Lane Mapping and Navigation

Abstract

To provide systems and methods for mapping lanes for use in vehicle navigation.SOLUTION: At least one processing device may be programmed to receive navigation information from a first vehicle and a second vehicle that have navigated along a road segment including a lane split feature; receive at least one image associated with the road segment; determine, from first navigation information, a first actual trajectory of the first vehicle and a second actual trajectory of the second vehicle; determine deviation between the first actual trajectory and the second actual trajectory; determine, on the basis of analysis of the at least one image, the deviation between the first actual trajectory and the second actual trajectory indicates the lane split feature; and update a vehicle road navigation model to include a first target trajectory and a second target trajectory that branches from the first target trajectory after the lane split feature.SELECTED DRAWING: Figure 36

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of priority to U.S. Provisional Application No. 62 / 771,335, filed November 26, 2018, U.S. Provisional Application No. 62 / 795,868, filed January 23, 2019, and U.S. Provisional Application No. 62 / 800,845, filed February 4, 2019. All of the above applications are incorporated herein by reference in their entirety.

[0002] FIELD OF THE DISCLOSURE This disclosure relates generally to autonomous vehicle navigation. In particular, this disclosure relates to systems and methods for mapping lane splits or lane merging and navigating using the mapped lane splits or lane merging. [Background technology]

[0003] As technology continues to evolve, the goal of fully autonomous vehicles capable of navigating roads becomes more realistic. An autonomous vehicle may need to consider various factors and, based on those factors, make appropriate decisions to safely and accurately reach its intended destination. For example, an autonomous vehicle may need to process and interpret visual information (e.g., information captured from a camera) and may also use information obtained from other sources (e.g., a GPS device, a speed sensor, an accelerometer, a suspension sensor, etc.). At the same time, to navigate to its destination, an autonomous vehicle may need to identify its location within a particular road (e.g., a particular lane within 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 interchanges. Utilizing and interpreting the vast amount of information collected by an autonomous vehicle as it travels to its destination poses many design challenges. The vast amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that an autonomous vehicle may need to analyze, access, and / or store poses challenges that can limit or adversely affect autonomous navigation in practice. Furthermore, if an autonomous vehicle relies on traditional mapping techniques to navigate, the vast amount of data required to store and update maps poses daunting challenges.

[0004] In addition to collecting data to update the map, autonomous vehicles must be able to use the map for navigation, so the size and detail of the map, as well as its construction and transmission, must be optimized. Summary of the Invention

[0005] Embodiments according to the present disclosure provide systems and methods for autonomous vehicle navigation. The disclosed embodiments may use cameras to provide autonomous vehicle navigation features. For example, according to embodiments of the present disclosure, the disclosed systems may include one, two, or more cameras that monitor the vehicle's environment. The disclosed systems may provide navigation responses, for example, based on analysis of images captured by one or more of the cameras.

[0006] In one embodiment, a system for navigating a host vehicle is disclosed. The system includes receiving first navigation information from a first vehicle that navigated along a road segment, the road segment including a lane split feature, the road segment including at least a first driving lane before the lane split feature transitioning into at least a second driving lane and a third driving lane after the lane split feature; receiving second navigation information from a second vehicle that navigated along the road segment; receiving at least one image associated with the road segment; determining from the first navigation information a first actual trajectory of the first vehicle along the first and second driving lanes of the road segment; and determining from the second navigation information a first actual trajectory of the first vehicle along the first and second driving lanes of the road segment. The system may include at least one processor programmed to: determine a second actual trajectory of the second vehicle along the first lane and a third travel lane; determine a deviation between the first actual trajectory and the second actual trajectory; determine, based on analysis of the at least one image, that the deviation between the first actual trajectory and the second actual trajectory is indicative of the presence of a lane splitting feature in the road segment; and update the vehicle road navigation model to include a first target trajectory corresponding to the first travel lane before the lane splitting feature and extending along the second travel lane after the lane splitting feature, and a second target trajectory diverging from the first target trajectory and extending along the third travel lane after the lane splitting feature.

[0007] In one embodiment, a method for mapping lane splits for use in vehicle navigation is disclosed, the method including receiving first navigation information from a first vehicle that navigated along a road segment, the road segment including a lane split feature, the road segment including at least a first travel lane before the lane split feature transitioning into at least a second travel lane and a third travel lane after the lane split feature, receiving second navigation information from a second vehicle that navigated along the road segment, receiving at least one image associated with the road segment, determining from the first navigation information a first actual trajectory of the first vehicle along the first travel lane and the second travel lane of the road segment, and calculating from the second navigation information a first actual trajectory of the first vehicle along the first travel lane and the second travel lane of the road segment. The method may include determining a second actual trajectory of the second vehicle along a first driving lane and a third driving lane of the road segment; determining a deviation between the first actual trajectory and the second actual trajectory; determining, based on analysis of at least one image, that the deviation between the first actual trajectory and the second actual trajectory indicates the presence of a lane splitting feature in the road segment; and updating the vehicle road navigation model to include a first target trajectory corresponding to the first driving lane before the lane splitting feature and extending along the second driving lane after the lane splitting feature, and a second target trajectory diverging from the first target trajectory and extending along the third driving lane after the lane splitting feature.

[0008] In one embodiment, a system for navigating a host vehicle along a road segment is disclosed. The system may include at least one processing device programmed to: receive, from a server-based system, a vehicle road navigation model, the vehicle road navigation model including a first target trajectory corresponding to a first driving lane along the road segment prior to a lane splitting feature associated with the road segment and extending along a second driving lane of the road segment after the lane splitting feature, the vehicle road navigation model also including a second target trajectory diverging from the first target trajectory and extending along a third driving lane of the road segment after the lane splitting feature; receive information indicative of an environment of the host vehicle; determine, based on the information indicative of the environment of the host vehicle, whether to navigate the host vehicle along the first target trajectory or the second target trajectory; and determine a navigation operation to navigate the host vehicle along the determined target trajectory.

[0009] In one embodiment, a method for navigating a host vehicle along a road segment is disclosed. The method may include receiving, from a server-based system, a vehicle road navigation model, the vehicle road navigation model including a first target trajectory corresponding to a first driving lane along the road segment prior to a lane splitting feature associated with the road segment and extending along a second driving lane of the road segment after the lane splitting feature, the vehicle road navigation model also including a second target trajectory diverging from the first target trajectory and extending along a third driving lane of the road segment after the lane splitting feature; receiving information indicative of an environment of the host vehicle; determining, based on the information indicative of the environment of the host vehicle, whether to navigate the host vehicle along the first target trajectory or the second target trajectory; and determining a navigation operation to navigate the host vehicle along the determined target trajectory.

[0010] In one embodiment, a system for mapping lane merges for use in vehicle navigation includes receiving first navigation information from a first vehicle that navigated along a road segment, the road segment including a lane merge feature, the road segment including at least a first travel lane and a second travel lane before the lane merge feature that transition into a third travel lane after the lane merge feature; receiving second navigation information from a second vehicle that navigated along the road segment; receiving at least one image associated with the road segment; determining from the first navigation information a first actual trajectory of the first vehicle along the first travel lane and the third travel lane of the road segment; and The vehicle may include at least one processor programmed to: determine a second actual trajectory of the second vehicle along a second travel lane and a third travel lane of the road segment from the image information; determine convergence between the first actual trajectory and the second actual trajectory; determine, based on analysis of the at least one image, that the convergence between the first actual trajectory and the second actual trajectory indicates the presence of a lane merge feature on the road segment; and update the vehicle road navigation model to include a first target trajectory corresponding to the first travel lane before the lane merge feature and extending along the third travel lane after the lane merge feature, and a second target trajectory extending along the second travel lane before the lane merge feature and combining with the first target trajectory.

[0011] In one embodiment, a system for navigating a host vehicle along a road segment may include at least one processor programmed to receive a vehicle road navigation model from a server-based system, the vehicle road navigation model including a first target trajectory corresponding to a first driving lane before a lane merge feature and extending along a third driving lane after the lane merge feature, the vehicle road navigation model also including a second target trajectory extending along a second driving lane before the lane merge feature and joining the first target trajectory. The at least one processor may be further programmed to receive information indicative of an environment of the host vehicle, determine whether to navigate the host vehicle along the first target trajectory or the second target trajectory based on the information indicative of the environment of the host vehicle, and determine a navigation operation for navigating the host vehicle along the determined target trajectory.

[0012] According to other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that are executed by at least one processing device and that perform any of the methods described herein.

[0013] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the scope of the claims. [Brief explanation of the drawings]

[0014] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments.

[0015] [Figure 1] 1 is a diagrammatic representation of an exemplary system according to the disclosed embodiments.

[0016] [Figure 2A] 1 is a side view representation of an exemplary vehicle including a system according to disclosed embodiments.

[0017] [Figure 2B] 2B is a top view representation of the vehicle and system shown in FIG. 2A according to a disclosed embodiment.

[0018] [Figure 2C] 1 is a top view representation of another embodiment of a vehicle including a system according to the disclosed embodiments.

[0019] [Figure 2D] 1 is a top view representation of yet another embodiment of a vehicle including a system according to the disclosed embodiments.

[0020] [Figure 2E] 1 is a top view representation of yet another embodiment of a vehicle including a system according to the disclosed embodiments.

[0021] [Figure 2F] 1 is a diagrammatic representation of an exemplary vehicle control system according to the disclosed embodiments.

[0022] [Figure 3A] 1 is a diagrammatic representation of the interior of a vehicle including a rearview mirror and a user interface of a vehicle imaging system according to disclosed embodiments.

[0023] [Figure 3B] 1 is a diagram of an example of a camera mount configured to be positioned behind a rearview mirror and opposite a vehicle windshield, according to a disclosed embodiment.

[0024] [Figure 3C] 3C is a diagram of the camera mount shown in FIG. 3B from a different perspective, according to a disclosed embodiment.

[0025] [Figure 3D] 1 is a diagram of an example of a camera mount configured to be positioned behind a rearview mirror and opposite a vehicle windshield, according to a disclosed embodiment.

[0026] [Figure 4] FIG. 1 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations in accordance with the disclosed embodiments.

[0027] [Figure 5A] 1 is a flowchart illustrating an exemplary process for generating one or more navigational responses based on monocular image analysis, according to disclosed embodiments.

[0028] [Figure 5B] 1 is a flowchart illustrating an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images, according to disclosed embodiments.

[0029] [Figure 5C] 1 is a flowchart illustrating an exemplary process for detecting road markings and / or lane geometry information in a set of images, according to disclosed embodiments.

[0030] [Figure 5D] 1 is a flowchart illustrating an exemplary process for detecting traffic lights in a set of images, according to disclosed embodiments.

[0031] [Figure 5E] 1 is a flowchart of an exemplary process for generating one or more navigational responses based on a vehicle path, according to disclosed embodiments.

[0032] [Figure 5F] 1 is a flowchart illustrating an example process for determining whether a leading vehicle is changing lanes, according to disclosed embodiments.

[0033] [Figure 6] 1 is a flowchart illustrating an example process for generating one or more navigational responses based on stereo image analysis, according to disclosed embodiments.

[0034] [Figure 7] 1 is a flowchart illustrating an exemplary process for generating one or more navigational responses based on an analysis of three sets of images, according to disclosed embodiments.

[0035] [Figure 8] 1 illustrates a sparse map for providing autonomous vehicle navigation according to a disclosed embodiment.

[0036] [Figure 9A] 1 illustrates a polynomial representation of a portion of a road segment according to a disclosed embodiment.

[0037] [Figure 9B] 1 illustrates a curve in three-dimensional space representing a desired trajectory of a vehicle for a particular road segment contained in a sparse map, according to a disclosed embodiment.

[0038] [Figure 10] 1 illustrates examples of landmarks that may be included in a sparse map, consistent with the disclosed embodiments.

[0039] [Figure 11A] 1 illustrates a polynomial representation of a trajectory according to a disclosed embodiment.

[0040] [Figure 11B] 1 illustrates a target trajectory along a multi-lane road according to a disclosed embodiment. [Figure 11C] 1 illustrates a target trajectory along a multi-lane road according to a disclosed embodiment.

[0041] [Figure 11D] 1 illustrates an exemplary road signature profile, according to a disclosed embodiment.

[0042] [Figure 12]FIG. 1 is a schematic diagram of a system using crowdsourced data received from multiple vehicles for autonomous vehicle navigation, according to disclosed embodiments.

[0043] [Figure 13] 1 illustrates an example autonomous vehicle road navigation model represented by a plurality of cubic splines, according to the disclosed embodiments.

[0044] [Figure 14] 1 illustrates a map skeleton generated from combining location information from many runs, according to disclosed embodiments.

[0045] [Figure 15] 10 illustrates an example of longitudinal alignment of two runs with exemplary signs as landmarks, according to disclosed embodiments.

[0046] [Figure 16] 10 illustrates an example of longitudinal alignment of many runs with exemplary signs as landmarks, according to disclosed embodiments.

[0047] [Figure 17] FIG. 1 is a schematic diagram of a system for generating driving data using a camera, a vehicle, and a server, according to disclosed embodiments.

[0048] [Figure 18] FIG. 1 is a schematic diagram of a system for crowdsourcing sparse maps, according to disclosed embodiments.

[0049] [Figure 19] 1 is a flowchart illustrating an example process for generating a sparse map for autonomous vehicle navigation along a road segment, according to a disclosed embodiment.

[0050] [Figure 20] FIG. 1 illustrates a block diagram of a server according to the disclosed embodiments.

[0051] [Figure 21] FIG. 1 illustrates a block diagram of a memory in accordance with disclosed embodiments.

[0052] [Figure 22] 1 illustrates a process for clustering vehicle trajectories associated with a vehicle according to a disclosed embodiment.

[0053] [Figure 23] 1 illustrates a navigation system for a vehicle that may be used for autonomous navigation, according to disclosed embodiments.

[0054] [Figure 24] 1 is a flowchart illustrating an exemplary process for generating a road navigation model for use in autonomous vehicle navigation, according to disclosed embodiments.

[0055] [Figure 25] FIG. 1 illustrates a block diagram of a memory in accordance with disclosed embodiments.

[0056] [Figure 26] 1 is a flowchart illustrating an exemplary process for autonomously navigating a vehicle along a road segment, according to disclosed embodiments.

[0057] [Figure 27] FIG. 1 illustrates a block diagram of a memory in accordance with disclosed embodiments.

[0058] [Figure 28A] 1 shows example run data from four separate runs, according to disclosed embodiments.

[0059] [Figure 28B] 1 shows example run data from five separate runs according to disclosed embodiments.

[0060] [Figure 28C] 1 illustrates an example vehicle path determined from driving data from five separate trips, according to disclosed embodiments.

[0061] [Figure 29] 1 is a flowchart illustrating an exemplary process for determining a line representation of road surface features extending along a road segment, according to the disclosed embodiments.

[0062] [Figure 30] FIG. 1 illustrates a block diagram of a memory in accordance with disclosed embodiments.

[0063] [Figure 31] 1 is a flowchart illustrating an exemplary process for collecting road surface information for a road segment, according to the disclosed embodiments.

[0064] [Figure 32] FIG. 1 illustrates a block diagram of a memory in accordance with disclosed embodiments.

[0065] [Figure 33A] An example of a vehicle crossing a lane without using lane markings is shown.

[0066] [Figure 33B] 33A shows the example of FIG. 33A after the vehicle's position and heading have been drifted.

[0067] [Figure 33C] The example of Figure 33B is shown after the position and heading have drifted further, causing the expected location of the landmark to differ significantly from its actual location.

[0068] [Figure 34A] 1 illustrates an example of a vehicle crossing a lane without using lane markings, according to a disclosed embodiment.

[0069] [Figure 34B]34A illustrates an example of reduced position and heading drift according to disclosed embodiments.

[0070] [Figure 34C] FIG. 34B shows an example in which the expected location of a landmark closely matches its actual location, according to the disclosed embodiments.

[0071] [Figure 35] 4 is a flowchart illustrating an exemplary process for correcting the position of a vehicle navigating a road segment, according to the disclosed embodiments.

[0072] [Figure 36] 1 illustrates an exemplary road segment with lane splitting, according to the disclosed embodiments.

[0073] [Figure 37A] 1 illustrates an example vehicle trajectory that may be used to identify lane splitting, according to disclosed embodiments.

[0074] [Figure 37B] 1 illustrates an exemplary clustering of vehicle trajectories for determining lane splitting, according to disclosed embodiments.

[0075] [Figure 37C] 1 illustrates an example target trajectory for identifying lane splits, according to disclosed embodiments.

[0076] [Figure 38A] 1 illustrates an exemplary process for adjusting the location of a branch point, according to disclosed embodiments.

[0077] [Figure 38B] 10 illustrates an example of an adjusted target trajectory for identifying lane splits, according to disclosed embodiments.

[0078] [Figure 39A]10 illustrates examples of anomalies that may occur in a target trajectory, according to disclosed embodiments. [Figure 39B] 10 illustrates examples of anomalies that may occur in a target trajectory, according to disclosed embodiments. [Figure 39C] 10 illustrates examples of anomalies that may occur in a target trajectory, according to disclosed embodiments.

[0079] [Figure 40A] 1 illustrates an exemplary road segment including lane split features, according to the disclosed embodiments.

[0080] [Figure 40B] 10A-10C illustrate example images that may be used by a host vehicle in determining a target trajectory associated with a lane splitting feature, according to disclosed embodiments.

[0081] [Figure 40C] 1 illustrates another example road segment including lane split features, according to the disclosed embodiments.

[0082] [Figure 40D] 10 illustrates another example image that may be used by a host vehicle in determining a target trajectory associated with a lane splitting feature, according to disclosed embodiments.

[0083] [Figure 41] 41 is a flowchart illustrating an example process 4100 for mapping lane splits for use in vehicle navigation, according to a disclosed embodiment.

[0084] [Figure 42] 42 is a flowchart illustrating an example process 4200 for mapping lane splits for navigating a host vehicle along a road segment, according to a disclosed embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0085] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several exemplary embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the components shown in the drawings, and the exemplary methods described herein may be modified by substituting, reordering, deleting, or adding steps of 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.

[0086] Autonomous Vehicle Overview

[0087] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that can implement at least one navigation change without driver input. A "navigation change" refers to one or more changes in the steering, braking, or acceleration of the vehicle. To be autonomous, a vehicle need not be fully automatic (e.g., operating completely without a driver or driver input). Rather, an autonomous vehicle includes a vehicle that can operate under driver control during certain periods of time and without driver control during other periods of time. An autonomous vehicle can also include a vehicle that controls only some aspects of vehicle navigation, such as steering (e.g., to maintain the vehicle course between vehicle lane constraints), but leaves other aspects (e.g., braking) to the driver. In some cases, an autonomous vehicle may handle some or all aspects of the vehicle's braking, speed control, and / or steering.

[0088] Because human drivers typically rely on visual cues and observations to control their vehicles, transportation infrastructure is built accordingly, with lane markings, traffic signs, and traffic lights all designed to provide visual information to drivers. In light of these design features of transportation infrastructure, autonomous vehicles may include cameras and processing units that analyze visual information captured from the vehicle's environment. Visual information may include, for example, transportation infrastructure components observable by the driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, autonomous vehicles may use stored information when navigating, such as information that provides a model of the vehicle's environment. For example, the vehicle may use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information related to the vehicle's environment while the vehicle is traveling, and the vehicle (and other vehicles) may use the information to locate itself within the model.

[0089] In some embodiments of the present disclosure, an autonomous vehicle may use information obtained while navigating (e.g., from cameras, GPS devices, accelerometers, speed sensors, suspension sensors, etc.). In other embodiments, an autonomous vehicle may use information obtained from past navigation by the vehicle (or other vehicles) while navigating. In still other embodiments, an autonomous vehicle may use a combination of information obtained while navigating and information obtained from past navigation. The following sections provide an overview of a system according to disclosed embodiments, followed by an overview of a forward-looking imaging system and method according to the system. The following sections disclose systems and methods for building, using, and updating sparse maps for autonomous vehicle navigation.

[0090] System Overview

[0091] FIG. 1 is a block diagram representation of a system 100 according to an exemplary embodiment. System 100 may include various components depending on particular implementation requirements. 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, image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements of a particular application. 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, image capture device 126, etc. 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 one or more wired and / or wireless links for transmitting image data acquired by image acquisition device 120 to processing unit 110.

[0092] Wireless transceiver 172 may include one or more devices configured to exchange transmissions with one or more networks (e.g., cellular, Internet, etc.) over a wireless interface using radio frequencies, infrared frequencies, magnetic fields, or electric fields. Wireless transceiver 172 may send and / or receive data using any known standard (e.g., Wi-Fi, Bluetooth, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications from the host vehicle to one or more remotely located servers. Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to facilitate coordinating the host vehicle's navigation in light of or with target vehicles in the host vehicle's environment), as well as broadcast transmissions to unspecified recipients in the transmitting vehicle's vicinity.

[0093] Both application processor 180 and image processor 190 may include various types of processing devices. For example, either or both of application processor 180 and image processor 190 may include a microprocessor, a preprocessor (e.g., an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for running applications and processing and analyzing images. In some embodiments, application processor 180 and / or image processor 190 may include any type of single-core or multi-core processor, mobile device microcontroller, central processing unit, etc. Various processing devices are available and may include various architectures (e.g., x86 processor, ARM, etc.), including, for example, processors available from manufacturers such as Intel®, AMD®, or GPUs available from manufacturers such as NVIDIA®, ATI®, etc.

[0094] In some embodiments, application processor 180 and / or image processor 190 may include any of the EyeQ series of processors available from Mobileye®. These processor designs include multiple processing units, each with its own local memory and instruction set. Such processors may include video inputs that receive image data from multiple image sensors and may also include video output capabilities. In one example, the EyeQ2® uses 90 nm-micron technology operating at 332 MHz. The EyeQ2® architecture consists of two floating-point, hyper-threaded 32-bit RISC CPUs (MIPS32® 34K® cores), five Vision Computation Engines (VCEs), three Vector Microcode Processors (VMP®), a Denali 64-bit mobile DDR controller, a 128-bit internal audio interconnect, dual 16-bit video input and 18-bit video output controllers, a 16-channel DMA, and several peripherals. The MIPS34K CPU manages five VCEs, three VMP™ processors and DMA, a second MIPS34K CPU and multi-channel DMA, and other peripherals. The five VCEs, three VMP™ processors, and the MIPS34K CPU can perform intensive vision calculations required by feature-rich bundled applications. In another example, the disclosed embodiments may use the EyeQ3™, a third-generation processor that is six times more powerful than the EyeQ2™. In another example, the EyeQ4™ and / or EyeQ5™ processors may be used with the disclosed embodiments. Of course, newer or future EyeQ processing devices may be used with the disclosed embodiments.

[0095] Any of the processing devices disclosed herein can be configured to perform specific functions. Configuring a processing device, such as any of the described EyeQ processors or other controllers or microprocessors, to perform specific functions may include programming computer-executable instructions and providing those instructions to the processing device for execution during operation of the processing device. In some embodiments, configuring a processing device may include directly programming architectural instructions into the processing device. For example, processing devices such as field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), and the like may be configured using, for example, one or more hardware description languages ​​(HDLs).

[0096] In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible by the processing device during operation. For example, the processing device may access the memory during operation to retrieve and execute the stored instructions. In any event, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system that controls multiple hardware-based components of a host vehicle.

[0097] 1 shows two separate processing devices included in processing unit 110, more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to accomplish the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by three or more processing devices. Furthermore, in some embodiments, system 100 may include one or more of processing units 110 without including other components, such as image acquisition unit 120.

[0098] The processing unit 110 may include various types of devices. For example, the processing unit 110 may include various devices such as a controller, an image preprocessor, a central processing unit (CPU), a graphics processing unit (GPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device that processes and analyzes images. The image preprocessor may include a video processor that captures, digitizes, and processes images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuits may be any number of circuits commonly known in the art, including cache, power supplies, clocks, and input / output circuits. The memory may store software that, when executed by the processor, controls the operation of the system. The memory may include databases and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage devices, tape storage devices, removable storage devices, and other types of storage devices. In one example, the memory may be separate from the processing unit 110. In another example, the memory may be integrated into the processing unit 110.

[0099] Each memory 140, 150 may contain software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. These memory units may include various databases and image processing software, as well as trained systems such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage devices, tape storage devices, removable storage devices, and / or any other type of storage device. In some embodiments, memory units 140, 150 may be separate from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

[0100] Position sensor 130 may include any type of device suitable for determining a location associated with at least one component of system 100. In some embodiments, position sensor 130 may include a GPS receiver. Such a receiver may determine the location and velocity of a user by processing signals broadcast by Global Positioning System satellites. Position information from position sensor 130 may be provided to application processor 180 and / or image processor 190.

[0101] In some embodiments, system 100 may include components such as a speed sensor (e.g., a tachometer, speedometer) for measuring the speed of vehicle 200 and / or an accelerometer (either single-axis or multi-axis) for measuring the acceleration of vehicle 200.

[0102] User interface 170 may include any device suitable for providing information 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, a microphone, a keyboard, a pointer device, a track wheel, a camera, a knob, buttons, etc. Using such input devices, a user may be able to provide information input or commands to system 100 by typing instructions or information, providing voice commands, selecting on-screen menu options using buttons, pointer or eye tracking, or through any other suitable technique for communicating information to system 100.

[0103] User interface 170 may comprise one or more processing devices configured to provide information to or receive information from a user and process that information, for example, for use by application processor 180. In some embodiments, such processing devices may execute instructions to recognize and track eye movements, receive and interpret voice commands, recognize and interpret touches and / or gestures made on a touchscreen, respond to keyboard entries or menu selections, etc. In some embodiments, user interface 170 may include a display, a speaker, a tactile device, and / or any other device that provides output information to a user.

[0104] Map database 160 may include any type of database that stores map data useful to system 100. In some embodiments, map database 160 may include data related to the locations in a reference coordinate system of various items, including roads, water features, geographic features, businesses, points of interest, restaurants, gas stations, etc. Map database 160 may store not only the locations of such items, but also descriptors related to those items, including, for example, names associated with any of the stored features. In some embodiments, map database 160 may be physically located with other components of system 100. Alternatively or additionally, map database 160 or portions thereof may be located remotely with respect to other components of system 100 (e.g., processing unit 110). In such embodiments, information from map database 160 may be downloaded to a network via a wired or wireless data connection (e.g., via a cellular network and / or the Internet, etc.). In some cases, map database 160 may store sparse data models including polynomial representations of particular road features (e.g., lane markings) or a desired trajectory of the host vehicle. Systems and methods for generating such maps are discussed below with reference to FIGS.

[0105] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from an environment. Furthermore, any number of image capture devices may be used to obtain images for input to the 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. Image capture devices 122, 124, and 126 are further described below with reference to Figures 2B-2E.

[0106] System 100 or various components of system 100 may be incorporated into a variety of different platforms. In some embodiments, system 100 may be included in vehicle 200, as shown in FIG. 2A. For example, vehicle 200 may include processing unit 110 and any other components of system 100, as described above with respect to FIG. 1. In some embodiments, vehicle 200 may include only a single image capture device (e.g., a camera), while in other embodiments, such as those discussed in connection with FIGS. 2B-2E, multiple image capture devices may be used. For example, as shown in FIG. 2A, either of image capture devices 122 and 124 of vehicle 200 may be part of an ADAS (Advanced Driver Assistance Systems) imaging suite.

[0107] The image capture device included in vehicle 200 as part of image acquisition unit 120 may be located in any suitable location. In some embodiments, as shown in Figures 2A-2E and 3A-3C, image capture device 122 may be located near the rearview mirror. This location may provide a line of sight similar to that of the driver of vehicle 200 and may assist in determining what the driver can and cannot see. While image capture device 122 may be located anywhere near the rearview mirror, placing image capture device 122 on the driver's side of the mirror may further assist in capturing images representative of the driver's field of view and / or line of sight.

[0108] Other locations for the image capture devices of image acquisition unit 120 can also be used. For example, image capture device 124 can be located on or within the bumper of vehicle 200. Such a location can be particularly suitable for image capture devices with a wide field of view. The line of sight of an image capture device located on the bumper can be different from the driver's line of sight, and thus the bumper image capture device and the driver do not always see the same object. Image capture devices (e.g., image capture devices 122, 124, and 126) can also be located in other locations. For example, the image capture devices can be located on one or both side mirrors of vehicle 200, on the roof of vehicle 200, on the hood of vehicle 200, in the trunk of vehicle 200, on the sides of vehicle 200, mounted on, positioned behind, or positioned in front of any window of vehicle 200, mounted in or near the front and / or rear lights of vehicle 200, etc.

[0109] In addition to the image capture device, vehicle 200 may include various other components of system 100. For example, processing unit 110 may be integrated into the vehicle's engine control unit (ECU) or may be included in vehicle 200 separate from the ECU. Vehicle 200 may also be equipped with a location sensor 130, such as a GPS receiver, and vehicle 200 may also include a map database 160 and memory units 140 and 150.

[0110] As described above, wireless transceiver 172 may transmit and / or receive data via one or more networks (e.g., a cellular network, the Internet, etc.). For example, wireless transceiver 172 may upload data collected by system 100 to one or more servers and download data from one or more servers. Via wireless transceiver 172, system 100 may receive updates to data stored in map database 160, memory 140, and / or memory 150, for example, periodically or on demand. Similarly, wireless transceiver 172 may upload any data from system 100 (e.g., images captured by image acquisition unit 120, data received by position sensor 130, other sensors, or vehicle control systems, etc.) and / or any data processed by processing unit 110 to one or more servers.

[0111] System 100 may upload data to a server (e.g., the cloud) based on a privacy level setting. For example, system 100 may implement a privacy level setting that regulates or limits the types of data (including metadata) that may uniquely identify the vehicle and / or the driver / owner of the vehicle that are sent to the server. Such settings may be set by a user via wireless transceiver 172, initialized by factory default settings, or set by data received by wireless transceiver 172, for example.

[0112] In some embodiments, system 100 may upload data according to a "high" privacy level, where under certain settings, system 100 may transmit data (e.g., location information associated with a route, captured images, etc.) without any details about the specific vehicle and / or driver / owner. For example, when uploading data according to a "high" privacy level, system 100 may not include the vehicle identification number (VIN) or the name of the vehicle's driver or owner, but instead transmit data such as captured images and / or limited location information associated with a route.

[0113] Other privacy levels are contemplated. For example, system 100 may transmit data to a server according to a “medium” privacy level, which may include additional information not included under a “high” privacy level, such as the make and / or model of the vehicle and / or vehicle type (e.g., passenger car, sport utility vehicle, truck, etc.). In some embodiments, system 100 may upload data according to a “low” privacy level. Under the “low” privacy level setting, system 100 may upload and include sufficient data to uniquely identify a particular vehicle, owner / driver, and / or some or all of the route traveled by the vehicle. Such “low” privacy level data may include, for example, one or more of: VIN, driver / owner name, vehicle's starting point prior to departure, vehicle's intended destination, vehicle make and / or model, vehicle type, etc.

[0114] Figure 2A is a side view representation of an exemplary vehicle imaging system according to a disclosed embodiment. Figure 2B is a top view representation of the embodiment shown in Figure 2A. As shown in Figure 2B, the disclosed embodiment may show a vehicle 200 including within its body a system 100 having a first image capture device 122 positioned near a rearview mirror and / or near a driver of the vehicle 200, a second image capture device 124 positioned on or within a bumper area (e.g., one of bumper areas 210) of the vehicle 200, and a processing unit 110.

[0115] As shown in Figure 2C, both image capture devices 122 and 124 may be positioned near the rearview mirror and / or near the driver of vehicle 200. Furthermore, while two image capture devices 122 and 124 are shown in Figures 2B and 2C, it should be understood that other embodiments may include three or more image capture devices. For example, in the embodiment shown in Figures 2D and 2E, a first image capture device 122, a second image capture device 124, and a third image capture device 126 are included in system 100 of vehicle 200.

[0116] 2D , image capture device 122 may be positioned near the rearview mirror and / or near the driver of vehicle 200, and image capture devices 124 and 126 may be positioned on a bumper area (e.g., one of bumper areas 210) of vehicle 200. Also, as shown in FIG. 2E , image capture devices 122, 124, and 126 may be positioned near the rearview mirror and / or near the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number or configuration of image capture devices, and image capture devices may be positioned in any suitable location within and / or on vehicle 200.

[0117] It should be understood that the disclosed embodiments are not limited to vehicles and may be applicable in other contexts. It should also be understood that the disclosed embodiments are not limited to a particular type of vehicle 200 and may be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0118] First image capture device 122 may include any suitable type of image capture device. Image capture device 122 may include an optical axis. In one example, image capture device 122 may include an Aptina M9V024 WVGA sensor with a global shutter. In other embodiments, image capture device 122 may provide a resolution of 1280 x 960 pixels and may include a rolling shutter. Image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included to provide, for example, a desired focal length and field of view for the image capture device. In some embodiments, image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, image capture device 122 may be configured to capture an image having a desired field of view (FOV) 202, as shown in FIG. 2D . For example, image capture device 122 may be configured to have a conventional FOV, such as within the range of 40 degrees to 56 degrees, including a 46 degree FOV, a 50 degree FOV, a 52 degree FOV, or degrees greater than 52 degrees. Alternatively, image capture device 122 may be configured to have a narrower FOV, such as a 23 to 40 degree FOV, such as a 28 degree FOV or a 36 degree FOV. Additionally, image capture device 122 may be configured to have a wider FOV, such as a 100 to 180 degree FOV. In some embodiments, image capture device 122 may include a wide-angle bumper camera or a bumper camera with an FOV of up to 180 degrees. In some embodiments, image capture device 122 may be a 7.2 Mpixel image capture device with an aspect ratio of approximately 2:1 (e.g., H×V=3800×1900 pixels) with a horizontal FOV of approximately 100 degrees. Such an image capture device may be used instead of a three-dimensional image capture device configuration. Due to large lens distortion, the vertical FOV of such image capture devices can be much less than 50 degrees in implementations in which the image capture device uses a radially symmetric lens, for example, such lenses are not radially symmetric, thereby allowing a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

[0119] First image capture device 122 may acquire multiple first images of a scene associated with vehicle 200. The multiple first images may each be acquired as a series of image scan lines, which may be captured using a rolling shutter. Each scan line may include multiple pixels.

[0120] The first image capture device 122 may have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate may refer to the rate at which the image sensor can acquire image data associated with each pixel included in a particular scan line.

[0121] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, including, for example, CCD sensors or CMOS sensors. In one embodiment, a CMOS image sensor may be utilized with a rolling shutter, whereby each pixel in a row is read one at a time, and the scanning of the rows proceeds row by row until the entire image frame is captured. In some embodiments, the rows may be captured sequentially from top to bottom relative to the frame.

[0122] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) may constitute high-resolution imagers and may have a resolution of greater than 5M pixels, greater than 7M pixels, greater than 10M pixels, or more.

[0123] The use of a rolling shutter can result in pixels in different rows being exposed and captured at different times, which can cause skew and other image artifacts in the captured image frame. On the other hand, if image capture device 122 is configured to operate using a global or synchronous shutter, all pixels can be exposed for the same amount of time during a common exposure period. As a result, image data in a frame collected from a system utilizing a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a particular time. Conversely, when applying a rolling shutter, each row in a frame is exposed and data is captured at a different time. Therefore, moving objects can appear distorted with an image capture device having a rolling shutter. This phenomenon is described in more detail below.

[0124] Second image capture device 124 and third image capture device 126 may be any type of image capture device. Like first image capture device 122, each of image capture devices 124 and 126 may include an optical axis. In one embodiment, each of image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of image capture devices 124 and 126 may include a rolling shutter. Like image capture device 122, image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with image capture devices 124 and 126 may provide the same FOV as that associated with image capture device 122 (such as FOV 202) or a narrower FOV (such as FOVs 204 and 206). For example, image capture devices 124 and 126 may have a FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less than 20 degrees.

[0125] Image capture devices 124 and 126 may acquire second and third multiple images of a scene associated with vehicle 200. Each of the second and third multiple images may be acquired as second and third series of image scan lines, which may be captured using a rolling shutter. Each scan line or row may have a plurality of pixels. Image capture devices 124 and 126 may have second and third scan rates associated with acquiring each image scan line included in the second and third series.

[0126] Each image capture device 122, 124, and 126 may be positioned in any suitable location and in any suitable orientation relative to vehicle 200. The relative positions of image capture devices 122, 124, and 126 may be selected to facilitate fusing together information obtained from the image capture devices. For example, in some embodiments, the FOV associated with image capture device 124 (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).

[0127] Image capture devices 122, 124, and 126 may be positioned on vehicle 200 at any suitable relative height. In one example, there may be a height difference between image capture devices 122, 124, and 126, which may provide sufficient parallax information to enable stereo analysis. For example, as shown in FIG. 2A, two image capture devices 122 and 124 are at different heights. There may also be a lateral displacement difference between image capture devices 122, 124, and 126, which may provide additional parallax information for stereo analysis by processing unit 110, for example. The lateral displacement difference may be calculated as d x In some embodiments, a forward or aft displacement (e.g., range displacement) may exist between image capture devices 122, 124, and 126. For example, image capture device 122 may be positioned 0.5 to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of displacement may allow one of the image capture devices to cover a potential blind spot for the other image capture device.

[0128] Image capture device 122 may have any suitable resolution capability (e.g., number of pixels associated with the image sensor), and the resolution of the image sensor associated with image capture device 122 may be higher, lower, or the same as the resolution of the image sensors associated with image capture devices 124 and 126. In some embodiments, the image sensors associated with image capture device 122 and / or image capture devices 124 and 126 may have a resolution of 640x480, 1024x768, 1280x960, or any other suitable resolution.

[0129] The frame rate (e.g., the rate at which the image capture device acquires a set of pixel data for one image frame before moving on to acquire pixel data associated with the next image frame) may be controllable. The frame rate associated with image capture device 122 may be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 may depend on various factors that may affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 may include a selectable pixel delay period imposed before or after acquisition of image data associated with one or more pixels of an image sensor within image capture devices 122, 124, and / or 126. Generally, image data corresponding to each pixel may be acquired according to the device's clock rate (e.g., one pixel per clock cycle). Furthermore, in embodiments including a rolling shutter, one or more of image capture devices 122, 124, and 126 may include a selectable horizontal blanking period imposed before or after acquisition of image data associated with a row of pixels of an image sensor in image capture devices 122, 124, and / or 126. Furthermore, one or more of image capture devices 122, 124, and / or 126 may include a selectable vertical blanking period imposed before or after acquisition of image data associated with an image frame of image capture devices 122, 124, and 126.

[0130] These timing controls may enable the frame rates associated with image capture devices 122, 124, and 126 to be synchronized even if the line scan rate of each image capture device is different. Additionally, as discussed in more detail below, among other factors (e.g., image sensor resolution, maximum line scan rate, etc.), these selectable timing controls may enable the synchronization of image capture from areas where the FOV of image capture device 122 overlaps with the FOV of one or more of image capture devices 124 and 126, even if the field of view of image capture device 122 differs from the FOV of image capture devices 124 and 126.

[0131] The frame rate timing for image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, assuming both devices have similar line scan rates, if one device includes an image sensor with a resolution of 640x480 and the other device includes an image sensor with a resolution of 1280x960, capturing a frame of image data from the sensor with the higher resolution will require a longer time.

[0132] Another factor that may affect the timing of image data acquisition at image capture devices 122, 124, and 126 is the maximum line scan rate. For example, acquisition of a row of image data from the image sensors included in image capture devices 122, 124, and 126 requires some minimum amount of time. Assuming no pixel delay period is added, this minimum amount of time to acquire a row of image data will be related to the maximum line scan rate of a particular device. Devices that offer higher maximum line scan rates have the potential to provide higher frame rates than devices with lower maximum line scan rates. In some embodiments, one or both of image capture devices 124 and 126 may have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more the maximum line scan rate of image capture device 122.

[0133] In another embodiment, image capture devices 122, 124, and 126 may have the same maximum line scan rate, but image capture device 122 may operate at a scan rate that is equal to or less than that maximum scan rate. The system may be configured so that one or both of image capture devices 124 and 126 operate at a line scan rate that is equal to the line scan rate of image capture device 122. In other examples, the system may be configured so that the line scan rate of image capture device 124 and / or image capture device 126 may be 1.25, 1.5, 1.75, or 2 times or more the line scan rate of image capture device 122.

[0134] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric. That is, the image capture devices may include cameras with different fields of view (FOV) and focal lengths. The fields of view of image capture devices 122, 124, and 126 may include, for example, any desired area of ​​the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, the environment behind vehicle 200, the environment on either side of vehicle 200, or a combination thereof.

[0135] Additionally, the focal length associated with each image capture device 122, 124, and / or 126 may be selectable (e.g., by inclusion of an appropriate lens, etc.) so that each device captures images of objects at a desired distance range from vehicle 200. For example, in some embodiments, image capture devices 122, 124, and 126 may capture images of close-up objects within a few meters of the vehicle. Image capture devices 122, 124, 126 may also be configured to capture images of objects at greater distances from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or more). Furthermore, the focal lengths of image capture devices 122, 124, and 126 may be selected such that one image capture device (e.g., image capture device 122) can capture images of objects relatively close to the vehicle (e.g., within 10 m or within 20 m), while the other image capture devices (e.g., image capture devices 124 and 126) can capture images of objects farther away from vehicle 200 (e.g., more than 20 m, more than 50 m, more than 100 m, more than 150 m, etc.).

[0136] According to some embodiments, the FOV of one or more of image capture devices 122, 124, and 126 may have a wide angle. For example, it may be advantageous to have an FOV of 140 degrees, particularly for image capture devices 122, 124, and 126 that may be used to capture images of areas near vehicle 200. For example, image capture device 122 may be used to capture images of areas to the right or left of vehicle 200, and in such embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0137] The field of view associated with each of image capture devices 122, 124, and 126 may depend on the respective focal lengths. For example, as the focal lengths increase, the corresponding field of view decreases.

[0138] Image capture devices 122, 124, and 126 may be configured to have any suitable field of view. In one particular example, image capture device 122 may have a horizontal FOV of 46 degrees, image capture device 124 may have a horizontal FOV of 23 degrees, and image capture device 126 may have a horizontal FOV between 23 and 46 degrees. In another example, image capture device 122 may have a horizontal FOV of 52 degrees, image capture device 124 may have a horizontal FOV of 26 degrees, and image capture device 126 may have a horizontal FOV between 26 and 52 degrees. In some embodiments, the ratio between the FOV of image capture device 122 and the FOV of image capture device 124 and / or image capture device 126 may vary between 1.5 and 2.0. In other embodiments, this ratio may vary between 1.25 and 2.25.

[0139] System 100 may be configured so that the field of view of image capture device 122 at least partially or completely overlaps the field of view of image capture device 124 and / or image capture device 126. In some embodiments, system 100 may be configured so that the fields of view of image capture devices 124 and 126, for example, fall within the field of view of image capture device 122 (e.g., are smaller than the field of view of image capture device 122) and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs or may have partially overlapping FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 may be aligned such that the center of image capture device 124 and / or 126, which has the narrower FOV, may be located in the bottom half of the field of view of device 122, which has the wider FOV.

[0140] 2F is a diagrammatic representation of an exemplary vehicle control system according to disclosed embodiments. As shown in FIG. 2F, vehicle 200 may include a throttle system 220, a braking system 230, and a steering system 240. System 100 may provide inputs (e.g., control signals) to one or more of throttle system 220, braking system 230, and steering system 240 via one or more data links (e.g., any wired and / or wireless link or link that transmits 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 throttle system 220, braking system 230, and steering system 240 to navigate vehicle 200 (e.g., by causing it to accelerate, turn, lane shift, etc.). Additionally, system 100 may receive inputs indicative of the operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.) from one or more of throttle system 220, braking system 230, and steering system 24. Further details are provided below in connection with Figures 4-7.

[0141] As shown in FIG. 3A , vehicle 200 may also include a user interface 170 for interacting with a driver or passenger of vehicle 200. For example, user interface 170 in a vehicle application may include a touchscreen 320, knobs 330, buttons 340, and a microphone 350. A driver or passenger of vehicle 200 may also interact with system 100 using a steering wheel (e.g., located on or near a steering column of vehicle 200, including, for example, a turn signal handle), buttons (e.g., located on the steering wheel of vehicle 200), and the like. In some embodiments, microphone 350 may be positioned adjacent to rearview mirror 310. Similarly, in some embodiments, image capture device 122 may be located near rearview mirror 310. In some embodiments, user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, system 100 may provide various notifications (e.g., alerts) via speaker 360.

[0142] 3B-3D are diagrams of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and facing a vehicle windshield, according to disclosed embodiments. As shown in FIG. 3B , camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be positioned behind glare shield 380, which may be in direct contact with the vehicle windshield and may include a film and / or anti-reflective material composition. For example, glare shield 380 may be positioned such that the shield is aligned facing the vehicle windshield with a matching slope. In some embodiments, each of image capture devices 122, 124, and 126 may be positioned behind glare shield 380, for example, as shown in FIG. 3D . The disclosed embodiments are not limited to any particular configuration of image capture devices 122, 124, and 126, camera mount 370, and glare shield 380. FIG. 3C is a view of the camera mount 370 shown in FIG. 3B from the front.

[0143] As will be appreciated by those skilled in the art having the benefit of this disclosure, many variations and / or modifications may be made to the above-disclosed embodiments. For example, not all components are essential to the operation of system 100. Furthermore, any component may be located in any suitable portion of system 100, and the components may be rearranged in various configurations while still providing the functionality of the disclosed embodiments. Accordingly, the configurations discussed above are examples, and regardless of the configuration described above, system 100 may provide a wide range of functionality for analyzing the surroundings of vehicle 200 and navigating vehicle 200 in response to the analysis.

[0144] As discussed in more detail below, according to various disclosed embodiments, system 100 may provide various features related to autonomous driving and / or driver assistance technologies. For example, system 100 may analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 may collect data for analysis from, for example, image capture unit 120, location sensor 130, and other sensors. Furthermore, system 100 may analyze the collected data to identify whether vehicle 200 should take a particular action and then automatically take the determined action without human intervention. For example, when vehicle 200 navigates without human intervention, system 100 may automatically control the braking, acceleration, and / or steering of vehicle 200 (e.g., by sending control signals to one or more of throttle system 220, braking system 230, and steering system 240). Furthermore, system 100 may analyze the collected data and issue warnings and / or alerts to vehicle occupants based on the analysis of the collected data. Further details regarding various embodiments provided by system 100 are provided below.

[0145] Forward-facing multi-imaging system

[0146] As discussed above, system 100 may provide driving assistance features 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 of the vehicle or the rear of the vehicle. In one embodiment, for example, system 100 may use a two-camera imaging system, in which a first camera and a second camera (e.g., image capture devices 122 and 124) may be positioned at the front and / or side of the vehicle (e.g., vehicle 200). The first camera may have a field of view that is larger, smaller, or partially overlaps that of the second camera. Furthermore, the first camera may be connected to a first image processor to perform monocular image analysis of images provided by the first camera, and the second camera may be connected to a second image processor to perform monocular image analysis of images provided by the second camera. The outputs (e.g., processed information) of the first and second image processors may be combined. In some embodiments, the second image processor may receive images from both the first and second cameras and perform stereo analysis. In another embodiment, system 100 may use a three-camera imaging system, where each camera has a different field of view. Thus, such a system may make decisions based on information derived from objects at various distances both in front of and to the sides of the vehicle. References to monocular image analysis may refer to cases where image analysis is performed based on images captured from a single viewpoint (e.g., a single camera). Stereo image analysis may refer to cases where image analysis is performed based on two or more images captured with one or more image capture parameters changed. For example, captured images suitable for performing stereo analysis may include images captured from two or more different positions, images captured from different fields of view, images captured using different focal lengths, images captured with parallax information, etc.

[0147] For example, in one embodiment, system 100 may implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees or other value selected from the range of approximately 20 to 45 degrees), image capture device 124 may provide a wide field of view (e.g., 150 degrees or other value selected from the range of approximately 100 to approximately 180 degrees), and image capture device 126 may provide a medium field of view (e.g., 46 degrees or other value selected from the range of approximately 35 to approximately 60 degrees). In some embodiments, image capture device 126 may operate as the main or primary camera. Image capture devices 122, 124, and 126 may be positioned substantially side-by-side (e.g., 6 cm apart) behind rearview mirror 310. Additionally, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 may be mounted behind a glare shield 380 that is flush with the windshield of vehicle 200. Such a shield may operate to minimize the impact of any reflections from the interior of the vehicle on image capture devices 122, 124, and 126.

[0148] 3B and 3C, the wide field of view camera (e.g., image capture device 124 in the example above) may be mounted lower than the narrow main field of view camera (e.g., image capture devices 122 and 126 in the example above). This configuration may provide a free line of sight from the wide field of view camera. To reduce reflections, the camera may be mounted near the windshield of vehicle 200 and may include a polarizer to attenuate reflected light.

[0149] A three-camera system may offer certain performance characteristics. For example, some embodiments may include the ability to verify the detection of an object by one camera based on the detection results from another camera. In the three-camera configuration discussed above, processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), each dedicated to processing images captured by one or more of image capture devices 122, 124, and 126.

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

[0151] The second processing device may receive images from the primary camera and perform vision processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Furthermore, the second processing device may calculate camera displacement, calculate pixel discrepancies between successive images based on the displacement, and create a 3D reconstruction (e.g., structure-from-motion) of the scene. The second processing device may send the structure-from-motion based on the 3D reconstruction to the first processing device and combine the structure-from-motion with the stereoscopic 3D image.

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

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

[0154] In some embodiments, system 100 may use two image capture devices (e.g., image capture devices 122 and 124) in providing navigation assistance to vehicle 200, and may use a third image capture device (e.g., image capture device 126) to provide redundancy and verify the analysis of data received from the other two image capture devices. For example, in such a configuration, image capture devices 122 and 124 may provide images for stereo analysis by system 100 for navigating vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of information derived based on images captured from image capture device 122 and / or image capture device 124. That is, image capture device 126 (and corresponding processing device) may be considered to provide a redundant subsystem that provides a check on the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Additionally, in some embodiments, redundancy and validation of received data can be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside the vehicle, etc.).

[0155] Those skilled in the art will recognize that the above camera configurations, camera placements, camera numbers, camera locations, etc. are merely exemplary. These components, etc., described for an overall system, may be assembled and used in a variety of different configurations without departing from the scope of the disclosed embodiments. Further details regarding the use of multi-camera systems to provide driver assistance and / or autonomous vehicle functionality follow below.

[0156] 4 is an example functional block diagram of memory 140 and / or 150 that may be stored / programmed with instructions to perform one or more operations in accordance with the disclosed embodiments. While reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0157] 4 , memory 140 may store a monocular image analysis module 402, a stereo image analysis module 404, a velocity and acceleration module 406, and a 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 modules 402, 404, 406, and 408 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, any steps of the following processes may be performed by one or more processing devices.

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

[0159] In one embodiment, stereo image analysis module 404 may store instructions (e.g., computer vision software) that, when executed by processing unit 110, perform stereo image analysis of first and second sets of images acquired by a combination of image capture devices selected from image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from the first and second sets of images with additional sensory information (e.g., information from radar) to perform stereo image analysis. For example, stereo image analysis module 404 may include instructions to perform stereo image analysis based on the first set of images acquired by image capture device 124 and the second set of images acquired by image capture device 126. As described below in connection with FIG. 6 , stereo image analysis module 404 may include instructions to detect a set of features in the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and hazards. Based on the analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, such as turns, lane shifts, and acceleration changes, as described below in connection with navigation response module 408. Additionally, in some embodiments, stereo image analysis module 404 may implement techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems, such as systems that may be configured to use computer vision algorithms to detect and / or label objects in an environment from which sensory information has been captured and processed. In one embodiment, stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0160] In one embodiment, speed and acceleration module 406 may store software configured to analyze data received from one or more computational and electromechanical devices within vehicle 200 configured to alter the speed and / or acceleration of vehicle 200. For example, processing unit 110 may execute instructions associated with speed and acceleration module 406 to calculate a target speed of vehicle 200 based on data derived from the execution of monocular image analysis module 402 and / or stereo image analysis module 404. Such data may include, for example, target position, speed, and / or acceleration, the position and / or speed of vehicle 200 relative to nearby vehicles, pedestrians, or road objects, and the position information of vehicle 200 relative to lane markings on the road. Additionally, processing unit 110 may calculate a target speed of vehicle 200 based on sensory input (e.g., information from radar) and input from other systems of vehicle 200, such as throttle system 220, braking system 230, and / or steering system 240 of vehicle 200. Based on the calculated target speed, the processing unit 110 may send electronic signals to the throttle system 220, the braking system 230 and / or the steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration, for example, by physically releasing the brakes or easing the accelerator of the vehicle 200.

[0161] In one embodiment, the navigation response module 408 may store executable software by the processing unit 110 to determine a desired navigation response based on data derived from execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include position and speed information associated with nearby vehicles, pedestrians, and road objects, as well as target position information for the vehicle 200. Additionally, in some embodiments, the navigation response may be based (partially or fully) on map data, a predetermined position of the vehicle 200, and / or the relative speed or relative acceleration between the vehicle 200 and one or more objects detected from execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine a desired navigation response based on sensory input (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle system 220, the braking system 230, and the steering system 240 of the vehicle 200. Based on the desired navigation response, processing unit 110 may send electronic signals to throttle system 220, braking system 230, and steering system 240 of vehicle 200 to trigger the desired navigation response, for example, by turning the steering wheel of vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, processing unit 110 may use the output of navigation response module 408 (e.g., the desired navigation response) as input to the execution of velocity and acceleration module 406 to calculate a change in velocity of vehicle 200.

[0162] Additionally, any of the modules disclosed herein (e.g., modules 402, 404, and 406) may implement techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems.

[0163] 5A is a flowchart illustrating an example process 500A for generating one or more navigational responses based on monocular image analysis, according to a disclosed embodiment. At step 510, processing unit 110 may receive a plurality of images via data interface 128 between processing unit 110 and image acquisition unit 120. For example, a camera (e.g., image capture device 122 having field of view 202) included in image acquisition unit 120 may capture a plurality of images of an area in front of vehicle 200 (or, for example, 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.). Processing unit 110 may execute monocular image analysis module 402 to analyze the plurality of images at step 520, as described in further detail below in connection with FIGS. 5B-5D . By performing the analysis, processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, and traffic lights.

[0164] Processing unit 110 may also execute monocular image analysis module 402 in step 520 to detect various road hazards, such as truck tire parts, fallen road signs, loose cargo, and small animals. Road hazards may vary in structure, shape, size, and color, making such hazards more difficult to detect. In some embodiments, processing unit 110 may execute monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road hazards. For example, processing unit 110 may estimate camera motion between consecutive image frames and calculate pixel discrepancies between frames to build a 3D map of the road. Processing unit 110 may then use the 3D map to detect the road surface and hazards present on the road surface.

[0165] At step 530, processing unit 110 may execute navigation response module 408 to cause one or more navigational responses in vehicle 200 based on the analysis performed in step 520 and the techniques described above in connection with FIG. 4 . Navigational responses may include, for example, a turn, a lane shift, and an acceleration change. In some embodiments, processing unit 110 may use data derived from execution of speed and acceleration module 406 to cause one or more navigational responses. Furthermore, multiple navigational responses may be performed simultaneously, sequentially, or any combination thereof. For example, processing unit 110 may cause vehicle 200 to cross a lane and then accelerate, for example, by sequentially sending control signals to steering system 240 and throttle system 220 of vehicle 200. Alternatively, processing unit 110 may cause vehicle 200 to brake and simultaneously shift lanes by simultaneously sending control signals to braking system 230 and steering system 240 of vehicle 200.

[0166] FIG. 5B 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 execute monocular image analysis module 402 to perform process 500B. In step 540, processing unit 110 may identify 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 locations within each image that may contain a target object (e.g., a vehicle, a pedestrian, or portions thereof). The predetermined patterns may be specified to achieve a low rate of “false hits” and a low rate of “misses.” For example, processing unit 110 may use a low similarity threshold to the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. By doing so, processing unit 110 may reduce the probability of missing (e.g., not identifying) a candidate object representing a vehicle or pedestrian.

[0167] At step 542, processing unit 110 may filter the set of candidate objects to exclude certain candidates (e.g., irrelevant or less relevant objects) based on classification criteria. Such criteria may be derived from various characteristics associated with object types stored in a database (e.g., a database stored in memory 140). The characteristics may include the object's shape, dimensions, texture, and location (e.g., relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to reject false candidates from the set of candidate objects.

[0168] At step 544, processing unit 110 may analyze multiple image frames to identify whether objects in the set of candidate images represent vehicles and / or pedestrians. For example, processing unit 110 may track detected candidate objects across successive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to vehicle 200, etc.). Additionally, processing unit 110 may estimate parameters of the detected objects and compare the object's frame-by-frame position data to predicted positions.

[0169] In step 546, processing unit 110 may construct a set of measurements of the detected objects. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to vehicle 200) associated with the detected objects. In some embodiments, processing unit 110 may construct the measurements based on estimation techniques using a series of time-based observations, such as a Kalman filter or linear quadratic estimation (LQE), and / or modeling data available for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). A Kalman filter may be based on a measure of the object's scale, where the scale measure is proportional to the time to impact (e.g., the amount of time it takes vehicle 200 to reach the object). Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing in the set of captured images and derive information (e.g., position, velocity, size) associated with the vehicles and pedestrians. Based on the identification and derived information, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in connection with FIG. 5A .

[0170] In step 548, processing unit 110 may perform optical flow analysis of one or more images to reduce the probability of detecting “false hits” and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing movement patterns, distinct from road surface movement, for vehicle 200 in one or more images associated with other vehicles and pedestrians. Processing unit 110 may calculate the movement of candidate objects by observing different positions of the object across multiple image frames captured at different times. Processing unit 110 may use the position and time values ​​as inputs to a mathematical model to calculate the movement of candidate objects. Thus, optical flow analysis may provide another method for detecting vehicles and pedestrians in the vicinity of vehicle 200. Processing unit 110 may perform optical flow analysis in combination with steps 540-546 to provide redundancy for detecting vehicles and pedestrians and increase the reliability of system 100.

[0171] 5C is a flowchart illustrating an example process 500C for detecting road marks and / or lane geometry information in a set of images according to the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500C. In step 550, processing unit 110 may detect a set of objects by scanning one or more images. To detect lane mark segments, lane geometry information, and other related road marks, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., small holes, small rocks, etc.). In step 552, processing unit 110 may group together segments detected in step 550 that belong to the same road or lane mark. Based on the grouping, processing unit 110 may develop a model, such as a mathematical model, to represent the detected segments.

[0172] At 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 the real-world plane. The projection may be characterized using a third-order polynomial with coefficients corresponding to physical properties of the detected road, such as its position, slope, curvature, and curvature derivative. In generating the projection, processing unit 110 may take into account road surface variations and pitch and roll rates associated with vehicle 200. Additionally, processing unit 110 may model road height by analyzing the position and motion cues present on the road surface. Furthermore, processing unit 110 may estimate pitch and roll rates associated with vehicle 200 by tracking a set of feature points in one or more images.

[0173] In step 556, processing unit 110 may perform a multi-frame analysis, for example, by tracking the detected segment across successive image frames and accumulating frame-by-frame data associated with the detected segment. When processing unit 110 performs a multi-frame analysis, the set of measurements constructed in step 554 may become more reliable and may be associated with an increasingly higher degree of confidence. Thus, by performing steps 550, 552, 554, and 556, processing unit 110 may identify road marks appearing in the set of captured images and derive lane geometry information. Based on the identification and derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described above in connection with FIG. 5A .

[0174] In step 558, processing unit 110 may consider additional information sources to further develop a safety model of vehicle 200 in the vehicle's surroundings. Processing unit 110 may use the safety model to define situations in which system 100 may safely perform autonomous control of vehicle 200. To develop the safety model, in some embodiments, processing unit 110 may consider the positions and movements of other vehicles, detected road edges and barriers, and / or general road shape descriptions extracted from map data (such as data from map database 160). By considering additional information sources, processing unit 110 may provide redundancy in detecting road marks and lane geometry and increase the reliability of system 100.

[0175] FIG. 5D is a flowchart illustrating an example process 500D for detecting traffic lights in a set of images according to disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500D. In step 560, processing unit 110 may scan the set of images and identify objects that appear in locations within the images that are likely to contain traffic lights. For example, processing unit 110 may filter the identified objects to construct a set of candidate objects that excludes objects that are unlikely to correspond to traffic lights. Filtering may be based on various characteristics associated with traffic lights, such as shape, size, texture, and location (e.g., relative to vehicle 200). Such characteristics may be based on many examples of traffic lights and traffic control signals and may be 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 the candidate objects across consecutive image frames, estimate the real-world locations 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 object to identify the relative location of the detected color represented within the potential traffic light.

[0176] In step 562, processing unit 110 may analyze the geometry of the intersection. The analysis may be based on any combination of (i) the number of lanes detected on either side of vehicle 200, (ii) markings (such as arrow markings) detected on the road, and (iii) a description of the intersection extracted from map data (such as data from map database 160). Processing unit 110 may perform the analysis using information derived from execution of monocular analysis module 402. In addition, processing unit 110 may identify correspondences between traffic lights detected in step 560 and lanes appearing near vehicle 200.

[0177] As vehicle 200 approaches the intersection, in step 564, processing unit 110 may update the confidence associated with the analyzed intersection geometry and detected traffic lights. For example, the number of traffic lights estimated to appear at the intersection compared to the number that actually appear at the intersection may affect the confidence. Thus, based on the confidence, processing unit 110 may delegate control to the driver of vehicle 200 to improve the safety situation. By performing steps 560, 562, and 564, processing unit 110 may identify traffic lights that appear in the set of captured images and analyze the intersection geometry information. Based on the identification and analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in connection with FIG. 5A .

[0178] 5E is a flowchart of an example process 500E for generating one or more navigation responses in vehicle 200 based on a vehicle path, according to a disclosed embodiment. In step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path may be represented using a set of points represented by coordinates (x, y), with the distance d between any two points in the set of points being i may be in the range of 1 to 5 meters. In one embodiment, processing unit 110 may construct an initial vehicle path using two polynomials, such as left and right road polynomials. Processing unit 110 may calculate the geometry midpoint between the two polynomials and, if there is a predetermined offset (a zero offset may correspond to driving in the center of the lane), offset each point in the resulting vehicle path by the predetermined offset (e.g., a smart lane offset). The offset may be perpendicular to the segment between any two points in the vehicle path. In another embodiment, processing unit 110 may use one polynomial and an estimated lane width to offset each point in the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0179] In step 572, processing unit 110 may update the vehicle path constructed in step 570. Processing unit 110 may update the distance d k is the distance d i A higher resolution may be used to reconstruct the vehicle path constructed in step 570 so that the distance d is shorter than k may be in the range of 0.1 to 0.3 meters. Processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may result in 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).

[0180] In step 574, processing unit 110 calculates the look-ahead point ((x l ,z l ) in coordinates. The processing unit 110 may extract look-ahead points from the cumulative distance vector S, and the look-ahead points may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance may have a lower bound range of 10 to 20 meters and may be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, as the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until a lower bound is reached). The look-ahead time, which may range from 0.5 to 1.5 seconds, may be inversely proportional to the gain of one or more control loops associated with producing a navigation response in the vehicle 200, such as a heading error tracking control loop. For example, the gain of the heading error tracking control loop may depend on the bandwidth of the yaw rate loop, the steering actuator loop, and the vehicle lateral dynamics. Thus, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0181] In step 576, processing unit 110 may determine a heading error and yaw rate command based on the look-ahead point identified in step 574. Processing unit 110 may calculate the arctangent of the look-ahead point, e.g., arctan(x l / z l) to identify the heading error. Processing unit 110 may determine the yaw rate command as the product of the heading error and a high-level control gain. The high-level control gain may be equal to (2 / look ahead time) if the look ahead distance is not at a lower limit. If the look ahead distance is at a lower limit, the high-level control gain may be equal to (2*velocity of vehicle 200 / look ahead distance).

[0182] 5F is a flowchart illustrating an example process 500F for determining whether a leading vehicle is changing lanes, according to the disclosed embodiments. In step 580, processing unit 110 may determine navigation information associated with the leading vehicle (e.g., a vehicle traveling in front of vehicle 200). For example, processing unit 110 may determine the position, velocity (e.g., direction and speed), and / or acceleration of the leading vehicle using the techniques described above in connection with FIGS. 5A and 5B. Processing unit 110 may also determine one or more road polynomials, lookahead points (associated with vehicle 200), and / or snail trails (e.g., a set of points describing the path taken by the leading vehicle) using the techniques described above in connection with FIG. 5E.

[0183] In step 582, processing unit 110 may analyze the navigation information identified in step 580. In one embodiment, processing unit 110 may calculate the distance (e.g., along the trail) between the snail trail and the road polynomial. If the difference in this distance along the trail exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters for a straight road, 0.3 to 0.4 meters for a gently curving road, or 0.5 to 0.6 meters for a sharply curving road), processing unit 110 may determine that the leading vehicle is likely changing lanes. If multiple vehicles are detected traveling in front of vehicle 200, processing unit 110 may compare the snail trails associated with each vehicle. Based on the comparison, processing unit 110 may determine that a vehicle whose snail trail does not match the snail trails of the other vehicles is likely changing lanes. Processing unit 110 may further compare the curvature of the snail trail (associated with the leading vehicle) to the expected curvature of the road segment along which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., data from map database 160), road polynomials, snail trails of other vehicles and prior knowledge about the road, etc. If the difference between the snail trail curvature and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely changing lanes.

[0184] In another embodiment, processing unit 110 may compare the instantaneous position of the leading vehicle to a look-ahead point (associated with vehicle 200) over a specific time period (e.g., 0.5-1.5 seconds). If the cumulative sum of the distance difference and divergence between the instantaneous position of the leading vehicle and the look-ahead point during the specific time period exceeds a predetermined threshold (e.g., 0.3-0.4 meters for straight roads, 0.7-0.8 meters for gently curving roads, and 1.3-1.7 meters for sharply curving roads), processing unit 110 may determine that the leading vehicle is likely changing lanes. In another embodiment, processing unit 110 may analyze the geometry of the snail trail by comparing the lateral distance traveled along the trail to the expected curvature of the snail trail. The expected radius of curvature is calculated as: (δz 2 +δ x 2 ) / 2 / (δ x ) in which σ x represents the lateral movement distance, and σ z represents the longitudinal movement distance. If the difference between the lateral movement distance and the expected curvature exceeds a predetermined threshold (e.g., 500-700 meters), processing unit 110 may determine that the leading vehicle is likely changing lanes. In another embodiment, processing unit 110 may analyze the position of the leading vehicle. If the position of the leading vehicle obscures the road polynomial (e.g., the leading vehicle overlaps the road polynomial), processing unit 110 may determine that the leading vehicle is likely changing lanes. If the position of the leading vehicle is such that another vehicle is detected ahead of the leading vehicle and the snail trails of the two vehicles are not parallel, processing unit 110 may determine that the (closer) leading vehicle is likely changing lanes.

[0185] In step 584, processing unit 110 may determine whether leading vehicle 200 is changing lanes based on the analysis performed in step 582. For example, processing unit 110 may make that determination based on a weighted average of the individual analyses performed in step 582. Under such a scheme, for example, a determination by processing unit 110 that the leading vehicle is likely to be changing lanes based on a particular type of analysis may be assigned a value of “1” (with a “0” representing a determination that the leading vehicle is unlikely to be changing lanes). Different weights may be assigned to different analyses performed in step 582, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0186] 6 is a flowchart illustrating an example process 600 for generating one or more navigational responses based on stereo image analysis, according to disclosed embodiments. In step 610, processing unit 110 may receive first and second pluralities of images via data interface 128. For example, cameras 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 pluralities of images of an area ahead 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 pluralities of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0187] At step 620, processing unit 110 may execute stereo image analysis module 404 to perform stereo image analysis of the first and second plurality of images to create a 3D map of the road ahead of the vehicle and detect features in the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road hazards. The stereo image analysis may be performed similarly to the steps described above in connection with FIGS. 5A-5D . For example, processing unit 110 may execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road marks, traffic lights, road hazards, etc.) in the first and second plurality of images, filter out a subset of the candidate objects based on various criteria, perform multi-frame analysis, construct measurements, and identify 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 only one 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 a candidate object that appears in both the first and second plurality of images. As another example, processing unit 110 may estimate the position and / or velocity (e.g., relative to vehicle 200) of a candidate object by observing that the object appears in one of the plurality of images but not in the other, or other differences that may exist for the object appearing in the two image streams. For example, the position, velocity, and / or acceleration relative to vehicle 200 may be determined based on the trajectory, location, movement characteristics, etc. of features associated with the object that appear in one or both of the image streams.

[0188] In step 630, processing unit 110 may execute navigation response module 408 to generate one or more navigational responses in vehicle 200 based on the analysis performed in step 620 and the techniques described above in connection with FIG. 4. The navigational responses may include, for example, turns, lane shifts, acceleration changes, speed changes, braking, etc. In some embodiments, processing unit 110 may generate one or more navigational responses using data derived from execution of speed and acceleration module 406. Furthermore, multiple navigational responses may be performed simultaneously, sequentially, or any combination thereof.

[0189] 7 is a flowchart illustrating an example process 700 for generating one or more navigational responses based on the analysis of three sets of images, according to disclosed embodiments. In step 710, processing unit 110 may receive first, second, and third pluralities 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 pluralities of images of an area in front of and / or to the sides of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive the first, second, and third pluralities 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 that communicates data to processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0190] At step 720, processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road hazards. The analysis may be performed similar to the steps described above in connection with FIGS. 5A-5D and 6. 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 of monocular image analysis module 402 and based on the steps described above in connection with FIGS. 5A-5D). Alternatively, processing unit 110 may perform stereo image analysis on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images (e.g., via execution of stereo image analysis module 404 and based on the steps described above in connection with FIG. 6). Processed information corresponding to the analysis of the first, second, and / or third plurality of images may be combined. In some embodiments, processing unit 110 may perform a combination of monocular image analysis and stereo image analysis. For example, processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via execution of monocular image analysis module 402) and stereo image analysis on the second and third plurality of images (e.g., via execution of stereo image analysis module 404). The configuration of image capture devices 122, 124, and 126—including their respective positions and fields of view 202, 204, and 206—may affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a particular configuration of image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0191] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed in steps 710 and 720. Such tests may provide an indicator of the overall performance of system 100 with a particular configuration of image capture devices 122, 124, and 126. For example, processing unit 110 may identify the rate of "false hits" (e.g., when system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses."

[0192] In step 730, processing unit 110 may cause one or more navigation responses in vehicle 200 based on information derived from two of the first, second, and third pluralities of images. The selection of two of the first, second, and third pluralities of images may depend on various factors, such as, for example, the number, type, and size of objects detected in each of the multiple images. Processing unit 110 may make the selection based on the quality and resolution of the images, the effective field of view reflected in the images, the number of captured frames, and the extent to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which the object appears, the proportion in which the object appears in each such frame, etc.).

[0193] In some embodiments, processing unit 110 may select information derived from two of the first, second, and third pluralities of images by identifying the extent to which information derived from one image source is consistent with information derived from the other image sources. For example, processing unit 110 may combine processed information (whether monocular analysis, stereo analysis, or any combination of the two) derived from each of image capture devices 122, 124, and 126 to identify visual indicators (e.g., lane markings, detected vehicles and / or their positions and / or paths, detected traffic lights, etc.) that are consistent across the captured images from each of image capture devices 122, 124, and 126. Processing unit 110 may also filter out information that is inconsistent across the captured images (e.g., a vehicle changing lanes, a lane model showing a vehicle too close to vehicle 200, etc.). Thus, processing unit 110 may select information derived from two of the first, second, and third pluralities of images based on the identification of consistent and inconsistent information.

[0194] The navigational responses may include, for example, turns, lane shifts, and acceleration changes. Processing unit 110 may generate one or more navigational responses based on the analysis performed in step 720 and the techniques described above in connection with FIG. 4 . Processing unit 110 may also generate one or more navigational responses using data derived from execution of velocity and acceleration module 406. In some embodiments, processing unit 110 may generate one or more navigational responses based on the relative position, relative velocity, and / or relative acceleration between vehicle 200 and an object detected in any of the first, second, and third plurality of images. The multiple navigational responses may be performed simultaneously, sequentially, or any combination thereof.

[0195] Analysis of the captured images may enable the generation and use of a sparse map model for autonomous vehicle navigation. Additionally, analysis of the captured images may enable localization of an autonomous vehicle using identified lane markings. Embodiments for detecting specific characteristics based on one or more specific analyses of the captured images, and for navigating an autonomous vehicle using the sparse map model, are discussed below with reference to Figures 8-28C.

[0196] Sparse Road Models for Autonomous Vehicle Navigation

[0197] In some embodiments, the disclosed systems and methods may use a sparse map for autonomous vehicle navigation. Specifically, the sparse map may be for autonomous vehicle navigation along road segments. For example, the sparse map may provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed in more detail below, an autonomous vehicle may use the sparse map to navigate one or more roads based on one or more stored trajectories.

[0198] Sparse Maps for Autonomous Vehicle Navigation

[0199] In some embodiments, the disclosed systems and methods may create sparse maps for autonomous vehicle navigation. For example, the sparse map may 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) may navigate one or more roads using the sparse map. For example, in some embodiments, the sparse map may include data related to the road and potential landmarks along the road that may be sufficient for vehicle navigation but also present a small data footprint. For example, the sparse data map, described in more detail below, may require significantly less storage space and data transfer bandwidth compared to a digital map that includes detailed map information, such as image data collected along the road.

[0200] For example, rather than storing detailed representations of road segments, a sparse data map may store three-dimensional polynomial representations of preferred vehicle paths along roads. These paths may require little data storage space. Furthermore, in the described sparse data maps, landmarks may be identified and included in the sparse map road model to aid navigation. These landmarks may be spaced at any suitable interval to enable vehicle navigation, although in some cases, it is not necessary to identify and include such landmarks at high density and at short intervals. Rather, in some cases, navigation may be possible based on landmarks at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart. As discussed in more detail in other sections, sparse maps may be generated based on data collected or measured by vehicles equipped with various sensors and devices, such as image capture devices, global positioning system sensors, and motion sensors, as the vehicles travel along roads. In some cases, sparse maps may be generated based on data collected during multiple trips of one or more vehicles along a particular road. Generating a sparse map using multiple trips of one or more vehicles can be referred to as "crowdsourcing" the sparse map.

[0201] According to disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed systems and methods may deliver a sparse map for generating a road navigation model for an autonomous vehicle and navigate the autonomous vehicle along a road segment using the sparse map and / or the generated road navigation model. A sparse map according to the present disclosure may include one or more three-dimensional contours that may represent predetermined trajectories that the autonomous vehicle may traverse when traveling along the associated road segment.

[0202] Sparse maps according to the present disclosure may also include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and other road-related features useful for navigating a vehicle. Sparse maps according to the present disclosure may enable autonomous navigation of a vehicle based on a relatively small amount of data included in the sparse map. For example, even without including detailed representations of roads, such as data detailing road edges, road curvature, images associated with road segments, or other physical features associated with road segments, disclosed embodiments of sparse maps may require relatively little storage space (and relatively little bandwidth when portions of the sparse map are transferred to the vehicle) but may still adequately provide autonomous vehicle navigation. The small data footprint of the disclosed sparse maps, discussed in more detail below, may be achieved in some embodiments by storing representations of road-related elements that require a small amount of data but still enable autonomous navigation.

[0203] For example, rather than storing detailed representations of various aspects of a road, the disclosed sparse maps may store polynomial representations of one or more trajectories that a vehicle may follow along the road. Thus, using the disclosed sparse maps, rather than storing (or having to transfer) details about the physical properties of the road to enable navigation along the road, a vehicle may be navigated along a particular road segment, in some cases, without having to interpret the physical aspects of the road, but rather by aligning its travel path to a trajectory (e.g., a polynomial spline) along the particular road segment. In this way, a vehicle may be navigated primarily based on the stored trajectory (e.g., a polynomial spline), which may require much less storage space than approaches that include storing road images, road parameters, road layouts, etc.

[0204] 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 may 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) mounted on a vehicle traveling along the road segment. The digital signatures may be of reduced size relative to the signals acquired by the sensors. In some embodiments, the digital signatures may be created to be compatible with classifier functions configured to detect and identify road features from signals acquired by the sensors during the travel, for example. In some embodiments, the digital signatures may be created to have as small a footprint as possible while retaining the ability to correlate or match road features with the stored signatures based on images of the road features captured by a camera mounted on a vehicle subsequently traveling along the same road segment (or digital signals generated by a sensor, if the stored signature is not based on images and / or includes other data).

[0205] In some embodiments, the size of the data object may be further related to the uniqueness of the road feature. For example, for a road feature detectable by a vehicle-mounted camera, if the vehicle-mounted camera system is coupled to a classifier that can distinguish image data corresponding to the road feature as being associated with a particular type of road feature, e.g., a road sign, and if such road sign is locally unique in the region (e.g., there are no identical or type of road signs nearby), it may be sufficient to store data indicating the type of road feature and its location.

[0206] As discussed in more detail below, road features (e.g., landmarks along a road segment) may be stored as small data objects that can represent the road feature in a relatively few bytes while providing sufficient information to recognize and use such features for navigation. In one example, road signs may be identified as recognized landmarks upon which vehicle navigation may be based. Representations of road signs may 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 landmark's location (e.g., coordinates). Navigating based on such data-aspect representations of landmarks (e.g., using representations sufficient to locate, recognize, and navigate based on the landmarks) may provide the desired level of navigation functionality associated with sparse maps without significantly increasing the data overhead associated with sparse maps. Such lean representations of landmarks (and other road features) may take advantage of sensors and processors onboard such vehicles that are configured to detect, identify, and / or classify specific road features.

[0207] For example, if a sign or a particular type of sign is locally unique in a particular area (e.g., there are no other signs or there are no other signs of the same type), the sparse map may use data indicating the type of landmark (sign or particular type of sign), and during navigation (e.g., autonomous navigation) when a camera mounted on an autonomous vehicle captures an image of an area containing the sign (or particular type of sign), a processor may process the image, detect the sign (if in fact present in the image), classify the image as a sign (or as a particular type of sign), and correlate the location of the image with the location of the sign stored in the sparse map.

[0208] Sparse map generation

[0209] In some embodiments, the sparse map may include at least one line representation of a road surface feature extending along the road segment and a plurality of landmarks associated with the road segment. In certain aspects, the sparse map may be generated through "crowdsourcing," e.g., through image analysis of a plurality of images acquired as one or more vehicles traverse the road segment.

[0210] 8 illustrates a sparse map 800 that one or more vehicles, e.g., vehicle 200 (which may be an autonomous vehicle), may access to provide autonomous vehicle navigation. 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 drive, a compact disc, flash memory, a magnetic-based memory device, an optical-based memory device, etc. In some embodiments, sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150 or another type of storage device.

[0211] In some embodiments, sparse map 800 may be stored on a storage device or non-transitory computer-readable medium (e.g., a storage device included in a navigation system onboard vehicle 200) onboard vehicle 200. A processor (e.g., processing unit 110) onboard vehicle 200 may access sparse map 800 stored on a storage device or computer-readable medium onboard vehicle 200 to generate navigation instructions for guiding autonomous vehicle 200 as the vehicle traverses road segments.

[0212] However, sparse map 800 need not be stored locally with respect to the vehicle. In some embodiments, sparse map 800 may be stored on a storage device or computer-readable medium provided on a remote server in communication with vehicle 200 or a device associated with vehicle 200. A processor (e.g., processing unit 110) onboard vehicle 200 may receive the data included in sparse map 800 from the remote server and execute the data to guide the automated navigation of vehicle 200. In such embodiments, the remote server may store all or only a portion of sparse map 800. Accordingly, a storage device or computer-readable medium onboard vehicle 200 and / or one or more additional vehicles may store the remaining portions of sparse map 800.

[0213] Further, in such embodiments, sparse map 800 may be accessible to multiple vehicles (e.g., tens, hundreds, thousands, or millions of vehicles) traversing various road segments. Note also that sparse map 800 may include multiple sub-maps. For example, in some embodiments, sparse map 800 may include hundreds, thousands, millions, or more sub-maps that may be used in navigating a vehicle. Such sub-maps may be referred to as local maps, and a vehicle traveling along a road may access any number of local maps relevant to where the vehicle is traveling. The local map areas of sparse map 800 may be stored with a global navigation satellite system (GNSS) key as an index into a database of sparse map 800. Thus, steering angle calculations for navigating a host vehicle in the system may be performed without relying on the GNSS position of the host vehicle, road features, or landmarks, although such GNSS information may be used to look up the relevant local map.

[0214] The collection of data and generation of sparse map 800 are described in more detail below, for example, with respect to FIG. 19 . In general, however, sparse map 800 may be generated based on data collected from one or more vehicles as they travel along a road. For example, sensors (e.g., cameras, speedometers, GPS, accelerometers, etc.) mounted on one or more vehicles may be used to record the trajectories of one or more vehicles traveling along a road, and a polynomial representation of a preferred trajectory for a vehicle making a subsequent trip along the road may be determined based on the collected trajectories traveled by one or more vehicles. Similarly, data collected by one or more vehicles may assist in identifying potential landmarks along a particular road. Data collected from traversing vehicles may also be used to identify road profile information, such as a road width profile, a road roughness profile, a traffic line spacing profile, road conditions, etc. Using the collected information, sparse map 800 may be generated and distributed (e.g., for local storage or via on-the-fly data transmission) for use in navigating one or more autonomous vehicles. However, in some embodiments, map generation may not end with the initial birth of the map. As discussed in more detail below, sparse map 800 may be continuously or periodically updated based on data collected from vehicles as they continue to traverse roads included in sparse map 800.

[0215] 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 may be obtained using GPS data collected from vehicles traversing roads. For example, a vehicle passing an identified landmark may determine the location of the identified landmark using GPS location information associated with the vehicle and determine the location of the identified landmark relative to the vehicle (e.g., based on image analysis of data collected from one or more cameras mounted on the vehicle). Such location determination of the identified landmark (or other feature included in the sparse map 800) may be repeated as additional vehicles pass the location of the identified landmark. Some or all of the additional location determinations may be used to refine the location information stored in the sparse map 800 associated with the identified landmark. For example, in some embodiments, multiple location measurements associated with a particular feature stored in the sparse map 800 may be averaged together. However, any other mathematical operation may be used to refine the stored location of the map element based on multiple determined locations of the map element.

[0216] The sparse maps of the disclosed embodiments may enable autonomous navigation of a vehicle using a relatively small amount of stored data. In some embodiments, the sparse map 800 may have a data density (e.g., including data representing target trajectories, landmarks, and other stored road features) of less than 2 MB per kilometer of road, less than 1 MB per kilometer of road, less than 500 kB per kilometer of road, or less than 100 kB per kilometer of road. In some embodiments, the data density of the sparse map 800 may be less than 10 kB per kilometer of road, or less than 2 kB per kilometer of road (e.g., 1.6 kB per kilometer), or 10 kB or less per kilometer of road, or 20 kB or less per kilometer of road. In some embodiments, most, if not all, of the roads in the United States may be navigated autonomously using a sparse map having a total of 4 GB or less of data. These data density values ​​may represent averages across the entire sparse map 800, across local maps within the sparse map 800, and / or across specific road segments within the sparse map 800.

[0217] As mentioned above, 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 cubic splines. The target trajectories stored in the sparse map 800 may be determined based on two or more reconstructed trajectories of a vehicle's previous trajectories along a particular road segment, for example, as discussed with respect to FIG. 29 . A road segment may be associated with a single target trajectory or multiple target trajectories. For example, on a two-lane road, a first target trajectory may be stored to represent an intended driving path along the road in a first direction, and a second target trajectory may be stored to represent an intended driving path along the road in another direction (e.g., opposite the first direction). Additional target trajectories may be stored for a particular road segment. For example, on a multi-lane road, one or more target trajectories may be stored representing the vehicle's intended driving path for one or more lanes associated with the multi-lane road. In some embodiments, each lane of a multi-lane road may be associated with its own target trajectory. In other embodiments, there may be fewer stored target trajectories than there are lanes on a multi-lane road. In such cases, a vehicle navigating a multi-lane road may use any of the stored target trajectories to guide navigation, taking into account the amount of lane offset from the lane for which the target trajectory is stored (e.g., if a vehicle is traveling in the leftmost lane of a three-lane highway and target trajectories are stored only for the center lane of the highway, the vehicle may navigate using the target trajectory of the center lane, taking into account the amount of lane offset between the center lane and the leftmost lane, when generating navigation instructions).

[0218] In some embodiments, the target trajectory may represent an ideal path that the vehicle should take as it travels. The target trajectory may be positioned approximately in the center of the driving lane, for example. In other cases, the target trajectory may be positioned elsewhere relative to the road segment. For example, the target trajectory may approximately coincide with the center of the road, the edge of the road, or the edge of the lane. In such cases, navigation based on the target trajectory may include a determined amount of offset to maintain relative to the position of the target trajectory. Furthermore, in some embodiments, the determined amount of offset to maintain relative to the position of the target trajectory may differ based on the type of vehicle (e.g., a passenger car including two axles may have a different offset along at least a portion of the target trajectory than a truck including three or more axles).

[0219] The sparse map 800 may also include data related to a number of predetermined landmarks 820 associated with particular road segments, local maps, etc. As discussed in more detail below, these landmarks may be used to navigate the autonomous vehicle. For example, in some embodiments, the landmarks may be used to determine the vehicle's current position relative to a stored target trajectory. Using this position information, the autonomous vehicle may be able to adjust its heading to match the direction of the target trajectory at the determined location.

[0220] Multiple landmarks 820 may be identified and stored in sparse map 800 at any suitable interval. In some embodiments, landmarks may be stored at a relatively high density (e.g., every few meters or more). However, in some embodiments, significantly larger landmark spacing values ​​may be used. For example, in sparse map 800, identified (or recognized) landmarks may be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, identified landmarks may be located more than 2 kilometers apart.

[0221] While determining the vehicle's position between landmarks, and thus relative to the target trajectory, the vehicle may navigate based on dead reckoning, in which the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Errors may accumulate during dead reckoning navigation, causing the accuracy of the position determination relative to the target trajectory to gradually decrease over time. The vehicle may use landmarks present in the sparse map 800 (and their known locations) to eliminate dead reckoning-induced errors in the position determination. In this manner, identified landmarks included in the sparse map 800 may serve as navigation anchors, from which the vehicle's precise position relative to the target trajectory may be determined. Because some error may be tolerated in the position determination, the identified landmarks need not always be available to the autonomous vehicle. Rather, as noted above, adequate navigation may be possible based on landmark spacing of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or even more. In some embodiments, a density of one identified landmark per kilometer of road may be sufficient to maintain longitudinal positioning accuracy within 1 meter, and therefore not all potential landmarks that appear along a road segment need to be stored in sparse map 800.

[0222] Additionally, in some embodiments, lane marks may be used to locate the vehicle between landmark intervals. Using lane marks between landmark intervals may minimize buildup during dead-reckoning navigation. Such localization, in particular, is discussed below with respect to FIG. 35.

[0223] In addition to the target trajectory and identified landmarks, the sparse map 800 may include information related to various other road features. For example, FIG. 9A shows a representation of a curve along a particular road segment that may be stored in the sparse map 800. In some embodiments, a single lane of a road may be modeled by a three-dimensional polynomial description of the left and right sides of the road. Such polynomials representing the left and right sides of a single lane are shown in FIG. 9A . Regardless of the number of lanes a road may have, polynomials may be used to represent the road in a manner similar to that shown in FIG. 9A . For example, the left and right sides of a multi-lane road may be represented by polynomials similar to those shown in FIG. 9A , and intermediate lane markings included in a multi-lane road (e.g., dashed line markings representing lane boundaries, solid yellow lines representing boundaries between lanes traveling in different directions, etc.) may also be represented using polynomials such as those shown in FIG. 9A .

[0224] As shown in FIG. 9A , lane 900 may be represented using a polynomial (e.g., a linear, quadratic, cubic, or any suitable degree polynomial). For purposes of illustration, lane 900 is shown as a two-dimensional lane, and the polynomials are shown as two-dimensional polynomials. As shown in FIG. 9A , lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial may be used to represent positions on each side of a road or lane boundary. For example, left side 910 and right side 920 may each be represented by multiple polynomials of any suitable length. In some cases, the polynomials may be approximately 100 meters long, although other lengths greater or less than 100 meters may also be used. Furthermore, polynomials may overlap one another to facilitate seamless transitions when navigating based on subsequently encountered polynomials as the host vehicle travels along the roadway. For example, each of the left side 910 and the right side 920 may be represented by multiple third-order polynomials separated into segments approximately 100 meters in length (an example first predetermined range) and overlapping each other by approximately 50 meters. The polynomials representing the left side 910 and the right side 920 may or may not be in 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.

[0225] In the example shown in FIG. 9A , the left side 910 of lane 900 is represented by two groups of third-order polynomials. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. The two groups are substantially parallel to each other but follow their respective positions on each side of the road. Polynomial segments 911, 912, 913, 914, 915, and 916 are approximately 100 meters long and overlap adjacent segments in the series by approximately 50 meters. However, as noted above, the length and amount of overlap may also use different polynomials. For example, the polynomials may be 500 meters, 1 km, or longer, and the amount of overlap may vary from 0 to 50 meters, from 50 meters to 100 meters, or greater than 100 meters. 9A is shown as representing polynomials extending in 2D space (e.g., on the surface of a piece of paper), it should be understood that these polynomials may represent curves extending in three dimensions (e.g., including a height component) to represent changes in elevation of the road segment in addition to XY curvature. In the example shown in FIG. 9A, the right side 920 of lane 900 is further represented by a first group having polynomial sections 921, 922, and 923, and a second group having polynomial sections 924, 925, and 926.

[0226] Returning to the target trajectories of the sparse map 800, FIG. 9B shows a cubic polynomial that represents a target trajectory for a vehicle traveling along a particular road segment. The target trajectory represents not only the XY path that the host vehicle should travel along a particular road segment, but also the elevation changes that the host vehicle will experience as it travels along the road segment. Thus, each target trajectory in the sparse map 800 may be represented by one or more cubic polynomials, such as cubic polynomial 950 shown in FIG. 9B. The sparse map 800 may include multiple trajectories (e.g., millions or billions or more to represent vehicle trajectories along various road segments along roads around the world). In some embodiments, each target trajectory may correspond to a spline connecting the cubic polynomial segments.

[0227] With respect to the data footprint of the polynomial curves stored in sparse map 800, in some embodiments, each third-order polynomial is represented by four parameters, each of which may require four bytes of data. A suitable representation may be obtained with a third-order polynomial requiring approximately 192 bytes of data per 100 meters. This may translate to a data usage / transfer requirement of approximately 200 kB per hour for a host vehicle traveling approximately 100 km / hr.

[0228] The sparse map 800 may describe the lane network using a combination of geometry descriptors and metadata. The geometry may be described with polynomials or splines, as described above. The metadata may describe the number of lanes, special characteristics (such as carpool lanes), and possibly other sparse labels. The total footprint of such metrics may be negligible.

[0229] Thus, a sparse map according to embodiments of the present disclosure may include at least one line representation of a road surface feature extending along a road segment, with each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as discussed above, the at least one line representation of the road surface feature may include a spline, a polynomial representation, or a curve. Further, in some embodiments, the road surface feature may include at least one of a road edge or a lane marking. Furthermore, as discussed below with respect to "crowdsourcing," the road surface feature may be identified by image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0230] As previously described, sparse map 800 may include a plurality of predetermined landmarks associated with a road segment. Rather than storing actual images of the landmarks and relying, for example, on image recognition analysis based on captured and stored images, each landmark in sparse map 800 may be represented and recognized using less data than a stored actual image would require. The data representing the landmarks may include sufficient information to describe or identify the landmarks along the road. Storing data describing the characteristics of the landmarks rather than actual images of the landmarks may reduce the size of sparse map 800.

[0231] FIG. 10 shows examples of types of landmarks that may be represented in sparse map 800. Landmarks may include visible and identifiable objects along a road segment. Landmarks may be selected to be fixed and infrequently changing in terms of location and / or content. Landmarks included in sparse map 800 may be useful in determining the position of vehicle 200 relative to a target trajectory as the vehicle traverses a particular road segment. Examples of landmarks may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside furniture (e.g., lampposts, reflectors), and other suitable categories. In some embodiments, lane markings on roads may also be included as landmarks in sparse map 800.

[0232] 10 includes traffic signs, directional signs, roadside furniture, 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 including one or more arrows indicating one or more directions to different locations. For example, directional signs may include a highway sign 1025 with arrows for directing vehicles to different roads or locations, an exit sign 1030 with arrows for directing vehicles to exit a road, etc. Thus, at least one of the plurality of landmarks may include a road sign.

[0233] A general sign may be non-traffic related. For example, a general sign may include a billboard used in advertising or a welcome board adjacent to the boundary between two countries, states, counties, cities, or towns. Figure 10 shows a general sign 1040 ("Joe's Restaurant"). As shown in Figure 10, the general sign 1040 may have a rectangular shape, although the general sign 1040 may have other shapes such as a square, circle, triangle, etc.

[0234] Landmarks may also include roadside furniture. Roadside furniture may be objects that are not signs and may not be traffic or directional related. For example, roadside furniture may include lampposts (e.g., lamppost 1035), power poles, traffic light poles, etc.

[0235] Landmarks may also include beacons specially designed for use in autonomous vehicle navigation systems. For example, such beacons may include freestanding structures placed at predetermined intervals to assist a host vehicle in navigating. Such beacons may also include visual / graphical information added to existing road signs (e.g., icons, emblems, bar codes, etc.) that can be identified or recognized by vehicles traveling along a road segment. Such beacons may also include electronic components. In such embodiments, electronic beacons (e.g., RFID tags, etc.) may be used to transmit non-visual information to the host vehicle. Such information may include, for example, landmark-specific and / or landmark location information that the host vehicle can use in determining its position along the target trajectory.

[0236] 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 landmark's physical size (e.g., to support estimation of distance to the landmark based on a known size / scale), distance to the previous landmark, lateral offset, height, type code (e.g., landmark type—directional sign, traffic sign, etc.), GPS coordinates (e.g., to support global localization), and other suitable parameters. Each parameter may be associated with a data size. For example, landmark size may be stored using 8 bytes of data. The distance to the previous landmark, lateral offset, and height may be specified using 12 bytes of data. A type code associated with a landmark such as a directional sign or traffic sign may require approximately 2 bytes of data. For a generic sign, an image signature that allows identification of the generic sign may be stored using 50 bytes of data storage. The GPS location of a landmark may be associated with 16 bytes of data storage. These data sizes for each parameter are merely examples and other data sizes may be used.

[0237] Representing landmarks in the sparse map 800 in this manner may provide a lean solution for efficiently representing landmarks in a database. In some embodiments, signs may be referred to as semantic and non-semantic signs. Semantic signs may include any class of signs with a standardized meaning (e.g., speed limit signs, warning signs, directional signs, etc.). Non-semantic signs may include any signs not associated with a standardized meaning (e.g., general advertising signs, signs identifying businesses, etc.). For example, each semantic sign may be represented by 38 bytes of data (e.g., 8 bytes for size, 12 bytes for distance to previous landmark, lateral offset, height, 2 bytes for type code, and 16 bytes for GPS coordinates). The sparse map 800 may use a tag system to represent landmark types. In some cases, each traffic or directional sign may be associated with a unique tag, which may be stored in the database as part of the landmark ID. For example, the database may include as many as 1,000 different tags to represent various traffic signs and as many as 10,000 different tags to represent directional signs. Of course, any suitable number of tags may be used, and additional tags may be created as needed. A generic sign may, in some embodiments, be represented using less than about 100 bytes (e.g., about 86 bytes, including 8 bytes for size, 12 bytes for distance to previous landmark, lateral offset, and height, 50 bytes for image signature, and 16 bytes for GPS coordinates).

[0238] Thus, for semantic road signs that do not require image signatures, the data density impact on sparse map 800 can be as much as about 760 bytes per kilometer, even with a relatively high landmark density of about 1 per 50 meters (e.g., 20 landmarks per km × 38 bytes per landmark = 760 bytes). For generic signs that include an image signature component, the data density impact is still about 1.72 kB per km (e.g., 20 landmarks per km × 86 bytes per landmark = 1,720 bytes). For semantic road signs, this corresponds to a data usage of about 76 kB per hour for a vehicle traveling at 100 km / hr. For generic signs, this corresponds to a data usage of about 170 kB per hour for a vehicle traveling at 100 km / hr.

[0239] In some embodiments, a generally rectangular object, such as a rectangular sign, may be represented in sparse map 800 with 100 bytes of data or less. A representation of a generally rectangular object (e.g., generic sign 1040) in sparse map 800 may include a condensed image signature (e.g., condensed image signature 1045) associated with the generally rectangular object. This condensed image signature may be used, for example, to aid in the identification of the generic sign, e.g., as a recognized landmark. Such a condensed image signature (e.g., image information derived from actual image data representing the object) may avoid the need to store actual images of the object or the need for comparative image analysis to be performed on the actual images in order to recognize the landmark.

[0240] 10 , sparse map 800 may include or store a condensed image signature 1045 associated with generic sign 1040, rather than an actual image of generic sign 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of generic sign 1040, a processor (e.g., image processor 190 or any other processor capable of processing images, either on-board or remotely located relative to the host vehicle) may perform image analysis to extract / create condensed image signature 1045 that includes a unique signature or pattern associated with generic sign 1040. In one embodiment, condensed image signature 1045 may include a shape, color pattern, brightness pattern, or any other feature that can be extracted from an image of generic sign 1040 to describe generic sign 1040.

[0241] For example, in FIG. 10 , the circles, triangles, and stars shown in condensed image signature 1045 may represent regions of different colors. The patterns represented by the circles, triangles, and stars may be stored in sparse map 800, e.g., within the 50 bytes designated to contain the image signature. Notably, the circles, triangles, and stars are not meant to necessarily indicate that such shapes are stored as part of the image signature. Rather, these shapes are intended to conceptually represent recognizable regions having distinguishable color differences, text areas, graphic shapes, or other variations of characteristics that may be associated with generic signs. Such condensed image signatures may be used to identify landmarks in the form of generic signs. For example, the condensed image signatures may be used to perform a match analysis based on a comparison of image data captured using, for example, a camera mounted on an autonomous vehicle to the stored condensed image signature.

[0242] Thus, multiple landmarks may be identified by image analysis of multiple images acquired as one or more vehicles traverse a road segment. As described below with respect to "crowdsourcing," in some embodiments, image analysis to identify multiple landmarks may include accepting a potential landmark if a ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold. Further, in some embodiments, image analysis to identify multiple landmarks may include rejecting a potential landmark if a ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0243] Returning to the target trajectory that the host vehicle may use to navigate a particular road segment, FIG. 11A illustrates a polynomial representation trajectory captured during the process of building or maintaining sparse map 800. The polynomial representation of the target trajectory included in sparse map 800 may be determined based on two or more reconstructed trajectories of the vehicle's previous trajectories along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in sparse map 800 may be an aggregation of two or more reconstructed trajectories of the vehicle's previous trajectories along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in sparse map 800 may be an average of two or more reconstructed trajectories of the vehicle's previous trajectories along the same road segment. Other mathematical operations may also be used to construct a target trajectory along a road path based on reconstructed trajectories collected from vehicles traversing along the road segment.

[0244] As shown in FIG. 11A, road segment 1100 may be traveled by multiple vehicles 200 at different times. Each vehicle 200 may collect data related to the path the vehicle took along a road segment. The path traveled by a particular vehicle may be determined based on camera data, accelerometer information, speed sensor information, and / or GPS information, among other potential sources of information. Such data may be used to reconstruct the trajectory of the vehicle traveling along the road segment, and based on these reconstructed trajectories, a target trajectory (or target trajectories) for the particular road segment may be determined. Such target trajectories may represent a preferred path for the host vehicle (e.g., as guided by an autonomous navigation system) as the vehicle travels along the road segment.

[0245] 11A , a first reconstructed trajectory 1101 may 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 may 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 may be obtained from a third vehicle traversing road segment 1100 during a third time period (e.g., day 3). Each of trajectories 1101, 1102, and 1103 may be represented by a polynomial, such as a cubic polynomial. Note that in some embodiments, any of the reconstructed trajectories may be provided to and assembled on a vehicle traversing road segment 1100.

[0246] Additionally or alternatively, such reconstructed trajectories may be determined on the server side based on information received from vehicles traversing road segment 1100. For example, in some embodiments, vehicles 200 may transmit data related to their movement along road segment 1100 (e.g., steering angle, heading, time, position, speed, detected road geometry, and / or detected landmarks, among others) to one or more servers. The servers may reconstruct the trajectories of vehicles 200 based on the received data. The server may also generate a target trajectory based on first, second, and third trajectories 1101, 1102, and 1103 to guide the navigation of autonomous vehicles that subsequently travel along the same road segment 1100. While a target trajectory may be associated with a single previous traversal of a road segment, in some embodiments, each target trajectory included in sparse map 800 may be determined based on two or more reconstructed trajectories of vehicles traversing the same road segment. In FIG. 11A , the target trajectory is represented by 1110. In some embodiments, the target trajectory 1110 may be generated based on an average of the first, second, and third trajectories 1101, 1102, and 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 may be an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories. Aligning trip data to construct a trajectory is further discussed below with reference to FIG. 29.

[0247] 11B and 11C further illustrate the concept of a target trajectory associated with road segments present within a geographic region 1111. As shown in FIG. 11B , a first road segment 1120 within the geographic region 1111 may include a multi-lane road including two lanes 1122 designated for vehicle travel in a first direction and two additional lanes 1124 designated for vehicle travel in a second direction opposite the first direction. The lanes 1122 and 1124 may be separated by a double yellow line 1123. The geographic region 1111 may also include a branch road segment 1130 that intersects with the road segment 1120. The road segment 1130 may include a two-lane road, with each lane designated for a different direction of travel. The geographic region 1111 may also include other road features, such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0248] 11C , sparse map 800 may include a local map 1140 that includes a road model to assist in the autonomous navigation of a vehicle within geographic region 1111. For example, local map 1140 may include target trajectories for one or more lanes associated with road segments 1120 and / or 1130 within geographic region 1111. For example, local map 1140 may include target trajectories 1141 and / or 1142 that the autonomous vehicle may access or rely on when traversing lane 1122. Similarly, local map 1140 may include target trajectories 1143 and / or 1144 that the autonomous vehicle may access or rely on when traversing lane 1124. Additionally, local map 1140 may include target trajectories 1145 and / or 1146 that the autonomous vehicle may access or rely on when traversing road segment 1130. Target trajectory 1147 represents a preferred path that the autonomous vehicle should follow when transitioning from lane 1120 (specifically, corresponding to target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (specifically, corresponding to target trajectory 1145 associated with a first side of road segment 1130). Similarly, target trajectory 1148 represents a preferred path that the autonomous vehicle should follow when transitioning from road segment 1130 (specifically, corresponding to target trajectory 1146) to a portion of road segment 1124 (specifically, corresponding to target trajectory 1143 associated with the left lane of lane 1124, as shown).

[0249] The sparse map 800 may also include representations of other road-related features associated with the geographic region 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in the geographic region 1111. Such landmarks may include a first landmark 1150 associated with a stop line 1132, a second landmark 1152 associated with a stop sign 1134, a third landmark 1154 associated with a speed limit sign 1154, and a fourth landmark 1156 associated with a hazard sign 1138. Such landmarks may be used, for example, to assist an autonomous vehicle in determining its current position relative to any of the depicted target trajectories, so that the vehicle may adjust its heading to match the direction of the target trajectory at the determined location. Navigating using landmarks from a sparse map is discussed further below with reference to FIG. 26 .

[0250] In some embodiments, the sparse map 800 may also include a road signature profile. Such a road signature profile may be associated with identifiable / measurable variations in at least one parameter associated with the road. For example, in some cases, such a profile may be associated with changes in road surface information, such as changes in the surface roughness of a particular road segment, changes in road width across a particular road segment, changes in the distance between dashed lines drawn along a particular road segment, changes in the curvature of the road along a particular road segment, etc. FIG. 11D shows an example road signature profile 1160. While the profile 1160 may represent any of the parameters described above or other parameters, in one example, the profile 1160 may represent a measure of road surface roughness, for example, obtained by monitoring one or more sensors that provide an output indicative of the amount of suspension displacement as the vehicle travels over a particular road segment.

[0251] Alternatively, or simultaneously, profile 1160 may represent changes in road width determined based on image data acquired via a camera mounted on a vehicle traveling a particular road segment. Such a profile may be useful, for example, to determine a particular position of an autonomous vehicle relative to a particular target trajectory. That is, as the autonomous vehicle traverses a road segment, the autonomous vehicle may measure a profile associated with one or more parameters associated with the road segment. If the measured profile can be correlated / matched with a pre-defined profile that plots changes in the parameters with respect to position along the road segment, the measured pre-defined profile may be used (e.g., by overlaying corresponding sections of the measured pre-defined profile) to determine the current position along the road segment, and thus the current position relative to the target trajectory of the road segment.

[0252] In some embodiments, sparse map 800 may include different trajectories based on different characteristics associated with the user of the autonomous vehicle, environmental conditions, and / or other parameters related to the trip. For example, in some embodiments, different trajectories may be generated based on the preferences and / or profiles of different users. Sparse map 800 including such different trajectories may be provided to different autonomous vehicles of different users. For example, some users may prefer to avoid toll roads, while other users may prefer to take the shortest or fastest route, regardless of whether the route includes toll roads. The disclosed system may generate different sparse maps with different trajectories based on the preferences or profiles of such different users. As another example, some users may prefer to travel in faster-moving lanes, while other users may prefer to always maintain a center lane position.

[0253] Different trajectories may be generated and included in the sparse map 800 based on different environmental conditions, such as day and night, snow, rain, fog, etc. An autonomous vehicle traveling in different environmental conditions may provide a sparse map 800 generated based on such different environmental conditions. In some embodiments, a camera provided on the autonomous vehicle may detect environmental conditions and provide such information to a server that generates and provides the sparse map. For example, the server may generate or update an already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous traveling under the detected environmental conditions. Updating the sparse map 800 based on environmental conditions may be performed dynamically as the autonomous vehicle travels along a road.

[0254] Other different parameters related to driving may also be used as the basis for generating and providing different sparse maps for different autonomous vehicles. For example, when an autonomous vehicle is driving at high speeds, turning may be difficult. Trajectories associated with particular lanes, rather than roads, may be included in sparse map 800 so that the autonomous vehicle may stay within a particular lane as it follows a particular trajectory. If images captured by a camera mounted on the autonomous vehicle indicate that the vehicle has drifted outside of its lane (e.g., crossed a lane marking), an action may be triggered within the vehicle to return the vehicle to its designated lane according to the particular trajectory.

[0255] Crowdsourcing sparse maps

[0256] In some embodiments, the disclosed systems and methods may create sparse maps for autonomous vehicle navigation. For example, the disclosed systems and methods may use crowdsourced data to generate a sparse map that one or more autonomous vehicles may use to navigate along a system of roads. As used herein, "crowdsourcing" means receiving data from various vehicles (e.g., autonomous vehicles) traveling a road segment at different times and using such data to generate and / or update a road model. The model may then be transmitted to these vehicles or other vehicles that subsequently travel along the road segment to assist autonomous vehicle navigation. The road model may include multiple target trajectories that represent preferred trajectories for the autonomous vehicle to follow when traversing the road segment. The target trajectories may be the same as reconstructed actual trajectories collected from vehicles traversing the road segment and transmitted from the vehicles to a server. In some embodiments, the target trajectories may differ from actual trajectories previously taken by one or more vehicles when traversing the road segment. The target trajectories may be generated based on the actual trajectories (e.g., by averaging or other suitable operations). An example of aligning crowdsourced data to generate a target trajectory is discussed below with reference to FIG.

[0257] The vehicle trajectory data that a vehicle may upload to the server may correspond to the vehicle's actual reconstructed trajectory, or may correspond to a recommended trajectory that may be based on or related to the vehicle's actual reconstructed trajectory, but may differ from the actual reconstructed trajectory. For example, the vehicle may modify the actual reconstructed trajectory and send (e.g., recommend) the modified actual trajectory to the server. The road model may use the recommended modified trajectory as a target vehicle trajectory for autonomous navigation of other vehicles.

[0258] In addition to trajectory information, other information for potential use in constructing the sparse data map 800 may include information related to potential landmark candidates. For example, by crowdsourcing information, the disclosed systems and methods may identify potential landmarks in the environment and refine the landmark locations. The landmarks may be used by the autonomous vehicle's navigation system to determine and / or adjust the vehicle's position along the target trajectory.

[0259] The reconstructed trajectory that a vehicle may generate as it travels along a road may be obtained by any suitable method. In some embodiments, the reconstructed trajectory may be developed by piecing together segments of the vehicle's motion using, for example, ego-motion estimation (e.g., 3D translation and 3D rotation of the camera and thus the body of the vehicle). Estimates of rotation and translation may be determined based on analysis of images captured by one or more image capture devices, along with information from other sensors or devices, such as inertial sensors and speed sensors. For example, the inertial sensors may include accelerometers or other suitable sensors configured to measure changes in translation and / or rotation of the vehicle body. The vehicle may include a speed sensor to measure the speed of the vehicle.

[0260] In some embodiments, the ego-motion of the camera (and thus the vehicle body) can be estimated based on optical flow analysis of captured images. Optical flow analysis of a series of images identifies pixel movements from the series of images and determines the movement of the vehicle based on the identified movements. The ego-motion can be integrated over time along a road segment to reconstruct a trajectory associated with the road segment traversed by the vehicle.

[0261] Data (e.g., reconstructed trajectories) collected by multiple vehicles on multiple trips along a road segment at different times may be used to construct a road model (e.g., including a target trajectory, etc.) included in sparse data map 800. Data collected by multiple vehicles on multiple trips along a road segment at different times may also be averaged to increase the accuracy of the model. In some embodiments, data regarding road geometry and / or landmarks may be received from multiple vehicles traveling a common road segment at different times. Such data received from different vehicles may be combined to generate and / or update a road model.

[0262] The geometry of the reconstructed trajectory (and target trajectory) along the road segment may be represented by a curve in three-dimensional space, which may be a spline connecting three-dimensional polynomials. The reconstructed trajectory curve may be determined from an analysis of a video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a location is identified in each frame or image several meters ahead of the vehicle's current position. This location is where the vehicle is expected to travel within a predetermined period of time. This operation may be repeated for each frame, and simultaneously, the vehicle may calculate the ego-motion (rotation and translation) of the camera. For each frame or image, a short-range model of the desired path is generated by the vehicle in the camera-mounted reference frame. The short-range models may be stitched together to obtain a three-dimensional model of the road in a coordinate frame, which may be any coordinate frame or a predetermined coordinate frame. The three-dimensional model of the road may then be fitted by a spline, which may include or connect one or more polynomials of the appropriate order.

[0263] One or more detection modules may be used to conclude a short-distance road model for each frame. For example, a bottom-up lane detection module may be used. The bottom-up lane detection module may be useful when lane markings are painted on the road. This module may locate edges in the image and assemble them to form lane markings. A second module may be used together with the bottom-up lane detection module. The second module is an end-to-end deep neural network that may be trained to predict the correct short-distance path from the input image. In either module, the road model is detected in the image coordinate frame and transformed into a three-dimensional space that may be virtually connected to the camera.

[0264] Although the reconstructed orbit modeling approach may result in error accumulation due to the integration of egomotion over long periods, which may include noise components, such errors may be insignificant because the generated model may provide sufficient accuracy for navigation at local scales. Additionally, external information sources, such as satellite imagery or geodetic measurements, may be used to cancel the integrated errors. For example, the disclosed systems and methods may use a GNSS receiver to cancel the accumulated errors. However, GNSS positioning signals are not always available and accurate. The disclosed systems and methods may enable steering applications that are weakly dependent on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed systems may use GNSS signals only for database indexing purposes.

[0265] In some embodiments, a range scale (e.g., local scale) that may be relevant for an autonomous vehicle navigation and steering application may be as large as 50 meters, as large as 100 meters, as large as 200 meters, as large as 300 meters, etc. Such distances may be used because the geometric road model is primarily used for two purposes: planning the trajectory ahead and locating the vehicle on the road model. In some embodiments, when a control algorithm steers a vehicle according to a target point located 1.3 seconds ahead (or any other time, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.), the planning task may use the model over a typical range of 40 meters ahead (or other suitable distance ahead, such as 20 meters, 30 meters, 50 meters, etc.). The localization task uses the road model over a typical range of 60 meters behind the vehicle (or other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.), following a method called “tail alignment,” which is described in more detail in another section. The disclosed systems and methods can generate a model of the geometry with sufficient accuracy over a specified range, such as 100 meters, so that the planned trajectory does not deviate from the lane center by more than 30 cm, for example.

[0266] As mentioned above, a 3D road model can be constructed by detecting short-distance sections and stitching them together. Stitching can be made possible by calculating a 6-degree ego-motion model using video and / or images captured by cameras, data from inertial sensors reflecting the vehicle's movement, and the host vehicle's speed signal. The cumulative error can be small enough at some local range scales, such as 100 meters or so. At all of these range scales, a particular road segment can be completed in a single drive.

[0267] In some embodiments, multiple runs may be used to average the resulting model to further improve its accuracy. The same vehicle may run the same route multiple times, or multiple vehicles may send collected model data to a central server. In either case, a matching procedure may be performed to identify overlapping models and enable averaging to generate a target trajectory. The constructed model (e.g., including the target trajectory) may be used for steering once convergence criteria are met. Subsequent runs may be used to further improve the model and to accommodate infrastructure changes.

[0268] When multiple vehicles are connected to a central server, sharing of driving experience (such as sensor data) between multiple vehicles becomes possible. Each vehicle client may store a partial copy of a universal road model that may be relevant to its current location. A bidirectional update procedure between the vehicle and the server may be performed by the vehicle and the server. The small footprint concept discussed above allows the disclosed system and method to perform bidirectional updates using very low bandwidth.

[0269] Information related to potential landmarks may also be determined and transferred to a central server. For example, the disclosed systems and methods may determine one or more physical characteristics of a potential landmark based on one or more images including the landmark. The physical characteristics may include the physical size of the landmark (e.g., height, width), the distance from the vehicle to the landmark, the distance from the landmark to the previous landmark, the lateral position of the landmark (e.g., the position of the landmark relative to the driving lane), the GPS coordinates of the landmark, the type of landmark, identification of text on the landmark, etc. For example, the vehicle may analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

[0270] The vehicle may determine the distance from the vehicle to the landmark based on analysis of one or more images. In some embodiments, the distance may be determined based on analysis of the image of the landmark using appropriate image analysis methods, such as scaling and / or optical flow methods. In some embodiments, the disclosed systems and methods may be configured to determine the type or classification of a potential landmark. If the vehicle determines that a particular potential landmark corresponds to a predetermined type or classification stored in the sparse map, it may be sufficient for the vehicle to communicate an indication of the landmark type or classification along with its location to a server. The server may store such an indication. Later, another vehicle may capture an image of the landmark, process the image (e.g., using a classifier), and compare the results of processing the image with the indication of the landmark type stored on the server. Various types of landmarks may exist, and different types of landmarks may be associated with different types of data that are uploaded and stored on the server; different processes onboard the vehicle may detect the landmarks and communicate information about the landmarks to the server; and a system onboard the vehicle may receive the landmark data from the server and use the landmark data to identify the landmark in autonomous navigation.

[0271] In some embodiments, multiple autonomous vehicles traveling on a road segment may communicate with a server. The vehicles (or clients) may generate curves that describe their travel in any coordinate frame (e.g., by ego-motion integration). The vehicles may detect landmarks and place them in the same frame. The vehicles may upload the curves and landmarks to the server. The server may collect data from the vehicles over multiple travels and generate a unified road model. For example, as discussed below with respect to FIG. 19, the server may use the uploaded curves and landmarks to generate a sparse map with a unified road model.

[0272] The server may also distribute the model to clients (such as vehicles). For example, as discussed below with respect to FIG. 24, the server may distribute a sparse map to one or more vehicles. The server may continuously or periodically update the model as it receives new data from the vehicles. For example, the server may process the new data to evaluate whether the data contains information that should trigger an update or the creation of new data on the server. The server may distribute updated models or updates to vehicles to provide autonomous vehicle navigation.

[0273] The server may use one or more criteria to determine whether new data received from a vehicle should trigger a model update or the creation of new data. For example, if the new data indicates that a previously recognized landmark at a particular location is no longer present or has been replaced by another landmark, the server may determine that the new data should trigger a model update. As another example, if the new data indicates that a road segment is closed, and this is corroborated by data received from other vehicles, the server may determine that the new data should trigger a model update.

[0274] The server may distribute the updated model (or updated portion of the model) to one or more vehicles traveling on a road segment with which the update to the model is associated. The server may also distribute the updated model to vehicles about to travel on a road segment with which the update to the model is associated, or to vehicles on a planned trip that includes the road segment. For example, while the autonomous vehicle is traveling along another road segment before reaching the road segment with which the update is associated, the server may distribute the update or updated model to the autonomous vehicle before the vehicle reaches the road segment.

[0275] In some embodiments, a remote server may collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a common road segment). The server may use the landmarks to match curves and create an average road model based on the trajectories collected from multiple vehicles. The server may also calculate the most likely path at each node or junction of the road graph and road segment. For example, as discussed with respect to FIG. 29 below, the remote server may align the trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0276] The server may average landmark properties received from multiple vehicles traveling along a common road segment, such as the distance from one landmark to another (e.g., the previous landmark along the road segment) measured by the multiple vehicles, to determine arc-length parameters and support position location and speed calibration along each client vehicle's path. The server may average physical dimensions of landmarks measured by multiple vehicles traveling along a common road segment and recognizing the same landmark. The averaged physical dimensions may be used to support distance estimation, such as the distance from the vehicle to the landmark. The server may average lateral positions of landmarks (e.g., the position of the landmark from the lane in which the vehicle is traveling) measured by multiple vehicles traveling along a common road segment and recognizing the same landmark. The averaged lateral positions may be used to support lane assignment. The server may average GPS coordinates of landmarks measured by multiple vehicles traveling along the same road segment and recognizing the same landmark. The averaged GPS coordinates of the landmark may be used to support global localization or positioning of the landmark within the road model.

[0277] In some embodiments, the server may identify model changes, such as construction, detours, new signs, sign removals, etc., based on data received from the vehicles. The server may update the model continuously, periodically, or instantaneously as it receives new data from the vehicles. The server may distribute model updates or updated models to the vehicles to provide autonomous navigation. For example, as discussed further below, the server may use crowdsourced data to filter out "ghost" landmarks detected by the vehicles.

[0278] In some embodiments, the server may analyze driver intervention during autonomous driving. The server may analyze data received from the vehicle at the time and location of the intervention and / or data received prior to the time the intervention occurs. The server may identify specific portions of data that caused or are closely related to the intervention, such as data indicating a temporary lane closure configuration or data indicating a pedestrian on the road. The server may update the model based on the identified data. For example, the server may modify one or more trajectories stored in the model.

[0279] FIG. 12 is a schematic diagram of a system for generating sparse maps using crowdsourcing (and distributing and navigating using crowdsourced sparse maps). FIG. 12 shows a road segment 1200 including one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 may be traveling on the road segment 1200 at the same time or at different times (although FIG. 12 shows them appearing on the road segment 1200 at the same time). At least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. For simplicity of this example, we will assume that all of the vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0280] 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 a vehicle 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 through one or more networks (e.g., via a cellular network and / or the Internet, etc.) via wireless communication path 1235, as shown by the dotted line. Each vehicle may send data to and receive data from server 1230. For example, server 1230 may collect data from multiple vehicles traveling road segment 1200 at different times and process the collected data to generate an autonomous vehicle road navigation model or model updates. Server 1230 may transmit the autonomous vehicle road navigation model or model updates to vehicles that sent data to server 1230. Server 1230 may transmit the autonomous vehicle road navigation model or updates to the model to other vehicles that subsequently travel road segment 1200.

[0281] As the vehicles 1205, 1210, 1215, 1220, and 1225 travel along the road segment 1200, navigation information collected (e.g., detected, sensed, or measured) by the vehicles 1205, 1210, 1215, 1220, and 1225 may be transmitted to the server 1230. In some embodiments, the navigation information may be associated with a common road segment 1200. The navigation information may include trajectories associated with each of the vehicles 1205, 1210, 1215, 1220, and 1225 as each vehicle travels along the road segment 1200. In some embodiments, the trajectories may be reconstructed based on data sensed by various sensors and devices provided on the vehicles 1205. For example, the trajectories may be reconstructed based on at least one of accelerometer data, speed data, landmark data, road geometry or profile data, vehicle position data, and egomotion data. In some embodiments, the trajectory may be reconstructed based on data from inertial sensors, such as accelerometers, and the velocity of the vehicle 1205 as sensed by a speed sensor. Additionally, in some embodiments, the trajectory may be determined based on sensed ego-motion of the cameras (e.g., by a processor on board each of the vehicles 1205, 1210, 1215, 1220, and 1225), which may indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The ego-motion of the cameras (and thus the vehicle body) may be determined from an analysis of one or more images captured by the cameras.

[0282] In some embodiments, the trajectory of vehicle 1205 may be determined by a processor onboard vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 may receive data sensed by various sensors and devices onboard vehicle 1205 and determine the trajectory based on the data received from vehicle 1205.

[0283] In some embodiments, navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 may include data regarding the road surface, road geometry, or road profile. The geometry of road segment 1200 may include lane structure and / or landmarks. The lane structure may include the total number of lanes on road segment 1200, the type of lane (e.g., unidirectional lane, bidirectional lane, travel lane, passing lane, etc.), markings on the lane, lane width, etc. In some embodiments, navigation information may include lane assignments, such as which lane of multiple lanes the vehicle is traveling in. For example, a numeric value "3" may be associated with a lane assignment to indicate that the vehicle is traveling in the third lane from the left or right. As another example, a text value "center lane" may be associated with a lane assignment to indicate that the vehicle is traveling in the center lane.

[0284] Server 1230 may store the navigation information on a non-transitory computer-readable medium, such as a hard drive, compact disc, tape, memory, etc. Server 1230 may generate (e.g., via a processor included in server 1230) at least a portion of an autonomous vehicle road navigation model of the common road segment 1200 based on navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225 and store the model as part of a sparse map. Server 1230 may determine a trajectory associated with each lane based on crowdsourced data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling the lanes of the road segment at different times. Server 1230 may generate the autonomous vehicle road navigation model or a portion of the model (e.g., an updated portion) based on the multiple trajectories determined based on the crowdsourced navigation data. 24, server 1230 may transmit the model or updated portions of the model to one or more of autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 or any other autonomous vehicles that later travel the road segment to update an existing autonomous vehicle road navigation model provided in the vehicle's navigation system. As described in more detail below with respect to FIG. 26, the autonomous vehicle road navigation model may be used by the autonomous vehicles as they autonomously navigate along common road segment 1200.

[0285] As described above, the autonomous vehicle road navigation model may be included in a sparse map (e.g., sparse map 800 shown in FIG. 8 ). Sparse map 800 may include a sparse record of data related to road geometry and / or landmarks along the road, which may provide sufficient information to guide the autonomous navigation of the autonomous vehicle, but without requiring excessive data storage. In some embodiments, the autonomous vehicle road navigation model may be stored separately from sparse map 800, and may use map data from sparse map 800 when the model is implemented for navigation. In some embodiments, the autonomous vehicle road navigation model may use the map data included in sparse map 800 to determine a target trajectory along road segment 1200 to guide the autonomous navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles that subsequently travel along road segment 1200. For example, when the autonomous vehicle road navigation model is executed by a processor included in the navigation system of vehicle 1205, the model may cause the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory included in sparse map 800 to verify and / or correct the current course of travel of vehicle 1205.

[0286] In an autonomous vehicle road navigation model, the geometry of road features or target trajectories may be encoded by curves in three-dimensional space. In one embodiment, the curves may be cubic splines including one or more connected cubic polynomials. As one skilled in the art will appreciate, splines may be numerical functions piecewise defined by a series of polynomials for fitting data. Splines for fitting the three-dimensional road geometry data may include linear splines (first order), quadratic splines (second order), cubic splines (third order), or other splines (other orders), or combinations thereof. Splines may include one or more cubic polynomials of different orders that connect (e.g., fit) data points of the three-dimensional road geometry data. In some embodiments, the autonomous vehicle road navigation model may include cubic splines corresponding to a common road segment (e.g., road segment 1200) or a target trajectory along a lane of road segment 1200.

[0287] 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 images of the landmark. A processor (e.g., processors 180, 190, or processing unit 110) mounted on vehicle 1205 may process the images of the landmarks to extract the landmark identification information. Landmark-specific information may be stored in sparse map 800 rather than actual images of the landmarks. The landmark-specific information may require much less storage space than the actual images. Other sensors or systems (e.g., a GPS system) may also provide specific identification information of landmarks (e.g., the location of the landmarks). The landmarks may include at least one of a traffic sign, an arrow mark, a lane mark, a dashed lane mark, a traffic light, a stop line, a directional sign (e.g., a highway exit sign with an arrow indicating a direction, a highway sign with an arrow pointing in a different direction or location), a landmark beacon, or a light pole. A landmark beacon refers to a device (e.g., an RFID device) installed along a road segment that transmits or reflects a signal to a receiver installed in a vehicle, so that when the vehicle passes by the device, the beacon received by the vehicle and the location of the device (e.g., determined from the device's GPS location) can be used as a landmark included in the autonomous vehicle road navigation model and / or sparse map 800.

[0288] The identification of the at least one landmark may include a location of the at least one landmark. The location of the landmark may be determined based on position measurements performed using sensor systems (e.g., global positioning systems, inertial-based positioning systems, landmark beacons, etc.) associated with the multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of the landmark may be determined by averaging position measurements detected, collected, or received by sensor systems on different vehicles 1205, 1210, 1215, 1220, and 1225 over multiple runs. For example, the vehicles 1205, 1210, 1215, 1220, and 1225 may transmit position measurement data to the server 1230, which may average the position measurements and use the average position measurement as the location of the landmark. The location of the landmark may be continually refined with measurements received from the vehicles on subsequent runs.

[0289] The identification of the landmark may include the size of the landmark. A processor provided in the vehicle (e.g., 1205) may estimate the physical size of the landmark based on an analysis of the image. The server 1230 may receive multiple estimates of the physical size of the same landmark from different vehicles over different trips. The server 1230 may average the different estimates to arrive at the physical size of the landmark and store the landmark size in the road model. The physical size estimate may be used to further determine or estimate the distance from the vehicle to the landmark. The distance to the landmark may be estimated based on the vehicle's current speed and a scale of magnification based on the position of the landmark as it appears in the image relative to the camera's magnification focus. For example, the distance to the landmark may be estimated as Z=V*dt*R / D, where V is the vehicle speed, R is the distance in the image from the landmark to the magnification focus at time t1, D is the change in the distance of the landmark in the image from t1 to t2, and dt represents (t2-t1). For example, the distance to a landmark may be estimated as Z=V*dt*R / D, where V is the vehicle speed, R is the distance in the image between the landmark and the magnification focus, dt is the time interval, and D is the image displacement of the landmark along the epipolar line. The above equation and other equivalent equations may be used to estimate the distance to a landmark, such as Z=V*ω / Δω, where V is the vehicle speed, ω is the image length (e.g., object width), and Δω is the change in that image length per unit time.

[0290] If the physical size of the landmark is known, the distance to the landmark can also be determined based on the following formula: Z=f*W / ω, where f is the focal length, W is the size of the landmark (such as height or width), and ω is the number of pixels the landmark passes through in the image. From the above formula, the change in distance Z is ΔZ=f*W*Δω / ω 2 +f*ΔW / ω, where ΔW decays to zero through averaging and Δω is the number of pixels that represent the accuracy of the bounding box in the image. An estimate of the physical size of the landmark can be calculated on the server side by averaging multiple observations. The resulting error in distance estimation can be very small. There are two sources of error that can occur when using the above formula: ΔW and Δω. The contribution to the distance error is ΔZ=f*W*Δω / ω 2is given by f*ΔW / ω, where ΔW decays to zero through averaging, and therefore ΔZ is determined by Δω (e.g., the inaccuracy of the image's bounding box).

[0291] For landmarks of unknown dimensions, the distance to the landmark may be estimated by tracking feature points on the landmark between successive frames. For example, a particular feature displayed on a speed limit sign may be tracked between two or more image frames. Based on these tracked features, a distance distribution for each feature point may be generated. A distance estimate may be extracted from the distance distribution. For example, the most frequent distance appearing in the distance distribution may be used as the distance estimate. As another example, the mean of the distance distribution may be used as the distance estimate.

[0292] FIG. 13 shows an example autonomous vehicle road navigation model represented by multiple 3-dimensional splines 1301, 1302, and 1303. The curves 1301, 1302, and 1303 shown in FIG. 13 are for illustrative purposes only. Each spline may include one or more 3-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 having different orders. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to landmarks (e.g., size, location, and landmark identification information) and / or road signature profiles (e.g., road geometry, road roughness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 may be associated with data related to landmarks and other data points may be associated with data related to road signature profiles.

[0293] FIG. 14 shows raw position data 1410 (e.g., GPS data) received from five separate runs. One run may be distinct from another if separate vehicles crossed at the same time, if the same vehicle crossed at different times, or if separate vehicles crossed at different times. To account for errors in the position data 1410 and different positions of vehicles in the same lane (e.g., one vehicle may be closer to the left side of the lane than another), the server 1230 may generate a map skeleton 1420 using one or more statistical techniques to determine whether changes in the raw position data 1410 represent actual deviations or statistical errors. Each route in the skeleton 1420 may be linked back to the raw data 1410 that formed that route. For example, the route between A and B in the skeleton 1420 is linked to raw data 1410 from runs 2, 3, 4, and 5, but not from run 1. While the skeleton 1420 may not be detailed enough to be used for navigating a vehicle (e.g., because it combines travel from multiple lanes on the same road, unlike the splines described above), it may provide useful topological information and may be used to define intersections.

[0294] FIG. 15 illustrates an example in which additional detail may be generated for a sparse map within a section of a map skeleton (e.g., section A to B in skeleton 1420). As shown in FIG. 15, data (e.g., ego-motion data, road mark data, etc.) may be shown as a function of position S (or S1 or S2) along the run. Server 1230 may identify landmarks in the sparse map by identifying unique matches between landmarks 1501, 1503, and 1505 of run 1510 and landmarks 1507 and 1509 of run 1520. Such a matching algorithm may lead to the identification of landmarks 1511, 1513, and 1515. However, one skilled in the art will recognize that other matching algorithms may be used. For example, probability optimization may be used instead of or in combination with unique matching. As described in more detail below with respect to FIG. 29, server 1230 may align runs longitudinally to align matched landmarks. For example, the server 1230 may select one run (e.g., run 1520) as a reference run and then shift and / or elastically stretch the other runs (e.g., run 1510) for alignment.

[0295] FIG. 16 shows an example of registered landmark data for use with a sparse map. In the example of FIG. 16, landmark 1610 includes a road sign. The example of FIG. 16 also shows data from multiple runs 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the example of FIG. 16, the data from run 1613 consists of "ghost" landmarks, and server 1230 may identify the landmark as a "ghost" because none of runs 1601, 1603, 1605, 1607, 1609, or 1611 include identification of a landmark in the vicinity of an identified landmark in run 1613. Thus, server 1230 may accept a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or may reject a potential landmark if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0296] FIG. 17 illustrates a system 1700 for generating trip data that may be used to crowdsource a sparse map. As shown in FIG. 17 , the system 1700 may include a camera 1701 and a location device 1703 (e.g., a GPS locator). The camera 1701 and the location device 1703 may be mounted on a vehicle (e.g., one of the vehicles 1205, 1210, 1215, 1220, and 1225). The camera 1701 may generate multiple types of data, such as ego-motion data, traffic sign data, road data, etc. The camera data and location data may be segmented into trip segments 1705. For example, each trip segment 1705 may have camera data and location data for trips of less than 1 km.

[0297] 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 remove the redundant data so that travel segment 1705 includes only one copy of the landmark's location and metadata associated with the landmark. As a further example, if a lane marking appears in multiple images from camera 1701, system 1700 may remove the redundant data so that travel segment 1705 includes only one copy of the lane marking's location and metadata associated with the lane mark.

[0298] System 1700 also includes a server (e.g., server 1230), which may receive trip segments 1705 from the vehicles and recombine the trip segments 1705 into a single trip 1707. Such an arrangement may reduce bandwidth requirements when transferring data between the vehicles and the server, and the server may also store data related to an entire trip.

[0299] Figure 18 shows the system 1700 of Figure 17 further configured for crowdsourcing a sparse map. As in Figure 17, the system 1700 includes a vehicle 1810 that captures trip data using, for example, a camera (e.g., generating ego-motion data, traffic sign data, road data, etc.) and a location device (e.g., a GPS locator). As in Figure 17, the vehicle 1810 segments the collected data into trip segments (shown in Figure 18 as "DS1 1," "DS2 1," and "DSN 1"). The server 1230 then receives the trip segments and reconstructs a trip (shown in Figure 18 as "Journey 1") from the received segments.

[0300] As further shown in FIG. 18 , system 1700 also receives data from additional vehicles. For example, vehicle 1820 also captures trip data using, for example, a camera (e.g., generating self-motion data, traffic sign data, road data, etc.) and a location device (e.g., a GPS locator). Similar to vehicle 1810, vehicle 1820 segments the collected data into trip segments (shown in FIG. 18 as “DS1 2,” “DS2 2,” and “DSN 2”). Server 1230 then receives the trip segments and reconstructs a trip (shown in FIG. 18 as “Journey 2”) from the received segments. Any number of additional vehicles may be used. For example, FIG. 18 also includes “Car N,” which captures trip data, segments it into trip segments (shown in FIG. 18 as “DS1 N,” “DS2 N,” and “DSN N”), and sends it to server 1230 for reconstruction into a trip (shown in FIG. 18 as “Journey N”).

[0301] As shown in FIG. 18, the server 1230 may build a sparse map (shown as "Map") using reconstructed trips (e.g., "Run 1," "Run 2," and "Run N") collected from multiple vehicles (e.g., "Car 1" (also referred to as vehicle 1810), "Car 2" (also referred to as vehicle 1820), and "Car N").

[0302] 19 is a flowchart illustrating an example process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 may be performed by one or more processing devices included in server 1230.

[0303] Process 1900 may include receiving a plurality of images acquired as one or more vehicles traverse the road segment (step 1905). Server 1230 may receive the images from cameras included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 may receive pruned image data, in which redundancies are removed by a processor on vehicle 1205, as discussed above with respect to FIG. 17 .

[0304] Process 1900 may further include identifying at least one line representation of a road surface feature extending along the road segment based on the multiple images (step 1910). Each line representation may represent a path along the road segment that substantially corresponds to the road surface feature. For example, server 1230 may analyze the environmental images received from camera 122 to identify road edges or lane markings and determine a trajectory of travel along road segment 1200 associated with the road edges or lane markings. In some embodiments, the trajectory (or line representation) may include a spline, a polynomial representation, or a curve. Server 1230 may determine a trajectory of travel of vehicle 1205 based on the ego-motion (e.g., three-dimensional translational and / or three-dimensional rotational) of the camera received in step 1905.

[0305] Process 1900 may also include identifying multiple landmarks associated with the road segment based on the 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 identify landmarks using analysis of multiple images acquired as one or more vehicles traverse the road segment. To enable crowdsourcing, the analysis may include rules for accepting and rejecting landmarks that may be associated with the road segment. For example, the analysis may include accepting a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0306] Process 1900 may include other operations or steps performed by server 1230. For example, the navigation information may include a target trajectory for a vehicle to travel along a road segment, and process 1900 may include clustering, by server 1230, vehicle trajectories associated with a plurality of vehicles traveling on the road segment and determining the target trajectory based on the clustered vehicle trajectories, as discussed in further detail below. Clustering the vehicle trajectories may include clustering, by server 1230, the plurality of trajectories associated with the vehicles traveling on the road segment into a plurality of clusters based on at least one of the absolute headings of the vehicles or the lane assignments of the vehicles. Generating the target trajectory may include averaging, by server 1230, the clustered trajectories.

[0307] By way of further example, process 1900 may include aligning the received data in step 1905, as discussed in more detail below with respect to Figure 29. As noted above, other processes or steps performed by server 1230 may also be included in process 1900.

[0308] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates rather than global coordinates. In the case of autonomous driving, some systems may display data in global coordinates, for example, using longitude and latitude coordinates on the Earth's surface. To use a map for steering, the host vehicle may determine its position and orientation relative to the map. It seems natural to use an on-board GPS device to locate the vehicle on the map and find the rotational transformation between the body's reference frame and the world's reference frame (e.g., north, east, and down). Once the body's reference frame is aligned with the map's reference frame, the desired route may be represented in the body's reference frame and steering commands may be calculated or generated.

[0309] However, one potential problem with this strategy is that current GPS technology typically does not provide a vehicle's location and position with sufficient accuracy and availability. To overcome this problem, landmarks whose world coordinates are known can be used to construct highly detailed maps (called high-definition maps or HD maps) that include different types of landmarks. Thus, a sensor-equipped vehicle can detect and locate landmarks within its own reference frame. Once the relative positions between the vehicle and the landmarks are found, the landmarks' world coordinates can be determined from the HD map, and the vehicle can use them to calculate its own location and position.

[0310] Nevertheless, this method may use a global world coordinate system as a mediator to establish alignment between the map's reference frame and the body's reference frame. That is, landmarks may be used to compensate for the limitations of the vehicle's GPS device. The landmarks, together with the HD map, may be able to calculate the exact vehicle position in global coordinates, thus solving the map body alignment problem.

[0311] In the disclosed systems and methods, instead of using one global map of the world, many map pieces or local maps may be used for autonomous navigation. Each piece of map or each local map may define its own coordinate frame. These coordinate frames may be arbitrary. Vehicle coordinates on the local map may not need to indicate where the vehicle is located on Earth. Furthermore, the local map may not need to be accurate at large scales, which means there may not be a rigid transformation that can embed the local map in a global world coordinate system.

[0312] There are two main processes associated with this representation of the world: one related to the generation of maps, and the other related to their use. Regarding map generation, this type of representation can be created and maintained by crowdsourcing. Due to the limited use of HD maps, there is no need to apply advanced survey equipment, and thus crowdsourcing can be possible. Regarding use, an efficient method can be adopted to align the local map to the body's reference frame without going through a standard world coordinate system. Therefore, at least in most scenarios and situations, it may not be necessary to accurately estimate the vehicle's position and location in global coordinates. Furthermore, the memory footprint of the local map can be kept very small.

[0313] The principle underlying map generation is the integration of ego-motion. The vehicle may sense camera motion in space (3D translation and 3D rotation). The vehicle or server may reconstruct the vehicle's trajectory by integrating ego-motion over time and use this integrated path as a model of the road geometry. This process may be combined with detection of near-field lane markings, so that the reconstructed route reflects the path the vehicle should take, rather than the specific path the vehicle took. In other words, the reconstructed route or trajectory may be modified based on the sensing data related to near-field lane markings, and the modified reconstructed trajectory may be used as a recommended trajectory or target trajectory and stored in a road model or sparse map for use by other vehicles navigating the same road segment.

[0314] In some embodiments, the map coordinate system may be arbitrary. At any time, a reference frame for the camera may be selected and used as the origin of the map. The integrated trajectory of the camera may be expressed in the coordinate system of that particular selected frame. The values ​​of the route coordinates in the map may not directly represent positions on Earth.

[0315] The integrated path may accumulate errors. This may be because the self-motion detection may not be completely accurate. As a result of the accumulated errors, the local map may deviate and cannot be considered a local copy of the global map. The larger the size of the local map piece, the greater the deviation from the "true" geometry on Earth.

[0316] The randomness and deviations of the local map may not be the result of integration methods that may be applied to build the map in a crowdsourced manner (e.g., by vehicles driving along a road), but the vehicle may utilize the local map for steering.

[0317] The map may deviate over long distances. Because the map is used to plan the vehicle's immediate trajectory, the effect of the deviation may be acceptable. In any case, the system (e.g., server 1230 or vehicle 1205) may repeat the alignment procedure and use the map to predict road position (in the camera coordinate frame) approximately 1.3 seconds into the future (or any other seconds, such as 1.5 seconds, 1.0 seconds, 1.8 seconds, etc.). As long as the cumulative error over that distance is small enough, it may use the steering commands provided for autonomous navigation.

[0318] In some embodiments, a local map focuses on a local area and may not cover an area that is too large. This means that a vehicle using a local map for autonomous navigation may at some point reach the end of the map and need to switch to another local piece or section of the map. The local maps may overlap one another to enable the switch. When the vehicle enters an area common to both maps, the system (e.g., server 1230 or vehicle 1205) may continue to generate steering commands based on the first local map (the map in use), but at the same time, the system may locate the vehicle on the other map (or second local map) that overlaps the first local map. In other words, the system may simultaneously align the camera's current coordinate frame with both the coordinate frame of the first map and the coordinate frame of the second map. Once the new alignment is established, the system may switch to the other map and plan the vehicle's trajectory there.

[0319] The disclosed system may include additional features related to how the system aligns the coordinate frames of the vehicle and the map. As described above, landmarks can be used for alignment, assuming the vehicle can measure its relative position relative to the landmarks. While this is useful for autonomous driving, in some cases, it may require a large number of landmarks and therefore a large memory footprint. Therefore, the disclosed system may use an alignment procedure that addresses this issue. In the alignment procedure, the system may use sparse landmarks and an integral of the vehicle's velocity to calculate a 1D estimate of the vehicle's position along the road. The system may use the shape of the trajectory itself to calculate the rotational portion of the alignment using a tail alignment method, discussed in detail in another section below. Thus, to align the tail with the map, the vehicle may reconstruct its own trajectory while driving its "tail" and calculate a rotation about its assumed position along the road. Such an alignment procedure differs from the alignment of crowdsourced data discussed below with respect to FIG. 29.

[0320] In the disclosed systems and methods, the GPS device may still be used. The global coordinates may be used to index a database that stores trajectories and / or landmarks. Relevant local map pieces and associated landmarks in the vicinity of the vehicle may be stored in memory and retrieved from memory using the global GPS coordinates. However, in some embodiments, the global coordinates may not be used for route planning and may not be accurate. In one example, the use of the global coordinates may be limited to indexing information.

[0321] In situations where "tail alignment" cannot perform well, the system may use more landmarks to calculate the vehicle's position. This may be a rare case and the impact on memory footprint may be moderate. Road intersections are an example of such situations.

[0322] The disclosed systems and methods may use semantic landmarks (e.g., traffic signs) because they can be reliably detected from the scene and matched to landmarks stored in a road model or sparse map. In some cases, the disclosed systems may also use non-semantic landmarks (e.g., generic signs), in which case the non-semantic landmarks may be attached to the appearance signature as discussed above. The system may use learning methods for generating signatures that follow a "same or not" recognition paradigm.

[0323] For example, as discussed above with respect to FIG. 14, given a number of trips with GPS coordinates along the trip, the disclosed system can generate intersections and road segments for the underlying road structure. The roads are assumed to be sufficiently far apart so that they can be distinguished using GPS. In some embodiments, only a coarse-grained map may be required. To generate the underlying road structure graph, space may be divided into a grid of a given resolution (e.g., 50 m x 50 m). Every trip may be viewed as an ordered list of grid sites. The system may color all grid sites belonging to a trip to create an image of the combined trip. The colored grid points may be represented as nodes on the combined trip. Trips passing from one node to another may be represented as links. The system may fill small holes in the image to avoid lane separation and correct for GPS errors. The system may use an appropriate thinning algorithm (e.g., the so-called "Zhang-Suen" thinning algorithm) to obtain the skeleton of the image. This skeleton may represent the underlying road structure, and intersections may be found using a mask (e.g., points connected to at least three other points). After intersections are found, segments may be the skeleton parts that connect them. To match the trip back to the skeleton, the system may use a hidden Markov model. Every GPS point may be associated with a grid site with a probability inversely proportional to the distance from that site. An appropriate algorithm (e.g., an algorithm called the "Viterbi" algorithm) is used to match GPS points to grid sites and to prevent consecutive GPS points from being matched to non-adjacent grid sites.

[0324] Several methods can be used to map the runs back onto the map. For example, a first solution can involve tracking during the thinning process. A second solution can use proximity matching. A third solution can use a hidden Markov model. A hidden Markov model assumes a hidden state that underlies all observations and assigns a probability to a given observation given a state and to a state given a previous state. The Viterbi algorithm can be used to find the most probable state given a list of observations.

[0325] The disclosed systems and methods may include additional features. For example, the disclosed systems and methods may detect highway on- and off-ramp traffic. Multiple trips in the same area may be combined into the same coordinate system using GPS data. The system may use visual landmarks for mapping and location.

[0326] In some embodiments, generic visual features may be used as landmarks for the purpose of accurately overlaying the position and orientation of a moving vehicle on a trip (localization phase) onto a map generated by a vehicle traversing the same stretch of road on a previous trip (mapping phase). These vehicles may be equipped with calibrated cameras and GPS receivers that image the vehicle's surroundings. The vehicles may communicate with a central server (e.g., server 1230) that maintains an up-to-date map containing these visual landmarks coupled with other meaningful geometric and semantic information (e.g., lane structure, types and locations of road signs, types and locations of road markings, shape of nearby drivable surface areas bounded by locations of physical obstacles, shape of previously traveled vehicle paths when controlled by a human driver, etc.). The total amount of data that may be communicated between the central server and the vehicles per length of road is small in both the mapping and localization phases.

[0327] In the mapping phase, the disclosed system (e.g., an autonomous vehicle and / or one or more servers) may detect feature points (FPs). Feature points may include one or more points used to track associated objects, such as landmarks. For example, the eight points that make up the corners of a stop sign may be feature points. The disclosed system may further compute descriptors associated with the FPs (e.g., using features from an Accelerated Segment Test (FAST) detector, a Binary Robust Invariant Scalable Keypoint (BRISK) detector, a Binary Robust Independent Basic Function (BRIEF) detector, and / or an Oriented FAST and Rotational BRIEF (ORB) detector, or using detector / descriptor pairs trained using a training library). The system may track FPs between frames in which they appear by using the motion of the FPs in the image plane and matching associated descriptors using, for example, Euclidean or Hamming distance in descriptor space. The system may use the tracked FPs to estimate camera motion and the world position of the object from which the FPs were detected and tracked. For example, a tracked FP may be used to estimate vehicle motion and / or the location of the landmark where the FP was originally detected.

[0328] The system may further classify the FP as likely or unlikely to be detected in future runs (e.g., FPs detected with textures of fleetingly moving objects, parked cars, and shadows are unlikely to reappear in future runs). This classification may be referred to as repeatability classification (RC) and may be a function of the light intensity within a pyramid region surrounding the detected FP, the movement of the tracked FP within the image plane, and / or the range of viewpoints over which the FP was successfully detected and tracked. In some embodiments, the vehicle may transmit to server 1230 a descriptor associated with the FP, the FP's estimated 3D position relative to the vehicle, and the vehicle's GPS coordinates at the time of detection / tracking of the FP.

[0329] During the mapping phase, when communication bandwidth between the mapping vehicle and the central server is limited, the vehicle may transmit FPs to the server at high frequencies if the presence of FPs or other semantic landmarks (such as road signs and lane structures) in the map is limited and insufficient for localization purposes. Furthermore, while vehicles typically transmit FPs at low spatial frequencies to the server during the mapping phase, FPs may be aggregated within the server. Detection of repeat FPs may also be performed by the server, which may store a set of repeat FPs and / or ignore non-repeating FPs. The visual appearance of landmarks may, at least in some cases, be affected by the time of day or season at which they are captured. Therefore, to increase the probability of FP repeatability, received FPs may be binned by the server into time bins, seasonal bins, etc. In some embodiments, the vehicle may also transmit 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 traveled by a human driver in a planned drive to a parking spot, etc.).

[0330] In the localization phase, the server may send a map containing landmarks in the form of FP positions and descriptors to one or more vehicles. Feature points (FPs) may be detected and tracked by the vehicle in near real time within the current set of consecutive frames. The tracked FPs may be used to estimate camera motion and / or the location of associated objects, such as landmarks. Detected FP descriptors may be searched for matches with a list of FPs contained in the map and having GPS coordinates within a finite GPS uncertainty radius estimated from the vehicle's current GPS readings. Matching may be performed by searching all pairs of current FPs and mapped FPs that minimize the Euclidean or Hamming distance in the descriptor space. Using the FP matches and their current and map positions, the vehicle may rotate and / or translate between the instantaneous vehicle position and the local map coordinate system.

[0331] The disclosed systems and methods may include methods for training a reproducible classifier. Training may be performed in one of the following ways, in order of increasing labeling cost and resulting classifier accuracy:

[0332] In the first approach, a database containing a large number of clips recorded by vehicle cameras with consistent instantaneous vehicle GPS positions may be collected. This database may contain a representative sample of trips (with respect to various properties, 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 may be likely to match within the GPS uncertainty radius. Non-matching FPs may be labeled as non-repeatable, and matching FPs may be labeled as repeatable. A classifier may then be trained to predict the repeatability label of an FP, taking into account its appearance in the image pyramid, its instantaneous position relative to the vehicle, and the range of viewpoint positions over which the FP was successfully tracked.

[0333] In a second approach, the FP pairs extracted from the clip database described in the first approach can also be labeled by a human being responsible for annotating FP matches between clips.

[0334] In a third approach, a database augmenting the first approach with precise vehicle position, vehicle orientation, and image pixel depth using light detection and ranging (LIDAR) measurements can be used to accurately match world positions across different runs. Feature point descriptors can then be computed for image regions corresponding to these world points at different viewpoints and run times. A classifier can then be trained to predict the average distance in descriptor space where a descriptor is located from a matching descriptor. In this case, recall can be measured by the likelihood that a descriptor has a short distance.

[0335] According to disclosed embodiments, the system may generate an autonomous vehicle road navigation model based on the observed trajectories of vehicles traversing a common road segment (e.g., which may correspond to trajectory information forwarded by the vehicles to a server). However, the observed trajectories may not correspond to the actual trajectories taken by the vehicles traveling on the road segment. Rather, in certain circumstances, the trajectories uploaded to the server may be modified with respect to the actual reconstructed trajectories determined by the vehicles. For example, while reconstructing the trajectories actually taken, the vehicle system may use sensor information (e.g., analysis of images provided by a camera) 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 an onboard camera, that the vehicle has not been traveling in the center of the lane for a determined period of time or has crossed a lane boundary. In such cases, among other things, refinement of the vehicle's reconstructed trajectory (the actual path traversed) may be performed based on information obtained from the sensor output. The refined trajectory, rather than the actual trajectory, may then be uploaded to the server and potentially used to build or update the sparse data map 800.

[0336] In some embodiments, a processor included in a vehicle (e.g., vehicle 1205) may then determine the actual trajectory of vehicle 1205 based on output from one or more sensors. For example, based on analysis of images output from camera 122, the processor may identify landmarks along road segment 1200. Landmarks may include traffic signs (e.g., speed limit signs), directional signs (e.g., highway directional signs pointing to different routes or locations), and general signs (e.g., rectangular business signs associated with a unique signature such as a color pattern). The identified landmarks may be compared to landmarks stored in sparse map 800. If a match is found, the location of the landmark stored in sparse map 800 may be used as the location of the identified landmark. The location of the identified landmark may be used to determine the location of vehicle 1205 along the target trajectory. In some embodiments, the processor may also determine the location of vehicle 1205 based on GPS signals output by GPS unit 1710.

[0337] The processor may also determine a target trajectory to send to server 1230. The target trajectory may be the same as the actual trajectory determined by the processor based on the sensor outputs. However, in some embodiments, the target trajectory may differ from the actual trajectory determined based on the sensor outputs. For example, the target trajectory may include one or more corrections to the actual trajectory.

[0338] In one example, if data from camera 122 includes a barrier, such as a temporary lane-shift barrier, 100 meters ahead of vehicle 1250 changing lanes (e.g., if construction or an accident ahead causes a temporary lane change), the processor may detect the temporary lane-shift barrier from the image and, in accordance with the temporary lane shift, select a lane different from the lane corresponding to the target trajectory stored in the road model or sparse map. The vehicle's actual trajectory may reflect this lane change. However, if the lane shift is temporary and may be resolved, for example, within the next 10, 15, or 30 minutes, vehicle 1205 may accordingly modify the actual trajectory taken by vehicle 1205 (i.e., lane shift) to reflect that the target trajectory should differ from the actual trajectory taken by vehicle 1205. For example, the system may recognize that the traveled route differs from the preferred trajectory of the road segment. Accordingly, the system may adjust the reconstructed trajectory before uploading the trajectory information to the server.

[0339] In other embodiments, the actual reconstructed trajectory information may be uploaded, and one or more recommended trajectory refinements (e.g., the size and direction of translations to be made to at least a portion of the reconstructed trajectory) may also be uploaded. In some embodiments, processor 1715 may transmit the modified actual trajectory to server 1230. Server 1230 may generate or update a target trajectory based on the received information and may transmit the target trajectory to other autonomous vehicles that later travel the same road segment, as discussed in more detail below with respect to FIG. 24.

[0340] As another example, the environmental image may include an object, such as a pedestrian, that suddenly appears on the road segment 1200. The processor may detect the pedestrian, causing the vehicle 1205 to change lanes to avoid colliding with the pedestrian. The actual trajectory of the vehicle 1205 reconstructed based on the detected data may include a lane change. However, the pedestrian may quickly leave the roadway. Thus, the vehicle 1205 may modify (or determine a recommended modification of) the actual trajectory to reflect that the target trajectory should differ from the trajectory actually taken (because the appearance of a pedestrian is a temporary condition that should not be considered in determining the target trajectory). In some embodiments, the vehicle may send data to a server indicating a temporary deviation from the predetermined trajectory when the actual trajectory is modified. 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 of the deviation may be useful. For example, if the deviation is due to the driver noticing a recent accident and reacting by steering to avoid a collision, the server may plan a gradual adjustment to the model based on the cause of the deviation, or may plan a specific trajectory associated with the road segment. As another example, if the deviation is caused by a pedestrian crossing the road, the server may determine that no future trajectory changes are necessary.

[0341] By way of further example, the environmental image may include lane markings that indicate that the vehicle 1205 is traveling slightly outside of its lane, perhaps under the control of a human driver. The processor may detect the lane markings from the captured image and may correct the actual trajectory of the vehicle 1205 to account for the deviation from the lane. For example, a translation may be applied to the reconstructed trajectory so that the reconstructed trajectory falls within the center of the observed lane.

[0342] Crowdsourced sparse map distribution

[0343] The disclosed systems and methods may enable autonomous vehicle navigation (e.g., steering control) with low-footprint models that can be collected by the autonomous vehicle itself without the aid of expensive surveying equipment. To support autonomous navigation (e.g., steering applications), the road model may include a sparse map having the road's geometry, its lane structure, and landmarks that can be used to determine the vehicle's location or position along the trajectory included in the model. As discussed above, generation of the sparse map may be performed by a remote server that communicates with and receives data from vehicles traveling on the road. The data may include sensed data, a reconstructed trajectory based on the sensed data, and / or a recommended trajectory that may represent a modified reconstructed trajectory. As discussed below, the server may transmit the model to these vehicles or other vehicles that subsequently travel on the road to assist with autonomous navigation.

[0344] 20 shows a block diagram of the server 1230. The server 1230 may include a communication unit 2005 that includes both hardware components (e.g., communication control circuits, switches, and antennas) and software components (e.g., communication protocols, computer code). For example, the communication unit 2005 may include at least one network interface. The server 1230 may communicate with the vehicles 1205, 1210, 1215, 1220, and 1225 through the communication unit 2005. For example, the server 1230 may receive navigation information transmitted from the vehicles 1205, 1210, 1215, 1220, and 1225 through the communication unit 2005. The server 1230 may distribute an autonomous vehicle road navigation model to one or more autonomous vehicles through the communication unit 2005.

[0345] Server 1230 may include at least one non-transitory storage medium 2010, such as a hard drive, compact disc, 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 autonomous vehicle road navigation models that server 1230 generates based on the navigation information. Storage device 2010 may be configured to store any other information, such as a sparse map (e.g., sparse map 800 discussed above with respect to FIG. 8).

[0346] In addition to, or instead 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 for sparse map 800), an autonomous vehicle road navigation model, and / or navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225.

[0347] Server 1230 may include at least one processing device 2020 configured to execute computer codes 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 vehicles that subsequently travel road segment 1200). Processing device 2020 may be similar to or different from processors 180, 190, or processing unit 110.

[0348] 21 shows a block diagram of a memory 2015 that may store computer code or instructions for performing one or more operations for generating a road navigation model for use in autonomous vehicle navigation. As shown in FIG. 21 , the memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, the memory 2015 may include a model generation module 2105 and a model distribution module 2110. The processor 2020 may execute instructions stored in either of the modules 2105 and 2110 included in the memory 2015.

[0349] 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 of a common road segment (e.g., road segment 1200) based on navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225. For example, in generating the autonomous vehicle road navigation model, the processor 2020 may cluster vehicle trajectories along the common road segment 1200 into different clusters. The processor 2020 may determine a target trajectory along the common road segment 1200 based on the clustered vehicle trajectories for each of the different clusters. Such an operation may include finding an average or mean trajectory of the clustered vehicle trajectories in each cluster (e.g., by averaging data representing the clustered vehicle trajectories). In some embodiments, the target trajectory may be associated with a single lane of the common road segment 1200.

[0350] The autonomous vehicle road navigation model may include multiple target trajectories, each associated with a separate lane of a common road segment 1200. In some embodiments, the target trajectories may be associated with the common road segment 1200 instead of a single lane of the road segment 1200. The target trajectories may be represented by cubic splines. In some embodiments, the splines may be defined with less than 10 kilobytes per kilometer, less than 20 kilobytes per kilometer, less than 100 kilobytes per kilometer, less than 1 megabyte per kilometer, 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 discussed below with respect to FIG. 24 .

[0351] The road model and / or sparse map may store trajectories associated with road segments. These trajectories may be referred to as target trajectories and are provided to the autonomous vehicle for autonomous navigation. The target trajectories may be received from multiple vehicles and may be generated based on actual trajectories or recommended trajectories (actual trajectories with some modifications) received from multiple vehicles. The target trajectories included in the road model or sparse map may be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0352] A vehicle traveling along a road segment may collect data through various sensors. The data may include landmarks, road signature profiles, vehicle movements (e.g., accelerometer data, speed data), and vehicle position (e.g., GPS data) to reconstruct the actual trajectory itself or transmit the data to a server, which reconstructs the vehicle's actual trajectory. In some embodiments, the vehicle may transmit data regarding the trajectory (e.g., curves in any reference frame), landmark data, and lane assignments along the traveled path to server 1230. Different vehicles traveling along the same road segment over multiple trips may have different trajectories. Server 1230 may identify the path or trajectory associated with each lane from the trajectories received from the vehicles through a clustering process.

[0353] 22 shows a process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine a target trajectory for a common road segment (e.g., road segment 1200). The target trajectory or target trajectories determined from the clustering process may be included in autonomous vehicle road navigation model or sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 may transmit multiple trajectories 2200 to server 1230. In some embodiments, server 1230 may generate trajectories based on landmark, road geometry, and vehicle motion information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate the autonomous vehicle road navigation model, the server 1230 may cluster the vehicle trajectory 1600 into multiple clusters 2205, 2210, 2215, 2220, 2225, and 2230, as shown in FIG. 22.

[0354] Clustering may be performed using various criteria. In some embodiments, all trips within a cluster may be similar in terms of absolute heading along the road segment 1200. The absolute heading may be obtained from GPS signals received by the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, dead reckoning may be used to obtain the absolute heading. As one skilled in the art will appreciate, dead reckoning may be used to determine the current positions, and therefore heading, of the vehicles 1205, 1210, 1215, 1220, and 1225 using previously determined positions, estimated speeds, etc. Trajectories clustered by absolute heading may be useful for identifying routes along a road.

[0355] In some embodiments, all trips within a cluster may be similar with respect to lane assignment along the trip of road segment 1200 (e.g., same lane before and after an intersection). Trajectories clustered by lane assignment may be useful for identifying lanes along a road. In some embodiments, both criteria (e.g., absolute heading and lane assignment) may be used for clustering.

[0356] For each cluster 2205, 2210, 2215, 2220, 2225, and 2230, the trajectories may be averaged to obtain a target trajectory associated with a particular cluster. For example, trajectories from multiple runs associated with the same lane cluster may be averaged. The average trajectory may be a target trajectory associated with a particular lane. To average a cluster of trajectories, server 1230 may select a reference frame for any trajectory C. For all other trajectories (C, ..., C), server 1230 may find a rigid transformation that maps C to C, where i = 1, 2, ..., n, where n is a positive integer corresponding to the total number of trajectories included in the cluster. Server 1230 may calculate the average curve or trajectory in the C reference frame.

[0357] In some embodiments, the landmarks may define arc lengths that are consistent between different runs, and the arc lengths may be used to align the track with the lanes. In some embodiments, lane marks before and after intersections may be used to align the track with the lanes.

[0358] To assemble lanes from the trajectory, server 1230 may select a reference frame for any lane. Server 1230 may map overlapping lanes to the selected reference frame. Server 1230 may continue mapping until all lanes are in the same reference frame. Lanes that are adjacent to each other may be aligned as if they were the same lane and may later be shifted laterally.

[0359] Landmarks recognized along a road segment may be mapped to a common reference frame, first at the lane level and then at the intersection level. For example, the same landmark may be recognized multiple times by multiple vehicles on multiple runs. Data about the same landmark received on different runs may be slightly different. Such data may be averaged and mapped to the same reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of data for the same landmark received on multiple runs may be calculated.

[0360] In some embodiments, each lane of road segment 120 may be associated with a target trajectory and specific landmarks. The target trajectory or multiple such target trajectories may be included in an autonomous vehicle road navigation model that may later be used by other autonomous vehicles traveling along the same road segment 1200. Landmarks identified by vehicles 1205, 1210, 1215, 1220, and 1225 while they travel along road segment 1200 may be recorded in association with the target trajectory. The target trajectory and landmark data may be continuously or periodically updated with new data received from other vehicles on subsequent trips.

[0361] For localization of an autonomous vehicle, the disclosed system and method may use an extended Kalman filter. The vehicle's position may be determined based on three-dimensional position data and / or three-dimensional orientation data, and prediction of the vehicle's future position beyond its current position by integrating egomotion. The vehicle's position may be corrected or adjusted by observing images of landmarks. For example, if the vehicle detects a landmark in an image captured by a camera, the landmark may be compared to known landmarks stored in the road model or sparse map 800. The known landmark may have a known position (e.g., GPS data) along a target trajectory stored in the road model and / or sparse map 800. Based on the current speed and images of the landmark, the distance from the vehicle to the landmark may be estimated. The vehicle's position along the target trajectory may be adjusted based on the distance to the landmark and the known position of the landmark (stored in the road model or sparse map 800). The landmark position / location data (e.g., average values ​​from multiple trips) stored in the road model and / or sparse map 800 may be assumed to be accurate.

[0362] In some embodiments, the disclosed system may form a closed-loop subsystem in which an estimate of the vehicle's six degrees of freedom (e.g., three-dimensional position data and three-dimensional orientation data) position can be used to navigate (e.g., steer the wheels) the autonomous vehicle to reach a desired point (e.g., 1.3 seconds ahead of a stored point). Data measured from the steering and actual navigation can then be used to estimate the six degrees of freedom position.

[0363] In some embodiments, poles along roads, such as lampposts and power or cable poles, may be used as landmarks for vehicle location. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along road segments, may also be used as landmarks for vehicle location. When poles are used for location, the x observation of the pole (i.e., the viewing angle from the vehicle) may be used rather than the y observation (i.e., the distance to the pole), since the bottom of the pole may be occluded and not on the road plane.

[0364] FIG. 23 illustrates a navigation system for a vehicle that may be used for autonomous navigation using a crowdsourced sparse map. For purposes of illustration, the vehicle is referred to as vehicle 1205. The vehicle illustrated in FIG. 23 may be any other vehicle disclosed herein, including, for example, vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 illustrated in other embodiments. As illustrated in FIG. 12, vehicle 1205 may be in communication 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 to travel along 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. The accelerometer 2325 may be configured to detect acceleration or deceleration of the vehicle 1205. The vehicle 1205 shown in Figure 23 may be an autonomous vehicle, and the navigation system 2300 may be used to provide navigation guidance for the autonomous journey. Alternatively, the vehicle 1205 may be a non-autonomous human-controlled vehicle, and the navigation system 2300 may still be used to provide navigation guidance.

[0365] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 over the 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 the GPS signals, map data from the sparse map 800 (which may be stored in a storage device onboard the vehicle 1205 and / or received from the server 1230), road geometry sensed by the road profile sensor 2330, images captured by the camera 122, and / or an autonomous vehicle road navigation model received from the server 1230. The road profile sensor 2330 may include different types of devices for measuring different types of road profiles, such as road surface roughness, road width, road elevation, road curvature, etc. For example, the road surface profile sensor 2330 may include a device that measures suspension movement of the vehicle 2305 to derive a road surface roughness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor to measure the distance from the vehicle 1205 to the side of the road (e.g., a barrier on the side of the road), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the elevation above and below the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure road curvature. For example, a camera (e.g., camera 122 or another camera) may be used to capture images of the road showing the road curvature. The vehicle 1205 may use such images to detect the road curvature.

[0366] The at least one processor 2315 may be programmed to receive, from the camera 122, at least one environmental image associated with the vehicle 1205. The at least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with the vehicle 1205. The navigation information may include a trajectory associated with the vehicle 1205 traveling along the road segment 1200. The at least one processor 2315 may determine the trajectory based on motion of the camera 122 (and thus the vehicle), such as three-dimensional translational motion and three-dimensional rotational motion. In some embodiments, the at least one processor 2315 may determine the translational and rotational motion of the camera 122 based on analysis of multiple images acquired by the camera 122. In some embodiments, the navigation information may include lane assignment information (e.g., whether the vehicle 1205 is traveling in that lane along the road segment 1200). 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 from server 1230 to vehicle 1205 to provide autonomous navigation guidance to vehicle 1205.

[0367] The at least one processor 2315 may also be programmed to transmit navigation information from the vehicle 1205 to the server 1230. In some embodiments, the navigation information may be transmitted to the server 1230 along with road information. The road position information may include at least one of a GPS signal received by the GPS unit 2310, landmark information, road geometry, lane information, etc. The at least one processor 2315 may receive an autonomous vehicle road navigation model or a portion of the model from the server 1230. The autonomous vehicle road navigation model received from the server 1230 may include at least one update based on the navigation information transmitted from the vehicle 1205 to the server 1230. The portion of the model transmitted from the server 1230 to the vehicle 1205 may include an updated portion of the model. The at least one processor 2315 may cause at least one navigation action by the vehicle 1205 (e.g., making a turn, braking, accelerating, steering to pass another vehicle, etc.) based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0368] The at least one processor 2315 may be configured to communicate with various sensors and components included in the vehicle 1205, including the communication unit 1705, the GPS unit 2315, the camera 122, the speed sensor 2320, the accelerometer 2325, and the road profile sensor 2330. The 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 through 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.

[0369] In some embodiments, the vehicles 1205, 1210, 1215, 1220, and 1225 may communicate with each other and share navigation information with each other, such that at least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may generate an autonomous vehicle road navigation model using crowdsourcing, for example, based on information shared by other vehicles. In some embodiments, the vehicles 1205, 1210, 1215, 1220, and 1225 may share navigation information with each other, and each vehicle may update its own autonomous vehicle road navigation model, which is provided to the vehicle. In some embodiments, at least one of the vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) may function as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) may perform some or all of the functions performed by the server 1230. For example, the at least one processor 2315 of the hub vehicle may communicate with and receive navigation information from other vehicles. The at least one processor 2315 of the hub vehicle may generate an autonomous vehicle road navigation model or updates to the model based on the shared information received from the other vehicles. The at least one processor 2315 of the hub vehicle may transmit the autonomous vehicle road navigation model or updates to the model to the other vehicles to provide autonomous navigation guidance.

[0370] 24 is a flowchart illustrating an example process 2400 for generating a road navigation model for use in autonomous vehicle navigation. Process 2400 may be performed by server 1230 or processor 2315 included in the hub vehicle. In some embodiments, process 2400 may be used to aggregate vehicle navigation information to provide an autonomous vehicle road navigation model or update the model.

[0371] Process 2400 may include a server receiving navigation information from multiple vehicles (step 2405). For example, server 1230 may receive navigation information from vehicles 1205, 1210, 1215, 1220, and 1225. The navigation information from the multiple vehicles may be associated with a common road segment (e.g., road segment 1200) traveled by the multiple vehicles, e.g., 1205, 1210, 1215, 1220, and 1225.

[0372] Process 2400 may further include storing, by the server, the navigation information associated with the common road segment (step 2410). For example, server 1230 may store the navigation information in storage device 2010 and / or memory 2015.

[0373] Process 2400 may further include generating, by the server, at least a portion of an autonomous vehicle road navigation model of the common road segment based on the navigation information from the multiple vehicles (step 2415). The autonomous vehicle road navigation model of the common road segment may include at least one line representation of a road surface feature extending along the common road segment, where each line representation may represent a path along the common road segment that substantially corresponds to the road surface feature. For example, the road surface feature may include a road edge or lane marking. Further, the road surface feature may be identified by image analysis of multiple images acquired as the multiple vehicles traverse the common road segment. For example, server 1230 may generate at least a portion of the autonomous vehicle road navigation model of the common road segment 1200 based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 traveling on the common road segment 1200.

[0374] In some embodiments, the autonomous vehicle road navigation model may be configured to be overlaid on a map, image, or satellite imagery. For example, the model may be overlaid on a map or imagery provided by a conventional navigation service such as Google® Maps, Waze, or the like.

[0375] In some embodiments, generating at least a portion of the autonomous vehicle road navigation model may include identifying multiple landmarks associated with a common road segment based on image analysis of the multiple images. In certain aspects, this analysis may include accepting a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold. For example, if a potential landmark appears in data from vehicle 1210 but does not appear in data from vehicles 1205, 1215, 1220, and 1225, the system may determine that a ratio of 1:5 is below the threshold for accepting a potential landmark. By further example, if a potential landmark appears in data from vehicles 1205, 1215, 1220, and 1225 but does not appear in data from vehicle 1210, the system may determine that a ratio of 4:5 is above the threshold for accepting a potential landmark.

[0376] Process 2400 may further include 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 (step 2420). For example, server 1230 may distribute the autonomous vehicle road navigation model or a portion of the model (e.g., an update) to vehicles 1205, 1210, 1215, 1220, and 1225, or any other vehicles that subsequently travel road segment 1200, for use in autonomously navigating the vehicles along road segment 1200.

[0377] Process 2400 may include additional operations or steps. For example, generating the autonomous vehicle road navigation model may include clustering vehicle trajectories received from vehicles 1205, 1210, 1215, 1220, and 1225 into multiple clusters along road segment 1200 and / or aligning data received from vehicles 1205, 1210, 1215, 1220, and 1225, as discussed in more detail below with respect to FIG. 29 . Process 2400 may include determining a target trajectory along the common road segment 1200 by averaging the clustered vehicle trajectories within each cluster. Process 2400 may also include associating the target trajectory with a single lane of the common road segment 1200. Process 2400 may include determining a cubic spline to represent the target trajectory in the autonomous vehicle road navigation model.

[0378] Using crowdsourced sparse maps for navigation

[0379] As discussed above, the server 1230 may distribute the generated road navigation model to one or more vehicles. As described in detail above, the road navigation model may be included in a sparse map. According to embodiments of the present disclosure, one or more vehicles may be configured to use the distributed sparse map for autonomous navigation.

[0380] 25 is an exemplary functional block diagram of memory 140 and / or 150 that may be stored / programmed with instructions to perform one or more operations in accordance with the disclosed embodiments. While reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0381] 25 , memory 140 may store a sparse map module 2502, an image analysis module 2504, a road surface feature module 2506, and a 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 modules 2502, 2504, 2506, and 2508 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, any steps of the following processes may be performed by one or more processing devices.

[0382] In one embodiment, the sparse map module 2502 may store instructions that, when executed by the processing unit 110, receive (and, in some embodiments, store) a sparse map distributed by the server 1230. The sparse map module 2502 may receive the entire sparse map in one communication, or may receive a subportion of the sparse map, the subportion corresponding to the area in which the vehicle is operating.

[0383] In one embodiment, image analysis module 2504 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform image analysis of one or more images acquired by one of image capture devices 122, 124, and 126. As described in further detail below, image analysis module 2504 may analyze the one or more images to determine the current location of the vehicle.

[0384] In one embodiment, the road surface feature module 2506 may store instructions that, when executed by the processing unit 110, identify road surface features within a sparse map received by the sparse map module 2502 and / or within one or more images acquired by one of the image capture devices 122, 124, and 126.

[0385] In one embodiment, the navigation response module 2508 may store software executable by the processing unit 110 to determine a desired navigation response based on data derived from execution of the sparse map module 2502, the image analysis module 2504, and / or the road surface features module 2506.

[0386] Additionally, any of the modules disclosed herein (e.g., modules 2502, 2504, and 2506) may implement techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems.

[0387] 26 is a flowchart illustrating an example process 2600 for autonomously navigating a vehicle along a road segment. The process 2600 may be performed by a processor 2315 included in the navigation system 2300.

[0388] Process 2600 may include receiving a sparse map model (step 2605). For example, processor 2315 may receive the sparse map from server 1230. In some embodiments, the sparse map model may include at least one line representation of a road surface feature extending along the road segment, each line representation representing a path along the road segment that substantially corresponds to the road surface feature. For example, the road feature may include a road edge or a lane marking.

[0389] Process 2600 may further include receiving at least one image from a camera representing the vehicle's environment (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.

[0390] Process 2600 may also include analyzing the sparse map model and at least one image received from the camera (step 2615). For example, analyzing the sparse map model and the at least one image received from the camera may include determining a current position of the vehicle relative to a longitudinal position along at least one line representation of a road surface feature extending along the road segment. In some embodiments, this determination may be based on identification of at least one recognized landmark in the at least one image. In some embodiments, process 2600 may further include determining an estimated offset based on an expected position of the vehicle relative to the longitudinal position and the current position of the vehicle relative to the longitudinal position.

[0391] Process 2600 may further include determining an autonomous navigation response of the vehicle based on an analysis of the sparse map model and at least one image received from the camera (step 2620). In embodiments in which 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 the at least one line representation, processor 2315 may shift the vehicle toward the right (e.g., by changing the direction of the wheels). As a further example, if processor 2315 determines that an identified landmark is offset from an expected position, processor 2315 may shift the vehicle to move the identified landmark toward its expected position. Thus, in some embodiments, process 2600 may further include adjusting a steering system of the vehicle based on the autonomous navigation response.

[0392] Aligning crowdsourced map data

[0393] As discussed above, the generation of a crowdsourced sparse map may use data from multiple runs along a common road segment. This data may be aligned to generate a coherent sparse map. As discussed above with respect to FIG. 14, generating a map skeleton may be insufficient to construct splines for use in navigation. Thus, embodiments of the present disclosure may enable alignment of crowdsourced data from multiple runs.

[0394] 27 shows a block diagram of a memory 2015 that may store computer code or instructions for performing one or more operations for generating a road navigation model for use in autonomous vehicle navigation. As shown in FIG. 21, the memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, the memory 2015 may include a driving data receiving module 2705 and a longitudinal alignment module 2710. The processor 2020 may execute instructions stored in either of the modules 2705 and 2710 included in the memory 2015.

[0395] The driving data receiving module 2705 may store instructions that, when executed by the processor 2020, may control the communication device 2005 to receive driving data from one or more vehicles (e.g., 1205, 1210, 1215, 1220, and 1225).

[0396] The longitudinal alignment module 2710 may store instructions that, when executed by the processor 2020, align data received using the driving data receiving module 2705 when the data relates to a common road segment (e.g., road segment 1200) based on navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225. For example, the longitudinal alignment module 2710 may align the data along patches, which may make it easier to optimize error correction associated with the alignment. In some embodiments, the longitudinal alignment module 2710 may further score the alignment of each patch with a confidence score.

[0397] Figure 28A shows an example of raw position data from four different runs. In the example of Figure 28A, raw data from the first run is shown as a series of star shapes, raw data from the second run is shown as a series of filled squares, raw data from the third run is shown as a series of hollow squares, and raw data from the fourth run is shown as a series of hollow circles. As one skilled in the art will recognize, the shapes are merely illustrative of the data itself, which may be stored as a series of coordinates, whether local or global.

[0398] As can be seen in Figure 28A, trips may occur in different lanes along the same road (represented by lane 1200). Additionally, Figure 28A illustrates that trip data may contain variance due to errors in location measurement (e.g., GPS) and data points may be missing due to system errors. Finally, Figure 28A also illustrates that each trip may start and end at different points within a segment along the road.

[0399] Figure 28B shows another example of raw position data from five different runs. In the example of Figure 28B, raw data from the first run is shown as a series of solid squares, raw data from the second run is shown as a series of hollow squares, raw data from the third run is shown as a series of hollow circles, raw data from the fourth run is shown as a series of stars, and raw data from the fifth run is shown as a series of triangles. As one skilled in the art will recognize, the shapes are merely illustrative of the data itself, which may be stored as a series of coordinates, whether local or global.

[0400] FIG. 28B shows similar characteristics of trip data as FIG. 28A. FIG. 28B further illustrates that an intersection may be detected by tracking the movement of a fifth trip away from the other trips. For example, the example data in FIG. 28B may suggest that an exit ramp is on the right side of the road (represented by line 1200). FIG. 28B also illustrates that an added lane may be detected if the data begins on a new portion of the road. For example, the fourth trip in the example data in FIG. 28B may suggest that a fourth lane is added to the road immediately after the detected exit ramp.

[0401] 28C shows an example of raw position data with a target trajectory from it. For example, a first running data (represented by a triangle) and a second running data (represented by a hollow square) have an associated target trajectory 2810. Similarly, a third running data (represented by a hollow circle) has an associated target trajectory 2820, and a fourth running data (represented by a solid square) has an associated target trajectory 2830.

[0402] In some embodiments, the driving data may be reconstructed so that one target trajectory is associated with each driving lane, as shown in FIG. 28C. Such target trajectories may be generated from one or more simple smooth line models when proper alignment of patches of driving data is performed. Process 2900, discussed below, is one example of proper alignment of patches.

[0403] 29 is a flowchart illustrating an example process 2900 for determining a line representation of road surface features extending along a road segment. The line representation of the road surface features may be configured for use in autonomous vehicle navigation, for example, using process 2600 of FIG. 26 above. Process 2900 may be performed by server 1230 or processor 2315 included in the hub vehicle.

[0404] Process 2900 may include receiving, by a server, a first set of driving data including location information associated with road surface features (step 2905). The location information may be determined based on analysis of an image of a road segment, and the road surface features may include road edges or lane markings.

[0405] Process 2900 may further include receiving, by the server, a second set of driving data including location information associated with road surface features (step 2910). Similar to step 2905, the location information may be determined based on an analysis of an image of a road segment, and the road surface features may include road edges or lane markings. Depending on when the first set of driving data and the second set of driving data are collected, steps 2905 and 2910 may be performed simultaneously, or there may be a lapse of time between steps 2905 and 2910.

[0406] Process 2900 may also include segmenting the first set of driving data into first driving patches and the second set of driving data into second driving patches (step 2915). The patches may be defined by data size or driving length. The size or length defining the patch may be predefined to one or more values ​​or may be updated using neural networks or other machine learning techniques. For example, the patch length may always be predefined to 1 km, or may be predefined to 1 km when driving along roads at speeds greater than 30 km / hr, or 0.8 km when driving along roads at speeds less than 30 km / hr. Alternatively or simultaneously, machine learning analysis may optimize the size or length of the patch based on several dependent variables, such as driving conditions, driving speed, etc. Furthermore, in some embodiments, a route may be defined by data size and driving length.

[0407] 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 embodiments, process 2900 may further include determining whether to accept or reject the landmarks in the sets of data based on one or more thresholds, as described above with respect to FIG.

[0408] Process 2900 may include longitudinally aligning the first set of driving data with the second set of driving data within the corresponding patch (step 2920). For example, longitudinal alignment may involve selecting either the first set of data or the second set of data as a reference data set, and then shifting and / or elastically stretching the other set of data to align the patches within the set. In some embodiments, aligning the sets of data may further include aligning GPS data included in both sets and associated with the patches. For example, connections between the sets of patches may be adjusted to more closely align with the GPS data. However, in such embodiments, the adjustment must be limited to prevent limitations of the GPS data from compromising the alignment. For example, GPS data is not three-dimensional, and therefore, when projected onto a three-dimensional representation of the road, unnatural twists and turns may occur.

[0409] Process 2900 may further include determining a line representation of the road surface features based on the longitudinally aligned first and second driving data for the first and second draft patches (step 2925). For example, the line representation may be constructed using a smooth line model on the aligned data. 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 the first set of driving data or the second set of driving data. For example, the first set of data and / or the second set of data may be expressed in local coordinates, but the use of a smooth line model requires both sets to have the same coordinate axes. Thus, in certain aspects, the first set of data and / or the second set of data may be aligned to have the same coordinate axes as each other.

[0410] In some embodiments, determining the line representation may include determining and applying a set of average transformations, each of which may be based on a transformation determined on link data from a first set of driving data across sequential patches and on link data from a second set of driving data across sequential patches.

[0411] Process 2900 may include additional operations or steps. For example, process 2900 may further include overlaying the line representations of the road surface features onto at least one geographic image. For example, the geographic image may be a satellite image. By way of further example, process 2900 may further include filtering out landmark information and / or driving data that appear erroneous based on the determined line representations and longitudinal alignment. Such filtering may be similar in concept to rejecting potential landmarks based on one or more thresholds, as described above with respect to FIG. 19 .

[0412] Crowdsourcing of road surface information

[0413] In addition to crowdsourcing landmarks and line representations to generate a sparse map, the disclosed systems and methods may also crowdsource road surface information, such that road conditions may be stored along with and / or within the sparse map used to navigate an autonomous vehicle.

[0414] 30 is an exemplary functional block diagram of memory 140 and / or 150 that may be stored / programmed with instructions to perform one or more operations in accordance with the disclosed embodiments. While reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0415] 30 , memory 140 may store an image receiving module 3002, a road surface feature module 3004, a position determining module 3006, and a 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 modules 3002, 3004, 3006, and 3008 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, any steps of the following processes may be performed by one or more processing devices.

[0416] 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) images acquired by one of the image capture devices 122, 124, and 126.

[0417] In one embodiment, road surface feature module 3004 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform analysis of one or more images acquired by one of image capture devices 122, 124, and 126 to identify road surface features. For example, the road surface features may include road edges or lane markings.

[0418] In one embodiment, the position determination module 3006 may store instructions (such as GPS software or visual odometry software) that, when executed by the processing unit 110, receive position information regarding the vehicle. For example, the position determination module 3006 may receive GPS data and / or egomotion data including the vehicle's location. In some embodiments, the position determination module 3006 may calculate one or more locations using the received information. For example, the position determination module 3006 may receive one or more images acquired by one of the image capture devices 122, 124, and 126 and use an analysis of the images to determine the vehicle's location.

[0419] In one embodiment, the navigation response module 3008 may store software executable by the processing unit 110 to determine a desired navigation response based on data derived from execution of the image receiving module 3002, the road surface feature module 3004, and / or the position determination module 3006.

[0420] Additionally, any of the modules disclosed herein (e.g., modules 3002, 3004, and 3006) may implement techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems.

[0421] 31 is a flowchart illustrating an example process 3100 for collecting road surface information for a road segment. The process 3100 may be performed by a processor 2315 included in the navigation system 2300.

[0422] Process 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.

[0423] The process 3100 may further include identifying, in the at least one image, at least one road surface feature along the portion of the road segment (step 3010). For example, the at least one road surface feature may include a road edge or may include a lane marking.

[0424] Process 3100 may also include determining a plurality of positions associated with the road surface features according to a local coordinate system of the vehicle (step 3115). For example, processor 2315 may determine the plurality of positions using ego-motion data and / or GPS data.

[0425] Process 3100 may further include transmitting the determined locations from the vehicle to a server (step 3120). For example, the determined locations may be configured to enable the server to determine a line representation of road surface features extending along the road segment, as described above with respect to Figure 29. In some embodiments, the line representation may represent a path along the road segment that substantially corresponds to the road surface features.

[0426] Process 3100 may include additional operations or steps. For example, process 3100 may further include receiving the line representation from a server. In this example, processor 2315 may receive the line representation as part of a sparse map received, for example, according to process 2400 of FIG. 24 and / or process 2600 of FIG. 26. By way of further example, process 2900 may further include overlaying the line representation of the road surface features onto at least one geographic image. For example, the geographic image may be a satellite image.

[0427] As described above with respect to landmark crowdsourcing, in some embodiments, the server may implement selection criteria to determine whether to accept or reject potential road surface features received from vehicles. For example, the server may accept a road surface feature if the ratio of the set of locations where the road surface feature appears to the set of locations where the road surface feature does not appear exceeds a threshold, and / or may reject a potential road surface feature if the ratio of the set of locations where the road surface feature does not appear to the set of locations where the road surface feature appears exceeds a threshold.

[0428] Vehicle location

[0429] In some embodiments, the disclosed systems and methods may use a sparse map for autonomous vehicle navigation. Specifically, the sparse map may be for autonomous vehicle navigation along road segments. For example, the sparse map may provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed in more detail below, an autonomous vehicle may use the sparse map to navigate one or more roads based on one or more stored trajectories.

[0430] Lane Localization for Autonomous Vehicles Using Lane Markings

[0431] As described above, an autonomous vehicle may navigate based on dead reckoning between landmarks. However, errors may accumulate during dead reckoning navigation, and thus the accuracy of position determination relative to a target trajectory may gradually decrease over time. As described below, lane marks may be used to identify the vehicle's position between landmark intervals, minimizing the accumulation of errors during dead reckoning navigation.

[0432] For example, a spline can be expressed as follows:

number

[0433] In the example of Equation 1, B(u) is the curve representing the spline, b k (u) is the basis function, P (k) represents a control point. The control point can be transformed into local coordinates, for example, according to Equation 2 below:

number

[0434] In the example of Equation 2, P l (k) is the control point P transformed into local coordinates (k) where R is a rotation matrix that can be estimated from the direction of travel of the vehicle, and R T denotes the transpose of the rotation matrix, and T denotes the position of the vehicle.

[0435] In some embodiments, the local curve representing the vehicle's path may be determined using Equation 3 below.

number

[0436] In the example of Equation 3, f is the focal length of the camera and B lz , B ly , and B lx represents the component of the curve B in local coordinates. The derivation of H can be expressed as Equation 4 below.

number

[0437] Based on Eq. 1, B' in Eq. 4 l can be further represented by Equation 5 below:

number

[0438] Equation 5 may be solved, for example, by a Newton-Raphson-based solution. In certain aspects, the solution may be performed in five steps or less. To solve for x, some embodiments may use Equation 6 below.

number

[0439] In some embodiments, the derivative of the trajectory may be used. For example, the derivative may be given by Equation 7 below:

number

[0440] In the example of Equation 7, X j may represent, for example, a state component of the vehicle's position. In certain embodiments, j may represent an integer between 1 and 6.

[0441] To solve Equation 7, in some embodiments, the following Equation 8 may be used:

number

[0442] To solve Equation 8, in some embodiments, implicit differentiation may be used to obtain Equations 9 and 10 below.

number

[0443] Equations 9 and 10 may be used to obtain the derivative of the trajectory. In some embodiments, an extended Kalman filter may be used to locate the lane measurements. As described above, by locating the lane measurements, lane marks may be used to minimize error accumulation during dead-reckoning navigation. The use of lane marks is described in more detail below with respect to Figures 32-35.

[0444] 32 is an exemplary functional block diagram of memory 140 and / or 150 that may be stored / programmed with instructions to perform one or more operations in accordance with the disclosed embodiments. While reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0445] 32 , memory 140 may store a position determination module 3202, an image analysis module 3204, a distance determination module 3206, and an offset determination module 3208. 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 modules 3202, 3204, 3206, and 3208 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, any steps of the following processes may be performed by one or more processing devices.

[0446] In one embodiment, the position determination module 3202 may store instructions (such as GPS software or visual odometry software) that, when executed by the processing unit 110, receive position information regarding the vehicle. For example, the position determination module 3202 may receive GPS data and / or egomotion data including the vehicle's location. In some embodiments, the position determination module 3202 may calculate one or more locations using the received information. For example, the position determination module 3202 may receive one or more images acquired by one of the image capture devices 122, 124, and 126 and use an analysis of the images to determine the vehicle's location.

[0447] The position determination module 3202 may also use other navigation sensors to determine the vehicle's position. For example, a speed sensor or accelerometer may send information to the position determination module 3202 for use in calculating the vehicle's position.

[0448] In one embodiment, image analysis module 3204 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform an analysis of one or more images acquired by one of image capture devices 122, 124, and 126. As described in further detail below, image analysis module 3204 may analyze the one or more images to identify at least one lane marking.

[0449] In one embodiment, the distance determination module 3206 may store instructions that, when executed by the processing unit 110, perform an analysis of one or more images acquired by one of the image capture devices 122, 124, and 126 to determine the distance from the vehicle to the lane markings identified by the image analysis module 3204.

[0450] In one embodiment, the offset determination module 3208 may store software executable by the processing unit 110 to determine an estimated offset of the vehicle from the road model trajectory. For example, the offset determination module 3208 may calculate the estimated offset using the distance determined by the distance determination module 3206. A desired navigation response may then be determined based on data derived from execution of the position determination module 3202, the image analysis module 3204, the distance determination module 3206, and / or the offset determination module 3208.

[0451] Additionally, any of the modules disclosed herein (e.g., modules 3202, 3204, and 3206) may implement techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems.

[0452] Figure 33A shows an example of a vehicle navigating by dead reckoning without using lane markings. In the example of Figure 33A, the vehicle navigates along trajectory 3310 but does not use lane markings (e.g., marks 3320A or 3320B) for navigation.

[0453] Figure 33B shows an example 350 m after Figure 33A. As shown in Figure 33B, the vehicle's trajectory 3310 is not perfectly aligned with the lane markings (e.g., marks 3320A or 3320B) due to the accumulation of dead-reckoning errors.

[0454] Figure 33C shows an example 1 km later than Figures 33A and 33B. As shown in Figure 33C, the expected position 3330A of the landmark is not aligned with the actual position 3330B of the landmark. Here, the vehicle may use the landmark to correct for accumulated dead-reckoning errors over the course of 1 km, but the systems and methods of the present disclosure may use lane marks to enable the accumulation of dead-reckoning errors between landmarks to be minimized.

[0455] Figure 34A shows an example of a vehicle navigating with dead reckoning using lane marks. In the example of Figure 34A, the vehicle navigates along a trajectory 3410 and also along identified lane marks (e.g., marks 3420A and 3420B) for location and use for navigation.

[0456] Figure 34B shows an example 350 m after Figure 34A. As shown in Figure 34B, the vehicle has used the identified lane marks to correct for dead-reckoning errors so that the vehicle's trajectory 3410 is substantially aligned with the lane marks (e.g., marks 3420A and 3420B).

[0457] Figure 34C shows an example 1 km later than Figures 34A and 34B. As shown in Figure 34C, the expected location 3430A of the landmark is substantially aligned with the actual location 3430B of the landmark. Thus, upon encountering the landmark, the vehicle in Figure 34C may make a significantly smaller correction than the vehicle in Figure 33C. Process 3500 in Figure 35, described below, is an example process by which a vehicle may use lane markings for navigation, as in Figures 34A-34C.

[0458] 35 is a flowchart illustrating an example process 3500 for correcting the position of a vehicle navigating a road segment. The process 3500 may be performed by a processor 2315 included in the navigation system 2300.

[0459] Process 3500 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 (step 3505). For example, the predetermined road model trajectory may be associated with a road segment, and in some embodiments, the predetermined road model trajectory may include a three-dimensional polynomial representation of a target trajectory along the road segment. The at least one navigation sensor may include, for example, a speed sensor or an accelerometer.

[0460] Process 3500 may further include receiving at least one image representing the vehicle's environment from an image capture device (step 3510). 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.

[0461] Process 3500 may also include analyzing the at least one image to identify at least one lane marking. The at least one lane marking may be associated with a travel lane along the road segment. Process 3500 may further include determining a distance from the vehicle to the at least one lane marking based on the at least one image. For example, various known algorithms for calculating the distance of an object in an image may be used.

[0462] Process 3500 may include determining an estimated offset of the vehicle from a predetermined road model trajectory based on the measured position of the vehicle and the determined distance. In some embodiments, determining the estimated offset may further include determining whether the vehicle is on a trajectory that intersects with at least one lane mark based on the distance to the at least one lane mark. Alternatively, or simultaneously, in some embodiments, determining the estimated offset may further include determining whether the vehicle is within a p...

Claims

1. 1. A system for mapping lane divisions for use in vehicle navigation, the system comprising: receiving navigation information from a plurality of vehicles that have navigated along a road segment, the road segment including a lane split feature, the road segment including at least a first travel lane before the lane split feature that transitions into at least a second travel lane and a third travel lane after the lane split feature; receiving a plurality of images associated with the road segment; From the navigation information, a first actual trajectory of a first vehicle along the first travel lane and the second travel lane of the road segment; a second actual trajectory of a second vehicle along the first travel lane and the third travel lane of the road segment; a third actual trajectory of a third vehicle along the first travel lane and the second travel lane of the road segment; and a fourth actual trajectory of a fourth vehicle along the first travel lane and the third travel lane of the road segment; and determining clustering the first actual trajectory and the third actual trajectory together into a first cluster; clustering the second actual trajectory and the fourth actual trajectory together into a second cluster; determining a deviation between the first cluster and the second cluster; selecting at least one image from the plurality of images based on a location of the deviation, the at least one image being associated with the location of the deviation; analyzing the selected at least one image to determine whether the deviation indicates the presence of the lane dividing feature in the road segment; a first target trajectory corresponding to the first driving lane before the lane splitting feature and extending along the second driving lane after the lane splitting feature; a second target trajectory diverging from the first target trajectory and extending along the third travel lane after the lane split feature; updating the vehicle-road navigation model to include 1. A system comprising: at least one processor programmed to:

2. 2. The system of claim 1, wherein the at least one processor is further configured to verify that the deviation between the first cluster and the second cluster is associated with the lane dividing feature included in the road segment based on a determined lateral spacing between the first actual trajectory and the second actual trajectory.

3. 3. The system of claim 2, wherein determining that the deviation between the first cluster and the second cluster is associated with the lane division feature included in the road segment is based on at least one of a representation of lane markings detected in the at least one image or a representation of road structure detected in the at least one image.

4. The system of any one of claims 1 to 3, wherein the second and third travel lanes extend parallel to one another after the lane split feature.

5. The system of any one of claims 1 to 3, wherein the second and third travel lanes diverge from one another after the lane split feature.

6. 6. The system of claim 1, wherein a first one of the navigation information includes a location identifier recorded by the first vehicle while traversing the road segment, and a second one of the navigation information includes a location identifier recorded by the second vehicle while traversing the road segment.

7. The system of any one of claims 1 to 6, wherein the at least one image is captured by an image capture device of the first vehicle or the second vehicle.

8. The system of any one of claims 1 to 6, wherein the at least one image is obtained from a server.

9. The system of any one of claims 1 to 7, wherein the analysis of the at least one image comprises the application of a trained model.

10. 10. The system of claim 1, wherein the at least one processor is configured to cluster the third actual trajectory with the first actual trajectory at a plurality of locations along the road segment.

11. 11. The system of claim 10, wherein the first actual trajectory and the second actual trajectory are clustered together in at least one first location before the lane splitting feature and clustered separately in at least one second location after the lane splitting feature.

12. The system of claim 10 , wherein the locations are separated by a predetermined distance longitudinally along the road segment.

13. The system of claim 10 , wherein the first target trajectory and the second target trajectory are determined based on the clustering.

14. 14. The system of claim 1, wherein the at least one processor is further programmed to refine the location where the second target trajectory diverges from the first target trajectory by analyzing distances between the first cluster and the second cluster at multiple locations surrounding a bifurcation point to determine a location where the first cluster and the second cluster begin to diverge.

15. The system of any one of claims 1 to 14, wherein the at least one processor is further programmed to distribute the updated vehicle road navigation model to a plurality of vehicles.

16. 16. The system of any one of claims 1 to 15, wherein the at least one processor is further programmed to remove at least one anomaly from at least one of the first target trajectory or the second target trajectory.

17. The system of claim 16 , wherein the at least one anomaly includes a deviation between the first target trajectory and the second target trajectory that does not exhibit the lane splitting characteristic.

18. the at least one processor: sampling the first actual trajectory and the second actual trajectory at a plurality of distances in a longitudinal direction along the road segment before and / or after the deviation-defining cluster, the plurality of distances being less than a predetermined distance; determining a distance between the first actual trajectory and the second actual trajectory in a transverse direction relative to the longitudinal direction at each of the plurality of distances; adjusting a position of the deviation based on where the first actual trajectory and the second actual trajectory begin to deviate; The system of any one of claims 1 to 17, configured to:

19. 1. A system for mapping lane divisions for use in vehicle navigation, the system comprising: receiving navigation information from a plurality of vehicles that have navigated along a road segment, the road segment including a lane split feature, the road segment including at least a first travel lane before the lane split feature that transitions into at least a second travel lane and a third travel lane after the lane split feature; From the navigation information, a first actual trajectory of a first vehicle along the first travel lane and the second travel lane of the road segment; a second actual trajectory of a second vehicle along the first travel lane and the third travel lane of the road segment; a third actual trajectory of a third vehicle along the first travel lane and the second travel lane of the road segment; and a fourth actual trajectory of a fourth vehicle along the first travel lane and the third travel lane of the road segment; and determining clustering the first actual trajectory and the third actual trajectory together into a first cluster; clustering the second actual trajectory and the fourth actual trajectory together into a second cluster; determining a deviation between the first cluster and the second cluster; a first target trajectory corresponding to the first driving lane before the lane splitting feature and extending along the second driving lane after the lane splitting feature; a second target trajectory diverging from the first target trajectory and extending along the third travel lane after the lane split feature; updating the vehicle-road navigation model to include at least one processor programmed to perform the at least one processor: sampling the first actual trajectory and the second actual trajectory at a plurality of distances in a longitudinal direction along the road segment before and / or after the deviation-defining cluster, the plurality of distances being less than a predetermined distance; determining a distance between the first actual trajectory and the second actual trajectory in a transverse direction relative to the longitudinal direction at each of the plurality of distances; adjusting a position of the deviation based on where the first actual trajectory and the second actual trajectory begin to deviate; A system configured to:

20. 1. A method performed by a system for mapping lane splits for use in vehicle navigation, the method comprising: the system receiving navigation information from a plurality of vehicles that have navigated along a road segment, the road segment including a lane split feature, the road segment including at least a first travel lane before the lane split feature that transitions into at least a second travel lane and a third travel lane after the lane split feature; receiving a plurality of images associated with the road segment; The system, from the navigation information, a first actual trajectory of a first vehicle along the first travel lane and the second travel lane of the road segment; a second actual trajectory of a second vehicle along the first travel lane and the third travel lane of the road segment; a third actual trajectory of a third vehicle along the first travel lane and the second travel lane of the road segment; and a fourth actual trajectory of a fourth vehicle along the first travel lane and the third travel lane of the road segment; and determining the system clustering the first actual trajectory and the third actual trajectory together into a first cluster; the system clustering the second actual trajectory and the fourth actual trajectory together into a second cluster; the system determining a deviation between the first cluster and the second cluster; selecting at least one image from the plurality of images based on a location of the deviation, the at least one image being associated with the location of the deviation; analyzing the selected at least one image to determine whether the deviation indicates the presence of the lane dividing feature in the road segment; a first target trajectory corresponding to the first driving lane before the lane splitting feature and extending along the second driving lane after the lane splitting feature; a second target trajectory that diverges from the first target trajectory and extends along the third travel lane after the lane split feature; and updating the vehicle-road navigation model to include: A method comprising:

21. 1. A system for mapping lane merges for use in vehicle navigation, the system comprising: receiving navigation information from a plurality of vehicles that have navigated along a road segment, the road segment including a lane merge feature, the road segment including at least a first travel lane and a second travel lane before the lane merge feature that transition into a third travel lane after the lane merge feature; receiving a plurality of images associated with the road segment; From the navigation information, a first actual trajectory of a first vehicle along the first and third travel lanes of the road segment; a second actual trajectory of a second vehicle along the second and third travel lanes of the road segment; a third actual trajectory of a third vehicle along the first travel lane and the third travel lane of the road segment; and a fourth actual trajectory of a fourth vehicle along the second and third travel lanes of the road segment; and determining clustering the first actual trajectory and the third actual trajectory together into a first cluster; clustering the second actual trajectory and the fourth actual trajectory together into a second cluster; determining convergence between the first cluster and the second cluster; selecting at least one image from the plurality of images based on the location of the convergence, the at least one image being associated with the location of the convergence; analyzing the selected at least one image to determine whether the convergence indicates the presence of the lane merge feature in the road segment; a first target trajectory corresponding to the first driving lane before the lane merging feature and extending along the third driving lane after the lane merging feature; a second target trajectory extending along the second travel lane prior to the lane merge feature and joining the first target trajectory; updating the vehicle-road navigation model to include 1. A system comprising: at least one processor programmed to:

Images