation. The following sections provide an overview of a system consistent with the disclosed embodiments, followed by an overview of a forward imaging system and methods consistent with that system. The following sections disclose systems and methods for constructing, using, and updating sparse maps for autonomous vehicle navigation.

[0091] System Overview

[0092] Figure 1 This is a block diagram representation of system 100 according to the disclosed example embodiments. System 100 may include various components depending on the requirements of a particular implementation. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. Processing unit 110 may include one or more processing devices. In some embodiments, 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, image acquisition unit 120 may include any number of image acquisition devices and components. In some embodiments, image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 may also include a data interface 128 that communicatively connects processing device 110 to image acquisition device 120. For example, data interface 128 may include any wired and / or wireless links or multiple links for transmitting image data acquired by image acquisition device 120 to processing unit 110.

[0093] Wireless transceiver 172 may include one or more devices configured to exchange transmissions to one or more networks (e.g., cellular, Internet, etc.) via an air interface using radio frequency, infrared frequency, magnetic field, or electric field. Wireless transceiver 172 may use any well-known standard to send and / or receive data (e.g., Wi-Fi, etc.). (Bluetooth Smart, 802.15.4, ZigBee, etc.). This transmission can include communication from the master vehicle to one or more remotely located servers. This transmission can also include (one-way or two-way) communication between the master vehicle and one or more target vehicles in the master vehicle's environment (e.g., to coordinate the master vehicle's navigation in consideration of or in conjunction with target vehicles in the master vehicle's environment), or even broadcast transmissions to unspecified receivers near the sending vehicle.

[0094] Both application processor 180 and image processor 190 can include various types of processing devices. For example, either or both of application processor 180 and image processor 190 can include a microprocessor, a preprocessor (such as an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), auxiliary circuitry, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for running applications and for image processing and analysis. In some embodiments, application processor 180 and / or image processor 190 can include any type of single-core or multi-core processor, mobile device microcontroller, central processing unit, etc. Various processing devices can be used, including, for example, those available from, such as… Processors obtained from manufacturers such as [unclear], or from [unclear] GPUs obtained from manufacturers, and can include various architectures (e.g., x86 processors, ...). wait).

[0095] In some embodiments, application processor 180 and / or image processor 190 may include components that can be accessed from... Any EyeQ series processor chip obtained. These processor designs all include multiple processing units with local memory and instruction sets. Such a processor may include video input for receiving image data from multiple image sensors, and may also include video output capability. In one example, It uses 90 nanometer-micrometer technology that operates at 332 MHz. The architecture consists of two floating-point hyper-threaded 32-bit RISC CPUs ( (core), five Visual Computing Engines (VCE), and three Vector Microcode Processors The system consists of a Denali 64-bit mobile DDR controller, a 128-bit internal Sonics Interconnect, dual 16-bit video input and 18-bit video output controllers, a 16-channel DMA, and several peripherals. The MIPS34K CPU manages these five VCEs and three VMPs. TM And DMA, a second MIPS34K CPU and multi-channel DMA, and other peripherals. These five VCEs, three... The MIPS34K CPU can perform the intensive vision computations required for versatile bundled applications. In another example, as a third-generation processor and... Six times stronger It can be used in the disclosed embodiments. In other examples, it can be used in the disclosed embodiments. and / or Of course, any newer or future EyeQ processing devices can also be used with the disclosed embodiments.

[0096] Any processing device disclosed herein can 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 those instructions available to the processing device during its operation for execution. In some embodiments, configuring a processing device may include programming the processing device directly using architectural instructions. In any 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 master vehicle. For example, processing devices such as field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), etc., may be configured using, for example, one or more hardware description languages ​​(HDLs).

[0097] In other embodiments, configuring the processing device may include storing executable instructions on 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.

[0098] 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 perform the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by two or more processing devices. Additionally, in some embodiments, system 100 may include one or more of processing units 110 without including other components such as image acquisition unit 120.

[0099] Processing unit 110 may include various types of devices. For example, processing unit 110 may include various devices such as controllers, image preprocessors, central processing units (CPUs), graphics processing units (GPUs), auxiliary circuitry, digital signal processors, integrated circuits, memory, or any other type of device for image processing and analysis. Image preprocessors may include video processors for capturing, digitizing, and processing images from image sensors. CPUs may include any number of microcontrollers or microprocessors. GPUs may include any number of microcontrollers or microprocessors. Auxiliary circuitry may be any number of circuits known in the art, including caches, power supplies, clocks, and input / output circuits. Memory may store software that controls the operation of the system when executed by the processor. Memory may include databases and image processing software. Memory may include any number of random access memories, read-only memories, flash memory, disk drives, optical storage, magnetic tape storage, removable storage, and other types of storage. In one instance, the memory may be separate from processing unit 110. In another instance, the memory may be integrated into processing unit 110.

[0100] Each memory unit 140, 150 may include software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), can control the operation of various aspects of system 100. These memory units may include various database and image processing software. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage, magnetic tape storage, removable storage, and / or any other type of storage. In some embodiments, memory units 140, 150 may be decoupled from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

[0101] The position sensor 130 may include any type of device suitable for determining the location associated with at least one component of the system 100. In some embodiments, the position sensor 130 may include a GPS receiver. Such a receiver can determine the user's location and speed by processing signals broadcast by Global Positioning System satellites. The location information from the position sensor 130 may be made available to the application processor 180 and / or the image processor 190.

[0102] In some embodiments, system 100 may include components such as a rate sensor (e.g., tachometer, speedometer) for measuring the speed of vehicle 200 and / or an accelerometer (single-axis or multi-axis) for measuring the acceleration of vehicle 200.

[0103] User interface 170 may include any device suitable for providing information to or receiving input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including, for example, a touchscreen, microphone, keyboard, pointer device, tracking wheel, camera, knob, button, etc. Using such input devices, users can provide information input or commands to system 100 by typing instructions or information, providing voice commands, selecting menu options on the screen using buttons, pointers, or eye-tracking capabilities, or by any other technology suitable for transmitting information to system 100.

[0104] User interface 170 may be equipped with one or more processing devices configured to provide and receive information from the user, and process the information for use by, for example, 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 touch and / or gestures made on a touchscreen, respond to keyboard input or menu selection, etc. In some embodiments, user interface 170 may include a display, speaker, haptic device, and / or any other device for providing output information to the user.

[0105] Map database 160 may include any type of database for storing map data useful to system 100. In some embodiments, map database 160 may include data relating 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. Map database 160 may not only store the locations of these items but also descriptors associated with them, including, for example, names associated with any stored features. In some embodiments, map database 160 may be physically located alongside other components of system 100. Alternatively or additionally, map database 160 or a portion thereof may be remotely located relative to other components of system 100 (e.g., processing unit 110). In such embodiments, information from map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via cellular networks and / or the Internet, etc.). In some cases, map database 160 may store sparse data models comprising a polynomial representation of certain road features (e.g., lane markings) or the target trajectory of a primary vehicle. The following is combined with... Figures 8 to 19 Discuss the systems and methods for generating such maps.

[0106] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from the environment. Furthermore, any number of image capture devices can be used to acquire images for input to an image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four or more image capture devices. Reference will be made below. Figures 2B to 2E Image capture devices 122, 124 and 126 are further described.

[0107] System 100 or its various components can be integrated into a variety of different platforms. In some embodiments, system 100 may be included on vehicle 200, such as... Figure 2A As shown. For example, vehicle 200 may be equipped with the above-mentioned features. Figure 1 The system 100 described includes the processing unit 110 and any other components. 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 combining... Figures 2B to 2E The ones discussed can use multiple image capture devices. For example, Figure 2A Either of the image capture devices 122 and 124 of the vehicle 200 shown may be part of an ADAS (Advanced Driver Assistance System) imaging set.

[0108] The image capture device, included on the vehicle 200 and as part of the image acquisition unit 120, can be placed in any suitable location. In some embodiments, such as Figures 2A to 2E ,as well as Figures 3A to 3C As shown, the image capture device 122 can be located near the rearview mirror. This location provides a similar line of sight to that of the driver of vehicle 200, which can help determine 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 help obtain an image representing the driver's field of vision and / or line of sight.

[0109] Other locations for the image capturing device of the image acquisition unit 120 can also be used. For example, the image capturing device 124 can be located on or within the bumper of the vehicle 200. This location is particularly suitable for image capturing devices with a wide field of view. The line of sight of the image capturing device located on the bumper may be different from that of the driver, and therefore, the bumper image capturing device and the driver may not always see the same object. The image capturing devices (e.g., image capturing devices 122, 124, and 126) can also be located in other locations. For example, the image capturing device can be located on or within one or both of the side mirrors of the vehicle 200, on the roof of the vehicle 200, on the hood of the vehicle 200, on the trunk of the vehicle 200, on the side of the vehicle 200, mounted on any window of the vehicle 200, placed behind any window of the vehicle 200, or placed in front of any window, and in or near lighting equipment mounted on the front and / or rear of the vehicle 200.

[0110] In addition to the image capture equipment, vehicle 200 may also include various other components of system 100. For example, processing unit 110 may be included on vehicle 200, integrated with or separate from the vehicle's engine control unit (ECU). Vehicle 200 may also be equipped with position sensor 130 such as a GPS receiver, and may also include map database 160 and memory units 140 and 150.

[0111] As previously discussed, the wireless transceiver 172 can receive data via one or more networks (e.g., cellular networks, the Internet, etc.) and / or. 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 of data stored in map database 160, memory 140, and / or memory 150. Similarly, the wireless transceiver 172 can upload any data from the system 100 (e.g., images captured by image acquisition unit 120, data received by position sensor 130 or other sensors, vehicle control system, etc.) and / or any data processed by processing unit 110 to one or more servers.

[0112] System 100 can upload data to a server (e.g., to the cloud) based on privacy level settings. For example, System 100 can implement privacy level settings to specify or restrict the types of data (including metadata) that can uniquely identify a vehicle and / or its driver / owner that are sent to the server. Such settings can be configured by a user via, for example, a wireless transceiver 172, can be initialized by factory default settings, or by data received by the wireless transceiver 172.

[0113] In some embodiments, system 100 may upload data according to a “high” privacy level, and, if configured, system 100 may transmit data (e.g., route-related location information, captured images, etc.) without any details about a specific vehicle and / or driver / owner. For example, when uploading data according to a “high” privacy setting, system 100 may exclude the vehicle identification number (VIN) or the name of the vehicle’s driver or owner, and instead transmit data (such as captured images and / or restricted route-related location information).

[0114] Consider other privacy levels. For example, system 100 may transmit data to the server at an “intermediate” privacy level and may include additional information not included at a “high” privacy level, such as vehicle model and / or vehicle type (e.g., passenger vehicle, SUV, truck, etc.). In some embodiments, system 100 may upload data at a “low” privacy level. At a “low” privacy level setting, system 100 may upload data and include information sufficient to uniquely identify a particular vehicle, owner / driver, and / or part or all of the route traveled by the vehicle. Such “low” privacy level data may include one or more of the following: for example, VIN, driver / owner name, vehicle origin before departure, vehicle's intended destination, vehicle model and / or vehicle type, etc.

[0115] Figure 2A This is an illustrative side view representation of an example vehicle imaging system according to the disclosed embodiments. Figure 2B yes Figure 2A The illustrated top view of the embodiment shown is exemplary. Figure 2B As shown, the disclosed embodiments may include a vehicle 200, which includes a system 100 in its body, the system 100 having a first image capturing device 122 located near and / or close to the driver's side mirror of the vehicle 200, a second image capturing device 124 located on or in a bumper area of ​​the vehicle 200 (e.g., one of the bumper areas 210), and a processing unit 110.

[0116] like Figure 2C As shown, both image capturing devices 122 and 124 can be located near the rearview mirror of vehicle 200 and / or close to the driver. Furthermore, although... 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. For example, in Figure 2D and Figure 2E In the embodiment shown, the first image capture device 122, the second image capture device 124, and the third image capture device 126 are included in the system 100 of the vehicle 200.

[0117] like Figure 2D As shown, image capture device 122 may be located near and / or close to the rearview mirror of vehicle 200, and image capture devices 124 and 126 may be located above or in the bumper area of ​​vehicle 200 (e.g., one of the bumper areas 210). And as... Figure 2E As shown, image capturing devices 122, 124, and 126 may be located near the rearview mirror and / or close to the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capturing devices, and the image capturing devices may be located in any suitable position within or on vehicle 200.

[0118] It should be understood that the disclosed embodiments are not limited to vehicles and can be applied to other scenarios. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200 and can be applied to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0119] The first image capturing device 122 may include any suitable type of image capturing device. The image capturing device 122 may include an optical axis. In one example, the image capturing device 122 may include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capturing device 122 may provide a resolution of 1280 × 960 pixels and may include a rolling shutter. The image capturing device 122 may include various optical elements. In some embodiments, it may include one or more lenses, for example, for providing the desired focal length and field of view for the image capturing device. In some embodiments, the image capturing device 122 may be associated with a 6mm lens or a 12mm lens. In some embodiments, such as Figure 2DAs shown, the image capture device 122 can be configured to capture images 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 to 56 degrees, including 46-degree FOV, 50-degree FOV, 52-degree FOV, or larger. Alternatively, the image capture device 122 can be configured to have a narrow FOV in the range of 23 to 40 degrees, such as 28-degree FOV or 36-degree FOV. Furthermore, 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 can include a wide-angle bumper camera or a camera with an FOV of up to 180 degrees. In some embodiments, the image capture device 122 can be a 7.2M (megapixel) 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 instead of a three-image capture device configuration. Due to significant lens distortion, in embodiments of image capture devices using radially symmetrical lenses, the vertical field of view (FOV) of such image capture devices can be significantly less than 50 degrees. For example, such lenses may not be radially symmetrical, which would allow a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

[0120] The first image capturing device 122 can acquire multiple first images of a scene associated with the vehicle 200. Each of the multiple first images can be acquired as a series of image scan lines, which can be captured using a rolling shutter. Each scan line may include multiple pixels.

[0121] The first image capturing 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 rate at which the image sensor can acquire image data associated with each pixel contained in a particular scan line.

[0122] Image capturing devices 122, 124, and 126 may include any suitable type and number of image sensors, such as CCD sensors or CMOS sensors. In one embodiment, a CMOS image sensor and a rolling shutter may be employed, such that each pixel in a row is read one at a time, and scanning of each row continues on a line-by-line basis until the entire image frame has been captured. In some embodiments, rows may be captured sequentially from top to bottom relative to the frame.

[0123] In some embodiments, one or more of the image capturing devices disclosed herein (e.g., image capturing devices 122, 124, and 126) may constitute a high-resolution imager and may have a resolution greater than 5 megapixels, 7 megapixels, 10 megapixels, or greater.

[0124] The use of a rolling shutter can cause pixels in different rows to be exposed and captured at different times, which can cause distortion and other image artifacts in the captured image frame. On the other hand, when the image capture device 122 is configured to utilize global or synchronous shutter operation, all pixels can be exposed for the same amount of time and during a common exposure period. As a result, the image data in the frame collected from a system using a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a specific time. In contrast, in a rolling shutter application, each row in the frame is exposed and data is captured at different times. Therefore, in an image capture device with a rolling shutter, moving objects may appear distorted. This phenomenon will be described in more detail below.

[0125] The second image capturing device 124 and the third image capturing device 126 can be any type of image capturing device. Similar to the first image capturing device 122, each of image capturing devices 124 and 126 may include an optical axis. In one embodiment, each of image capturing devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of image capturing devices 124 and 126 may include a rolling shutter. Similar to image capturing device 122, image capturing devices 124 and 126 can be configured to include various lenses and optics. In some embodiments, the lenses associated with image capturing devices 124 and 126 may provide a field of view (FOV) (such as FOV 204 and 206) that is equal to or narrower than the FOV associated with image capturing device 122 (such as FOV 202). For example, image capturing devices 124 and 126 may have an FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0126] Image capturing devices 124 and 126 can acquire multiple second and third images of a scene associated with vehicle 200. Each of these multiple second and third images can be acquired as a second and third series of image scan lines, which can be captured using a rolling shutter. Each scan line or row can have multiple pixels. Image capturing devices 124 and 126 can have a second scan rate and a third scan rate associated with the acquisition of each image scan line included in the second and third series.

[0127] Each image capture device 122, 124, and 126 can be positioned at any suitable location and orientation relative to the vehicle 200. The relative positions of the image capture devices 122, 124, and 126 can be selected to facilitate the fusion of information acquired from the image capture devices. For example, in some embodiments, the field of view (FOV) associated with image capture device 124 (such as FOV 204) may partially or completely overlap with the FOV associated with image capture device 122 (e.g., FOV 202) and the FOV associated with image capture device 126 (e.g., FOV 206).

[0128] Image capturing devices 122, 124, and 126 can be located at any suitable relative height on vehicle 200. In one example, a height difference may exist between image capturing devices 122, 124, and 126, which can provide sufficient parallax information to enable stereoscopic analysis. For example, as Figure 2A As shown, the two image capture devices 122 and 124 are at different heights. For example, a lateral displacement difference may also exist between image capture devices 122, 124, and 126, providing additional parallax information for the stereo analysis of 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 forward or backward displacement (e.g., 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 devices 124 and / or 126. This type of displacement allows one of the image capture devices to cover potential blind spots of the other(one or more) image capture devices(s).

[0129] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with an image sensor), and the resolution of one or more image sensors associated with image capture device 122 may be higher, lower, or the same as the resolution of one or more image sensors associated with image capture devices 124 and 126. In some embodiments, one or more image sensors 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.

[0130] The frame rate (e.g., at which the image capture device acquires a set of pixel data for one image frame and then continues capturing pixel data associated with the next image frame) can be controllable. The frame rate associated with image capture device 122 can be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 can depend on various factors that may affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 may include selectable pixel delay periods that are applied before or after acquiring image data associated with one or more pixels of the image sensors in image capture devices 122, 124, and / or 126. Typically, image data corresponding to each pixel can be acquired based on the clock rate used for the device (e.g., one pixel per clock cycle). Additionally, in embodiments including a rolling shutter, one or more of the image capture devices 122, 124, and 126 may include a selectable horizontal blanking period applied before or after acquiring image data associated with a row of pixels of the image sensors in the image capture devices 122, 124, and / or 126. Furthermore, one or more images from the image capture devices 122, 124, and 126 may include a selectable vertical blanking period applied before or after acquiring image data associated with image frames from the image capture devices 122, 124, and 126.

[0131] These timing controls enable synchronization of frame rates associated with image capture devices 122, 124, and 126, even if each has a different line scan rate. Furthermore, as will be discussed in more detail below, these selectable timing controls, along with other factors (e.g., image sensor resolution, maximum line scan rate, etc.), enable synchronization of image capture from areas where the field of view (FOV) of image capture device 122 overlaps with one or more FOVs of image capture devices 124 and 126, even if the field of view of image capture device 122 differs from the FOVs of image capture devices 124 and 126.

[0132] The frame rate timing in image capture devices 122, 124, and 126 can depend on the resolution of the associated image sensor. For example, assuming that the line scan rates are similar for two 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, then more time is required to acquire one frame of image data from the sensor with the higher resolution.

[0133] 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, acquiring one line of image data from an image sensor included in image capture devices 122, 124, and 126 will require a certain minimum amount of time. Assuming no pixel delay period is added, this minimum amount of time for acquiring one line of image data will be related to the maximum line scan rate for a particular device. Devices offering a higher maximum line scan rate have the potential to offer 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 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.

[0134] In another embodiment, image capturing devices 122, 124, and 126 may have the same maximum line scan rate, but image capturing 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 capturing devices 124 and 126 operate at a line scan rate equal to the line scan rate of image capturing device 122. In other instances, the system may be configured such that the line scan rate of image capturing devices 124 and / or image capturing device 126 may be 1.25, 1.5, 1.75, or 2 or more times the line scan rate of image capturing device 122.

[0135] In some embodiments, image capturing devices 122, 124, and 126 may be asymmetrical. That is, they may include cameras with different fields of view (FOV) and focal lengths. For example, the fields of view of image capturing devices 122, 124, and 126 may include any desired area of ​​the environment of vehicle 200. In some embodiments, one or more of image capturing devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, behind vehicle 200, to the side of vehicle 200, or a combination thereof.

[0136] Furthermore, the focal length associated with each image capturing device 122, 124, and / or 126 can be selectable (e.g., by including a suitable lens, etc.) so that each device acquires an image of an object at a desired distance range relative to the vehicle 200. For example, in some embodiments, image capturing devices 122, 124, and 126 can acquire images of approaching objects within a few meters of the vehicle. Image capturing devices 122, 124, and 126 can also be configured to acquire images of objects at a greater distance from the vehicle (e.g., 25 meters, 50 meters, 100 meters, 150 meters, or more). Furthermore, the focal lengths of image capturing devices 122, 124, and 126 can be selected such that one image capturing device (e.g., image capturing device 122) can acquire images of objects relatively close to the vehicle (e.g., within 10 meters or 20 meters), while other image capturing devices (e.g., image capturing devices 124 and 126) can acquire images of objects farther away from the vehicle 200 (e.g., greater than 20 meters, 50 meters, 100 meters, 150 meters, etc.).

[0137] According to some embodiments, the field of view (FOV) of one or more image capture devices 122, 124, and 126 may have a wide angle. For example, an FOV of 140 degrees may be advantageous, especially for image capture devices 122, 124, and 126 that can be used to capture images of 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 such an embodiment, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0138] The field of view (FOV) associated with each image capturing device 122, 124, and 126 can depend on its respective focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0139] Image capturing devices 122, 124, and 126 can be configured to have any suitable field of view. In one particular example, image capturing device 122 can have a horizontal FOV of 46 degrees, image capturing device 124 can have a horizontal FOV of 23 degrees, and image capturing device 126 can have a horizontal FOV between 23 degrees and 46 degrees. In another example, image capturing device 122 can have a horizontal FOV of 52 degrees, image capturing device 124 can have a horizontal FOV of 26 degrees, and image capturing device 126 can have a horizontal FOV between 26 degrees and 52 degrees. In some embodiments, the ratio of the FOV of image capturing device 122 to the FOV of image capturing device 124 and / or image capturing device 126 can vary from 1.5 to 2.0. In other embodiments, this ratio can vary between 1.25 and 2.25.

[0140] System 100 may be configured such that the field of view of image capture device 122 at least partially or completely overlaps with the field of view of image capture devices 124 and / or 126. In some embodiments, system 100 may be configured such that the field of view of image capture devices 124 and 126, for example, falls within (e.g., is narrower than) the field of view of image capture device 122 and shares a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs, or may have partial overlap in their FOVs. In some embodiments, the field of view of image capture devices 122, 124, and 126 may be aligned such that the center of the narrower FOV image capture device 124 and / or 126 may be located in the lower half of the field of view of the wider FOV device 122.

[0141] Figure 2F This is a schematic representation of an example vehicle control system according to the disclosed embodiments. Figure 2F As indicated, vehicle 200 may include a throttle control system 220, a braking system 230, and a steering system 240. System 100 may provide inputs (e.g., control signals) to one or more of the throttle control system 220, braking system 230, and steering system 240 via one or more data links (e.g., any wired and / or wireless links for transmitting data). For example, based on analysis of images acquired by image capture devices 122, 124, and / or 126, system 100 may provide control signals to one or more of the throttle control system 220, braking system 230, and steering system 240 to navigate vehicle 200 (e.g., by inducing acceleration, maneuvering, lane changes, etc.). Furthermore, system 100 may receive inputs from one or more of the throttle control system 220, braking system 230, and steering system 240 indicative of the operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or maneuvering, etc.). The following is in conjunction with... Figures 4 to 7 Further details will be provided.

[0142] like Figure 3AAs shown, vehicle 200 may also include a user interface 170 for interacting with the driver or passengers of vehicle 200. For example, the user interface 170 in a vehicle application may include a touchscreen 320, a knob 330, a button 340, and a microphone 350. The driver or passengers of vehicle 200 may also interact with system 100 using handles (e.g., located on or near a joystick of vehicle 200, including, for example, a control lever), buttons (e.g., located on the steering wheel of vehicle 200), etc. In some embodiments, microphone 350 may be located adjacent to rearview mirror 310. Similarly, in some embodiments, image capture device 122 may be located near rearview mirror 310. In some embodiments, user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, system 100 may provide various notifications (e.g., alarms) via speaker 360.

[0143] Figures 3B to 3D This is an example of a camera mount 370 configured according to the disclosed embodiment to be located behind a rearview mirror (e.g., rearview mirror 310) and opposite the vehicle's windshield. Figure 3B As shown, camera mount 370 may include image capturing devices 122, 124, and 126. Image capturing devices 124 and 126 may be located behind a sunshade 380, wherein the sunshade 380 may be flush relative to the vehicle windshield and comprises a composite of a film and / or anti-reflective material. For example, the sunshade 380 may be positioned such that the plate is aligned relative to the windshield of a vehicle having a matching ramp. In some embodiments, each of image capturing devices 122, 124, and 126 may be located behind the sunshade 380, for example in Figure 3D The embodiments described herein are not limited to any particular configuration of the image capturing devices 122, 124 and 126, the camera mount 370 and the light shield 380. Figure 3C yes Figure 3B The image shows an example of a camera mount 370 from a frontal view.

[0144] As those skilled in the art who benefit from this disclosure will understand, many variations and / or modifications can be made to the disclosed embodiments. For example, not all components are necessary for the operation of system 100. Furthermore, any component may be located in any suitable part of system 100 and components may be rearranged into various configurations while providing the functionality of the disclosed embodiments. Thus, the foregoing configurations are exemplary, and regardless of the configurations discussed above, system 100 can provide a wide range of functions to analyze the surroundings of vehicle 200 and navigate vehicle 200 in response to that analysis.

[0145] As discussed in more detail below and according to various disclosed embodiments, system 100 can provide various features related to autonomous driving and / or driver assistance technologies. For example, system 100 can analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 can collect data from, for example, image acquisition unit 120, position sensor 130, and other sensors for analysis. Furthermore, system 100 can analyze the collected data to determine whether vehicle 200 should take a certain action, and then automatically take the determined action without human intervention. For example, when vehicle 200 is navigating without human intervention, system 100 can automatically control the braking, acceleration, and / or maneuvering of vehicle 200 (e.g., by sending control signals to one or more of throttle adjustment system 220, braking system 230, and maneuvering system 240). Additionally, system 100 can analyze the collected data and issue warnings and / or alerts to vehicle occupants based on the analysis of the collected data. Additional details regarding various embodiments of system 100 are provided below.

[0146] Forward Multi-Imaging System

[0147] As discussed above, system 100 can provide driver assistance functions using a multi-camera system. The multi-camera system may use one or more cameras facing forward of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side or rear of the vehicle. In one embodiment, for example, system 100 may use a dual-camera imaging system, wherein a first camera and a second camera (e.g., image capture devices 122 and 124) may be located at the front and / or side of the vehicle (e.g., vehicle 200).

[0148] The first camera may have a field of view that is larger than, smaller than, or partially overlaps with the field of view of the second camera. Furthermore, the first camera may be connected to a first image processor to perform monocular image analysis on images provided by the first camera, and the second camera may be connected to a second image processor to perform monocular image analysis on images provided by the second camera. The outputs of the first and second image processors (e.g., processed information) may be combined. In some embodiments, the second image processor may receive images from both the first and second cameras to perform stereo analysis. In another embodiment, system 100 may use a three-camera imaging system, where each camera has a different field of view. Therefore, such a system can make decisions based on information obtained from objects located at varying distances in front of and to the sides of the vehicle. Reference to monocular image analysis may refer to instances of image analysis performed based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may refer to instances of image analysis performed based on two or more images captured using one or more variations of image capture parameters. For example, images captured suitable for performing stereo image analysis may include images captured from two or more different locations, from different fields of view, using different focal lengths, or with parallax information, etc.

[0149] For example, in one embodiment, system 100 may use image capture devices 122, 124, and 126 to implement a three-camera configuration. In this configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees or other values ​​selected from the range of about 20 to 45 degrees), image capture device 124 may provide a wide field of view (e.g., 150 degrees or other values ​​selected from the range of about 100 to about 180 degrees), and image capture device 126 may provide an intermediate field of view (e.g., 46 degrees or other values ​​selected from the range of about 35 to about 60 degrees). In some embodiments, image capture device 126 may serve as a main camera or a base camera. Image capture devices 122, 124, and 126 may be located behind rearview mirror 310 and substantially side-by-side (e.g., 6 cm apart). Furthermore, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 may be mounted behind a sun visor 380 flush with the windshield of vehicle 200. This shielding can work to reduce the impact of any reflections from inside the vehicle on the image capture devices 122, 124, and 126.

[0150] In another embodiment, as described above... Figure 3B and 3CThe wide field-of-view camera discussed above (e.g., image capture device 124 in the example above) can be mounted below the narrow field-of-view camera and the main field-of-view camera (e.g., image capture devices 122 and 126 in the example above). This configuration provides 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.

[0151] A three-camera system can provide certain performance characteristics. For example, some embodiments may include the ability to verify object detection by one camera based on detection results from another camera. In the three-camera configuration discussed above, processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), wherein each processing device is dedicated to processing images captured by one or more of the image capture devices 122, 124, and 126.

[0152] 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, such as detecting other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the first processing device can calculate the pixel parallax between the images from the main camera and the narrow camera, and create a 3D reconstruction of the vehicle 200's environment. 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 the other camera.

[0153] 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. Additionally, the second processing device can calculate camera displacement and, based on this displacement, calculate the parallax of pixels between consecutive images and create a 3D reconstruction of the scene (e.g., a structure from motion). The second processing device can then send the 3D-reconstructed structure from motion to the first processing device for combination with the stereoscopic 3D images.

[0154] The third processing device can receive images from a wide field of view (FOV) camera and process them to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device can also execute additional processing instructions to analyze the images to identify moving objects, such as vehicles changing lanes or pedestrians.

[0155] In some embodiments, allowing the image-based information stream to be captured and processed independently can provide opportunities for redundancy in the system. This redundancy may include, for example, using a first image capture device and images processed from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0156] In some embodiments, system 100 uses two image capture devices (e.g., image capture devices 122 and 124) to provide 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 this configuration, image capture devices 122 and 124 can provide images for stereo analysis by system 100 to navigate vehicle 200, while image capture device 126 can provide images for monocular analysis by system 100 to provide redundancy and verification of information based on images captured from image capture devices 122 and / or 124. That is, image capture device 126 (and the corresponding processing device) can be considered as providing a redundant subsystem for providing checks on the analysis obtained from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Furthermore, in some embodiments, the redundancy and verification of received data may be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside the vehicle, etc.).

[0157] Those skilled in the art will recognize that the camera configurations, camera placements, number of cameras, camera positions, etc., described above are merely examples. These components, and other components described regarding the overall system, can 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.

[0158] Figure 4 This is an exemplary functional block diagram of memory 140 and / or memory 150, which may be stored / programmed with instructions to perform one or more operations consistent with embodiments of this 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 memory 150.

[0159] like Figure 4As shown, memory 140 may store monocular image analysis module 402, stereo image analysis module 404, velocity and acceleration module 406, and navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of the modules 402, 404, 406, and 408 contained in memory 140. Those skilled in the art will understand that in the following discussion, references to processing unit 110 may individually or uniformly refer to application processor 180 and image processor 190. Therefore, any of the following processing steps may be performed by one or more processing devices.

[0160] In one embodiment, the monocular image analysis module 402 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform monocular image analysis on a set of images acquired by one of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the set of images with additional sensing information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. As combined below... Figures 5A to 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 this analysis, system 100 (e.g., via processing unit 110) may elicit one or more navigation responses in vehicle 200, such as maneuvers, lane changes, changes in acceleration, etc., as discussed below in conjunction with navigation response module 408.

[0161] In one embodiment, the stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform stereo image analysis on a first set and a second set of images acquired by a combination of image capture devices selected from any combination of image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first set and the second set of images with additional sensing information (e.g., information from radar) to perform stereo image analysis. For example, the stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. (The following is a continuation of the previous paragraph.) Figure 6As described, the stereo image analysis module 404 may include instructions for detecting a set of features within a first and second set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, etc. Based on this analysis, the processing unit 110 may induce one or more navigation responses in the vehicle 200, such as maneuvering, lane changes, changes in acceleration, etc., as discussed below in conjunction with the navigation response module 408. Furthermore, in some embodiments, the stereo image analysis module 404 may implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems, such as a system that can be configured to use computer vision algorithms to detect and / or label objects in the environment from which sensor information is captured and processed. In one embodiment, the stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0162] 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 speed for the vehicle 200 based on data obtained from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, speed and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, and positional information of the vehicle 200 relative to lane markings on the road. Furthermore, the processing unit 110 may calculate the target speed of the vehicle 200 based on sensor inputs (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle control system 220, the braking system 230, and / or the steering system 240. Based on the calculated target speed, the processing unit 110 can transmit electronic signals to the throttle adjustment system 220, braking system 230 and / or control system 240 of the vehicle 200, for example, by physically pressing down the brake or releasing the accelerator of the vehicle 200 to trigger changes in speed and / or acceleration.

[0163] In one embodiment, the navigation response module 408 may store software executable by the processing unit 110 to determine a desired navigation response based on data obtained from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. This data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, target position information of vehicle 200, etc. Additionally, in some embodiments, the navigation response may be (partially or entirely) based on map data, the predetermined position of vehicle 200, and / or the relative velocity or relative acceleration between vehicle 200 and one or more objects detected from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine the desired navigation response based on sensor inputs (e.g., information from radar) and inputs from other systems of vehicle 200, such as the throttle control system 220, braking system 230, and steering system 240 of vehicle 200. Based on the desired navigation response, the processing unit 110 can transmit electronic signals to the throttle adjustment system 220, braking system 230, and steering system 240 of the vehicle 200 to trigger the desired navigation response, for example, by turning the steering wheel of the vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, the processing unit 110 can use the output of the navigation response module 408 (e.g., the desired navigation response) as input to the execution of the speed and acceleration module 406 to calculate the change in the speed of the vehicle 200.

[0164] Furthermore, any module disclosed herein (e.g., modules 402, 404, and 406) can implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems.

[0165] Figure 5A This is a flowchart illustrating an example process 500A for inducing one or more navigation responses based on monocular image analysis according to a disclosed embodiment. In step 510, processing unit 110 may receive multiple images via data interface 128 between processing unit 110 and image acquisition unit 120. For example, a camera included in image acquisition unit 120 (such as image capture device 122 having a field of view 202) may capture multiple images of a region in front of vehicle 200 (e.g., or to the side or rear of the vehicle) and transmit them to processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). In step 520, processing unit 110 may execute monocular image analysis module 402 to analyze the multiple images, as described below. Figures 5B to 5D In a further detailed description, by performing this analysis, the processing unit 110 can detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0166] In step 520, processing unit 110 may also execute monocular image analysis module 402 to detect various road hazards, such as components of truck tires, fallen road signs, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of such hazards more difficult. In some embodiments, processing unit 110 may execute monocular image analysis module 402 to perform multi-frame analysis on the multiple images to detect road hazards. For example, processing unit 110 may estimate camera motion between consecutive image frames and calculate disparity in pixels between frames to construct a 3D map of the road. Processing unit 110 can then use this 3D map to detect road surfaces and hazards present on the road surface.

[0167] In step 530, processing unit 110 may execute navigation response module 408 to perform the analysis performed in step 520 and as described above. Figure 4 The described techniques induce one or more navigation responses. Navigation responses may include, for example, maneuvering, lane changes, acceleration changes, etc. In some embodiments, processing unit 110 may induce one or more navigation responses using data obtained from the execution of speed and acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, processing unit 110 may induce vehicle 200 to change lanes and then accelerate by, for example, sequentially transmitting control signals to vehicle 200's steering system 240 and throttle adjustment system 220. Alternatively, processing unit 110 may induce vehicle 200 to brake and change lanes simultaneously by, for example, simultaneously transmitting control signals to vehicle 200's braking system 230 and steering system 240.

[0168] Figure 5B This is a flowchart illustrating an example process 500B for detecting one or more vehicles and / or pedestrians in a set of images according to a disclosed embodiment. Processing unit 110 may implement process 500B by executing monocular image analysis module 402. In step 540, processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 may scan one or more images, compare the images with one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or portions thereof). The predetermined patterns may be designed to achieve a high "false hit" rate and a low "missed" rate. For example, processing unit 110 may use a low similarity threshold in the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. Doing so allows processing unit 110 to reduce the likelihood of missing (e.g., not identifying) candidate objects representing vehicles or pedestrians.

[0169] In step 542, processing unit 110 may filter the group of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria can be derived from various attributes associated with object 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. Therefore, processing unit 110 may use one or more sets of criteria to reject false candidates from the group of candidate objects.

[0170] In step 544, processing unit 110 may analyze multiple frames of images to determine whether an object in the group 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.). Furthermore, processing unit 110 may estimate parameters of the detected objects and compare the object's frame-by-frame position data with its predicted position.

[0171] In step 546, processing unit 110 can construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to vehicle 200) associated with the detected objects. In some embodiments, processing unit 110 can construct these measurements based on a series of time-based observational estimation techniques, such as Kalman filters or linear quadratic estimation (LQE), 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 object's scale, where the scale measurement is proportional to the time of collision (e.g., the amount of time it takes for vehicle 200 to arrive at the object). Therefore, by performing steps 540 through 546, processing unit 110 can identify vehicles and pedestrians appearing within the set of captured images and obtain information associated with those vehicles and pedestrians (e.g., position, velocity, size). Based on this identification and the obtained information, processing unit 110 can induce one or more navigation responses in vehicle 200, as described above. Figure 5A As described.

[0172] In step 548, processing unit 110 may perform 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 vehicle 200, associated with other vehicles and pedestrians, and distinct from road surface motion in one or more images. Processing unit 110 can calculate the motion of candidate objects by observing different positions of the objects across multiple image frames captured at different times. Processing unit 110 can use this position and time value as input to a mathematical model used to calculate the motion of candidate objects. Therefore, optical flow analysis can provide an alternative method for detecting vehicles and pedestrians near vehicle 200. 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 system 100.

[0173] Figure 5C This is a flowchart illustrating an example process 500C for detecting road markings and / or lane geometry information in a set of images according to a disclosed embodiment. Processing unit 110 may implement processing 500C by executing monocular image analysis module 402. In step 550, processing unit 110 may detect a set of objects by scanning one or more images. To detect segments of lane markings, lane geometry information, and other relevant road markings, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., potholes, pebbles, etc.). In step 552, processing unit 110 may group segments detected in step 550 that belong to the same road marking or lane marking together. Based on this grouping, processing unit 110 may build a model, such as a mathematical model, representing the detected segments.

[0174] In step 554, processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, processing unit 110 may create a projection of the detected segment from the image plane onto a real-world plane. This projection may be characterized using a cubic polynomial with coefficients corresponding to physical properties such as the location, slope, curvature, and derivative of curvature of the detected road. In generating this projection, processing unit 110 may consider variations in the road surface, as well as the pitch and roll rates associated with vehicle 200. Furthermore, processing unit 110 may model the road elevation by analyzing positional and motion cues appearing on the road surface. Additionally, processing unit 110 may estimate the pitch and roll rates associated with vehicle 200 by tracking a set of feature points in one or more images.

[0175] In step 556, processing unit 110 can perform multi-frame analysis, for example, by tracking the detected segments across consecutive image frames and accumulating frame-by-frame data associated with the detected segments. Because processing unit 110 performs multi-frame analysis, the set of measurements constructed in step 554 can become more reliable and correlated with increasingly higher confidence levels. Therefore, by performing steps 550, 552, 554, and 556, processing unit 110 can identify road markings appearing in the set of captured images and obtain lane geometry information. Based on this identification and the obtained information, processing unit 110 can induce one or more navigation responses in vehicle 200, as described above. Figure 5A As described.

[0176] In step 558, processing unit 110 may consider additional information sources to further establish a safety model of vehicle 200 in its surrounding environment. Processing unit 110 can use this safety model to define the environment in which system 100 can safely perform autonomous control of vehicle 200. To establish this safety model, in some embodiments, processing unit 110 may consider the positions and movements of other vehicles, detected curbs and obstacles, 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 can provide redundancy for detecting road markings and lane geometry, and increase the reliability of system 100.

[0177] Figure 5D This is a flowchart illustrating an example process 500D for detecting traffic lights in a set of images according to a disclosed embodiment. Processing unit 110 may implement process 500D by executing monocular image analysis module 402. In step 560, processing unit 110 may scan the set of images and identify objects appearing in the images at locations that may contain traffic lights. For example, processing unit 110 may filter the identified objects to construct a set of candidate objects, excluding those that could not possibly correspond to traffic lights. Filtering may be based on various attributes associated with traffic lights, such as shape, size, texture, location (e.g., relative to 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, processing unit 110 may perform multi-frame analysis on the set of candidate objects reflecting possible traffic lights. For example, processing unit 110 may track candidate objects across consecutive image frames, estimate the real-world location of the candidate objects, and filter out moving objects (which are unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects and identify the relative positions of detected colors appearing within possible traffic lights.

[0178] In step 562, processing unit 110 can analyze the geometry of the intersection. This analysis can be based on any combination of: (i) the number of lanes detected on either side of vehicle 200, (ii) markings detected on the road (such as arrow markings), and (iii) a description of the intersection extracted from map data (e.g., data from map database 160). Processing unit 110 can perform the analysis using information obtained from the execution of monocular analysis module 402. Furthermore, processing unit 110 can determine the correspondence between traffic lights detected in step 560 and lanes appearing near vehicle 200.

[0179] In step 564, as vehicle 200 approaches the intersection, processing unit 110 can update the confidence level associated with the analyzed intersection geometry and the detected traffic lights. For example, comparing the number of traffic lights estimated to be present at the intersection with the actual number present at the intersection may affect the confidence level. Therefore, based on this confidence level, processing unit 110 can delegate control to the driver of vehicle 200 to improve safety conditions. By performing steps 560, 562, and 564, processing unit 110 can identify traffic lights appearing in the set of captured images and analyze intersection geometry information. Based on this identification and analysis, processing unit 110 can induce one or more navigation responses in vehicle 200, as described above. Figure 5A As described.

[0180] Figure 5E This is a flowchart illustrating an example process 500E for inducing one or more navigation responses in a vehicle based on a vehicle path, according to a disclosed embodiment. In step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path can be represented using a set of points expressed in coordinates (x, z), and the distance d between any two points in this set is... i The distance can fall within a range of 1 to 5 meters. In one embodiment, processing unit 110 can use two polynomials, such as a left-road polynomial and a right-road polynomial, to construct an initial vehicle path. 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., intelligent lane offset), if any (zero offset could correspond to driving in the middle of the lane). This offset can be in a direction perpendicular to the line segment between any two points in the vehicle path. In another embodiment, processing unit 110 can use a polynomial and an estimated lane width to offset each point in the vehicle path by half the estimated lane width plus a predetermined offset (e.g., intelligent lane offset).

[0181] In step 572, processing unit 110 may update the vehicle path constructed in step 570. Processing unit 110 may use a higher resolution to reconstruct the vehicle path constructed in step 570, such that the distance d between two points in the set representing the vehicle path is... k less than the above distance d i For example, the distance d k It can fall within the range of 0.1 to 0.3 meters. The processing unit 110 can reconstruct the vehicle path using the parabolic spline algorithm, which can generate a cumulative distance vector S corresponding to the total length of the vehicle path (i.e., based on the set of points representing the vehicle path).

[0182] In step 574, processing unit 110 can determine the look-ahead point (expressed in coordinates as (x, y, x) based on the updated vehicle path constructed in step 572. i ,z i Processing unit 110 can extract a forward-looking point from the accumulated distance vector S, and this forward-looking point can be associated with a forward-looking distance and a forward-looking time. The forward-looking distance can have a lower limit ranging from 10 meters to 20 meters and can be calculated as the product of the vehicle 200's speed and the forward-looking time. For example, as the speed of the vehicle 200 decreases, the forward-looking distance can also decrease (e.g., until it reaches the lower limit). The forward-looking time can range from 0.5 to 1.5 seconds and can be inversely proportional to the gain of one or more control loops, such as a heading error tracking control loop, that cause navigation responses in the vehicle 200. For example, the gain of this heading error tracking control loop can depend on the bandwidth of the yaw rate loop, the steering actuator loop, the vehicle's lateral dynamics, etc. Therefore, the higher the gain of the heading error tracking control loop, the shorter the forward-looking time.

[0183] In step 576, processing unit 110 can determine the heading error and yaw rate commands based on the foresight point determined in step 574. Processing unit 110 can do this by calculating the arctangent of the foresight point, for example, arctan(x). i / z i The yaw rate command is determined by the product of the heading error and the high-level control gain. If the forward look-ahead distance is not at the lower limit, the high-level control gain can be equal to: (2 / forward look-ahead time). Otherwise, the high-level control gain can be equal to: (2 × vehicle speed 200 / forward look-ahead distance).

[0184] Figure 5FThis is a flowchart illustrating an example process 500F for determining whether a vehicle ahead is changing lanes, according to a disclosed embodiment. In step 580, processing unit 110 may determine navigation information associated with the vehicle ahead (e.g., a vehicle traveling in front of vehicle 200). For example, processing unit 110 may use the above combination... Figure 5A and Figure 5B The described technology determines the position, speed (e.g., direction and velocity), and / or acceleration of a vehicle ahead. Processing unit 110 can also utilize a combination of the above. Figure 5E The described technique determines one or more road polynomials, forward viewpoints (associated with vehicle 200), and / or a snail trail (e.g., a set of points describing the path taken by the vehicle ahead).

[0185] 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 variation in this distance along the trajectory exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a sharp turn), processing unit 110 may determine that the vehicle ahead is likely changing lanes. In the case where multiple vehicles are detected traveling in front of vehicle 200, processing unit 110 may compare the tracking trajectory associated with each vehicle. Based on this comparison, processing unit 110 may determine that a vehicle whose tracking trajectory does not match the tracking trajectories of other vehicles is likely changing lanes. Processing unit 110 may additionally compare the curvature of the tracking trajectory (associated with the vehicle ahead) with the expected curvature of the road segment in which the vehicle ahead is traveling. The desired curvature can be extracted from map data (e.g., data from map database 160), from road polynomials, from tracking trajectories of other vehicles, from existing knowledge about the road, etc. If the difference between the curvature of the tracking trajectory and the desired curvature of the road segment exceeds a predetermined threshold, the processing unit 110 can determine that the vehicle ahead is likely changing lanes.

[0186] In another embodiment, processing unit 110 may compare the instantaneous position of the vehicle ahead with a forward viewpoint (as associated with vehicle 200) over a specific time period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the vehicle ahead and the forward viewpoint changes during this specific time period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a sharp turn), then processing unit 110 may determine that the vehicle ahead is likely changing lanes. In another embodiment, processing unit 110 may analyze the geometry of the tracking trajectory by comparing the lateral distance traveled along the tracking trajectory with the desired curvature of the tracking path. The desired radius of curvature can be determined according to the formula: (δ... z 2 +δ x 2 ) / 2 / (δ x ), where δ x Indicates the lateral distance traveled and δ z The longitudinal distance traveled is represented. If the difference between the lateral distance traveled and the desired curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 can determine that the vehicle ahead is likely changing lanes. In another embodiment, the processing unit 110 can analyze the position of the vehicle ahead. If the position of the vehicle ahead obscures the road polynomial (e.g., the vehicle ahead is overlaid on the road polynomial), the processing unit 110 can determine that the vehicle ahead is likely changing lanes. If the position of the vehicle ahead is such that another vehicle is detected in front of the vehicle ahead and the tracking trajectories of the two vehicles are not parallel, the processing unit 110 can determine that the (closer) vehicle ahead is likely changing lanes.

[0187] In step 584, processing unit 110 may determine whether the vehicle 200 ahead is changing lanes based on the analysis performed in step 582. For example, processing unit 110 may make this determination based on a weighted average of the various analyses performed in step 582. In this approach, for example, a decision by processing unit 110 based on a particular type of analysis that the vehicle ahead is likely to change lanes may be assigned a value "1" (and "0" to indicate a determination that the vehicle ahead is unlikely to change lanes). Different analyses performed in step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analysis and weights.

[0188] Figure 6This is a flowchart illustrating an example process 600 for inducing one or more navigation responses based on stereoscopic image analysis according to a disclosed embodiment. In step 610, processing unit 110 may receive first and second plurality of images via data interface 128. For example, a camera included in image acquisition unit 120 (such as image capture devices 122 and 124 having fields of view 202 and 204) may capture first and second plurality of images of an area in front of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive the first and second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0189] In step 620, the processing unit 110 can 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 in front of the vehicle and detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. Stereo image analysis can be performed in a manner similar to the above combination. Figures 5A-5D The steps described are performed in a manner consistent with the description. For example, processing unit 110 may execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) in the first and second plurality of images, filter out subsets of candidate objects based on various criteria, and perform multi-frame analysis, construct measurements, and determine confidence levels for the remaining candidate objects. In performing the above steps, processing unit 110 may consider information from both the first and second plurality of images, rather than information from a single set of images. For example, processing unit 110 may analyze differences in pixel-level data (or other subsets of data from the two streams of captured images) of candidate objects appearing in both the first and second plurality of images. As another example, processing unit 110 may estimate the position and / or velocity of a candidate object (e.g., relative to vehicle 200) by observing whether a candidate object appears in one of the plurality of images but not in another, or by other differences that may exist relative to objects appearing in the two image streams. For example, the position, velocity, and / or acceleration relative to vehicle 200 may be determined based on features such as trajectory, position, and movement characteristics associated with an object appearing in one or both of the image streams.

[0190] In step 630, processing unit 110 may execute navigation response module 408 to perform the analysis performed in step 620 and as described above. Figure 4The described technology induces one or more navigation responses in vehicle 200. Navigation responses may include, for example, maneuvering, lane changing, acceleration changes, speed changes, braking, etc. In some embodiments, processing unit 110 may use data obtained from the execution of speed and acceleration module 406 to induce the one or more navigation responses. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0191] Figure 7 This is a flowchart illustrating an example process 700 for evoking one or more navigation responses based on the analysis of three sets of images, according to a disclosed embodiment. In step 710, processing unit 110 may receive first, second, and third plurality of images via data interface 128. For example, cameras included in image acquisition unit 120 (such as image capture devices 122, 124, and 126 having fields of view 202, 204, and 206) may capture first, second, and third plurality of images of areas in front of and / or to the sides of vehicle 200 and transmit them to processing unit 110 via digital connections (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive first, second, and third plurality of images via three or more data interfaces. For example, each of image capture devices 122, 124, and 126 may have an associated data interface for transmitting data to processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0192] In step 720, the processing unit 110 can analyze the first, second, and third images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road hazards. This analysis can be performed in a manner similar to the combination described above. Figures 5A-5D and Figure 6 The steps described are performed in a manner that allows for execution. For example, processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., via execution by monocular image analysis module 402 and based on the above combination). Figures 5A-5D The steps described above). Alternatively, processing unit 110 may perform stereoscopic image analysis on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images (e.g., via execution by stereoscopic image analysis module 404 and based on the above combination). Figure 6(The steps described). Processed information corresponding to the analysis of the first, second, and / or third plurality of images can be combined. In some embodiments, processing unit 110 can perform a combination of monocular and stereoscopic image analysis. For example, processing unit 110 can perform monocular image analysis on the first plurality of images (e.g., via execution of monocular image analysis module 402) and perform stereoscopic image analysis on the second and third plurality of images (e.g., via execution of stereoscopic image analysis module 404). The configuration of image capturing devices 122, 124, and 126—including their respective positions and fields of view 202, 204, and 206—can affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a specific configuration of image capturing devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0193] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed in steps 710 and 720. Such tests can provide an indicator 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., situations where system 100 incorrectly determines the presence of vehicles or pedestrians) and “missed hits”.

[0194] In step 730, processing unit 110 may induce one or more navigation responses in 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. Processing unit 110 may also make the selection based on image quality and resolution, the effective field of view reflected in the image, the number of captured frames, the degree to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which objects appear, the proportion of objects appearing in each such frame), etc.

[0195] In some embodiments, processing unit 110 can select two pieces of information obtained from a first, second, and third plurality of images by determining the degree of consistency between information obtained from one image source and information obtained from other image sources. For example, processing unit 110 can combine processed information obtained from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination of both) and determine consistent visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.) between the images captured from each of image capture devices 122, 124, and 126. Processing unit 110 can also exclude inconsistent information between the captured images (e.g., vehicles changing lanes, lane models indicating that a vehicle is too close to vehicle 200, etc.). Therefore, processing unit 110 can select two pieces of information obtained from the first, second, and third plurality of images based on the determination of consistent and inconsistent information.

[0196] Navigation responses may include, for example, maneuvers, lane changes, braking, and changes in acceleration. Processing unit 110 may base its responses on the analysis performed in step 720 and the above-described combination. Figure 4 The described techniques induce one or more navigation responses. Processing unit 110 may also induce one or more navigation responses using data obtained from the execution of velocity and acceleration module 406. In some embodiments, processing unit 110 may induce one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration between the vehicle 200 and objects detected within any of the first, second, and third plurality of images. The plurality of navigation responses may occur simultaneously, sequentially, or in any combination thereof.

[0197] Analysis of captured images allows for the generation and use of sparse map models for autonomous vehicle navigation. Furthermore, analysis of captured images allows for the localization of autonomous vehicles using identified lane markings. The following will refer to... Figure 8 Figures 28 discuss embodiments of detecting specific features based on one or more specific analyses of captured images, and embodiments of navigating autonomous vehicles using sparse map models.

[0198] Sparse road model for autonomous vehicle navigation

[0199] In some embodiments, the disclosed systems and methods can use sparse maps for autonomous vehicle navigation. Specifically, sparse maps can be used for autonomous vehicle navigation along road segments. For example, sparse maps can provide sufficient information for navigating autonomous vehicles without requiring the storage and / or updating of large amounts of data. As discussed further in detail below, autonomous vehicles can use sparse maps to navigate one or more roads based on one or more stored trajectories.

[0200] Sparse maps for autonomous vehicle navigation

[0201] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, sparse maps can provide sufficient information for navigation without requiring excessive data storage or data transfer rates. As discussed in further detail below, a vehicle (which may be an autonomous vehicle) can use a sparse map to navigate one or more roads. For example, in some embodiments, a sparse map may include road-related data and potential landmarks along the road, which may be sufficient for vehicle navigation and exhibit a small data footprint. For example, sparse data maps, detailed below, may require significantly less storage space and data transfer bandwidth compared to digital maps that include detailed map information, such as image data collected along the road.

[0202] For example, sparse data maps can store a three-dimensional polynomial representation of preferred vehicle routes along a road, rather than a detailed representation of road segments. These routes may require very little data storage space. Furthermore, in the described sparse data map, landmarks can be identified and included in the sparse map road model to aid navigation. These landmarks can be positioned at any spacing suitable for achieving vehicle navigation, but in some cases, such landmarks do not need to be identified and included in the model with high density and short spacing. Instead, in some cases, navigation can be based on landmarks spaced at intervals of at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers. As will be discussed in more detail in other sections, sparse maps can be generated based on data collected or measured by vehicles equipped with various sensors and devices (such as image capture devices, GPS sensors, motion sensors, etc.) as vehicles travel along a roadway. In some cases, sparse maps can be generated based on data collected during multiple drives of one or more vehicles along a particular roadway. Generating sparse maps using multiple drives of one or more vehicles can be referred to as “crowdsourcing” of sparse maps.

[0203] Consistent with the disclosed embodiments, autonomous vehicle systems can use sparse maps for navigation. For example, the disclosed systems and methods can distribute sparse maps for generating road navigation models for autonomous vehicles, and the sparse maps and / or the generated road navigation models can be used to navigate autonomous vehicles along road segments. Sparse maps conforming to this disclosure may include one or more three-dimensional contours that can represent predetermined trajectories that autonomous vehicles can traverse as they move along associated road segments.

[0204] The sparse map conforming to this disclosure may also include data representing one or more road features. Such road features may include identified landmarks, road signature profiles, and any other road-related features useful in a navigation vehicle. The sparse map conforming to this disclosure can enable autonomous vehicle navigation based on the relatively small amount of data included in the sparse map. For example, embodiments of the disclosed sparse map may require relatively little storage space (and relatively little bandwidth when portions of the sparse map are transmitted to the vehicle) rather than including detailed representations of roads (such as road edges, road curvature, images associated with road segments, or data detailing other physical features associated with road segments), but it can still be adequately prepared for autonomous vehicle navigation. In some embodiments, the small data coverage area of ​​the disclosed sparse map, as further detailed below, can be achieved by storing representations of road-related elements that require a small amount of data but still enable autonomous navigation.

[0205] For example, the disclosed sparse map can store a polynomial representation of one or more trajectories that a vehicle can follow along a road, rather than storing detailed representations of all aspects of the road. Therefore, using the disclosed sparse map, instead of storing (or having to transfer) details about the physical properties of the road to enable navigation, a vehicle can navigate along a specific road segment by aligning its travel path with a trajectory (e.g., a polynomial spline) along that segment, without necessarily interpreting the physical aspects of the road in some cases. In this way, vehicles can be navigated primarily based on stored trajectories (e.g., polynomial splines), which may require significantly less storage space than methods involving storing images of the roadway, road parameters, road layouts, etc.

[0206] In addition to the stored polynomial representation of the trajectory along the road segment, the disclosed sparse map may also include small data objects that can represent road features. In some embodiments, the small data objects may include digital signatures derived from digital images (or digital signals) acquired by sensors (e.g., cameras or other sensors, such as suspension sensors) on a vehicle traveling along the road segment. The digital signatures may have a reduced size relative to the signals acquired by the sensors. In some embodiments, digital signatures may be created to be compatible with classifier functions configured to detect and identify road features from signals acquired by sensors, for example, during subsequent journeys. In some embodiments, digital signatures may be created such that they have the smallest possible coverage area while maintaining the ability to correlate or match road features with stored signatures based on images of road features captured by cameras on vehicles traveling along the same road segment at subsequent times (or digital signals generated by sensors, if the stored signature is not based on images and / or includes other data).

[0207] In some embodiments, the size of the data object may be further associated with the uniqueness of the road feature. For example, for road features that can be detected by a camera on a vehicle, and wherein the camera system on the vehicle is coupled to a classifier that is able to distinguish image data corresponding to road features associated with a particular type of road feature, such as road signs, and where such road signs are locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), it may be sufficient to store data indicating the type and location of the road feature.

[0208] As will be discussed in further detail below, road features (e.g., landmarks along a road segment) can be stored as small data objects that can represent road features in relatively few bytes while providing sufficient information for identification and use of such features for navigation. In one example, road signs can be identified as identifiable landmarks upon which vehicle navigation can be based. The representation of road signs can be stored in a sparse map to include, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign) and a few bytes of data indicating the location of the landmark (e.g., coordinates). Navigation based on such a data-light representation of landmarks (e.g., using a representation sufficient for landmark-based localization, identification, and navigation) can provide the desired level of navigation capability associated with a sparse map without significantly increasing the data overhead associated with the sparse map. This concise representation of landmarks (and other road features) can utilize sensors and processors included on such a vehicle, which are configured to detect, identify, and / or classify certain road features.

[0209] For example, when a sign or even a sign of a particular type is locally unique in a given area (e.g., when there are no other signs or other signs of the same type), a sparse map can use data indicating the type of landmark (a sign or a sign of a particular type), and during navigation (e.g., autonomous navigation), when a camera on an autonomous vehicle captures an image of an area that includes a sign (or a sign of a particular type), the processor can process the image, detect the sign (if it is indeed present in the image), classify the image as a sign (or as a sign of a particular type), and associate the location of the image with the location of the sign stored in the sparse map.

[0210] Generating sparse maps

[0211] In some embodiments, a sparse map may include at least one line representation of road surface features extending along a road segment and multiple landmarks associated with the road segment. In some aspects, the sparse map may be generated via “crowdsourcing,” for example, through image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0212] Figure 8 A sparse map 800 is shown, which one or more vehicles (e.g., vehicle 200, which may be an autonomous vehicle) can access to provide autonomous vehicle navigation. The sparse map 800 may be stored in a memory such as memory 140 or 150. Such a memory device may include any type of non-transitory storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 may include a hard disk drive, optical disk, flash memory, magnetic-based memory device, optical-based memory device, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150, or other types of storage devices.

[0213] In some embodiments, the sparse map 800 may be stored on a storage device provided on the vehicle 200 or on a non-transitory computer-readable medium (e.g., a storage device included in a navigation system on the vehicle 200). A processor (e.g., processing unit 110) provided on the vehicle 200 may access the sparse map 800 stored on the storage device or computer-readable medium provided on the vehicle 200 to generate navigation instructions for guiding the autonomous vehicle 200 as the vehicle traverses road segments.

[0214] However, instead of storing the sparse map 800 locally relative to the vehicle, in some embodiments, the sparse map 800 may be stored on a storage device or computer-readable medium provided on a remote server that communicates with the vehicle 200 or devices associated with the vehicle 200. A processor (e.g., processing unit 110) provided on the vehicle 200 may receive data included in the sparse map 800 from the remote server and may execute data for guiding autonomous driving of the vehicle 200. In such embodiments, the remote server may store all or only a portion of the sparse map 800. Therefore, storage devices or computer-readable media on the vehicle 200 and / or on one or more additional vehicles may store the remaining portions of the sparse map(s).

[0215] Furthermore, in such embodiments, the sparse map 800 can be accessed by multiple vehicles (e.g., tens, hundreds, thousands, or millions of vehicles) traversing various road segments. It should also be noted that the sparse map 800 may include multiple sub-maps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, millions, or more sub-maps that can be used by the navigating vehicle. Such sub-maps may be referred to as local maps, and vehicles traveling along the roadway can access any number of local maps related to the vehicle's current location. Local map segments of the sparse map 800 may be stored along with Global Navigation Satellite System (GNSS) keys that serve as an index to the database of the sparse map 800. Therefore, while the calculation of the steering angle used to navigate the primary vehicle in this system can be performed without relying on the primary vehicle's GNSS position, road features, or landmarks, this GNSS information can be used to retrieve the relevant local maps.

[0216] In the following text (e.g., regarding) Figure 19 The data collection and generation of the sparse map 800 are described in more detail below. However, typically, the sparse map 800 can be generated based on data collected from one or more vehicles as they travel along a roadway. For example, using sensors on one or more vehicles (e.g., cameras, speedometers, GPS, accelerometers, etc.), the trajectories of one or more vehicles traveling along a roadway can be recorded, and a polynomial representation of the preferred trajectory for subsequent journeys along the roadway can be determined based on the collected trajectories of one or more vehicles. Similarly, data collected by one or more vehicles can help identify potential landmarks along a particular roadway. Data collected from passing vehicles can also be used to identify road profile information, such as road width profiles, road smoothness profiles, traffic line spacing profiles, road conditions, etc. Using the collected information, the sparse map 800 can be generated and distributed (e.g., for local storage or via dynamic data transmission) for navigating one or more autonomous vehicles. However, in some embodiments, map generation may not end at the initial map generation stage. As will be discussed in more detail below, the sparse map 800 can be updated continuously or periodically based on data collected from these vehicles as they continue to traverse the roadways included in the sparse map 800.

[0217] The data recorded in the sparse map 800 may include location information based on Global Positioning System (GPS) data. For example, location information may be included in the sparse map 800 for various map elements, including, for example, landmark locations, road profile locations, etc. The locations of map elements included in the sparse map 800 can be obtained using GPS data collected from vehicles passing through a roadway. For example, a vehicle passing an identified landmark can determine the location of the identified landmark using GPS location information associated with the vehicle and a determination of the location of the identified landmark relative to the vehicle (e.g., based on image analysis of data collected from one or more cameras on the vehicle). This determination of location for the identified landmark (or any other feature included in the sparse map 800) can be repeated as additional vehicles pass through the location of the identified landmark. Some or all of the additional location determinations can be used to refine the location information stored in the sparse map 800 relative to the identified landmarks. For example, in some embodiments, multiple location measurements relative to a specific feature stored in the sparse map 800 can be averaged together. However, any other mathematical operations may also be used to refine the location of the stored map elements based on the locations of multiple determined map elements.

[0218] The sparse maps of the disclosed embodiments enable autonomous vehicle navigation using relatively little stored data. In some embodiments, the sparse map 800 may have a data density of less than 2 MB (megabytes) per kilometer of road, less than 1 MB per kilometer of road, less than 500 kB (kilobytes) per kilometer of road, or less than 100 kB per kilometer of road (e.g., including data representing target trajectories, landmarks, and any other stored road features). In some embodiments, the data density of the sparse map 800 may be less than 10 kB per kilometer of road, or even less than 2 kB per kilometer of road (e.g., 1.6 kB per kilometer), or no more than 10 kB per kilometer of road, or no more than 20 kB per kilometer of road. In some embodiments, a sparse map with a total of 4 GB or less of data can be used to autonomously navigate most (if not all) of the roads in the United States. These data density values ​​may represent averages across the entire sparse map 800, averages on local maps within the sparse map 800, and / or averages on specific road segments within the sparse map 800.

[0219] As noted, the sparse map 800 may include representations of multiple target trajectories 810 for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as 3D splines. The target trajectories stored in the sparse map 800 may be determined based on two or more reconstructed trajectories previously traversed by vehicles along a particular road segment, for example, as per [reference to...]. Figure 29The road segment under discussion can be associated with a single target trajectory or multiple target trajectories. For example, on a two-lane road, a first target trajectory can be stored to represent the expected path of travel along the road in a first direction, and a second target trajectory can be stored to represent the expected travel path of travel along the road in another direction (e.g., opposite to the first direction). Additional target trajectories can be stored relative to a particular road segment. For example, on a multi-lane road, one or more target trajectories can be stored representing the expected travel paths of vehicles in one or more lanes associated with the multi-lane road. In some embodiments, each lane of the multi-lane road can be associated with its own target trajectory. In other embodiments, the number of target trajectories stored can be less than the number of lanes present on the multi-lane road. In this case, a vehicle navigating a multi-lane road can use any of the stored target trajectories to guide its navigation by taking into account lane offsets from the lanes of the stored target trajectories (e.g., if a vehicle is traveling in the leftmost lane of a three-lane highway and target trajectories are stored only for the middle lane of the highway, the vehicle can navigate using the target trajectory of the middle lane by taking into account the lane offset between the middle lane and the leftmost lane when navigation instructions are generated).

[0220] In some embodiments, the target trajectory may represent the ideal path that the vehicle should take as it travels. The target trajectory may be located, for example, at the approximate center of the driving lane. In other cases, the target trajectory may be located at other locations relative to the road segment. For example, the target trajectory may approximately coincide with the center of the road, the edge of the road, or the edge of the lane. In this case, navigation based on the target trajectory may include a determined offset to be maintained relative to the position of the target trajectory. Furthermore, in some embodiments, the determined offset to be maintained relative to the position of the target trajectory may vary based on the type of vehicle (e.g., a passenger car including two axles may have a different offset than a truck with more than two axles that includes at least a portion of the target trajectory).

[0221] The sparse map 800 may also include data associated with multiple predetermined landmarks 820 linked to specific road segments, local maps, etc. These landmarks can be used in the navigation of autonomous vehicles, as discussed in more detail below. For example, in some embodiments, the landmarks can be used to determine the vehicle's current position relative to a stored target trajectory. Using this positional information, the autonomous vehicle can adjust its direction of travel to match the direction of the target trajectory at the determined location.

[0222] Multiple landmarks 820 can be identified and stored in the sparse map 800 at any suitable interval. In some embodiments, landmarks can be stored at a relatively high density (e.g., every few meters or more). However, in some embodiments, significantly larger landmark interval values ​​can be used. For example, in the sparse map 800, identified (or recognized) landmarks can be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, identified landmarks can be located at distances even greater than 2 kilometers apart.

[0223] Between landmarks, and therefore between the determination of the vehicle's position relative to a target trajectory, the vehicle can navigate based on dead reckoning, whereby the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Because errors can accumulate during navigation via dead reckoning, the position determination relative to the target trajectory can become increasingly inaccurate over time. The vehicle can use landmarks occurring in the sparse map 800 (and its known location) to eliminate errors caused by dead reckoning in the position determination. In this way, the identified landmarks included in the sparse map 800 can be used as navigation anchors, based on which the vehicle's precise position relative to the target trajectory can be determined. Because a certain amount of error is acceptable in position determination, the identified landmarks are not always valid for autonomous vehicles. Conversely, suitable navigation is possible even based on landmark spacing of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more as described above. In some embodiments, a density of one identified landmark per 1 km of road is sufficient to maintain longitudinal position determination accuracy within 1 m. Therefore, not every potential landmark that appears along the road segment needs to be stored in the sparse map 800.

[0224] Furthermore, in some embodiments, lane markings can be used for vehicle positioning during landmark intervals. By using lane markings during landmark intervals, the accumulation during navigation via dead reckoning can be minimized. In particular, reference is made below. Figure 35 Let's discuss this positioning.

[0225] In addition to target trajectories and identified landmarks, the sparse map 800 can include information related to various other road features. For example, Figure 9A This illustrates a representation of a curve along a specific road segment that can be stored in a sparse map 800. In some embodiments, a single lane of the road can be modeled using a three-dimensional polynomial description of the left and right sides of the road. This polynomial representing the left and right sides of a single lane is... Figure 9A As shown in the diagram. Regardless of how many lanes a road may have, it can be similar to... Figure 9A The method shown uses a polynomial to represent the road. For example, it can be represented by a polynomial similar to... Figure 9A The polynomial shown represents the left and right sides of a multi-lane road, and can also use polynomials such as Figure 9A The polynomial shown represents the markings for the middle lanes on multi-lane roads (e.g., dashed markings indicating lane boundaries, solid yellow lines indicating boundaries between lanes traveling in different directions).

[0226] like Figure 9A As shown, lane 900 can be represented using a polynomial (e.g., first-order, second-order, third-order, or any suitable order polynomial). For illustration, lane 900 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. Figure 9A As shown, lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial may be used to represent the positions of the sides of the road or lane boundary. For example, each of the left side 910 and right side 920 may be represented by multiple polynomials of any suitable length. In some cases, the polynomials may have a length of about 100 m, but other lengths greater or less than 100 m may also be used. Additionally, polynomials may overlap each other to facilitate a seamless transition in navigation based on subsequently encountered polynomials as the main vehicle travels along the carriageway. For example, each of the left side 910 and right side 920 may be represented by multiple third-order polynomials divided into segments of about 100 meters in length (an example of a first predetermined range) and overlapping each other by about 50 meters. The polynomials representing the left side 910 and right side 920 may or may not have the same order. For example, in some embodiments, some polynomials may be second-order polynomials, some may be third-order polynomials, and some may be fourth-order polynomials.

[0227] exist Figure 9A In the example shown, lane 900's left side 910 is represented by two sets of third-order polynomials. The first set includes polynomial segments 911, 912, and 913. The second set includes polynomial segments 914, 915, and 916. These two sets are substantially parallel to each other, but follow their respective roadside positions. Polynomial segments 911, 912, 913, 914, 915, and 916 are approximately 100 meters long and overlap with adjacent segments in the series by approximately 50 meters. However, as mentioned earlier, polynomials of different lengths and overlaps can also be used. For example, polynomials can have lengths of 500 meters, 1 kilometer, or longer, while overlaps can vary from 0 to 50 meters, 50 meters to 100 meters, or greater than 100 meters. Furthermore, although... Figure 9A These are shown as polynomials extending in 2D space (e.g., on the surface of paper), but it should be understood that these polynomials can represent curves extending in three dimensions (e.g., including height components) to represent elevation variations in a road segment in addition to XY curvature. Figure 9AIn the example shown, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922 and 923 and a second group having polynomial segments 924, 925 and 926.

[0228] Return to the target trajectory on the sparse map 800. Figure 9B The diagram illustrates a three-dimensional polynomial representing the target trajectory of a vehicle traveling along a specific road segment. The target trajectory represents not only the XY path the vehicle should take along the specific road segment, but also the elevation changes the vehicle will experience as it travels along the segment. Therefore, each target trajectory in the sparse map 800 can be represented by one or more three-dimensional polynomials, such as... Figure 9B The three-dimensional polynomial 950 is shown. The sparse map 800 may include multiple trajectories (e.g., millions or billions or more, to represent the trajectories of vehicles along various segments of roadways scattered throughout the world). In some embodiments, each target trajectory may correspond to a spline connecting segments of the three-dimensional polynomial.

[0229] Regarding the data coverage area of ​​the polynomial curves stored in the sparse map 800, in some embodiments, each cubic polynomial can be represented by four parameters, each requiring four bytes of data. A suitable representation can be obtained using cubic polynomials, requiring approximately 192 bytes of data per 100 meters. For a primary vehicle traveling at approximately 100 km / hr, this translates to a data usage / transmission requirement of approximately 200 kB per hour.

[0230] Sparse maps 800 can describe lane networks using a combination of geometric descriptors and metadata. The geometry can be described using polynomials or splines as described above. Metadata can describe the number of lanes, special features (such as car parking lanes), and any other possible sparse labels. The total coverage area of ​​these metrics is negligible.

[0231] Therefore, a sparse map according to embodiments of this disclosure may include at least one line representation of road surface features extending along a road segment, each line representation representing a path along a road segment substantially corresponding to the road surface feature. In some embodiments, as described above, the at least one line representation of the road surface feature may include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature may include at least one of a road edge or lane markings. And, as discussed below with respect to “crowdsourcing,” road surface features can be identified through image analysis of multiple images acquired as one or more vehicles traverse a road segment.

[0232] As previously mentioned, the sparse map 800 may include multiple predetermined landmarks associated with road segments. Instead of storing actual images of the landmarks and relying, for example, on image recognition analysis based on captured and stored images, less data than would be required to represent and identify each landmark in the sparse map 800. The data representing the landmarks may still include sufficient information to describe or identify landmarks along the road. Storing data describing the characteristics of the landmarks instead of storing actual images of the landmarks can reduce the size of the sparse map 800.

[0233] Figure 10 Examples of landmark types that can be represented in sparse map 800 are shown. Landmarks can include any visible and identifiable object along a road segment. Landmarks can be selected such that they are fixed and their position and / or content do not change frequently. Landmarks included in sparse map 800 can be used to determine the position of vehicle 200 relative to a target trajectory as a vehicle travels through a particular road segment. Examples of landmarks can include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lampposts, rearview mirrors, etc.), and any other suitable categories. In some embodiments, lane markings on the road can also be included as landmarks in sparse map 800.

[0234] Figure 10 Examples of landmarks shown include traffic signs, directional signs, roadside fixtures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), yield signs (e.g., yield sign 1005), route number signs (e.g., route number sign 1010), traffic light signs (e.g., traffic light sign 1015), and stop signs (e.g., stop sign 1020). Directional signs may include signs containing one or more arrows indicating one or more directions to different places. For example, directional signs may include a highway sign 1025 with arrows to guide vehicles to different roads or locations, an exit sign 1030 with arrows indicating vehicles to leave the road, etc. Therefore, at least one of the multiple landmarks may include a road sign.

[0235] General signs may not be related to traffic. For example, general signs may include billboards used for advertising, or welcome signs at the borders between two countries, states, counties, cities, or towns. Figure 10 The general sign 1040 (“Joe's Restaurant”) is shown. While the general sign 1040 can have a rectangular shape, such as... Figure 10 As shown, however, the general mark 1040 can also have other shapes, such as square, circle, triangle, etc.

[0236] Landmarks may also include roadside fixtures. Roadside fixtures may not be objects of a sign and may not be related to traffic or direction. For example, roadside fixtures may include lampposts (e.g., lamppost 1035), utility poles, traffic light poles, etc.

[0237] Landmarks can also include beacons specifically designed for autonomous vehicle navigation systems. For example, such beacons can include freestanding structures placed at predetermined intervals to aid in the navigation of the host vehicle. These beacons can also include visual / graphical information (e.g., icons, badges, barcodes, etc.) added to existing road signs, information that can be identified or recognized by vehicles traveling along the road segment. Such beacons can also include electronic components. In such embodiments, electronic beacons (e.g., RFID tags, etc.) can be used to transmit non-visual information to the host vehicle. This information can include, for example, landmark identifiers and / or landmark location information that the host vehicle can use to determine its position along a target trajectory.

[0238] In some embodiments, landmarks included in the sparse map 800 may be represented by data objects of a predetermined size. The data representing the landmarks may include any suitable parameters for identifying a particular landmark. For example, in some embodiments, landmarks stored in the sparse map 800 may include parameters such as: the physical size of the landmark (e.g., to support distance estimation to the landmark based on a known size / scale), distance to previous landmarks, lateral offset, height, type code (e.g., landmark type—what type of directional sign, traffic sign, etc.), GPS coordinates (e.g., to support global positioning), and any other suitable parameters. Each parameter may be associated with a data size. For example, 8 bytes of data may be used to store the landmark size. 12 bytes of data may be used to specify the distance to previous landmarks, lateral offset, and height. The type code associated with a landmark, such as a directional sign or traffic sign, may require approximately 2 bytes of data. For general landmarks, 50 bytes of data may be used to store an image signature that can identify a general landmark. The landmark GPS location may be associated with 16 bytes of data. These data sizes for each parameter are merely examples, and other data sizes may be used.

[0239] Representing landmarks in a sparse map 800 in this way provides an efficient scheme for representing landmarks in a database. In some embodiments, signs can be referred to as semantic signs and non-semantic signs. Semantic signs can include any category of signs with standardized meanings (e.g., speed limit signs, warning signs, directional signs, etc.). Non-semantic signs can include any sign that is not associated with standardized meanings (e.g., general advertising signs, signs identifying commercial establishments, etc.). For example, each semantic sign can be represented by 38 bytes of data (e.g., 8 bytes for size; 12 bytes for distance to the previous landmark, lateral offset, and height; 2 bytes for type code; 16 bytes for GPS coordinates). The sparse map 800 can use a labeling system to represent landmark types. In some cases, each traffic sign or directional sign can be associated with its own label, which can be stored in the database as part of the landmark identifier. For example, the database can include approximately 1,000 different labels to represent various traffic signs and approximately 10,000 different labels to represent directional signs. Of course, any suitable number of labels can be used, and additional labels can be created as needed. In some embodiments, a generic flag can be represented using fewer than about 100 bytes (e.g., about 86 bytes, including 8 bytes for size; 12 bytes for distance to previous landmarks, lateral offset, and height; 50 bytes for image signature; and 16 bytes for GPS coordinates).

[0240] Therefore, for semantic road signs that do not require image signatures, even at a relatively high landmark density of approximately one per 50 meters, the data density impact on the sparse map 800 can be approximated to about 760 bytes per kilometer (e.g., 20 landmarks per kilometer × 38 bytes per landmark = 760 bytes). Even for generic signs that include image signature components, the data density impact is approximately 1.72 kB / km (e.g., 20 landmarks per kilometer × 86 bytes per landmark = 1,720 bytes). For semantic road signs, this equates to approximately 76 kB of data usage per hour for a vehicle traveling at 100 km / h. For generic signs, this equates to approximately 170 kB per hour for a vehicle traveling at 100 km / h.

[0241] In some embodiments, a general rectangular object (such as a rectangular marker) can be represented in the sparse map 800 by no more than 100 bytes of data. The representation of a general rectangular object (e.g., a general marker 1040) in the sparse map 800 may include a compressed image signature (e.g., compressed image signature 1045) associated with the general rectangular object. This compressed image signature can be used, for example, to help identify generic markers, such as landmarks. Such a compressed image signature (e.g., image information derived from the actual image data representing the object) can avoid the need to store the actual image of the object or to perform comparative image analysis on the actual image to identify landmarks.

[0242] refer to Figure 10 The sparse map 800 may include or store a compressed image signature 1045 associated with the general sign 1040, rather than an actual image of the general sign 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of the general sign 1040, a processor (e.g., image processor 190 or any other processor that can process images on-board or at a distance relative to the host vehicle) may perform image analysis to extract / create a compressed image signature 1045 that includes a unique signature or pattern associated with the general sign 1040. In one embodiment, the compressed image signature 1045 may include shape, color pattern, brightness pattern, or any other features that can be extracted from the image of the general sign 1040 to describe the general sign 1040.

[0243] For example, in Figure 10 In the compressed image signature 1045, the circles, triangles, and stars can represent areas of different colors. Patterns represented by circles, triangles, and stars can be stored in the sparse map 800, for example, within 50 bytes designated for including the image signature. It is important to note that circles, triangles, and stars are not necessarily intended to indicate that these shapes are stored as part of the image signature. Rather, these shapes are intended to conceptually represent identifiable areas with discernible color differences, text areas, graphic shapes, or other variations that can be associated with general signs. This compressed image signature can be used to identify landmarks in the form of general signs. For example, based on a comparison of the stored compressed image signature with captured image data (e.g., using a camera on an autonomous vehicle), the compressed image signature can be used to perform the same or different analyses.

[0244] Therefore, multiple landmarks can be identified through image analysis of multiple images acquired while one or more vehicles are traversing a road segment. As explained below regarding "crowdsourcing," in some embodiments, image analysis for identifying multiple landmarks may include accepting potential landmarks when the ratio of images in which landmarks actually appear to images in which landmarks do not appear exceeds a threshold. Furthermore, in some embodiments, image analysis for identifying multiple landmarks may include rejecting potential landmarks when the ratio of images in which landmarks do not appear to images in which landmarks appear exceeds a threshold.

[0245] Returning to the main vehicle can be used to navigate a target trajectory for a specific road segment. Figure 11A The diagram illustrates a polynomial representation of the trajectory captured during the process of building or maintaining the sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 can be determined based on two or more reconstructed trajectories previously traversed by vehicles along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be a set of two or more reconstructed trajectories previously traversed by vehicles along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be the average of two or more reconstructed trajectories previously traversed by vehicles along the same road segment. Other mathematical operations can also be used to construct the target trajectory along the road path based on the reconstructed trajectories collected from vehicles traversing the road segment.

[0246] like Figure 11A As shown, road segment 1100 can be traveled by multiple vehicles 200 at different times. Each vehicle 200 can collect data related to the path it travels along the road segment. The path of a particular vehicle can be determined based on camera data, accelerometer information, speed sensor information, and / or GPS information, as well as other potential sources. Such data can be used to reconstruct the trajectory of vehicles traveling along the road segment, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) for a particular road segment can be determined. As vehicles travel along the road segment, such target trajectories can represent (e.g., guided by an autonomous navigation system) the preferred path of the master vehicle.

[0247] exist Figure 11AIn the example shown, a first reconstructed trajectory 1101 can be determined based on data received from a first vehicle traversing road segment 1100 during a first time period (e.g., day 1), a second reconstructed trajectory 1102 can be obtained from a second vehicle traversing road segment 1100 during a second time period (e.g., day 2), and a third reconstructed trajectory 1103 can be obtained from a third vehicle traversing road segment 1100 during a third time period (e.g., day 3). Each trajectory 1101, 1102, and 1103 can be represented by a polynomial, such as a three-dimensional polynomial. It should be noted that in some embodiments, any reconstructed trajectory can be fitted onto a vehicle traversing road segment 1100.

[0248] Alternatively or concurrently, such a reconstructed trajectory can be determined on the server side based on information received from vehicles traversing road segment 1100. For example, in some embodiments, vehicle 200 can transmit data to one or more servers relating to its movement along road segment 1100 (e.g., steering angle, heading, time, position, speed, sensed road geometry, and / or sensed landmarks, etc.). The server can reconstruct the trajectory of vehicle 200 based on the received data. The server can also generate target trajectories for navigation of an autonomous vehicle that will travel along the same road segment 1100 at a later time, based on first, second, and third trajectories 1101, 1102, and 1103. In some embodiments, the target trajectory may be associated with a single previous traversal of the road segment, and each target trajectory included in the sparse map 800 can be determined based on two or more reconstructed trajectories of vehicles traversing the same road segment. Figure 11A In this context, the target trajectory is represented by 1110. In some embodiments, the target trajectory 1110 can be generated based on the average of the first, second, and third trajectories 1101, 1102, and 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 can be an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories. See below for reference. Figure 29 Further discussion is given on aligning travel data to construct trajectories.

[0249] Figure 11B and 11C The concept of a target trajectory associated with road segments existing within geographic region 1111 is further illustrated. For example... Figure 11BAs shown, a first road segment 1120 within geographic area 1111 may include a multi-lane road comprising two lanes 1122 designated for vehicles traveling in a first direction, and two additional lanes 1124 designated for vehicles traveling in a second direction opposite to the first direction. Lanes 1122 and lanes 1124 may be separated by double yellow lines 1123. Geographic area 1111 may also include branch road segments 1130 intersecting with road segment 1120. Road segment 1130 may include a two-lane road, with each lane designated for a different direction of travel. Geographic area 1111 may also include other road features such as stop lines 1132, stop signs 1134, speed limit signs 1136, and hazard signs 1138.

[0250] like Figure 11C As shown, the sparse map 800 may include a local map 1140, which includes a road model for assisting autonomous navigation of vehicles within geographic region 1111. For example, the local map 1140 may include target trajectories of one or more lanes associated with road segments 1120 and / or 1130 within geographic region 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that the autonomous vehicle can access or rely on when traversing lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that the autonomous vehicle can access or rely on when traversing lane 1124. Furthermore, the local map 1140 may include target trajectories 1145 and / or 1146 that the autonomous vehicle can access or rely on when traversing road segment 1130. Target trajectory 1147 represents the preferred path that an autonomous vehicle should follow when transitioning from lane 1120 (and specifically, target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (and specifically, target trajectory 1145 associated with the first side of road segment 1130). Similarly, target trajectory 1148 represents the preferred path that an autonomous vehicle should follow when transitioning from road 1130 (and specifically, target trajectory 1146) to a portion of road segment 1124 (and specifically, as shown, target trajectory 1143 associated with the left lane of lane 1124).

[0251] The sparse map 800 may also include representations of other road-related features associated with geographic region 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in geographic region 1111. Such landmarks may include a first landmark 1150 associated with stop line 1132, a second landmark 1152 associated with stop sign 1134, a third landmark associated with speed limit sign 1154, and a fourth landmark 1156 associated with hazard sign 1138. Such landmarks can be used, for example, to assist autonomous vehicles in determining their current position relative to any indicated target trajectory, allowing the vehicle to adjust its heading to match the direction of the target trajectory at the determined location. See below for further details. Figure 26 Further discussion will focus on using landmarks from sparse maps for navigation.

[0252] In some embodiments, the sparse map 800 may also include a road signature profile. This road signature profile may be associated with any identifiable / measurable change in at least one parameter associated with a road. For example, in some cases, this profile may be associated with changes in road surface information, such as changes in the surface smoothness of a particular road segment, changes in the road width on a particular road segment, changes in the distance between dashed lines drawn along a particular road segment, changes in the road curvature along a particular road segment, etc. Figure 11D An example of a road signature profile 1160 is shown. While profile 1160 can represent any of the parameters described above or other parameters, in one example, profile 1160 can represent a measurement of road surface smoothness, which is obtained, for example, by monitoring one or more sensors that provide outputs indicating the amount of suspension displacement when a vehicle travels on a particular road segment.

[0253] Alternatively or simultaneously, profile 1160 may represent changes in road width, such as those determined based on image data obtained via cameras on a vehicle traveling on a particular road segment. For example, such a profile may be useful in determining the specific position of an autonomous vehicle relative to a specific target trajectory. That is, as it traverses a road segment, the autonomous vehicle can measure a profile associated with one or more parameters related to the road segment. If the measured profile can be correlated / matched with a predetermined profile that plots parameter changes relative to the position along the road segment, the measured and predetermined profiles (e.g., by overlaying corresponding portions of the measured and predetermined profiles) can be used to determine the current position along the road segment, and thus the current position relative to a target trajectory on the road segment.

[0254] In some embodiments, the sparse map 800 may include different trajectories based on different characteristics associated with the autonomous vehicle's user, environmental conditions, and / or other driving-related parameters. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or profiles. The sparse map 800 including such different trajectories can be provided to different autonomous vehicles for different users. For example, some users may prefer to avoid toll roads, while others may prefer to take the shortest or fastest route, regardless of whether there are toll roads on the route. The disclosed system can generate different sparse maps with different trajectories based on such different user preferences or profiles. As another example, some users may prefer to drive in fast-moving lanes, while others may prefer to always stay in the center lane.

[0255] Different trajectories can be generated and included in the sparse map 800 based on various environmental conditions, such as day and night, snow, rain, and fog. Autonomous vehicles driving under different environmental conditions can be equipped with the sparse map 800 generated based on these different environmental conditions. In some embodiments, cameras provided on the autonomous vehicle can detect environmental conditions and can provide such information back to the server that generates and provides the sparse map. For example, the server can generate or update the already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. As the autonomous vehicle travels along the road, updates to the sparse map 800 based on environmental conditions can be performed dynamically.

[0256] Other driving-related parameters can also be used as a basis for generating and providing different sparse maps to different autonomous vehicles. For example, when an autonomous vehicle is traveling at high speed, turning may be more urgent. Trajectories associated with a specific lane (rather than the road) can be included in the sparse map 800, allowing the autonomous vehicle to stay within a specific lane when following the specific trajectory. When an image captured by a camera on the autonomous vehicle indicates that the vehicle has drifted out of its lane (e.g., crossed lane markings), an action can be triggered inside the vehicle to bring the vehicle back to the designated lane according to the specific trajectory.

[0257] Crowdsourced sparse map

[0258] In some embodiments, the disclosed systems and methods can generate sparse data for autonomous vehicle navigation. For example, the disclosed systems and methods can use crowdsourced data to generate sparse data that one or more autonomous vehicles can use to navigate along a road system. As used herein, “crowdsourcing” means receiving data from various vehicles (e.g., autonomous vehicles) traveling on a road segment at different times, and this data is used to generate and / or update a road model. This model can then be transmitted to vehicles or other vehicles traveling later along the road segment to assist autonomous vehicle navigation. The road model can include multiple target trajectories that represent preferred trajectories that autonomous vehicles should follow when traversing the road segment. The target trajectories can be the same as reconstructed actual trajectories collected from vehicles traversing the road segment, which can be transmitted from the vehicles to a server. In some embodiments, the target trajectories can differ from the actual trajectories previously used by one or more vehicles while traversing the road segment. The target trajectories can be generated based on the actual trajectories (e.g., by averaging or any other suitable operation). References below Figure 29 This section discusses examples of alignment used to generate crowdsourced data for target trajectories.

[0259] Vehicle trajectory data uploaded to the server can correspond to the vehicle's actual reconstructed trajectory or a recommended trajectory, which may be based on or related to the vehicle's actual reconstructed trajectory but may differ from it. For example, vehicles can modify their actual reconstructed trajectories and submit (e.g., a recommendation) the modified actual trajectory to the server. The road model can use the recommended, modified trajectory as a target trajectory for autonomous navigation of other vehicles.

[0260] Besides trajectory information, other information that could potentially be used to construct a sparse data map 800 could include information related to potential landmark candidates. For example, through information crowdsourcing, publicly available systems and methods can identify potential landmarks in the environment and refine landmark locations. Landmarks can be used by the navigation systems of autonomous vehicles to determine and / or adjust the vehicle's position along the target trajectory.

[0261] A reconstructed trajectory that a vehicle can generate as it travels along a road can be obtained by any suitable method. In some embodiments, the reconstructed trajectory can be established by stitching together segments of the vehicle's motion using, for example, self-motion estimation (e.g., three-dimensional translation and three-dimensional rotation of the vehicle body from a camera, and therefore the vehicle's body). Rotation and translation estimates can be determined based on analysis of images captured by one or more image-capturing devices and information from other sensors or devices, such as inertial sensors and velocity sensors. For example, inertial sensors may include accelerometers or other suitable sensors configured to measure changes in the translation and / or rotation of the vehicle body. The vehicle may include a velocity sensor that measures the vehicle's speed.

[0262] In some embodiments, the self-motion of the camera (and therefore the vehicle body) can be estimated based on optical flow analysis of captured images. Optical flow analysis of an image sequence identifies movement of pixels from the image sequence, and based on the identified movement, the motion of the vehicle is determined. The self-motion can be integrated over time and along road segments to reconstruct a trajectory associated with road segments already followed by the vehicle.

[0263] Data collected by multiple vehicles during multiple trips along a road segment at different times (e.g., reconstructed trajectories) can be used to include in a road model (e.g., including target trajectories, etc.) constructed from sparse data 800. Data collected by multiple vehicles during multiple trips along a road segment at different times can also be averaged to increase the model's accuracy. In some embodiments, data regarding road geometry and / or landmarks can be received from multiple vehicles traveling through a public road segment at different times. This data received from different vehicles can be combined to generate and / or update the road model.

[0264] The geometry of the reconstructed trajectory (and target trajectory) along the road segment can be represented by a curve in three-dimensional space, which can be a spline connecting three-dimensional polynomials. The reconstructed trajectory curve can be determined based on analysis of a video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a location a few meters ahead of the vehicle's current position is identified in each frame or image. This location is the position the vehicle is expected to reach within a predetermined time period. This operation can be repeated frame by frame, and simultaneously, the vehicle can calculate the camera's self-motion (rotation and translation). At each frame or image, the vehicle generates a short-range model for the desired path in a reference frame attached to the camera. The short-range models can be stitched together to obtain a three-dimensional model of the road in a coordinate system, which can be arbitrary or predetermined. The three-dimensional model of the road can then be fitted using splines, which can include or connect one or more polynomials of appropriate order.

[0265] To derive a short-range road model at each frame, one or more detection modules can be used. For example, a bottom-up lane detection module can be used. The bottom-up lane detection module can be useful when lane markings are drawn on the road. This module can find edges in the image and assemble them to form lane markings. A second module can be used in conjunction with the bottom-up lane detection module. The second module is an end-to-end deep neural network that can be trained to predict the correct short-range path based on the input image. In both modules, the road model can be detected in the image coordinate system and transformed into a three-dimensional space that can be virtually attached to the camera.

[0266] While trajectory reconstruction modeling methods may introduce error accumulation due to the integration of self-motion over long periods, which may include noise components, such errors are likely insignificant because the generated model can provide sufficient accuracy for navigation at local scales. Furthermore, integrated errors can be eliminated by using external information sources, such as satellite imagery or geodesy. For example, the disclosed systems and methods can use a GNSS receiver to eliminate accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed systems and methods can weakly depend on the availability and accuracy of GNSS positioning to enable maneuvering applications. In such systems, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed system may use GNSS signals solely for database indexing purposes.

[0267] In some embodiments, the range scale (e.g., local scale) that may be associated with autonomous vehicle navigation and maneuvering applications can be approximately 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances can be used because the geometric road model is primarily used for two purposes: planning the forward trajectory and locating the vehicle on the road model. In some embodiments, when the control algorithm maneuvers the vehicle based on a target located 1.3 seconds ahead (or any other suitable distance, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.), the planning task can use the model within a typical range of 40 meters ahead (or any other suitable distance, such as 20 meters, 30 meters, 50 meters). According to a method known as “tail alignment” (described in more detail in another section), the localization task uses the road model within a typical range of 60 meters behind the vehicle (or any other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.). The disclosed systems and methods can generate geometric models with sufficient accuracy within a specific range (e.g., 100 meters) such that the planned trajectory does not deviate beyond, for example, a distance of 30 cm from the center of the lane.

[0268] As described above, a 3D road model can be constructed by detecting short segments and stitching them together. Stitching can be achieved by calculating a six-degree-of-freedom self-motion model using video and / or images captured by cameras, data reflecting vehicle motion from inertial sensors, and the main vehicle speed signal. The accumulated error may be small enough at certain local scales (such as approximately 100 meters). All of this can be accomplished in a single pass on a specific road segment.

[0269] In some embodiments, multiple trips can be used to average the resulting model and further improve its accuracy. The same car can travel the same route multiple times, or multiple cars can send their collected model data to a central server. In any case, a matching process can be performed to identify overlapping models and to average them in order to generate the target trajectory. Once convergence criteria are met, the constructed model (e.g., including the target trajectory) can be used for manipulation. Subsequent trips can be used for further model improvements and to facilitate adaptation to infrastructure changes.

[0270] If multiple vehicles are connected to a central server, sharing driving experiences (e.g., sensor data) among these vehicles becomes feasible. Each vehicle client can store a partial copy of a common road model, which can be associated with its current location. A bidirectional update process between the vehicles and the server can be performed by both the vehicles and the server. The aforementioned small coverage area concept enables the disclosed systems and methods to perform bidirectional updates using very little bandwidth.

[0271] Information related to potential landmarks can also be identified and forwarded to a central server. For example, the disclosed systems and methods can determine one or more physical attributes of potential landmarks based on one or more images including the landmark. Physical attributes may include the landmark's physical dimensions (e.g., height, width), distance from a vehicle to the landmark, distance between the landmark and previous landmarks, the landmark's lateral position (e.g., the landmark's position relative to a driving lane), the landmark's GPS coordinates, the landmark's type, and the recognition of text on the landmark, etc. For example, a vehicle can analyze one or more images captured by a camera to detect potential landmarks (such as speed limit signs).

[0272] Vehicles can determine the distance from a landmark based on the analysis of one or more images. In some embodiments, the distance can be determined based on the analysis of images of the landmark using suitable image analysis methods, such as scaling methods and / or optical flow methods. In some embodiments, the disclosed systems and methods can be configured to determine the type or classification of potential landmarks. If a vehicle determines that a potential landmark corresponds to a predetermined type or classification stored in a sparse map, it may be sufficient for the vehicle to communicate an indication of the landmark's type or classification and its location to a server. The server can store such indications. Later, other vehicles can capture images of the landmark, process the images (e.g., using a classifier), and compare the results of the image processing with the indications about the landmark type stored on the server. Various types of landmarks can exist, and different types of landmarks can be associated with different types of data to be uploaded and stored on the server. Different processing on the vehicle can detect landmarks and transmit information about them to the server, and systems on the vehicle can receive landmark data from the server and use the landmark data for landmark identification during autonomous navigation.

[0273] In some embodiments, multiple autonomous vehicles traveling on a road segment can communicate with a server. Vehicles (or clients) can generate curves describing their journeys (e.g., through self-motion integration) in any coordinate system. Vehicles can detect landmarks and position them within the same frame. Vehicles can upload curves and landmarks to the server. The server can collect data from vehicles across multiple journeys and generate a unified road model, for example, as referenced below. Figure 19 The server can use uploaded curves and landmarks to generate sparse maps with a uniform road model.

[0274] The server can also distribute models to clients (e.g., vehicles). See the following reference for examples. Figure 24 The server discussed can distribute sparse maps to one or more vehicles. When receiving new data from the vehicles, the server can update the model continuously or periodically. For example, the server can process the new data to evaluate whether it includes information that should trigger an update or the creation of new data on the server. The server can then distribute the updated model or updates to the vehicles to provide autonomous vehicle navigation.

[0275] The server can use one or more criteria to determine whether new data received from vehicles should trigger an update to the model or the creation of new data. For example, when new data indicates that a previously identified landmark at a specific location no longer exists or has been replaced by another landmark, the server can determine that the new data should trigger an update to the model. As another example, when new data indicates that a road segment has been closed, and when this has been confirmed by data received from other vehicles, the server can determine that the new data should trigger an update to the model.

[0276] The server can distribute an updated model (or an updated portion of a model) to one or more vehicles traveling on a road segment associated with the model update. The server can also distribute an updated model to vehicles about to travel on that road segment, or vehicles whose planned journey includes that road segment, with the model update associated with that road segment. For example, when an autonomous vehicle is traveling along another road segment before reaching the road segment associated with the update, the server can distribute the update or an updated model to the autonomous vehicle before the vehicle reaches that road segment.

[0277] In some embodiments, a remote server can collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a public road segment). The server can use landmarks to match curves and create an average road model based on the trajectories collected from multiple vehicles. The server can also calculate the most probable path at each node or junction of the road map and road segment. For example, as described below... Figure 29The remote server discussed can align trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0278] The server can average landmark attributes received from multiple vehicles traveling along a public road segment, such as the distance between one landmark and another measured by multiple vehicles (e.g., along the previous one on the road segment), to determine arc length parameters and support positioning along the path and speed calibration for each client vehicle. The server can average the physical dimensions of landmarks of the same type, measured and identified by multiple vehicles traveling along the public road segment. The averaged physical dimensions can be used to support distance estimation, such as the distance from a vehicle to a landmark. The server can average the lateral position of landmarks of the same type, measured and identified by multiple vehicles traveling along the public road segment (e.g., the position from the vehicle's lane to that landmark). The averaged lateral position can be used to support lane assignment. The server can average the GPS coordinates of landmarks of the same type, measured and identified by multiple vehicles traveling along the same road segment. The averaged GPS coordinates of landmarks can be used to support global positioning or localization of landmarks in the road model.

[0279] In some embodiments, the server can identify model changes, such as construction, detours, new signs, and marker removal, based on data received from the vehicle. The server can update the model continuously, periodically, or instantaneously as it receives new data from the vehicle. The server can distribute the updated model or a newer model to the vehicle for use in providing autonomous navigation. For example, as discussed further below, the server can use crowdsourced data to filter out “ghost” landmarks detected by the vehicle.

[0280] In some embodiments, the server can analyze driver interventions during autonomous driving. The server can analyze data received from the vehicle at the time and location of the intervention, and / or data received prior to the intervention. The server can identify portions of the data that caused or is closely related to the intervention, such as data indicating temporary lane closure settings or data indicating pedestrians in the road. The server can update the model based on the identified data. For example, the server can modify one or more trajectories stored in the model.

[0281] Figure 12 This is a schematic diagram of a system that uses crowdsourcing to generate sparse maps (and uses crowdsourced sparse maps for distribution and navigation). Figure 12 The diagram shows a road segment 1200 comprising one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 may travel on road segment 1200 simultaneously or at different times (although...). Figure 12(Indicated as vehicles appearing simultaneously on road segment 1200). At least one of vehicles 1205, 1210, 1215, 1220, and 1225 can be an autonomous vehicle. To simplify this example, it is assumed that all vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0282] Each vehicle may be similar to a vehicle disclosed in other embodiments (e.g., vehicle 200) and may include components or devices included in or associated with vehicles disclosed in other embodiments. Each vehicle may be equipped with an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle may communicate with a remote server 1230 via wireless communication path 1235 through one or more networks (e.g., via cellular networks and / or the Internet, etc.), as shown by dashed lines. Each vehicle may transmit data to and receive data from server 1230. For example, server 1230 may collect data from multiple vehicles traveling on road segment 1200 at different times and may process the collected data to generate an autonomous vehicle road navigation model, or an update to the model. Server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to the vehicle that sent data to server 1230. Server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to other vehicles traveling on road segment 1200 at subsequent times.

[0283] When vehicles 1205, 1210, 1215, 1220, and 1225 travel on road segment 1200, navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 can be transmitted to server 1230. In some embodiments, the navigation information may be associated with the public road segment 1200. The navigation information may include a trajectory associated with each of these vehicles as each vehicle 1205, 1210, 1215, 1220, and 1225 travels on road segment 1200. In some embodiments, the trajectory may be reconstructed based on data sensed by various sensors and devices provided on vehicle 1205. For example, the trajectory may be reconstructed based on at least one of accelerometer data, speed data, landmark data, road geometry or profile data, vehicle positioning data, and self-motion data. In some embodiments, the trajectory may be reconstructed based on data from inertial sensors (such as accelerometers) and the speed of vehicle 1205 sensed by a speed sensor. Additionally, in some embodiments, the trajectory can be determined based on the sensed ego motion of the camera (e.g., via a processor on each of vehicles 1205, 1210, 1215, 1220, and 1225), which can indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The ego motion of the camera (and therefore the vehicle body) can be determined by analyzing one or more images captured by the camera.

[0284] In some embodiments, the trajectory of vehicle 1205 may be determined by a processor provided on vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 may receive data sensed by various sensors and devices provided in vehicle 1205 and determine the trajectory based on the data received from vehicle 1205.

[0285] In some embodiments, navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 may include data about the road surface, road geometry, or road profile. The geometry of road segment 1200 may include lane structure and / or landmarks. Lane structure may include the total number of lanes in road segment 1200, lane type (e.g., one-way lane, two-way lane, driving lane, overtaking lane, etc.), lane markings, lane width, etc. In some embodiments, navigation information may include lane assignment, such as which lane a vehicle is traveling in among multiple lanes. For example, lane assignment may be associated with a numerical value "3" indicating that the vehicle is traveling in the third lane from the left or right. As another example, lane assignment may be associated with the text value "center lane" indicating that the vehicle is traveling in the center lane.

[0286] Server 1230 may store navigation information on a non-transitory computer-readable medium, such as a hard disk drive, optical disc, magnetic tape, memory, etc. Server 1230 may generate (e.g., via a processor included in server 1230) at least a portion of an autonomous vehicle road navigation model for public road segment 1200 based on navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225, and may store this model as part of a sparse map. Server 1230 may determine a trajectory associated with each lane based on crowdsourced data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling in lanes of the road segment at different times. Server 1230 may generate an autonomous vehicle road navigation model or a portion of the model (e.g., an updated portion) based on the multiple trajectories determined according to the crowdsourced source navigation data. (See below for more details.) Figure 24 To explain in more detail, server 1230 can transmit the model or an updated portion of the model to one of the autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or to multiple or subsequent autonomous vehicles traveling on the road segment, for updating the existing autonomous vehicle road navigation model provided in the vehicle's navigation system. See below for reference. Figure 26 To explain in more detail, the autonomous vehicle road navigation model can be used by autonomous vehicles for autonomous navigation along a public road segment 1200.

[0287] As mentioned above, autonomous vehicle road navigation models can be included in sparse maps (e.g., Figure 8 The sparse map 800 (drawn in the sparse map 800) may include sparse records of data relating to road geometry and / or landmarks along the road, which can provide sufficient information to guide autonomous vehicle navigation without requiring excessive data storage. In some embodiments, the autonomous vehicle road navigation model may be stored separately from the sparse map 800, and map data from the sparse map 800 may be used when the model is executed for navigation. In some embodiments, the autonomous vehicle road navigation model may use map data included in the sparse map 800 to determine a target trajectory along road segment 1200 for guiding autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles subsequently traveling along road segment 1200. For example, when the autonomous vehicle road navigation model is executed by a processor in a navigation system included in vehicle 1205, the model may enable the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory included in the sparse map 800 to verify and / or correct the current driving route of vehicle 1205.

[0288] In an autonomous vehicle road navigation model, the geometry of road features or target trajectories can be encoded by curves in three-dimensional space. In one embodiment, the curve can be a three-dimensional spline comprising one or more connected three-dimensional polynomials. As those skilled in the art will understand, a spline can be a numerical function defined piecewise by a series of polynomials for fitting data. The spline used to fit the three-dimensional geometry of the road can include linear splines (first order), quadratic splines (second order), cubic splines (third order), or any other spline (other orders), or combinations thereof. A spline can include one or more three-dimensional polynomials of different orders connecting (e.g., fitting) data points of the three-dimensional geometry of the road. In some embodiments, the autonomous vehicle road navigation model can include a three-dimensional spline corresponding to a target trajectory along a common road segment (e.g., segment 1200) or a lane of segment 1200.

[0289] As described above, the autonomous vehicle road navigation model included in the sparse map may include other information, such as the identification of at least one landmark along road segment 1200. The landmark may be visible within the field of view of a camera (e.g., camera 122) mounted on each of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 may capture an image of the landmark. A processor provided on vehicle 1205 (e.g., processor 180, 190, or processing unit 110) may process the image of the landmark to extract landmark identification information. The landmark identification information (rather than an actual image of the landmark) may be stored in the sparse map 800. The landmark identification information may require significantly less storage space than the actual image. Other sensors or systems (e.g., a GPS system) may also provide some identification information about the landmark (e.g., the location of the landmark). The landmark may include at least one of traffic signs, arrow markings, lane markings, dashed lane markings, traffic lights, stop lines, directional signs (e.g., highway exit signs with arrows indicating directions, highway signs with arrows pointing in different directions or places), landmark beacons, or lampposts. Landmark beacons refer to devices (e.g., RFID devices) installed along a road segment that transmit or reflect signals to receivers installed on vehicles, such that when a vehicle passes the device, the beacon received by the vehicle and the location of the device (e.g., determined based on the device's GPS positioning) can be used as landmarks to be included in the autonomous vehicle road navigation model and / or sparse map 800.

[0290] The identification of at least one landmark may include the location of at least one landmark. The location of a landmark may be determined based on location measurements performed using sensor systems (e.g., GPS, inertial positioning systems, landmark beacons, etc.) associated with multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of a landmark may be determined over multiple trips by averaging location measurements detected, collected, or received by sensor systems on different vehicles 1205, 1210, 1215, 1220, and 1225. For example, vehicles 1205, 1210, 1215, 1220, and 1225 may send location measurement data to server 1230, which may average the location measurements and use the averaged location measurements as the location of the landmark. The location of the landmark may be continuously refined by measurements received from the vehicles during subsequent driving.

[0291] Landmark identification can include the landmark's size. A processor provided on a vehicle (e.g., 1205) can estimate the physical size of the landmark based on analysis of the image. Server 1230 can receive multiple estimates of the physical size of the same landmark from different vehicles over different trips. Server 1230 can average the different estimates to arrive at the physical size of the landmark and store that landmark size in the road model. The physical size estimate can be used to further determine or estimate the distance from the vehicle to the landmark. The distance to the landmark can be estimated based on the vehicle's current speed and the expansion ratio based on the location of the landmark in the image relative to the extended focus of the camera. For example, the distance to the landmark can be estimated by Z = V * dt * R / D, where V is the vehicle's speed, R is the distance from the landmark to the extended focus in the image from time t1, and D is the change in distance of the landmark in the image from t1 to t2. dt represents (t2 - t1). For example, the distance to the landmark can be estimated by Z = V * dt * R / D, where V is the vehicle's speed, R is the distance between the landmark and the extended focus in the image, dt is the time interval, and D is the image displacement of the landmark along the epipolar line. Other formulas equivalent to the above formula, such as Z = V * ω / Δω, can be used to estimate the distance to a landmark. Here, V is the vehicle speed, ω is the image length (similar to object width), and Δω is the change in image length over time.

[0292] When the physical dimensions of a landmark are known, the distance to the landmark can be determined using the following formula: Z = f * W / ω, where f is the focal length, W is the dimensions of the landmark (e.g., height or width), and ω is the number of pixels the landmark is away from the image. Based on the above formula, ΔZ = f * W * Δω / ω can be used. 2The distance Z change is calculated using +f*ΔW / ω, where ΔW decays to zero through averaging, and Δω is the number of pixels representing the accuracy of the bounding box in the image. The estimated physical dimensions of the landmark can be calculated by averaging multiple observations on the server side. The resulting distance estimation error can be very small. Two sources of error may arise when using the above formula: ΔW and Δω. Their contributions to the distance error are given by ΔZ = f*W*Δω / ω. 2 +f*ΔW / ω is given. However, ΔW decays to zero by averaging; therefore, ΔZ is determined by Δω (e.g., the inaccuracy of the bounding box in the image).

[0293] For landmarks of unknown size, the distance to the landmark can be estimated by tracking feature points on the landmark between consecutive frames. For example, certain features appearing on a speed limit sign can be tracked between two or more image frames. Based on these tracked features, a distance distribution for each feature point can be generated. The distance estimate can be extracted from the distance distribution. For example, the most frequent distances appearing in the distance distribution can be used as the distance estimate. As another example, the average value of the distance distribution can be used as the distance estimate.

[0294] Figure 13 An example autonomous vehicle road navigation model is shown, represented by multiple three-dimensional splines 1301, 1302 and 1303. Figure 13 Curves 1301, 1302, and 1303 shown are for illustrative purposes only. Each spline may include one or more three-dimensional polynomials connecting multiple data points 1310. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or any suitable combination of polynomials with different orders. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data about landmarks (e.g., the size, location, and identification information of landmarks) and / or road signature profiles (e.g., road geometry, road smoothness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 may be associated with data about landmarks, while other data points may be associated with data about road signature profiles.

[0295] Figure 14The diagram illustrates raw location data 1410 (e.g., GPS data) received from five separate trips. Here, one trip is considered separate from another if it is traversed by separate vehicles at the same time, by the same vehicles at separate times, or by separate vehicles at separate times. To account for errors in the location data 1410 and the different positions of vehicles within the same lane (e.g., one vehicle may be closer to the left side of the lane than another), server 1230 can use one or more statistical techniques to generate a map skeleton 1420 to determine whether variations in the raw location data 1410 represent actual deviations or statistical errors. Each path within the skeleton 1420 can be linked back to the raw data 1410 that formed the path. For example, the path between A and B within the skeleton 1420 links to the raw data 1410 from trips 2, 3, 4, and 5, but not from the raw data from trip 1. The skeleton 1420 may not be detailed enough for navigating vehicles (e.g., unlike the splines described above, it combines multiple lanes on the same road), but it can provide useful topological information and can be used to define intersections.

[0296] Figure 15 An example is shown, from which additional detail can be generated for a sparse map within a segment of a map skeleton (e.g., segment A to B within skeleton 1420). Figure 15 As shown, data (e.g., self-motion data, road marking data, etc.) can be displayed as a function of the position S (or S1 or S2) along the journey. Server 1230 can identify landmarks in a sparse map by recognizing unique matches between landmarks 1501, 1503, and 1505 of journey 1510 and landmarks 1507 and 1509 of journey 1520. This matching algorithm can lead to the identification of landmarks 1511, 1513, and 1515. However, those skilled in the art will recognize that other matching algorithms can be used. For example, probabilistic optimization can be used instead of unique matching or in combination with unique matching. See below for reference. Figure 29 As described in further detail, server 1230 can vertically align travels to align matching landmarks. For example, server 1230 can select one travel (e.g., travel 1520) as a reference travel, and then move and / or elastically stretch other travels (e.g., travel 1510) for alignment.

[0297] Figure 16 An example of landmark data used for alignment in sparse maps is shown. Figure 16 In the example, landmark 1610 includes road signs. Figure 16 The examples further depict data from multiple journeys 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In Figure 16In the example, the data from trip 1613 consists of “ghosting” landmarks, and server 1230 can identify it this way because trips 1601, 1603, 1605, 1607, 1609, and 1611 do not include identifiers of landmarks near the landmarks identified in trip 1613. Therefore, server 1230 can accept a potential landmark when the ratio of images in which landmarks actually appear to images in which landmarks do not appear exceeds a threshold, and / or reject a potential landmark when the ratio of images in which landmarks do not appear to images in which landmarks appear exceeds a threshold.

[0298] Figure 17 A system 1700 for generating trip data is described, which can be used for crowdsourced sparse maps. For example... Figure 17 As shown, system 1700 may include camera 1701 and positioning device 1703 (e.g., GPS locator). Camera 1701 and positioning device 1703 may be mounted on a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). Camera 1701 may generate multiple types of data, such as self-motion data, traffic sign data, road data, etc. Camera data and location data may be segmented into travel segments 1705. For example, travel segments 1705 may each have camera data and location data from a driving distance of less than 1 km.

[0299] In some embodiments, system 1700 may remove redundancy in travel segment 1705. For example, if a landmark appears in multiple images from camera 1701, system 1700 may strip redundant data so that travel segment 1705 contains only one copy of the location of any metadata related to the landmark. As another example, if lane markings appear in multiple images from camera 1701, system 1700 may strip redundant data so that travel segment 1705 contains only one copy of the location and metadata of any lane markings.

[0300] System 1700 also includes a server (e.g., server 1230). Server 1230 can receive trip segments 1705 from the vehicle and recombine the trip segments 1705 into a single trip 1707. This arrangement allows for reduced bandwidth requirements when transmitting data between the vehicle and the server, while also allowing the server to store data related to the entire trip.

[0301] Figure 18 Depicting Figure 17 The system 1700, which is further configured for crowdsourced sparse maps, is as follows. Figure 17 As shown, system 1700 includes vehicle 1810, which uses, for example, a camera (which generates, for example, self-motion data, traffic sign data, road data, etc.) and positioning devices (e.g., a GPS locator). Figure 17 As shown, vehicle 1810 divides the collected data into multiple travel segments (in... Figure 18 The process is described as "DS1 1", "DS2 1", "DSN 1"). Then, server 1230 receives the process segments and reconstructs the process from the received segments (in... Figure 18 (Described as "Itinerary 1" in the text).

[0302] like Figure 18 As further described, system 1700 also receives data from other vehicles. For example, vehicle 1820 also uses, for example, cameras (which generate, for example, self-motion data, traffic sign data, road data, etc.) and positioning devices (e.g., GPS locators) to capture trip data. Similar to vehicle 1810, vehicle 1820 segments the collected data into multiple trip segments (in... Figure 18 The process is described as "DS1 2", "DS22", and "DSN 2". Then, server 1230 receives the process segments and reconstructs the process from the received segments (in...). Figure 18 (Described as "Ride 2" in the text). Any number of additional vehicles can be used. For example, Figure 18 It also includes "CAR N," which captures trip data and segments it into multiple trip segments (in... Figure 18 The data is described as "DS1N", "DS2N", and "DSNN" and sent to server 1230 for reconstruction into a process (in...). Figure 18 (Described as "Route N" in the text).

[0303] like Figure 18 As shown, server 1230 can use reconstructed trips (e.g., "trip 1", "trip 2" and "trip N") collected from multiple vehicles (e.g., "CAR 1" (also labeled as vehicle 1810), "CAR 2" (also labeled as vehicle 1820), and "CAR N") to construct a sparse map (described as "MAP").

[0304] Figure 19 This is a flowchart illustrating an example process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 can be executed by one or more processing devices included in server 1230.

[0305] Processing 1900 may include receiving multiple images acquired as one or more vehicles traverse the road segment (step 1905). Server 1230 may receive images from cameras included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, as vehicle 1205 travels along road segment 1200, camera 122 may capture one or more images of the environment surrounding vehicle 1205. In some embodiments, server 1230 may also receive simplified image data from which redundancy has been removed by a processor on vehicle 1205, as referenced above. Figure 17 The subject of discussion.

[0306] Processing 1900 may further include recognizing at least one line representation of road surface features extending along a road segment based on multiple images (step 1910). Each line representation may represent a path along a road segment substantially corresponding to the road surface features. For example, server 1230 may analyze environmental images received from camera 122 to identify road edges or lane markings and determine a driving trajectory along road segment 1200 associated with the road edges or lane markings. In some embodiments, the trajectory (or line representation) may include splines, polynomial representations, or curves. Server 1230 may determine the driving trajectory of vehicle 1205 based on camera ego motion (e.g., three-dimensional translation and / or three-dimensional rotational motion) received at step 1905.

[0307] Processing 1900 may also include identifying multiple landmarks associated with the road segment based on multiple images (step 1910). For example, server 1230 may analyze environmental images received from camera 122 to identify one or more landmarks, such as road signs along road segment 1200. Server 1230 may use analysis of multiple images acquired as one or more vehicles traverse the road segment to identify landmarks. To enable crowdsourcing, the analysis may include rules regarding the acceptance and rejection of potential landmarks associated with the road segment. For example, the analysis may include accepting a potential landmark when the ratio of images in which a landmark actually appears to images in which a landmark does not appear exceeds a threshold, and / or rejecting a potential landmark when the ratio of images in which a landmark does not appear to images in which a landmark does appear exceeds a threshold.

[0308] Processing 1900 may include other operations or steps performed by server 1230. For example, navigation information may include a target trajectory for vehicles traveling along a road segment, and processing 1900 may include server 1230 clustering vehicle trajectories associated with multiple vehicles traveling on the road segment and determining a target trajectory based on the clustered vehicle trajectories, as discussed in further detail below. Clustering vehicle trajectories may include server 1230 clustering multiple trajectories associated with vehicles traveling on the road segment into multiple clusters based on at least one of the vehicle's absolute heading or the vehicle's lane assignment. Generating the target trajectory may include server 1230 averaging the clustered trajectories.

[0309] As another example, processing 1900 may include aligning the data received in step 1905, as referenced below. Figure 29 Further details will be discussed later. As mentioned above, other processes or steps performed by server 1230 may also be included in process 1900.

[0310] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates instead of global coordinates. For autonomous driving, some systems may present data in world coordinates. For example, longitude and latitude coordinates on the Earth's surface may be used. To use a map for manipulation, the primary vehicle can determine its position and orientation relative to the map. Using a GPS device on the vehicle seems natural to position the vehicle on the map and to find the rotational transformation between the primary reference frame and the world reference frame (e.g., north, east, and down). Once the primary reference frame is aligned with the map reference frame, the desired route can be expressed in the primary reference frame, and manipulation commands can be calculated or generated.

[0311] However, a potential problem with this strategy is that current GPS technology often fails to provide subject positioning and location with sufficient accuracy and availability. To overcome this, highly detailed maps (called high-definition or HD maps) can be constructed using landmarks whose world coordinates are known. These landmarks contain various types of landmarks. Vehicles equipped with sensors can then detect and locate landmarks in their own frame of reference. Once the relative position between the vehicle and the landmarks is found, the world coordinates of the landmarks can be determined from the HD map, and the vehicle can use these coordinates to calculate its own positioning and location.

[0312] However, this method can use a global world coordinate system as an intermediary to establish alignment between the map and the main reference frame. That is, landmarks can be used to compensate for the limitations of GPS devices on vehicles. Landmarks and HD maps Figure 1 This allows for the calculation of precise vehicle positions in global coordinates, thus solving the map-subject alignment problem.

[0313] In the disclosed systems and methods, autonomous navigation can be achieved using numerous maps or local maps instead of a single global map of the world. Each map or local map can define its own coordinate system. These coordinate systems can be arbitrary. The vehicle's coordinates in a local map may not need to indicate the vehicle's position on the Earth's surface. Furthermore, it may not be required that the local maps be accurate on a large scale, meaning there may be no rigid transformations that can embed local maps into a global world coordinate system.

[0314] This world representation involves two main processes: one concerning map generation, and the other concerning their use. Regarding map generation, this type of representation can be created and maintained through crowdsourcing. The application of sophisticated survey equipment may not be necessary, as the use of HD maps is limited, thus making crowdsourcing feasible. Regarding usage, efficient methods can be employed to align local maps with the main reference frame without traversing the standard world coordinate system. Therefore, at least in most cases and environments, precise estimation of vehicle location and position in global coordinates may not be required. Furthermore, the memory coverage area of ​​the local map can remain very small.

[0315] The fundamental principle of map generation is the integration of self-motion. Vehicles can sense the movement of cameras in space (3D translation and 3D rotation). Vehicles or servers can reconstruct a vehicle's trajectory through the integration of self-motion over time, and this integrated path can be used as a model of road geometry. This process can be combined with the sensing of nearby lane markings, and the reconstructed route can then reflect the path the vehicle should follow, rather than the specific path the vehicle actually follows. In other words, the reconstructed route or trajectory can be modified based on sensing data associated with nearby lane markings, and the modified reconstructed trajectory can be used as a recommended or target trajectory, which can be stored in the road model or sparse map for use by other vehicles navigating the same road segment.

[0316] In some embodiments, the map coordinate system can be arbitrary. A camera reference frame can be selected at any time and will be used as the map origin. The integrated trajectory of the camera can be represented in the coordinate system of that particular selected frame. The values ​​of the route coordinates in the map may not directly represent a location on Earth.

[0317] Integrated paths can accumulate errors. This may be because the sensing of self-motion may not be absolutely accurate. As a result of accumulated errors, local maps may diverge, and local maps may not be considered local copies of the global map. The larger the size of the local map tiles, the greater the deviation from the "real" geometry on Earth.

[0318] The arbitrariness and divergence of local maps may not be a result of ensemble methods, which can be applied to construct maps in a crowdsourced manner (e.g., by vehicles traveling along roads). However, vehicles can successfully manipulate using local maps.

[0319] The map may diverge over long distances. Since the map is used to plan trajectories near the vehicle, the effect of this divergence is likely acceptable. At any given time instance, the system (e.g., server 1230 or vehicle 1205) can repeat the alignment process and use the map to predict the road location (in camera coordinates) approximately 1.3 seconds ahead (or any other second, such as 1.5 seconds, 1.0 seconds, 1.8 seconds, etc.). As long as the accumulated error over this distance is sufficiently small, maneuvering commands provided for autonomous driving can be used.

[0320] In some embodiments, a local map can focus on a local area and may not cover a very large area. This means that a vehicle using a local map for maneuvering in autonomous driving may reach the end of the map at a certain point and may have to switch to another local patch or segment of the map. Switching can be enabled by overlapping local maps. Once the vehicle enters an area shared by two maps, the system (e.g., server 1230 or vehicle 1205) can continue to generate maneuvering commands based on the first local map (the map currently in use), but simultaneously the system can position the vehicle on another map (or a second local map) that overlaps with the first local map. In other words, the system can simultaneously align the camera's current coordinate system with both the coordinate systems of the first and second maps. When a new alignment is established, the system can switch to the other map and plan the vehicle's trajectory there.

[0321] The disclosed system may include additional features, one of which relates to how the system aligns the coordinate systems of the vehicle and the map. As mentioned above, assuming the vehicle can measure its relative position to landmarks, alignment can be performed using landmarks. This is useful in autonomous driving, but can sometimes lead to a need for a large number of landmarks, resulting in a large memory footprint. Therefore, the disclosed system can use an alignment process to address this problem. In this alignment process, the system can use an integration of sparse landmarks and ego velocities to compute a 1D estimator of the vehicle's position along the road. The system can use the shape of the trajectory itself to compute the rotational portion of the alignment using a tail alignment method discussed in detail below in other sections. Thus, the vehicle can reconstruct its own trajectory while driving the "tail" and compute rotations about its assumed position along the road to align the tail with the map. This alignment process differs from the one described in the reference below. Figure 29 The alignment of crowdsourced data under discussion.

[0322] GPS devices can still be used in the disclosed systems and methods. Global coordinates can be used to index databases storing tracks and / or landmarks. Relevant local map images and related landmarks near the vehicle can be stored in memory and retrieved from memory using global GPS coordinates. However, in some embodiments, global coordinates may not be used for route planning and may be inaccurate. In one example, the use of global coordinates for indexing information may be limited.

[0323] In cases where "tail alignment" doesn't work well, the system can use a larger number of landmarks to calculate the vehicle's position. This is likely a rare case, so the impact on memory coverage is probably moderate. Road intersections are an example of this.

[0324] The disclosed systems and methods can use semantic landmarks (e.g., traffic signs) because they can be reliably detected from the scene and matched with landmarks stored in a road model or sparse map. In some cases, the disclosed systems can also use non-semantic landmarks (e.g., generic signs), and in such cases, non-semantic landmarks can be attached to appearance signatures, as described above. The system can use learning methods to generate signatures that follow a "same or different" recognition paradigm.

[0325] For example, given many journeys along which they have GPS coordinates, the disclosed system can generate the underlying road structure intersections and road segments, as described above. Figure 14The discussion assumes that roads are far enough apart to be distinguishable using GPS. In some embodiments, only a coarse-grained map may be needed. To generate a map of the underlying road structure, the space can be divided into a grid of a given resolution (e.g., 50m by 50m). Each trip can be viewed as an ordered list of grid stations. The system can color each grid station belonging to a trip to produce an image of the merged trips. Colored grid points can be represented as nodes on the merged trips. A trip from one node to another can be represented as a link. The system can fill in small holes in the image to avoid distinguishing lanes and correct for GPS errors. The system can use a suitable thinning algorithm (e.g., an algorithm called the "Zhang-Suen" thinning algorithm) to obtain the skeleton of the image. This skeleton can represent the underlying road structure and intersections can be found using masks (e.g., points connected to at least three other points). Once intersections are found, these segments may be the skeleton parts connecting them. To match trips back to the skeleton, the system can use a Hidden Markov Model. Each GPS point can be associated with a grid station with a probability inversely proportional to its distance from that station. Use a suitable algorithm (e.g., the Viterbi algorithm) to match GPS points with grid point sites, without allowing consecutive GPS points to be matched with non-adjacent grid sites.

[0326] Several methods can be used to map the journey back to the map. For example, a first approach might involve maintaining tracking during refinement. A second approach might use nearest-neighbor matching. A third approach might use a Hidden Markov Model (HMM). An HMM assumes a latent hidden state for each observation and assigns a probability to a given observation given a given state, as well as a probability to a given previous state. Given a list of observations, the Viterbi algorithm can be used to find the most probable state.

[0327] The disclosed systems and methods may include additional features. For example, the disclosed systems and methods can detect highway entrances / exits. Multiple trips within the same area can be merged into the same coordinate system using GPS data. The system can use visual feature points for mapping and positioning.

[0328] In some embodiments, common visual features can be used as landmarks to record the position and orientation of a moving vehicle during a journey (localization phase) relative to a map generated by vehicles that traversed the same road segment in a previous journey (mapping phase). These vehicles may be equipped with calibrated cameras that image the vehicle's surroundings and GPS receivers. The vehicles may communicate with a central server (e.g., server 1230) that maintains an up-to-date map, which includes these visual landmarks connected to other important geometric and semantic information (e.g., lane structure, type and location of road signs, type and location of road markings, shape of nearby drivable ground areas depicted by the location of physical obstacles, shape of previously driven vehicle paths when controlled by a human driver, etc.). During the mapping and localization phases, the total amount of data that can be communicated between the central server and vehicles at each road segment length is small.

[0329] During the mapping phase, the disclosed system (e.g., an autonomous vehicle and / or one or more servers) can detect feature points (FPs). Feature points can include one or more points used to track related objects such as landmarks. For example, eight points including the corner of a stop sign can be feature points. The disclosed system can further compute descriptors associated with the FPs (e.g., using features from a Fast Segment Test (FAST) detector, a Binary Robust Invariant Scalable Keypoint (BRISK) detector, a Binary Robust Independent Basic Feature (BRIEF) detector, and / or an Oriented FAST and Rotated BRIEF (ORB) detector, or using features from detector / descriptor pairs trained using a training library). The system can use the motion of feature points in the image plane to track feature points between frames in which they appear, and match associated descriptors using, for example, Euclidean or Hamming distance in descriptor space. The system can use the tracked FPs to estimate camera motion and the world location of objects on which the FPs are detected and tracked. For example, the tracked FPs can be used to estimate the motion of a vehicle and / or the location of a landmark on which the FPs were initially detected.

[0330] The system can further classify FPs as those that are likely to be detected in future trips (e.g., FPs detected on momentarily moving objects, parked cars, and shadow textures are unlikely to reappear in future trips). This classification can be referred to as reproducibility classification (RC) and can be a function of the light intensity in the pyramid region surrounding the detected FP, the motion of the tracked FP in the image plane, and / or the viewpoint range of successful detection and tracking. In some embodiments, the vehicle can send to server 1230 a descriptor associated with the FP, an estimated 3D position of the vehicle relative to the FP, and the instantaneous vehicle GPS coordinates at the time of FP detection / tracking.

[0331] During the mapping phase, when the communication bandwidth between the mapping vehicle and the central server is limited, or when the presence of FPs or other semantic landmarks (such as road signs and lane structures) on the map is limited and insufficient for positioning purposes, the vehicle can send FPs to the server at a high frequency. Furthermore, although vehicles in the mapping phase can typically send FPs to the server at a low spatial frequency, FPs can be aggregated on the server. The server can also perform the detection of recurring FPs, and can store a set of these recurring FPs and / or ignore FPs that are no longer recurring. At least in some cases, the visual appearance of landmarks may be sensitive to the time of day or the season in which they are captured. Therefore, to increase the reproducibility probability of FPs, the received FPs can be binned by the server into time-based bins, seasonal bins, etc. In some embodiments, the vehicle can also send other semantic and geometric information associated with the FPs to the server (e.g., lane shape, road surface structure, 3D location of obstacles, free space in the instantaneous coordinate system of the mapping clip, the path driven by a human driver in the setup journey to the parking space, etc.).

[0332] During the localization phase, the server can send a map containing landmarks in the form of FP locations and descriptors to one or more vehicles. Within a set of current consecutive frames, feature points (FPs) can be detected and tracked by the vehicles in near real-time. Tracked FPs can be used to estimate camera motion and / or the location of associated objects (such as landmarks). Detected FP descriptors can be searched to match a list of FPs that includes GPS coordinates in the map and have estimated GPS uncertainties within a finite radius of the current GPS reading from the vehicle. Matching can be accomplished by searching all current pairs and mapping FPs that minimize Euclidean or Hamming distances in the descriptor space. Using FP matching and their current and map locations, the vehicle can rotate and / or translate between its instantaneous vehicle position and the local map coordinate system.

[0333] The disclosed systems and methods may include approaches for training reproducible classifiers. Training can be performed in one of the following schemes to increase labeling costs and the accuracy of the resulting classifier.

[0334] In the first approach, a database comprising a large number of clips recorded by vehicle cameras with matching instantaneous vehicle GPS positions can be collected. This database can include representative samples of the trips (regarding various attributes: e.g., time of day, season, weather conditions, road type). Feature points (FPs) extracted from frames of different trips with similar GPS positions and headings can potentially match within a GPS uncertainty radius. Mismatched FPs can be labeled as non-reproducible, while matching FPs can be labeled as reproducible. Given their appearance in the image pyramid, their instantaneous position relative to the vehicle, and the range of viewpoint positions where they were successfully tracked, a classifier can then be trained to predict the reproducibility labels of the FPs.

[0335] In the second approach, the FP pairs extracted from the clip database described in the first approach can also be labeled by the person responsible for annotating the FP matches between clips.

[0336] In the third approach, light detection and ranging (LIDAR) measurements are used to enhance the database from the first approach, which contains precise vehicle position, vehicle orientation, and image pixel depth. This database can then be used to accurately match world positions across different journeys. Feature point descriptors can then be computed at the image regions corresponding to these world points at different viewpoints and driving times. A classifier can then be trained to predict the average distance of a descriptor in the descriptor space of its matched descriptors. In this case, reproducibility can be measured by the possibility of low descriptor distances.

[0337] Consistent with the disclosed embodiments, the system can generate an autonomous vehicle road navigation model based on observed trajectories of vehicles traversing a public road segment (e.g., which may correspond to trajectory information forwarded by the vehicle to the server). However, the observed trajectories may not correspond to the actual trajectories taken by the vehicles traversing the road segment. Instead, in some cases, the trajectory uploaded to the server can be modified relative to the actual reconstructed trajectory determined by the vehicle. For example, while reconstructing the actual trajectory, the vehicle system can use sensor information (e.g., analysis of images provided by cameras) to determine that its own trajectory may not be the preferred trajectory for the road segment. For example, the vehicle may determine, based on image data from onboard cameras, that it is not driving in the center of the lane or that it has crossed the lane boundary for a defined period of time. In this case, in particular, the reconstructed trajectory (the actual path traversed) of the vehicle can be refined based on information derived from sensor outputs. The refined trajectory, instead of the actual trajectory, can then be uploaded to the server, potentially for use in constructing or updating sparse data graph 800.

[0338] Then, in some embodiments, a processor included in a vehicle (e.g., vehicle 1205) can determine the actual trajectory of vehicle 1205 based on the output from one or more sensors. For example, based on analysis of images output from camera 122, the processor can identify landmarks along road segment 1200. Landmarks can include traffic signs (e.g., speed limit signs), directional signs (e.g., highway directional signs pointing to different routes or places), and general signs (e.g., rectangular commercial signs associated with unique signatures, such as color patterns). The identified landmarks can be compared with landmarks stored in sparse map 800. When a match is found, the location of the landmark stored in sparse map 800 can be used as the location of the identified landmark. The location of the identified landmark can be used to determine the location of vehicle 1205 along the target trajectory. In some embodiments, the processor can also determine the position of vehicle 1205 based on GPS signals output from GPS unit 1710.

[0339] The processor can also determine a target trajectory for transmission to server 1230. The target trajectory may be the same as the actual trajectory determined by the processor based on sensor output. However, in some embodiments, the target trajectory may differ from the actual trajectory determined based on sensor output. For example, the target trajectory may include one or more modifications to the actual trajectory.

[0340] In one example, if the data from camera 122 includes roadblocks, such as a temporary lane-shifting roadblock 100 meters ahead of vehicle 1250 changing lanes (e.g., when a lane is temporarily shifted due to construction or an accident ahead), the processor can detect the temporary lane-shifting roadblock from the image and select a lane different from the lane corresponding to the target trajectory stored in the road model or sparse map based on the temporary lane shift. The vehicle's actual trajectory can reflect this lane change. However, if the lane shift is temporary and can be cleared in the next, for example, 10, 15, or 30 minutes, vehicle 1205 can therefore modify the actual trajectory already adopted by vehicle 1205 (i.e., lane shift) to reflect that the target trajectory should be different from the actual trajectory adopted by vehicle 1205. For example, the system can identify that the path traveled is different from the preferred trajectory of the road segment. Therefore, the system can adjust the reconstructed trajectory before uploading the trajectory information to the server.

[0341] In other embodiments, the actual reconstructed trajectory information can be uploaded via one or more recommended trajectory refinements (e.g., the magnitude and direction of translations to be made to at least a portion of the reconstructed trajectory). In some embodiments, processor 1715 can transmit the modified actual trajectory to server 1230. Server 1230 can generate or update the target trajectory based on the received information and can transmit the target trajectory to other autonomous vehicles subsequently traveling on the same road segment, as referenced below. Figure 24 Further detailed discussion.

[0342] As another example, the environmental image may include objects, such as a pedestrian suddenly appearing in road segment 1200. The processor can detect the pedestrian, and vehicle 1205 can change lanes to avoid a collision with the pedestrian. The actual trajectory reconstructed based on the sensing data may include lane changes by vehicle 1205. However, a pedestrian may soon leave the roadway. Therefore, vehicle 1205 may modify the actual trajectory (or determine a recommended modification) to reflect that the target trajectory should differ from the actual trajectory adopted (because the appearance of a pedestrian is a temporary condition that should not be considered in the determination of the target trajectory). In some embodiments, when the actual trajectory is modified, the vehicle may transmit data to the server indicating a temporary deviation from the predetermined trajectory. The data may indicate the cause of the deviation, or the server may analyze the data to determine the cause of the deviation. Knowing the cause can be useful. For example, when the deviation is due to the driver noticing a recent accident and responding by maneuvering the wheels to avoid a collision, the server may plan a more moderate adjustment to the model or specific trajectory associated with the road segment based on the cause of the deviation. As another example, when the cause of the deviation is a pedestrian crossing the road, the server may determine that a change in trajectory is not necessary in the future.

[0343] As another example, the environmental image may include lane markings indicating that vehicle 1205 is traveling slightly outside the lane, possibly under the control of a human driver. The processor can detect the lane markings from the captured image and can modify the actual trajectory of vehicle 1205 to account for lane deviation. For example, a translation can be applied to the reconstructed trajectory so that it falls into the center of the observed lane.

[0344] Distribute crowdsourced sparse maps

[0345] The disclosed systems and methods enable autonomous vehicle navigation (e.g., maneuvering control) with low-coverage models, which can be collected by the autonomous vehicle itself without the aid of expensive measurement equipment. To support autonomous navigation (e.g., maneuvering applications), the road model can include a sparse map with road geometry, its lane structure, and landmarks, which can be used to determine the location or position of vehicles along trajectories included in the model. As described above, the generation of the sparse map can be performed by a remote server that communicates with vehicles traveling on the road and receives data from the vehicles. The data can include sensed data, trajectories reconstructed based on the sensed data, and / or recommended trajectories that may represent modified reconstructed trajectories. As described below, the server can transmit the model back to vehicles or other vehicles subsequently traveling on the road to aid in autonomous navigation.

[0346] Figure 20A block diagram of server 1230 is shown. Server 1230 may include a communication unit 2005, which may include both hardware components (e.g., communication control circuitry, a switch, and an antenna) and software components (e.g., a communication protocol and computer code). For example, communication unit 2005 may include at least one network interface. Server 1230 can communicate with vehicles 1205, 1210, 1215, 1220, and 1225 through communication unit 2005. For example, server 1230 can receive navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 through communication unit 2005. Server 1230 can distribute autonomous vehicle road navigation models to one or more autonomous vehicles through communication unit 2005.

[0347] Server 1230 may include at least one non-transitory storage medium 2010, such as a hard disk drive, optical disk, magnetic tape, etc. Storage device 1410 may be configured to store data, such as navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and / or an autonomous vehicle road navigation model generated by server 1230 based on the navigation information. Storage device 2010 may be configured to store any other information, such as sparse maps (e.g., the information mentioned above regarding...). Figure 8 The sparse map under discussion (800).

[0348] In addition to or in place of storage device 2010, server 1230 may include memory 2015. Memory 2015 may be similar to or different from memory 140 or 150. Memory 2015 may be non-transitory memory, such as flash memory, random access memory, etc. Memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., processor 2020), map data (e.g., data from sparse map 800), autonomous vehicle road navigation models, and / or navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225.

[0349] Server 1230 may include at least one processing device 2020 configured to execute computer code or instructions stored in memory 2015 to perform various functions. For example, processing device 2020 may analyze navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and generate an autonomous vehicle road navigation model based on the analysis. Processing device 2020 may control communication unit 1405 to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles (e.g., one or more of vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicle subsequently traveling on road segment 1200). Processing device 2020 may be similar to or different from processor 180, 190, or processing unit 110.

[0350] Figure 21 A block diagram of a memory 2015 is shown, which can store computer code or instructions for performing one or more operations to generate a road navigation model for use in autonomous vehicle navigation. Figure 21 As shown, memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, memory 2015 may include model generation module 2105 and model distribution module 2110. Processor 2020 may execute instructions stored in any of the modules 2105 and 2110 included in memory 2015.

[0351] The model generation module 2105 may store instructions that, when executed by the processor 2020, may generate at least a portion of an autonomous vehicle road navigation model for a public road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, in generating the autonomous vehicle road navigation model, the processor 2020 may cluster vehicle trajectories along the public road segment 1200 into different clusters. The processor 2020 may determine a target trajectory along the public road segment 1200 based on the clustered vehicle trajectories in each of the different clusters. Such an operation may include finding the mean or average trajectory of the clustered vehicle trajectories in each cluster (e.g., by averaging data representing the clustered vehicle trajectories). In some embodiments, the target trajectory may be associated with a single lane of the public road segment 1200.

[0352] The autonomous vehicle road navigation model may include multiple target trajectories, each associated with a single lane of a public road segment 1200. In some embodiments, the target trajectory may be associated with the public road segment 1200, rather than with a single lane of the road segment 1200. The target trajectory may be represented by a three-dimensional spline. In some embodiments, the spline may be defined as less than 10 kilobytes / km, less than 20 kilobytes / km, less than 100 kilobytes / km, less than 1 megabyte / km, or any other suitable storage size per kilometer. The model distribution module 2110 may then distribute the generated model to one or more vehicles, for example, as referenced below. Figure 24 The subject of discussion.

[0353] Road models and / or sparse maps can store trajectories associated with road segments. These trajectories, referred to as target trajectories, are provided to autonomous vehicles for autonomous navigation. Target trajectories can be received from multiple vehicles, or they can be generated based on actual trajectories received from multiple vehicles or recommended trajectories (actual trajectories with some modifications). The target trajectories included in the road model or sparse map can be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0354] Vehicles traveling on a road segment can collect data through various sensors. This data may include landmarks, road signature profiles, vehicle motion (e.g., accelerometer data, speed data), vehicle position (e.g., GPS data), and may reconstruct the actual trajectory itself, or the data may be transmitted to a server, which will reconstruct the vehicle's actual trajectory. In some embodiments, vehicles may transmit data related to the trajectory (e.g., a curve in any reference frame), landmark data, and lane assignments along the travel path to server 1230. Various vehicles traveling along the same road segment at multiple points in the journey may have different trajectories. Server 1230 can identify routes or trajectories associated with each lane from the trajectories received by the vehicles through clustering processing.

[0355] Figure 22The diagram illustrates a process for clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine target trajectories for a common road segment (e.g., road segment 1200). The target trajectories or multiple target trajectories determined from the clustering process can be included in an autonomous vehicle road navigation model or sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 can be included in the autonomous vehicle road navigation model or sparse map 800. In some embodiments, server 1230 can generate trajectories based on landmarks, road geometry, and vehicle motion information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate the autonomous vehicle road navigation model, server 1230 can cluster vehicle trajectories 1600 into multiple clusters 2205, 2210, 2215, 2220, 2225, and 2230, as shown below. Figure 22 As shown.

[0356] Clustering can be performed using various criteria. In some embodiments, all trips in a cluster can be similar relative to their absolute heading along road segment 1200. Absolute headings can be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, absolute headings can be obtained using dead reckoning. As those skilled in the art will understand, dead reckoning can be used to determine the current position and thus the headings of vehicles 1205, 1210, 1215, 1220, and 1225 by using previously determined positions, estimated speeds, etc. Absolute headings can be used to identify routes along the roadway.

[0357] In some embodiments, all trips in a cluster can be similar in lane assignment relative to trips along segment 1200 (e.g., in the same lane before and after an intersection). Trajectories clustered by lane assignment can be used to identify lanes along the carriageway. In some embodiments, both criteria (e.g., absolute heading and lane assignment) can be used for clustering.

[0358] In each cluster 2205, 2210, 2215, 2220, 2225, and 2230, trajectories can be averaged to obtain a target trajectory associated with a specific cluster. For example, trajectories from multiple trips associated with the same lane cluster can be averaged. The averaged trajectory can be a target trajectory associated with a specific lane. For averaging trajectories across clusters, server 1230 can choose an arbitrary reference frame for trajectory C0. For all other trajectories (C1, ..., Cn), server 1230 can find a rigid transformation mapping Ci to C0, where i = 1, 2, ..., n, where n is a positive integer corresponding to the total number of trajectories contained in the cluster. Server 1230 can compute the mean curve or trajectory in the C0 reference frame.

[0359] In some embodiments, landmarks can define arc length matching between different journeys, which can be used for trajectory-lane alignment. In some embodiments, lane markings before and after intersections can be used for trajectory-lane alignment.

[0360] To assemble lanes from a trajectory, server 1230 can select any reference frame for the lanes. Server 1230 can map partially overlapping lanes to the selected reference frame. Server 1230 can continue mapping until all lanes are in the same reference frame. Lanes adjacent to each other can be aligned as if they were the same lanes, and then they can be laterally shifted.

[0361] Landmarks identified along a road segment can be mapped to a common reference frame, first at the lane level and then at the intersection level. For example, multiple vehicles on multiple trips may identify the same landmark multiple times. The data regarding the same landmark received on different trips may differ slightly. This data can be averaged and mapped to the same reference frame, such as the C0 reference frame. Additionally, or alternatively, the variance of the data regarding the same landmark received on multiple trips can be calculated.

[0362] In some embodiments, each lane of road segment 120 may be associated with a target trajectory and certain landmarks. The target trajectory or multiple such target trajectories may be included in an autonomous vehicle road navigation model, which may later be used by other autonomous vehicles traveling along the same road segment 1200. As vehicles travel along road segment 1200, landmarks identified by vehicles 1205, 1210, 1215, 1220, and 1225 may be recorded in association with the target trajectory. The target trajectory and landmark data may be continuously or periodically updated using new data received from other vehicles in subsequent journeys.

[0363] For autonomous vehicle localization, the disclosed systems and methods may use an Extended Kalman filter. Vehicle localization can be determined based on 3D position data and / or 3D orientation data, through the integration of self-motion to predict the future localization ahead of the vehicle's current localization. Vehicle localization can be corrected or adjusted by image observation of landmarks. For example, when the vehicle detects a landmark within an image captured by a camera, the landmark can be compared with known landmarks stored in the road model or sparse map 800. Known landmarks may have known localizations (e.g., GPS data) along a target trajectory stored in the road model and / or sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark can be estimated. The vehicle's position along the target trajectory can be adjusted based on the distance to the landmark and the landmark's known localization (stored in the road model or sparse map 800). It can be assumed that the location / localization data of landmarks stored in the road model and / or sparse map 800 (e.g., averages from multiple trips) is accurate.

[0364] In some embodiments, the disclosed system can form a closed-loop subsystem, wherein an estimate of the vehicle's six-DOF localization (e.g., three-dimensional position data plus three-dimensional orientation data) can be used for navigation (e.g., maneuvering the wheels of the autonomous vehicle) to bring the autonomous vehicle to a desired point (e.g., 1.3 seconds ahead of a stored location). In turn, data from maneuvering and actual navigation measurements can be used to estimate the six-DOF localization.

[0365] In some embodiments, posts along the road, such as lampposts and power line or cable posts, can be used as landmarks for locating vehicles. Other landmarks (such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along the road segment) can also be used as landmarks for locating vehicles. When posts are used for location, the x-view of the post (i.e., from the vehicle's perspective) can be used instead of the y-view (i.e., the distance to the post) because the base of the post may be obscured, and sometimes they are not on the road surface.

[0366] Figure 23 A navigation system for a vehicle is shown, which can be used for autonomous navigation using a crowdsourced sparse map. For illustration, the vehicle is referred to as vehicle 1205. Figure 23 The vehicle shown can be any other vehicle disclosed herein, including, for example, vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 shown in other embodiments. Figure 12As shown, vehicle 1205 can communicate with server 1230. Vehicle 1205 may include image capture device 122 (e.g., camera 122). Vehicle 1205 may include navigation system 2300 configured to provide navigation guidance for vehicle 1205 while driving on a road (e.g., road segment 1200). Vehicle 1205 may also include other sensors, such as speed sensor 2320 and accelerometer 2325. Speed ​​sensor 2320 may be configured to detect the speed of vehicle 1205. Accelerometer 2325 may be configured to detect acceleration or deceleration of vehicle 1205. Figure 23 The vehicle 1205 shown can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, the vehicle 1205 can also be a non-autonomous, human-controlled vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0367] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 via a communication path 1235. The navigation system 2300 may also include a GPS unit 2310 configured to receive and process GPS signals. The navigation system 2300 may further include at least one processor 2315 configured to process data such as GPS signals, map data from a sparse map 800 (which may be stored on storage devices provided on the vehicle 1205 and / or received from the server 1230), road geometry sensed by a road profile sensor 2330, images captured by a camera 122, and / or an autonomous vehicle road navigation model received from the server 1230. The road profile sensor 2330 may include different types of devices for measuring different types of road profiles (road smoothness, road width, road height, road curves, etc.). For example, the road profile sensor 2330 may include devices that measure the motion of the suspension of the vehicle 2305 to derive a road smoothness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor to measure the distance from the vehicle 1205 to the roadside (e.g., roadside obstacles), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 may include devices configured to measure the vertical height of the road. In some embodiments, the road profile sensor 2330 may include devices configured to measure the curvature of the road. For example, a camera (e.g., camera 122 or another camera) may be used to capture road images displaying the road curvature. The vehicle 1205 may use such images to detect the road curvature.

[0368] At least one processor 2315 may be programmed to receive at least one environmental image associated with vehicle 1205 from camera 122. At least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with vehicle 1205. The navigation information may include a trajectory associated with the vehicle 1205's travel along road segment 1200. At least one processor 2315 may determine the trajectory based on the motion of camera 122 (and therefore the motion of the vehicle), such as three-dimensional translation and three-dimensional rotation. In some embodiments, at least one processor 2315 may determine the translation and rotation of camera 122 based on the analysis of multiple images acquired by camera 122. In some embodiments, the navigation information may include lane assignment information (e.g., lanes where vehicle 1205 travels along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 may be used by server 1230 to generate and / or update an autonomous vehicle road navigation model, which may be transmitted back from server 1230 to vehicle 1205 for providing autonomous navigation guidance for vehicle 1205.

[0369] At least one processor 2315 may also be programmed to transmit navigation information from vehicle 1205 to server 1230. In some embodiments, the navigation information may be transmitted to server 1230 along with road information. Road positioning information may include at least one of GPS signals received by GPS unit 2310, landmark information, road geometry, lane information, etc. At least one processor 2315 may receive an autonomous vehicle road navigation model or a portion thereof from server 1230. The autonomous vehicle road navigation model received from server 1230 may include at least one update based on the navigation information transmitted from vehicle 1205 to server 1230. The model portion transmitted from server 1230 to vehicle 1205 may include an updated portion of the model. At least one processor 2315 may, based on the received autonomous vehicle road navigation model or the updated portion of the model, induce navigation maneuvers (e.g., maneuvers such as turning, braking, acceleration, overtaking another vehicle, etc.) of at least one vehicle 1205.

[0370] At least one processor 2315 may be configured to communicate with various sensors and components included in the vehicle 1205, including a communication unit 1705, a GPS unit 2315, a camera 122, a speed sensor 2320, an accelerometer 2325, and a road profile sensor 2330. At least one processor 2315 may collect information or data from the various sensors and components and transmit the information or data to the server 1230 via the communication unit 2305. Alternatively or additionally, the various sensors or components of the vehicle 1205 may also communicate with the server 1230 and transmit data or information collected by the sensors or components to the server 1230.

[0371] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can communicate with each other and share navigation information, such that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 can use crowdsourcing (e.g., based on information shared by other vehicles) to generate an autonomous vehicle road navigation model. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can share navigation information with each other, and each vehicle can update the autonomous vehicle road navigation model provided in its own vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) can be used as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) can perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle can communicate with other vehicles and receive navigation information from other vehicles. At least one processor 2315 of the central vehicle can generate an autonomous vehicle road navigation model or an update to the model based on shared information received from other vehicles. The at least one processor 2315 of the central vehicle can transmit the autonomous vehicle road navigation model or the update to other vehicles for use in providing autonomous navigation guidance.

[0372] Figure 24 This is a flowchart illustrating an exemplary process 2400 for generating a road navigation model for autonomous vehicle navigation. Process 2400 may be executed by a server 1230 or a processor 2315 included in a central vehicle. In some embodiments, process 2400 may be used to aggregate vehicle navigation information to provide an autonomous vehicle road navigation model or an update to the model.

[0373] Processing 2400 may include receiving navigation information from multiple vehicles by the server (step 2405). For example, server 1230 may receive navigation information from vehicles 1205, 1210, 1215, 1220, and 1225. Navigation information from multiple vehicles traveling along a common road segment (e.g., vehicles 1205, 1210, 1215, 1220, and 1225) may be associated with that common road segment (e.g., road segment 1200).

[0374] Processing 2400 may also include storing navigation information associated with public road segments by the server (step 2410). For example, server 1230 may store the navigation information in storage device 2010 and / or memory 2015.

[0375] Processing 2400 may further include generating at least a portion of an autonomous vehicle road navigation model for a public road segment by the server based on navigation information from multiple vehicles (step 2415). The autonomous vehicle road navigation model for the public road segment may include at least one line representation of road surface features extending along the public road segment, and each line representation may represent a path along the public road segment substantially corresponding to the road surface features. For example, road surface features may include road edges or lane markings. Furthermore, road surface features may be identified through image analysis of multiple images acquired as multiple vehicles traverse the public road segment. For example, server 1230 may generate at least a portion of the autonomous vehicle road navigation model for the public road segment 1200 based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 traveling on the public road segment 1200.

[0376] In some embodiments, the autonomous vehicle road navigation model can be configured to be overlaid on a map, image, or satellite image. For example, the model can be overlaid on a surface composed of, for example, maps, images, or satellite imagery. Traditional navigation services such as Maps and Waze provide maps or images on them.

[0377] In some embodiments, at least a portion of generating an autonomous vehicle road navigation model may include identifying multiple landmarks associated with a public road segment based on image analysis of multiple images. In some aspects, this analysis may include accepting a potential landmark when the ratio of images in which a landmark actually appears to images in which a landmark does not appear exceeds a threshold, and / or rejecting a potential landmark when the ratio of images in which a landmark does not appear to images in which a landmark does appear exceeds a threshold. For example, if a potential landmark appears in data from vehicle 1210 but not in data from vehicles 1205, 1215, 1220, and 1225, the system may determine that a 1:5 ratio is below the threshold for accepting a potential landmark. As another example, if a potential landmark appears in data from vehicles 1205, 1215, 1220, and 1225 but not in data from vehicle 1210, the system may determine that a 4:5 ratio is above the threshold for accepting a potential landmark.

[0378] Processing 2400 may further include the server distributing an autonomous vehicle road navigation model to one or more autonomous vehicles for autonomous navigation along a public road segment (step 2420). For example, server 1230 may distribute the autonomous vehicle road navigation model or a portion thereof (e.g., an update) to vehicles 1205, 1210, 1215, 1220, and 1225, or any other vehicle later traveling on road segment 1200, for use by vehicles autonomously navigating along road segment 1200.

[0379] Processing 2400 may include additional operations or steps. For example, generating an autonomous vehicle road navigation model may include clustering vehicle trajectories received along road segment 1200 from vehicles 1205, 1210, 1215, 1220, and 1225 into multiple clusters, and / or aligning data received from vehicles 1205, 1210, and 1215. See below for reference. Figure 29 As discussed in further detail, process 2400 may include determining a target trajectory along public road segment 1200 by averaging the clustered vehicle trajectories in each cluster. Process 2400 may also include associating the target trajectory with a single lane of public road segment 1200. Process 2400 may include determining a three-dimensional spline to represent the target trajectory in the autonomous vehicle road navigation model.

[0380] Navigation using crowdsourced sparse maps

[0381] As described above, server 1230 can distribute the generated road navigation model to one or more vehicles. As detailed above, the road navigation model can be included in a sparse map. According to embodiments of this disclosure, one or more vehicles can be configured to perform autonomous navigation using a distributed sparse map.

[0382] Figure 25 This is an exemplary functional block diagram of memory 140 and / or 150, which can be stored / programmed with instructions to perform one or more operations consistent with the disclosed embodiments. Although memory 140 is referred to below, those skilled in the art will recognize that instructions can be stored in memory 140 and / or 150.

[0383] like Figure 25 As shown, memory 140 may store sparse map module 2502, image analysis module 2504, road feature module 2506, and navigation response module 2508. The disclosed embodiments are not limited to any particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of the modules 2502, 2504, 2506, and 2508, which are included in memory 140. Those skilled in the art will understand that the reference numerals in the following discussion of processing unit 110 may individually or collectively refer to application processor 180 and image processor 190. Therefore, any of the following processing steps may be performed by one or more processing devices.

[0384] In one embodiment, the sparse map module 2502 may store instructions to receive (and in some embodiments, store) a sparse map distributed by the server 1230 when executed by the processing unit 110. The sparse map module 2502 may receive the entire sparse map in a single communication, or it may receive a sub-section of the sparse map corresponding to the area in which the vehicle is operating.

[0385] In one embodiment, the image analysis module 2504 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform analysis on one or more images acquired by one of the image capture devices 122, 124, and 126. As described in further detail below, the image analysis module 2504 may analyze one or more images to determine the current position of the vehicle.

[0386] In one embodiment, the road feature module 2506 may store instructions that, when executed by the processing unit 110, identify road features in a sparse map received from one or more images acquired by the sparse map module 2502 and / or by one of the image capture devices 122, 124 and 126.

[0387] In one embodiment, the navigation response module 2508 may store software executable by the processing unit 110 to determine the desired navigation response based on data derived from the execution of the sparse map module 2502, the image analysis module 2504, and / or the road feature module 2506.

[0388] Furthermore, any module disclosed herein (e.g., modules 2502, 2504, and 2506) can implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems.

[0389] Figure 26 This is a flowchart illustrating an exemplary process 2600 for autonomously navigating a vehicle along a road segment. Process 2600 may be executed by a processor 2315 included in a navigation system 2300.

[0390] Processing 2600 may include receiving a sparse map model (step 2605). For example, processor 2315 may receive a sparse map from server 1230. In some embodiments, the sparse map model may include at least one line representation of road surface features extending along a road segment, and each line representation may represent a path along a road segment substantially corresponding to the road surface features. For example, road features may include road edges or lane markings.

[0391] Processing 2600 may further include receiving at least one image representing the vehicle's environment from a camera (step 2610). For example, processor 2315 may receive at least one image from camera 122. Camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200.

[0392] Processing 2600 may further include analyzing the sparse map model and at least one image received from the camera (step 2615). For example, the analysis of the sparse map model and at least one image received from the camera may include determining the current position of the vehicle relative to a longitudinal position represented by at least one line of road surface features extending along the road segment. In some embodiments, this determination may be based on the identification of at least one recognized landmark in at least one image. In some embodiments, processing 2600 may further include determining an estimated offset based on the expected position of the vehicle relative to the longitudinal position and the current position of the vehicle relative to the longitudinal position.

[0393] Processing 2600 may further include determining the vehicle's autonomous navigation response based on analysis of a sparse map model and at least one image received from a camera (step 2620). In embodiments where processor 2315 determines an estimated offset, the autonomous navigation response may be further based on the estimated offset. For example, if processor 2315 determines that the vehicle is offset 1 meter to the left from at least one line representation, processor 2315 may cause the vehicle to shift to the right (e.g., by changing the direction of the wheels). As another example, if processor 2315 determines that an identified landmark deviates from a desired position, processor 2315 may cause the vehicle to shift to move the identified landmark to its desired position. Therefore, in some embodiments, processing 2600 may further include adjusting the vehicle's steering system based on the autonomous navigation response.

[0394] Align crowdsourced map data

[0395] As mentioned above, crowdsourced sparse maps can be generated using data from multiple trips along a common road segment. This data can be aligned to generate a coherent sparse map. (As discussed above...) Figure 14 As discussed, generating a map skeleton may be insufficient to construct splines for navigation. Therefore, embodiments of this disclosure may allow for the alignment of data from multiple trip crowdsourcing.

[0396] Figure 27 A block diagram of a memory 2015 is shown, which can store computer code or instructions for performing one or more operations to generate a road navigation model for autonomous vehicle navigation. Figure 21As shown, memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, memory 2015 may include trip data receiving module 2705 and longitudinal alignment module 2710. Processor 2020 may execute instructions stored in any of the modules 2705 and 2710 included in memory 2015.

[0397] The trip data receiving module 2705 can store instructions that, when executed by the processor 2020, can control the communication device 2005 to receive trip data from one or more vehicles (e.g., 1205, 1210, 1215, 1220, and 1225).

[0398] The longitudinal alignment module 2710 may store instructions, when executed by the processor 2020, to align data received by the trip data receiving module 2705 when the data is related to a common road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, the longitudinal alignment module 2710 may align data along segments, which may allow for easier optimization of the error correction required for alignment. In some embodiments, the longitudinal alignment module 2710 may further score each segment alignment with a confidence score.

[0399] Figure 28A Examples of raw positioning data from four different trips are shown. Figure 28A In the example, the raw data from the first pass is depicted as a series of stars, the raw data from the second pass is depicted as a series of filled squares, the raw data from the third pass is depicted as a series of hollow cubes, and the raw data from the fourth pass is described as a series of hollow circles. As those skilled in the art will recognize, the shape is merely a description of the data itself, which can be stored as a series of coordinates, whether local or global.

[0400] As in Figure 28A As can be seen, the journey can occur along the same road in different lanes (represented by line 1200). Furthermore, Figure 28A The travel data described may include discrepancies due to errors in location measurements (e.g., GPS), and may contain missing data points due to systematic errors. Finally, Figure 28A It also describes how each journey can begin and end at different points within the section along the road.

[0401] Figure 28B Another example of raw location data from five different trips is shown. Figure 28BIn the example, the raw data from the first pass is depicted as a series of filled squares, the raw data from the second pass is depicted as a series of hollow squares, the raw data from the third pass is depicted as a series of hollow circles, the raw data from the fourth pass is depicted as a series of stars, and the raw data from the fifth pass is depicted as a series of triangles. As those skilled in the art will recognize, the shape is merely a description of the data itself, which can be stored as a series of coordinates, whether local or global.

[0402] Figure 28B As shown Figure 28A The similarity attributes of the trip data shown. Figure 28B The text further describes how intersections can be detected by tracking the movement of the fifth stroke away from other strokes. For example, Figure 28B The example data in the diagram can show that the exit ramp exists on the right side of the road (represented by line 1200). Figure 28B It also describes how added lanes can be detected if data begins on a new section of the road. For example, Figure 28B The fourth trip in the example data can suggest adding a fourth lane to the road shortly after the detected exit ramp.

[0403] Figure 28C An example of raw positioning data with target trajectories is shown. For example, first travel data (represented by triangles) and second travel data (represented by hollow squares) have associated target trajectories 2810. Similarly, third travel data (represented by hollow circles) has associated target trajectories 2820, and fourth travel data (represented by filled squares) has associated target trajectories 2830.

[0404] In some embodiments, trip data can be reconstructed such that a target trajectory is associated with each trip lane, such as... Figure 28C As shown. If the segments of the travel data are properly aligned, such a target trajectory can be generated from one or more simple smooth line models. The processing 2900 discussed below is an example of proper segment alignment.

[0405] Figure 29 This is a flowchart illustrating an exemplary process 2900 for determining a line representation of road surface features extending along a road segment. The line representation of road surface features can be configured for use in autonomous vehicle navigation, for example, using... Figure 26 Processing 2600. Processing 2900 can be performed by server 1230 or processor 2315 included in the central vehicle.

[0406] Processing 2900 may include receiving, from the server, a first set of travel data including location information associated with road surface features (step 2905). The location information may be determined based on the analysis of images of the road segment, and the road surface features may include road edges or lane markings.

[0407] Processing 2900 may further include receiving a second set of travel data (step 2910) from the server, which includes location information associated with road surface features. Similar to step 2905, the location information may be determined based on analysis of images of the road segment, and the road surface features may include road edges or lane markings. Steps 2905 and 2910 may be performed simultaneously, or there may be a time interval between steps 2905 and 2910, depending on when the first and second sets of travel data are collected.

[0408] Processing 2900 may further include segmenting the first set of travel data into first travel segments and segmenting the second set of travel data into second travel segments (step 2915). Segments may be defined by data size or travel length. The size or length defining a segment may be predefined as one or more values, or may be updated using neural networks or other machine learning techniques. For example, the length of a segment may be preset to always 1 km, or it may be preset to 1 km when traveling along a road at a speed greater than 30 km / h, and to 0.8 km when traveling along a road at a speed not less than 30 km / h. Alternatively or simultaneously, machine learning analysis may optimize the size or length of the segments based on multiple dependent variables such as driving conditions, driving speed, etc. Furthermore, in some embodiments, the path may be defined by data size and travel length.

[0409] In some embodiments, the first set of data and the second set of data may include location information and may be associated with multiple landmarks. In such an embodiment, processing 2900 may further include determining whether to accept or reject landmarks within the set of data based on one or more thresholds, as referenced above. Figure 19 As stated above.

[0410] Processing 2900 may include longitudinally aligning a first set of travel data with a second set of travel data within a corresponding segment (step 2920). For example, longitudinal alignment may include selecting either the first or second set of data as a reference data set, and then shifting and / or elastically stretching the other set of data to align segments within the set. In some embodiments, aligning multiple sets of data may further include aligning GPS data included in two sets and associated with segments. For example, the connectivity between segments having sets may be adjusted to more closely align with GPS data. However, in such embodiments, adjustments must be limited to prevent constraints on the GPS data from disrupting the alignment. For example, GPS data is not three-dimensional, and therefore, when projected onto a three-dimensional representation of a road, unnatural distortions and slopes may occur.

[0411] Processing 2900 may further include determining a line representation of road features based on longitudinally aligned first and second travel data in the first and second travel segments (step 2925). For example, a smooth line model on the aligned data can be used to construct the line representation. In some embodiments, determining the line representation may include aligning the line representation with global coordinates based on GPS data acquired as part of at least one of a first set of travel data or a second set of travel data. For example, the first set of data and / or the second set of data can be represented using local coordinates; however, using a smooth line model requires both sets to have the same coordinate axes. Therefore, in some respects, the first set of data and / or the second set of data can be adjusted to have the same coordinate axes as each other.

[0412] In some embodiments, determining a line representation may include determining and applying a set of average transformations. For example, each average transformation may be a transformation determined based on link data from a first set of travel data spanning sequential segments and link data from a second set of travel data spanning sequential segments.

[0413] Process 2900 may include additional operations or steps. For example, process 2900 may further include overlaying a line representation of road surface features onto at least one geographic image. For example, the geographic image may be a satellite image. As another example, process 2900 may further include filtering out erroneous landmark information and / or travel data based on the determined line representation and longitudinal alignment. This filtering may conceptually be similar to landmarks that may be rejected based on one or more thresholds, as referenced above. Figure 19 As stated above.

[0414] Crowdsourced road information

[0415] In addition to crowdsourcing landmarks and line representations to generate sparse maps, the disclosed systems and methods can also crowdsource road surface information. Therefore, road conditions can be correlated with sparse maps used for navigation of autonomous vehicles. Figure 1 It is stored and / or stored within a sparse map.

[0416] Figure 30 This is an exemplary functional block diagram of memory 140 and / or 150, which can be stored / programmed with instructions to perform one or more operations consistent with the disclosed embodiments. Although memory 140 is referred to below, those skilled in the art will recognize that instructions can be stored in memory 140 and / or 150.

[0417] like Figure 30 As shown, memory 140 may store image receiving module 3002, road feature module 3004, positioning determination module 3006, and navigation response module 3008. The disclosed embodiments are not limited to any particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of the modules 3002, 3004, 3006, and 3008, which are included in memory 140. Those skilled in the art will understand that the reference numerals in the following discussion of processing unit 110 may individually or collectively refer to application processor 180 and image processor 190. Therefore, any steps of the following processes may be performed by one or more processing devices.

[0418] In one embodiment, the image receiving module 3002 may store instructions that, when executed by the processing unit 110, receive (and in some embodiments, store) an image acquired by one of the image capturing devices 122, 124, and 126.

[0419] In one embodiment, the road surface feature module 3004 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform analysis on one or more images acquired by one of the image capture devices 122, 124, and 126 and identify road surface features. For example, road surface features may include road edges or lane markings.

[0420] In one embodiment, the positioning determination module 3006 may store instructions (such as GPS software or visual ranging software) that receive vehicle-related positioning information when executed by the processing unit 110. For example, the positioning determination module 3006 may receive GPS data and / or self-motion data including the vehicle's position. In some embodiments, the positioning determination module 3006 may use the received information to calculate one or more locations. For example, the positioning determination module 3006 may receive one or more images acquired by one of the image capture devices 122, 124, and 126 and use image analysis to determine the vehicle's location.

[0421] In one embodiment, the navigation response module 3008 may store software executable by the processing unit 110 to determine the desired navigation response based on data derived from the execution of the image receiving module 3002, the road feature module 3004, and / or the positioning determination module 3006.

[0422] Furthermore, any module disclosed herein (e.g., modules 3002, 3004, and 3006) can implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems.

[0423] Figure 31 This is a flowchart illustrating an exemplary process 3100 for collecting road surface information for a road segment. Process 3100 may be executed by a processor 2315 included in the navigation system 2300.

[0424] Processing 3100 may include receiving at least one image representing a portion of the road segment from a camera (step 3105). For example, processor 2315 may receive at least one image from camera 122. Camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200.

[0425] Processing 3100 may further include identifying at least one road surface feature along the portion of the road segment in the at least one image (step 3010). For example, the at least one road surface feature may include a road edge or may include lane markings.

[0426] Processing 3100 may also include determining multiple locations associated with road surface features based on the vehicle's local coordinate system (step 3115). For example, processor 2315 may use automatic motion data and / or GPS data to determine multiple locations.

[0427] Processing 3100 may also include transmitting the determined multiple locations from the vehicle to the server (step 3120). For example, the determined locations may be configured such that the server can determine a line representation of road surface features extending along the road segment, as referenced above. Figure 29 As described. In some embodiments, a line representation may represent a path along a road segment that substantially corresponds to road surface features.

[0428] Processing 3100 may include additional operations or steps. For example, processing 3100 may further include receiving a line representation from a server. In this example, processor 2315 may receive the line representation as part of a received sparse map, for example, according to... Figure 24 Processing 2400 and / or Figure 26Processing 2600. As another example, processing 2900 may further include: overlaying a line representation of road surface features on at least one geographic image. For example, the geographic image may be a satellite image.

[0429] As explained above regarding the crowdsourcing of landmarks, in some embodiments, the server can implement selection criteria for deciding whether to accept or reject potential road features received from the vehicle. For example, the server may accept a road feature when the ratio of the location set in which road features actually appear to the location set in which road features do not appear exceeds a threshold, and / or reject a potential road feature when the ratio of the location set in which road features do not appear to the location set in which road features actually appear exceeds a threshold.

[0430] Vehicle positioning

[0431] In some embodiments, the disclosed systems and methods can use sparse maps for autonomous vehicle navigation. Specifically, sparse maps can be used for autonomous vehicle navigation along road segments. For example, sparse maps can provide sufficient information for navigating autonomous vehicles without requiring the storage and / or updating of large amounts of data. As discussed further in detail below, autonomous vehicles can use sparse maps to navigate one or more roads based on one or more stored trajectories.

[0432] Autonomous lane positioning using lane markings

[0433] As mentioned above, autonomous vehicles can navigate based on dead reckoning between landmarks. However, errors can accumulate during navigation using dead reckoning, so the position determination relative to the target trajectory may become increasingly inaccurate over time. As explained below, lane markings can be used for vehicle positioning during landmark intervals, which can minimize the accumulation of dead reckoning errors during navigation.

[0434] For example, a spline can be represented as shown in Formula 1 below:

[0435]

[0436] In the example of Formula 1, B(u) represents the curve of the spline, b k (u) is a basis function, and P (k) This represents a control point. Control points can be transformed into local coordinates using, for example, the following formula 2:

[0437] P l (k) =R T (P (k) -T)

[0438] Formula 2

[0439] In the example of Formula 2, P l (k) The control point P represents the transformation to local coordinates. (k) R is the rotation matrix, which can be inferred, for example, from the vehicle's heading. T Let T denote the transpose of the rotation matrix, and let T denote the position of the vehicle.

[0440] In some embodiments, the local curve representing the path of the vehicle can be determined using the following formula 3:

[0441] H i (u)=y i B lz (u)-fB ly (u)=0

[0442] Formula 3

[0443] In the example of Formula 3, f is the focal length of the camera, and B lz B ly and B lx This represents the component of curve B in the local coordinate system. The derivation of H can be expressed by the following formula 4:

[0444] H′(u)=y i B′ lz (u)-fB′ ly (u)

[0445] Formula 4

[0446] Based on Equation 1, B′ in Equation 4 l This can be further expressed by the following formula 5:

[0447]

[0448] For example, Equation 5 can be solved using a Newton-Raphson based solver. In some respects, the solver can run five or fewer steps. To solve for x, in some embodiments, the following Equation 6 can be used:

[0449]

[0450] In some embodiments, the derivative of the trajectory can be used. For example, the derivative can be given by the following formula 7:

[0451]

[0452] In the example of Formula 7, X j It can represent state components, such as the position of a vehicle. In some respects, j can represent an integer between 1 and 6.

[0453] In order to solve Equation 7, in some embodiments, the following Equation 8 can be used:

[0454]

[0455] To solve Equation 8, in some embodiments, implicit differentiation can be used to obtain the following Equations 9 and 10:

[0456]

[0457] Using Equations 9 and 10, the derivative of the trajectory can be obtained. Then, in some embodiments, an extended Kalman filter can be used to locate lane measurements. By locating lane measurements, as described above, lane markings can be used to minimize the accumulation of errors during navigation via dead reckoning. The use of lane markings is referenced below. Figure 32-35 Further detailed description.

[0458] Figure 32 This is an exemplary functional block diagram of memory 140 and / or 150, which can be stored / programmed with instructions to perform one or more operations consistent with the disclosed embodiments. Although memory 140 is referred to below, those skilled in the art will recognize that instructions can be stored in memory 140 and / or 150.

[0459] like Figure 32 As shown, memory 140 may store position determination module 3202, image analysis module 3204, distance determination module 3206, and offset determination module 3208. The disclosed embodiments are not limited to any particular configuration of memory 140. Application processor 180 and / or image processor 190 may execute instructions stored in any of the modules 3202, 3204, 3206, and 3208, which are included in memory 140. Those skilled in the art will understand that reference numerals in the following discussion of processing unit 110 may individually or collectively refer to application processor 180 and image processor 190. Therefore, any steps of the following processes may be performed by one or more processing devices.

[0460] In one embodiment, the location determination module 3202 may store instructions (such as GPS software or visual ranging software) that receive vehicle-related positioning information when executed by the processing unit 110. For example, the location determination module 3202 may receive GPS data and / or automatic motion data including the vehicle's position. In some embodiments, the location determination module 3202 may use the received information to calculate one or more locations. For example, the location determination module 3202 may receive one or more images acquired by one of the image capture devices 122, 124, and 126 and use image analysis to determine the vehicle's location.

[0461] The location determination module 3202 can also use other navigation sensors to determine the vehicle's position. For example, a speed sensor or accelerometer can send information to the location determination module 3202 to calculate the vehicle's position.

[0462] In one embodiment, the image analysis module 3204 may store instructions (su...

Claims

1. A method for generating a road navigation model for autonomous vehicle navigation, the method comprising: The server receives navigation information from multiple vehicles, including: The navigation information from multiple vehicles is associated with public road sections; The navigation information from multiple vehicles includes first and second location information of road surface features extending along the public road segment; and The first location information and the second location information have been determined based on the analysis of multiple images acquired when the multiple vehicles travel through the public road section; The server stores the navigation information associated with the public road segment; Based on the navigation information from multiple vehicles, the server generates at least a portion of an autonomous vehicle road navigation model for the public road segment, wherein the autonomous vehicle road navigation model for the public road segment includes at least one line representation of road surface features extending along the public road segment, wherein: Each line represents a path along the common road segment that substantially corresponds to the road surface features; Each line representation is constructed by aligning the first position information and the second position information; and The road surface features are identified through image analysis of multiple images acquired when the multiple vehicles travel through the public road section; and The server distributes the autonomous vehicle road navigation model to one or more autonomous vehicles for use in autonomous navigation along the public road segment.

2. The method as described in claim 1, wherein, The autonomous vehicle road navigation model is configured to be overlaid on a map, image, or satellite image.

3. The method as described in claim 1, wherein, Several road features include road edges or lane markings.

4. The method of claim 1, wherein, At least a portion of generating the autonomous vehicle road navigation model includes: identifying multiple landmarks associated with the public road segment based on image analysis of the multiple images.

5. The method of claim 4, wherein, At least a portion of generating the autonomous vehicle road navigation model also includes: accepting potential landmarks when the ratio of images in which the landmarks actually appear to images in which the landmarks do not appear exceeds a threshold.

6. The method of claim 4, wherein, At least a portion of generating the autonomous vehicle road navigation model also includes: rejecting potential landmarks when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

7. A system for generating a road navigation model for use in autonomous vehicle navigation, the system comprising: At least one network interface; At least one non-transitory storage medium; as well as At least one processing device, wherein the at least one processing device is configured to: The network interface is used to receive navigation information from multiple vehicles, wherein: The navigation information from multiple vehicles is associated with public road sections; The navigation information from multiple vehicles includes first and second location information of road surface features extending along the public road segment; and The first location information and the second location information have been determined based on the analysis of multiple images acquired when the multiple vehicles travel through the public road section; Navigation information associated with the public road segment is stored on the non-temporary storage medium; Based on the navigation information from multiple vehicles, at least a portion of an autonomous vehicle road navigation model for the public road segment is generated, wherein the autonomous vehicle road navigation model for the public road segment includes at least one line representation of road surface features extending along the public road segment, wherein: Each line represents a path along the common road segment that substantially corresponds to the road surface features; Each line representation is constructed by aligning the first position information and the second position information; and The road surface features are identified through image analysis of multiple images acquired when the multiple vehicles travel through the public road section; and The network interface is used to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles for use in autonomous navigation along public road segments.

8. The system of claim 7, wherein, The autonomous vehicle road navigation model is configured to be overlaid on a map, image, or satellite image.

9. The system of claim 7, wherein, Several road features include road edges or lane markings.

10. The system of claim 7, wherein, At least a portion of generating the autonomous vehicle road navigation model includes: identifying multiple landmarks associated with the public road segment based on image analysis of the multiple images.

11. The system of claim 10, wherein, At least a portion of generating the autonomous vehicle road navigation model also includes: accepting potential landmarks when the ratio of images in which the landmarks actually appear to images in which the landmarks do not appear exceeds a threshold.

12. The system of claim 10, wherein, At least a portion of generating the autonomous vehicle road navigation model also includes: rejecting potential landmarks when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

13. A non-transitory computer-readable medium storing instructions that, when executed by at least one processing device, cause a server to: Receives navigation information from multiple vehicles, including: The navigation information from multiple vehicles is associated with public road sections; The navigation information from multiple vehicles includes first and second location information of road surface features extending along the public road segment; as well as The first location information and the second location information have been determined based on the analysis of multiple images acquired when the multiple vehicles travel through the public road section; Store navigation information associated with the public road segment; Based on the navigation information from multiple vehicles, at least a portion of an autonomous vehicle road navigation model for the public road segment is generated, wherein the autonomous vehicle road navigation model for the public road segment includes at least one line representation of road surface features extending along the public road segment, wherein: Each line represents a path along the common road segment that substantially corresponds to the road surface features; Each line representation is constructed by aligning the first position information and the second position information; and The road surface features are identified through image analysis of multiple images acquired when the multiple vehicles travel through the public road section; and The autonomous vehicle road navigation model is distributed to one or more autonomous vehicles for use in autonomous navigation along public road segments.

14. The non-transitory computer-readable medium of claim 13, wherein, The autonomous vehicle road navigation model is configured to be overlaid on a map, image, or satellite image.

15. The non-transitory computer-readable medium of claim 13, wherein, Several road features include road edges or lane markings.

16. The non-transitory computer-readable medium of claim 13, wherein, Instructions for generating at least a portion of the autonomous vehicle road navigation model include: instructions for identifying multiple landmarks associated with the public road segment based on image analysis of the multiple images.

17. The non-transitory computer-readable medium of claim 16, wherein, The instructions for generating at least a portion of the autonomous vehicle road navigation model further include: accepting instructions for potential landmarks when the ratio of images in which the landmarks actually appear to images in which the landmarks do not appear exceeds a threshold.

18. The non-transitory computer-readable medium of claim 16, wherein, The instructions for generating at least a portion of the autonomous vehicle road navigation model further include: rejecting instructions for potential landmarks when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

19. The method of claim 1, wherein, Each line representation includes at least one of spline, polynomial, or curve representations.

20. The method of claim 19, wherein, At least a portion of generating an autonomous vehicle road navigation model includes applying a parabolic spline algorithm to the received navigation information to determine the at least one line representation.

21. The method of claim 19, wherein, At least a portion of generating an autonomous vehicle road navigation model includes: determining coefficients from received navigation information to store as the at least one line representation.

Images