System and method for vehicle navigation

Abstract

To provide a system and method for automatic drive vehicle navigation that provide a navigation response, based on an analysis of images captured by one or more cameras for monitoring a vehicle environment.SOLUTION: In a navigation system for a host vehicle, a method for specifying a speed of an object includes: specifying at least one index concerning ego-motion of the host vehicle; receiving a first point cloud including at least a part of first expression concerning the object, and a second point cloud including at least a part of second expression concerning the object from a LIDAR system related to the host vehicle; and specifying the speed of the object, based on at least the one index concerning the ego-motion of the host vehicle, and based on a comparison between the first point cloud including at least a part of the first expression concerning the object, and the second point cloud including at least a part of the second expression concerning the object.SELECTED DRAWING: Figure 31

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This application claims the benefit of priority based on U.S. Provisional Patent Application No. 62 / 957,000, filed on January 3, 2020, and U.S. Provisional Patent Application No. 63 / 082,619, filed on September 24, 2020. The foregoing applications are hereby incorporated by reference in their entirety.

[0002] This disclosure generally relates to autonomous vehicle navigation. [Background Information]

[0003] As technology continues to evolve, the goal of fully autonomous vehicles that can navigate roadways is approaching. Autonomous vehicles may need to consider various factors, make appropriate decisions based on such factors, and safely and accurately reach the 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 information sources (e.g., a GPS unit, speed sensor, accelerometer, suspension sensor, etc.). At the same time, to navigate to a destination, an autonomous vehicle may need to identify its position in a particular lane (e.g., a particular lane on a multi - lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, obey traffic signals and signs, and travel from one road to another at an appropriate intersection or interchange. The utilization and interpretation of the vast amount of information that an autonomous vehicle collects as it travels to a destination pose many design challenges. The huge 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 presents problems that can actually limit or even have an adverse impact on autonomous navigation. Further, when an autonomous vehicle uses conventional mapping techniques to navigate, the huge amount of data required to store and update maps presents a very difficult problem.

Summary of the Invention

[0004] Embodiments consistent with the present disclosure provide a system and method for autonomous vehicle navigation. The disclosed embodiments may use a camera to provide an autonomous vehicle navigation function. For example, without conflicting with the disclosed embodiments, the disclosed system may include one, two, or more cameras for monitoring the environment of the vehicle. The disclosed system may provide a navigation response, for example, based on the analysis of images captured by one or more of these cameras.

[0005] In one embodiment, a navigation system for a host vehicle includes at least one processor programmed to identify at least one metric of the ego motion of the host vehicle. The at least one processor may also be programmed to receive, from a LIDAR system associated with the host vehicle, a first point cloud including a first representation of at least a portion of an object based on a first LIDAR scan of the field of view of the LIDAR system. The at least one processor may further be programmed to receive, from a LIDAR system associated with the host vehicle, a first point cloud including a first representation of at least a portion of an object based on a first LIDAR scan of the field of view of the LIDAR system. The at least one processor may also be programmed to receive, from the LIDAR system, a second point cloud including a second representation of at least a portion of the object based on a second LIDAR scan of the field of view of the LIDAR system. The at least one processor may further be programmed to identify the speed of the object based on at least one metric of the ego motion of the host vehicle and based on a comparison between the first point cloud including a first representation of at least a portion of the object and the second point cloud including a second representation of at least a portion of the object.

[0006] In one embodiment, a method for detecting an object in the environment of a host vehicle may comprise identifying at least one metric of the ego-motion of the host vehicle. The method may also comprise receiving, from a LIDAR system associated with the host vehicle, a first point cloud including a first representation of at least a portion of the object, based on a first LIDAR scan of the field of view of the LIDAR system. The method may further comprise receiving, from the LIDAR system, a second point cloud including a second representation of at least a portion of the object, based on a second LIDAR scan of the field of view of the LIDAR system. The method may also comprise determining the velocity of the object based on at least one metric of the ego-motion of the host vehicle and based on a comparison between the first point cloud including the first representation of at least a portion of the object and the second point cloud including the second representation of at least a portion of the object.

[0007] In one embodiment, a navigation system for a host vehicle may include at least one processor programmed to receive a sparse map associated with at least one road segment along which the vehicle travels from an entity located remotely from the vehicle. The sparse map may include a plurality of mapped navigation landmarks and at least one target trajectory. Both the plurality of mapped navigation landmarks and the at least one target trajectory may be generated based on drive information collected from a plurality of vehicles that have traveled along the at least one road segment in the past. The at least one processor may also be programmed to receive point cloud information from a LIDAR system within the vehicle. The point cloud information may represent distances to various objects in the vehicle's environment. The at least one processor may further be programmed to compare the received point cloud information with at least one of the plurality of mapped navigation landmarks in the sparse map to provide LIDAR-based localization of the vehicle relative to the at least one target trajectory. The at least one processor may also be programmed to determine at least one navigation action for the vehicle based on the LIDAR-based localization of the vehicle relative to the at least one target trajectory. The at least one processor may further be programmed to cause the vehicle to execute the at least one navigation action.

[0008] In one embodiment, a method for controlling a navigation system for a host vehicle may comprise receiving, from an entity located remotely from the vehicle, a sparse map associated with at least one road segment along which the vehicle travels. The sparse map may include a plurality of mapped navigation landmarks and at least one target trajectory. Both the plurality of mapped navigation landmarks and the at least one target trajectory may be generated based on drive information collected from a plurality of vehicles that have traveled along the at least one road segment in the past. The method may also comprise receiving point cloud information from a LIDAR system within the vehicle. The point cloud information may represent distances to various objects in the vehicle's environment. The method may also comprise comparing the received point cloud information with at least one of the plurality of mapped navigation landmarks in the sparse map to provide LIDAR-based localization of the vehicle relative to the at least one target trajectory. The method may further comprise determining at least one navigation operation for the vehicle based on the LIDAR-based localization of the vehicle relative to the at least one target trajectory. The method may also comprise causing the vehicle to execute the at least one navigation operation.

[0009] In one embodiment, a navigation system for a host vehicle may include at least one processor programmed to receive at least one captured image representing the environment of the host vehicle from a camera within the host vehicle. The at least one processor may also be programmed to receive point cloud information from a LIDAR system within the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The at least one processor may further be programmed to associate the point cloud information with the at least one captured image and provide pixel-by-pixel depth information for one or more regions of the at least one captured image. The at least one processor may also be programmed to determine at least one navigation action for the host vehicle based on the pixel-by-pixel depth information for one or more regions of the at least one captured image and cause the host vehicle to execute the at least one navigation action.

[0010] In one embodiment, a method for determining a navigation action for a host vehicle may include receiving point cloud information from a LIDAR system within the host vehicle. The point cloud information may represent distances to a plurality of objects in the environment of the host vehicle. The method may also include associating the point cloud information with at least one captured image and providing pixel-by-pixel depth information for one or more regions of the at least one captured image. The method may further include determining at least one navigation action for the host vehicle based on the pixel-by-pixel depth information for one or more regions of the at least one captured image and causing the host vehicle to execute the at least one navigation action.

[0011] In one embodiment, a navigation system for a host vehicle may include at least one processor programmed to receive at least one captured image representing the environment of the host vehicle from a camera within the host vehicle. The camera may be disposed at a first location with respect to the host vehicle. The at least one processor may also be programmed to receive point cloud information from a LIDAR system within the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be disposed at a second location with respect to the host vehicle, and the second location may be different from the first location. The field of view of the camera may at least partially overlap with the field of view of the LIDAR system to provide a shared field of view region. The at least one processor may further be programmed to analyze the at least one captured image and the received point cloud information to detect one or more objects in the shared field of view region. The detected one or more objects may be represented by only one of the at least one captured image or the received point cloud information. The at least one processor may also be programmed to determine whether the difference in viewing positions between the first location of the camera and the second location of the LIDAR system takes into account one or more detected objects represented by only one of the at least one captured image or the received point cloud information. If the difference in viewing positions does not take into account one or more detected objects represented by only one of the at least one captured image or the received point cloud information, the at least one processor may be programmed to cause at least one corrective action to be performed. If the difference in viewing positions does not take into account one or more detected objects represented by only one of the at least one captured image or the received point cloud information, the at least one processor may be programmed to determine at least one navigation action to be performed by the host vehicle based on the one or more detected objects and to cause the at least one navigation action to be performed by the host vehicle.

[0012] In one embodiment, a method for determining a navigation operation for a host vehicle may include receiving, from a camera within the host vehicle, at least one captured image representing the environment of the host vehicle. The camera may be disposed at a first location relative to the host vehicle. The method may also include receiving point cloud information from a LIDAR system within the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be disposed at a second location relative to the host vehicle, and the second location may be different from the first location. The field of view of the camera may at least partially overlap with the field of view of the LIDAR system to provide a shared field of view region. The method may further include analyzing the at least one captured image and the received point cloud information to detect one or more objects in the shared field of view region. The detected one or more objects may be represented in only one of the at least one captured image or the received point cloud information. The method may also include determining whether the difference in viewing positions between the first location of the camera and the second location of the LIDAR system takes into account one or more detected objects represented in only one of the at least one captured image or the received point cloud information. The method may further include, if the difference in viewing positions does not take into account one or more detected objects represented in only one of the at least one captured image or the received point cloud information, then performing at least one corrective operation. The method may also include, if the difference in viewing positions does not take into account one or more detected objects represented in only one of the at least one captured image or the received point cloud information, then determining at least one navigation operation to be performed by the host vehicle based on the one or more detected objects and causing the host vehicle to perform the at least one navigation operation.

[0013] In one embodiment, a navigation system for a host vehicle may include at least one processor programmed to receive at least one captured central image including a representation of at least a portion of the environment of the host vehicle from a central camera within the host vehicle, at least one captured left surround image including a representation of at least a portion of the environment of the host vehicle from a left surround camera within the host vehicle, and at least one captured right surround image including a representation of at least a portion of the environment of the host vehicle from a right surround camera within the host vehicle. The field of view of the central camera may at least partially overlap both the field of view of the left surround camera and the field of view of the right surround camera. The at least one processor may also be programmed to provide the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image to an analysis module configured to generate an output corresponding to the at least one captured central image based on an analysis of the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image. The generated output includes per-pixel depth information for at least one region of the captured central image. The at least one processor may further be programmed to cause at least one navigation operation by the host vehicle based on the generated output, which includes per-pixel depth information for at least one region of the captured central image.

[0014] In one embodiment, a method for determining a navigation operation for a host vehicle may comprise receiving at least one captured central image including a representation of at least a portion of the environment of the host vehicle from a central camera within the host vehicle, receiving at least one captured left surround image including a representation of at least a portion of the environment of the host vehicle from a left surround camera within the host vehicle, and receiving at least one captured right surround image including a representation of at least a portion of the environment of the host vehicle from a right surround camera within the host vehicle. The field of view of the central camera at least partially overlaps both the field of view of the left surround camera and the field of view of the right surround camera. The method may also comprise providing the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image to an analysis module configured to generate an output corresponding to the at least one captured central image based on an analysis of the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image. The generated output includes per-pixel depth information for at least one region of the captured central image. The method may further comprise causing at least one navigation operation by the host vehicle based on the generated output including per-pixel depth information for at least one region of the captured central image.

[0015] Without conflicting with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that may be executed by at least one processing device to perform any of the methods described herein.

[0016] The foregoing summary and the following detailed description are illustrative and explanatory only and are not restrictive of the claims.

Brief Description of the Drawings

[0017] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various embodiments of the disclosure. The drawings are as follows.

[0018]

Figure 1

[0019]

Figure 2A

[0020]

Figure 2B

[0021]

Figure 2C

[0022]

Figure 2D

[0023]

Figure 2E

[0024]

Figure 2F

[0025]

Figure 3A

[0026]

Figure 3B

[0027]

Figure 3C

[0028]

Figure 3D

[0029]

Figure 4

[0030]

Figure 5A

[0031]

Figure 5B

[0032]

Figure 5C

[0033]

Figure 5D

[0034]

Figure 5E

[0035]

Figure 5F

[0036]

Figure 6

[0037]

Figure 7

[0038]

Figure 8

[0039]

Figure 9A

[0040]

Figure 9B

[0041]

Figure 10

[0042]

Figure 11A

[0043]

Figure 11B

Figure 11C

[0044]

Figure 11D

[0045]

Figure 12

[0046]

Figure 13

[0047]

Figure 14

[0048]

Figure 15

[0049]

Figure 16

[0050]

Figure 17

[0051]

Figure 18

[0052]

Figure 19

[0053]

Figure 20

[0054]

Figure 21

[0055]

Figure 22

[0056]

Figure 23

[0057]

Figure 24A

Figure 24B

Figure 24C

Figure 24D

[0058]

Figure 24E

[0059]

Figure 24F

[0060]

Figure 25A

[0061]

Figure 25B

[0062]

Figure 25C

Figure 25D

[0063]

Figure 26A

[0064]

Figure 26B

[0065]

Figure 27

[0066]

Figure 28

[0067]

Figure 29

[0068]

Figure 30A

[0069]

Figure 30B

[0070]

Figure 31

[0071]

Figure 32

[0072]

Figure 33

[0073]

Figure 34

[0074]

Figure 35A

[0075]

Figure 35B

[0076]

Figure 35C

[0077]

Figure 36

[0078]

Figure 37

[0079]

Figure 38

[0080]

Figure 39A

Figure 39B

[0081]

Figure 40

[0082]

Figure 41

[0083]

Figure 42

[0084]

Figure 43

[0085]

Figure 44

[0086]

Figure 45

DETAILED DESCRIPTION OF THE INVENTION

[0087] In the following detailed description, reference is made to the accompanying drawings. In the drawings and the following description, the same reference numerals are used to refer to the same or similar parts as much as possible. Although several exemplary embodiments are described herein, changes, modifications, and other implementation examples are also possible. For example, substitutions, additions, and changes may be made to the components shown in the drawings, and the exemplary methods described herein may be changed by replacing, rearranging, deleting, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0088] [Overview of Autonomous Vehicles]

[0089] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that can perform at least one navigation change without the need for driver input. "Navigation change" refers to a change in one or more of vehicle steering, braking, or acceleration. For a vehicle to be autonomous, it does not need to be fully autonomous (e.g., a full operation that does not require a driver or driver input). Rather, autonomous vehicles include those that can operate under driver control for a period of time and then operate without driver control for other periods. Autonomous vehicles may include those that control only some aspects of vehicle navigation, such as steering (e.g., to maintain the vehicle's path between vehicle lane boundaries), while leaving other aspects, such as braking, to the driver. In some cases, an autonomous vehicle may assume some or all aspects of vehicle braking, speed control, and / or steering.

[0090] Since a human driver typically uses visual cues and observations to control a vehicle, traffic infrastructure is built based on that, and thus lane markings, traffic signs, and traffic lights are all designed to provide visual information to the driver. Considering these design features of the traffic infrastructure, an autonomous vehicle may include a camera and a processing unit that analyzes visual information captured from the vehicle's environment. Visual information may include, for example, components of the traffic infrastructure observable by a driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, an autonomous vehicle may use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, a vehicle may use GPS data, sensor data (e.g., from an accelerometer, speed sensor, suspension sensor, etc.), and / or other map data to provide information related to its environment while the vehicle is in motion, and the vehicle (and other vehicles) may use that information to identify its position on the model.

[0091] In some embodiments of the present disclosure, an autonomous vehicle may use information obtained while navigating (e.g., from a camera, GPS device, accelerometer, speed sensor, suspension sensor, etc.). In other embodiments, an autonomous vehicle may use information obtained from past navigation by the vehicle (or other vehicles) while navigating. In yet 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 that is consistent with the disclosed embodiments, followed by an overview of a front imaging system and method that is consistent with the system. Subsequent sections disclose systems and methods for constructing, using, and updating a sparse map for autonomous vehicle navigation.

[0092] [System Overview]

[0093] FIG. 1 is a block diagram of a system 100 that is not inconsistent with the disclosed exemplary embodiments. System 100 may include various components depending on the requirements of a specific implementation example. 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. The processing unit 110 may include one or more processing devices. In some embodiments, the processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, the image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements for a particular application. In some embodiments, the image acquisition unit 120 may include one or more image capture devices (e.g., cameras) such as an image capture device 122, an image capture device 124, and an image capture device 126. System 100 may also include a data interface 128 that communicatively connects the processing device 110 to the image acquisition device 120. For example, the data interface 128 may include one or more arbitrary wired links and / or wireless links for transmitting the image data acquired by the image acquisition device 120 to the processing unit 110.

[0094] The wireless transceiver 172 may include one or more devices configured to communicate via an air interface to one or more networks (e.g., cellular, Internet, etc.) using radio frequency, infrared frequency, magnetic field, or electric field. The wireless transceiver 172 may transmit and / or receive data using any known standard (e.g., Wi-Fi®, Bluetooth®, Bluetooth Smart, 802.15.4, ZigBee®, etc.). Such transmissions may include communication to one or more servers remotely located from the host vehicle. Such transmissions may include communication (one-way or two-way) between the host vehicle and one or more target vehicles within the host vehicle's environment (e.g., to facilitate adjustment of the host vehicle's navigation considering or together with a target vehicle within the host vehicle's environment), or even broadcast transmissions to unspecified recipients in the vicinity of the transmitting vehicle.

[0095] Both the application processor 180 and the image processor 190 may include various types of processing devices. For example, either or both of the application processor 180 and the image processor 190 may include a microprocessor, a pre-processor (such as an image pre-processor), 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 executing applications and performing image processing and analysis. In some embodiments, the application processor 180 and / or the image processor 190 may include any type of single-core or multi-core processor, a mobile device microcontroller, a central processing unit, etc. For example, various processing devices including processors available from manufacturers such as Intel®, AMD®, etc., or GPUs available from manufacturers such as NVIDIA®, ATI®, etc., may be used, and may include various architectures (e.g., x86 processors, ARM®, etc.).

[0096] In some embodiments, the application processor 180 and / or the image processor 190 may include any of the EyeQ series of processor chips available from Mobileye®. Each of these processor designs includes multiple processing units with local memory and instruction sets. Such a processor may include a video input for receiving image data from multiple image sensors and may also include a video output function. In one example, EyeQ2® uses 90nm technology and operates at 332 MHz. The EyeQ2® architecture consists of two floating-point hyperthreaded 32-bit RISC CPUs (MIPS32® 34K® cores), five vision calculation engines (VCEs), three vector microcode processors (VMP®), a 64-bit mobile DDR controller from Denali, a 128-bit built-in Sonics Interconnect, a dual controller for 16-bit video input and 18-bit video output, 16-channel DMA, and several peripherals. The MIPS34K CPU manages the five VCEs, three VMP®s and DMA, the second MIPS34K CPU and multi-channel DMA, and other peripherals. The five VCEs, three VMP®s, and the MIPS34K CPU can perform intensive vision calculations required by multifunctional bundled applications. In another example, EyeQ3®, a third-generation processor with six times the processing power of EyeQ2®, may be used in the disclosed embodiments. In other examples, EyeQ4® and / or EyeQ5® may be used in the disclosed embodiments. Of course, any new or future EyeQ processing device may also be used in conjunction with the disclosed embodiments.

[0097] Any of the processing devices disclosed herein may be configured to perform a particular function. Configuring a processing device, such as any of the described EyeQ processors or other controllers or microprocessors, to perform a particular function may include programming computer-executable instructions and making these instructions available for execution by the processing device during operation of the processing device. In some embodiments, configuring the processing device may include directly programming the processing device with architecture instructions. For example, processing devices such as field programmable gate arrays (FPGAs) and application specific integrated circuits (ASICs) may be configured using, for example, one or more hardware description languages (HDLs).

[0098] In other embodiments, configuring the processing device may include storing executable instructions in a memory accessible by the processing device during operation. For example, during operation, the processing device may access the memory, retrieve, and execute the stored instructions. In either case, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system that controls multiple hardware-based components of the host vehicle.

[0099] FIG. 1 shows two separate processing devices included in processing unit 110, but 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 more than two processing devices. Further, in some embodiments, system 100 may include one or more of processing units 110 without including other components such as image acquisition unit 120.

[0100] 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 pre-processor, a central processing unit (CPU), a graphics processing unit (GPU), support circuits, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image pre-processor may include a video processor for capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The 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, for example, cache circuits, power circuits, clock circuits, and input / output circuits. The memory may store software that controls the operation of the system when executed by the processor. The memory may include a database and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage, tape storage, removable storage, and other types of storage. In one example, the memory may be separate from the processing unit 110. In another example, the memory may be integrated with the processing unit 110.

[0101] Each of the memories 140, 150 may contain software instructions which, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of the system 100. For example, these memory units may contain 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, tape storage, removable storage, and / or any other type of storage. In some embodiments, the memory units 140, 150 may be separate from the application processor 180 and / or the image processor 190. In other embodiments, these memory units may be integrated with the application processor 180 and / or the image processor 190.

[0102] The position sensor 130 may include any type of device suitable for determining the position associated with at least one component of the system 100. In some embodiments, the position sensor 130 may include a GPS receiver. Such a receiver can determine the user position and velocity by processing signals broadcast by satellites for the Global Positioning System. The position information from the position sensor 130 may be made available to the application processor 180 and / or the image processor 190.

[0103] In some embodiments, the system 100 may include components such as a speed sensor (e.g., a tachometer, a speedometer) for measuring the speed of the vehicle 200 and / or an accelerometer (either single-axis or multi-axis) for measuring the acceleration of the vehicle 200.

[0104] The user interface 170 may include any device suitable for providing information to one or more users of the system 100 or receiving input from such users. In some embodiments, the user interface 170 may include a user input device, and such devices may include, for example, a touch screen, a microphone, a keyboard, a pointer device, a track wheel, a camera, a knob, a button, and the like. Using such input devices, a user can provide information input or commands to the system 100, for example, type in instructions or information, provide voice commands, select menu options on the screen using buttons, pointers, or eye-tracking functions, or any other suitable method for conveying information to the system 100 may be used.

[0105] The user interface 170 may include one or more processing devices configured to transfer information to and from the user and, for example, process the information for use by the application processor 180. In some embodiments, such processing devices may execute instructions to recognize and track eye movements, receive and interpret voice commands, recognize and interpret touches and / or gestures made on a touch screen, respond to keyboard inputs or menu selections, and the like. In some embodiments, the user interface 170 may include a display, a speaker, a tactile device, and / or any other device for providing output information to the user.

[0106] The map database 160 may include any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 may include data related to positions in various reference coordinate systems of various types, such types including roads, water features, geographical features, stores, specific points of interest, restaurants, gas stations, and the like. The map database 160 may store not only the positions of such types, but also descriptors related to these types, such descriptors including, for example, names related to any of the stored features. In some embodiments, the map database 160 may be physically located together with other components of the system 100. Alternatively, or in addition, the map database 160 or a portion thereof may be located remotely from other components of the system 100 (e.g., the processing unit 110). In such embodiments, information from the map database 160 may be downloaded via a wired data connection or a wireless data connection to the network (e.g., via a cellular network and / or the Internet, etc.). In some cases, the map database 160 may store a sparse data model including specific road features (e.g., lane markings) or a polynomial representation of the target trajectory of the host vehicle. Systems and methods for generating such maps will be discussed below with reference to FIGS. 8-19.

[0107] The image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from the environment. Further, any number of image capture devices may be used to obtain images input to the image processor. In some embodiments, only one image capture device may be included, while in other embodiments, two, three, or even four or more image capture devices may be included. The image capture devices 122, 124, and 126 will be further described below with reference to FIGS. 2B-2E.

[0108] System 100 or its various components may be incorporated into various other platforms. In some embodiments, System 100 may be included in vehicle 200, as shown in FIG. 2A. For example, vehicle 200 may comprise a processing unit 110 and any of the other components of System 100, as described above in connection with FIG. 1. In some embodiments, vehicle 200 may comprise only one image capture device (e.g., a camera), although 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 System) imaging device.

[0109] The image capture device included in vehicle 200 as part of image acquisition unit 120 may be disposed in any suitable location. In some embodiments, as shown in FIGS. 2A-2E and FIGS. 3A-3C, image capture device 122 may be disposed near the rearview mirror. This location can provide a line of sight similar to that of the driver of vehicle 200 and may thus be useful in determining what the driver can see and what the driver cannot see. Image capture device 122 may be disposed anywhere near the rearview mirror, although disposing image capture device 122 on the driver's side of the mirror may be even more useful in obtaining an image representing the driver's field of view and / or line of sight.

[0110] Regarding the image capture device of the image acquisition unit 120, other locations may also be used. For example, the image capture device 124 may be disposed on or within the bumper of the vehicle 200. Such a location may be particularly suitable for an image capture device having a wide field of view. The line of sight of the image capture device disposed on the bumper may be different from that of the driver, and thus, the image capture device on the bumper and the driver may not always be looking at the same object. The image capture devices (e.g., image capture devices 122, 124, and 126) may be disposed at other locations. For example, the image capture device may be located on or within one or both side mirrors of the vehicle 200, on the roof of the vehicle 200, on the bonnet of the vehicle 200, on the trunk of the vehicle 200, on the side surface of the vehicle 200, may be attached to any of the window glasses of the vehicle 200, may be disposed behind it, may be disposed in front of it, or may be attached within or near a lighting device at the front and / or rear of the vehicle 200.

[0111] In addition to the image capture device, the vehicle 200 may include various other components of the system 100. For example, the processing unit 110 may be integrated with the engine control unit (ECU) of the vehicle or may be included in the vehicle 200 separately from the ECU. The vehicle 200 may also include a position sensor 130 such as a GPS receiver, and may also include a map database 160 and memory units 140 and 150.

[0112] As discussed above, the wireless transceiver 172 may transmit and / or receive data via one or more networks (e.g., a cellular network, the Internet, etc.). For example, the wireless transceiver 172 may upload data collected by the system 100 to one or more servers and download data from one or more servers. Via the wireless transceiver 172, the system 100 may receive, for example, periodic updates or updates in response to requests for data stored in the map database 160, the memory 140, and / or the memory 150. Similarly, the wireless transceiver 172 may upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, the vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0113] The system 100 may upload data to a server (e.g., to the cloud) based on a privacy level setting. For example, the system 100 may implement a privacy level setting to regulate or limit the types of data (including metadata) that can uniquely identify the vehicle and / or the driver / owner of the vehicle and that are sent to the server. Such a setting may be set by the user via, for example, the wireless transceiver 172, or may be initialized with a factory default setting or data received by the wireless transceiver 172.

[0114] In some embodiments, system 100 may upload data according to a privacy level of "high". While setting the settings, system 100 may transmit data (e.g., location information related to a route, captured images, etc.) without using any details regarding a specific vehicle and / or driver / owner. For example, when uploading data according to the privacy setting of "high", system 100 may not include the vehicle identification number (VIN) nor the name of the driver or owner of the vehicle. Instead, it may transmit data such as captured images and / or limited location information related to the route.

[0115] Other privacy levels are also conceivable. For example, system 100 may transmit data to the server according to a privacy level of "medium", and may include additional information not included in the privacy level of "high", such as information on the manufacturer and / or model of the vehicle, and / or vehicle type (e.g., passenger car, sports utility vehicle, truck, etc.). In some embodiments, system 100 may upload data according to a privacy level of "low". At the privacy level setting of "low", system 100 may upload data and include information sufficient to uniquely identify a specific vehicle, owner / driver, and / or part or all of the route on which the vehicle travels. Such privacy level "low" data may include, for example, one or more of the VIN, the name of the driver / owner, the starting point of the vehicle before departure, the intended destination of the vehicle, the manufacturer and / or model of the vehicle, the type of the vehicle, etc.

[0116] FIG. 2A is a schematic side view of an exemplary vehicle imaging system that does not conflict with the disclosed embodiments. FIG. 2B is a schematic top view of the embodiment shown in FIG. 2A. As shown in FIG. 2B, the disclosed embodiments may include a vehicle 200, and on its body, there are a first image capture device 122 disposed near the rearview mirror of the vehicle 200 and / or near the driver, and a second image capture device 124 disposed on or in a bumper region of the vehicle 200 (e.g., one of the bumper regions 210), and a system 100 having a processing unit 110 is included.

[0117] As shown in FIG. 2C, both image capture devices 122 and 124 may be disposed near the rearview mirror of the vehicle 200 and / or near the driver. Further, although FIGS. 2B and 2C show two image capture devices 122 and 124, it should be understood that other embodiments may include more than two image capture devices. For example, in the embodiments shown in FIGS. 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 the system 100 of the vehicle 200.

[0118] As shown in FIG. 2D, the image capture device 122 may be disposed near the rearview mirror of the vehicle 200 and / or near the driver, and the image capture devices 124 and 126 may be disposed on or in a bumper region of the vehicle 200 (e.g., one of the bumper regions 210). Also, as shown in FIG. 2E, the image capture devices 122, 124, and 126 may be disposed near the rearview mirror of the vehicle 200 and / or near the driver's seat. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices may be disposed at any suitable location inside and / or on the vehicle 200.

[0119] It should be understood that the disclosed embodiments are not limited to vehicles and may be applicable to other situations. It should also be understood that the disclosed embodiments are not limited to a particular type of vehicle 200 and may be applicable to any type of vehicle, including automobiles, trucks, trailers, and other types of vehicles.

[0120] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024 WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280×960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, for example, one or more lenses may be included to provide a desired focal length and field of view to the image capture device. In some embodiments, the image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, the 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, the image capture device 122 may be configured to have a standard FOV within a range of 40 degrees to 56 degrees, including an FOV of 46 degrees, 50 degrees, 52 degrees, or a wider FOV. Alternatively, the image capture device 122 may be configured to have a narrow FOV within a range of 23 degrees to 40 degrees, such as an FOV of 28 degrees or 36 degrees. Further, the image capture device 122 may be configured to have a wide FOV within a range of 100 degrees to 180 degrees. In some embodiments, the image capture device 122 may include a wide-angle bumper camera or one having an FOV of up to 180 degrees. In some embodiments, the image capture device 122 may be a 7.2M pixel image capture device having an aspect ratio of approximately 2:1 (e.g., H×V = 3800×1900 pixels) and a horizontal FOV of approximately 100 degrees. Such an image capture device may be used instead of a three-image capture device configuration. The vertical FOV of such an image capture device may be significantly less than 50 degrees in an implementation where the image capture device uses a radially symmetric lens due to significant lens distortion. For example, such a lens may not be radially symmetric, and doing so may allow for a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

[0121] The first image capture device 122 may obtain a plurality of first images of a scene related to the vehicle 200. Each of the plurality of first images may be obtained as a series of image scan lines, and these images may be captured using a rolling shutter. Each scan line may include a plurality of pixels.

[0122] The first image capture device 122 may have a scan speed associated with obtaining each of the first series of image scan lines. The scan speed may refer to the speed at which the image sensor can obtain image data related to each pixel included in a specific scan line.

[0123] The image capture devices 122, 124, and 126 may incorporate any suitable type and number of image sensors, including, for example, a CCD sensor or a CMOS sensor. In one embodiment, a CMOS image sensor may be used in conjunction with a rolling shutter, whereby each pixel in a row is read out one by one, and the scanning of the rows proceeds row by row until the entire image frame is captured. In some embodiments, each row may be sequentially captured from the top to the bottom of the frame.

[0124] In some embodiments, one or more of the image capture devices (e.g., image capture devices 122, 124, and 126) disclosed herein may constitute a high-resolution imaging device and may have a resolution exceeding 5 megapixels, 7 megapixels, 10 megapixels, or more pixels.

[0125] When using a rolling shutter, pixels in different rows may be exposed and captured at different times, which may cause skew and other image artifacts in the captured image frame. On the other hand, if the image capture device 122 is configured to operate with a global shutter or a synchronous shutter, all pixels can be exposed during a common exposure period for the same amount of time. As a result, the image data of the frames collected in a system using a global shutter represents a snapshot of the entire FOV (such as FOV202) at a specific time. In contrast, when applying a rolling shutter, each row in the frame is exposed and data is captured at different times. Therefore, in an image capture device with a rolling shutter, a moving object may appear distorted. This phenomenon will be described in more detail below.

[0126] The second image capture device 124 and the third image capture device 126 may be any type of image capture device. Similar to the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image capture devices 124 and 126 may provide the same or a narrower FOV (such as FOV204 and 206) than the FOV (such as FOV202) associated with the image capture device 122. For example, the image capture devices 124 and 126 may have an FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or narrower.

[0127] Image capture devices 124 and 126 may acquire a plurality of second and third images of a scene related to vehicle 200. Each of the plurality of second and third images may be acquired as a second and third series of image scan lines, and these images may be captured using a rolling shutter. Each scan line or row may include a plurality of pixels. Image capture devices 124 and 126 may have a second scan speed and a third scan speed associated with acquiring each of the plurality of image scan lines included in the second and third series of image scan lines.

[0128] Image capture devices 122, 124, and 126 may each be arranged at any suitable position and orientation with respect to vehicle 200. The relative arrangement of image capture devices 122, 124, and 126 may be selected to facilitate fusing information acquired from the image capture devices. For example, in some embodiments, the FOV associated with image capture device 124 (such as FOV204) may partially or fully overlap with the FOV associated with image capture device 122 (such as FOV202) and the FOV associated with image capture device 126 (such as FOV206).

[0129] Image capture devices 122, 124, and 126 may be arranged on vehicle 200 at any suitable relative height. In one example, there may be a difference in height 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, the heights of two image capture devices 122 and 124 are different. For example, there may also be a lateral displacement difference between image capture devices 122, 124, and 126, which provides additional parallax information for stereo analysis by processing unit 110. The difference in lateral displacement is d, as shown in FIGS. 2C and 2D. xIt may be represented by. In some embodiments, a displacement forward or backward (e.g., a range displacement) may exist between the image capture devices 122, 124, and 126. For example, the image capture device 122 may be located 0.5 to 2 meters behind, or even further behind, the image capture device 124 and / or the image capture device 126. This type of displacement may make it possible for one of these image capture devices to compensate for potential blind spots of one or more other image capture devices.

[0130] The image capture device 122 may have any suitable resolution (e.g., the number of pixels associated with the image sensor), and the resolution of one or more image sensors associated with the image capture device 122 may be higher than, lower than, or the same as the resolution of one or more image sensors associated with the image capture devices 124 and 126. In some embodiments, one or more image sensors associated with the image capture device 122 and / or the image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0131] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame before moving on to the acquisition of pixel data associated with the next image frame) may be controllable. The frame rate associated with image capture device 122 may be higher than, lower than, or the same as the frame rates associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 may depend on various factors that can 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 acquiring image data associated with one or more pixels of an image sensor included in image capture devices 122, 124, and / or 126. Generally, the image data corresponding to each pixel may be acquired according to the clock rate of the device (e.g., one pixel may be acquired per clock cycle). Further, 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 acquiring image data associated with pixels in a row of an image sensor included in image capture devices 122, 124, and / or 126. Further, one or more of image capture devices 122, 124, and / or 126 may include a selectable vertical blanking period imposed before or after acquiring image data associated with an image frame of image capture devices 122, 124, and 126.

[0132] These timing controls can enable synchronization of each frame rate associated with the image capture devices 122, 124, and 126, even when the respective line scan speeds are different. Further, as will be discussed in more detail below, these selectable timing controls can enable synchronization of image capture from regions where the field of view (FOV) of the image capture device 122 differs from the FOVs of the image capture devices 124 and 126, and even when the FOV of the image capture device 122 overlaps with one or more of the FOVs of the image capture devices 124 and 126, among other factors (e.g., resolution of the image sensor, maximum line scan speed, etc.).

[0133] The frame rate timing in the image capture devices 122, 124, and 126 can depend on the resolution of the associated image sensor. For example, assuming that the line scan speeds of both devices are similar, if one device includes an image sensor with a resolution of 640×480 and the other device includes an image sensor with a resolution of 1280×960, the sensor with the higher resolution will take longer to acquire the image data for one frame.

[0134] Another factor that can affect the timing of image data acquisition in the image capture devices 122, 124, and 126 is the maximum line scan speed. For example, to acquire the image data of a certain line from the image sensors included in the image capture devices 122, 124, and 126, a certain minimum amount of time is required. Assuming no additional pixel delay time, this minimum amount of time for acquiring the image data of a certain line will be related to the maximum line scan speed of a specific device. Devices that provide a high maximum line scan speed may be able to provide a higher frame rate than devices with a low maximum line scan speed. In some embodiments, one or both of the image capture devices 124 and 126 may have a maximum line scan speed higher than the maximum line scan speed associated with the image capture device 122. In some embodiments, the maximum line scan speed of the image capture device 124 and / or 126 may be 1.25 times, 1.5 times, 1.75 times, or 2 times, or greater than the maximum line scan speed of the image capture device 122.

[0135] In another embodiment, the image capture devices 122, 124, and 126 may have the same maximum line scan speed, but the image capture device 122 may operate at a scan speed less than or equal to its maximum scan speed. The system may be configured such that one or both of the image capture devices 124 and 126 operate at a line scan speed equal to the line scan speed of the image capture device 122. In other examples, the system may be configured such that the line scan speed of the image capture device 124 and / or the image capture device 126 can be 1.25 times, 1.5 times, 1.75 times, or 2 times, or greater than the line scan speed of the image capture device 122.

[0136] In some embodiments, the image capture devices 122, 124, and 126 may be asymmetric. That is, these image capture devices may include cameras with different fields of view (FOV) and focal lengths. The fields of view of the image capture devices 122, 124, and 126 may include any desired region with respect to the environment of the vehicle 200, for example. In some embodiments, one or more of the image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of the vehicle 200, behind the vehicle 200, to the side of the vehicle 200, or a combination thereof.

[0137] Furthermore, the focal length associated with each of the image capture devices 122, 124, and / or 126 may be selectable (e.g., by including an appropriate lens, etc.) such that each device acquires an image of an object within a desired distance range with respect to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 may acquire images of objects at a close distance within a few meters from the vehicle. The image capture devices 122, 124, and 126 may also be configured to acquire images of objects in a range that is further away from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or further). Furthermore, the focal lengths of the image capture devices 122, 124, and 126 may be selected such that one image capture device (e.g., the image capture device 122) can acquire an image of an object that is relatively close to the vehicle (e.g., within a range of 10 m, or within a range of 20 m), while the other image capture devices (e.g., the image capture devices 124 and 126) can acquire images of objects that are further away from the vehicle 200 (e.g., beyond 20 m, 50 m, 100 m, 150 m, etc.).

[0138] According to some embodiments, the FOVs of one or more image capture devices 122, 124, and 126 may be wide-angle. For example, having a FOV of 140 degrees can be particularly advantageous for image capture devices 122, 124, and 126 that can be used to capture images of areas close to vehicle 200. For example, image capture device 122 may be used to capture images of areas on the right or left side 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).

[0139] The field of view associated with each of image capture devices 122, 124, and 126 may depend on the respective focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0140] Image capture devices 122, 124, and 126 may be configured to have any suitable field of view. In one particular example, image capture device 122 may have a horizontal FOV of 46 degrees, image capture device 124 may have a horizontal FOV of 23 degrees, and image capture device 126 may have a horizontal FOV between 23 degrees and 46 degrees. In another example, image capture device 122 may have a horizontal FOV of 52 degrees, image capture device 124 may have a horizontal FOV of 26 degrees, and image capture device 126 may have a horizontal FOV between 26 degrees and 52 degrees. In some embodiments, the ratio of the FOV of image capture device 122 to the FOV of image capture device 124 and / or image capture device 126 may vary from 1.5 to 2.0. In other embodiments, this ratio may vary between 1.25 and 2.25.

[0141] System 100 may be configured such that the field of view of image capture device 122 at least partially or fully overlaps with the field of view of image capture device 124 and / or image capture device 126. In some embodiments, System 100 may be configured such that, for example, the fields of view of image capture devices 124 and 126 are included in the field of view of image capture device 122 (e.g., narrower than the field of view of image capture device 122) and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs and may have partial overlap within their respective FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 may be aligned such that the centers of the narrow FOV image capture devices 124 and / or 126 may be located in the lower half of the field of view of the wide FOV device 122.

[0142] FIG. 2F is a schematic diagram of an exemplary vehicle control system that does not conflict with the disclosed embodiments. As shown in FIG. 2F, vehicle 200 may include throttle device 220, brake device 230, and steering device 240. System 100 may provide an input (e.g., a control signal) to one or more of throttle device 220, brake device 230, and steering device 240 via one or more data links (e.g., one or more arbitrary wired links and / or wireless links for data transmission). For example, based on the analysis of the images acquired by image capture devices 122, 124, and / or 126, System 100 may provide a control signal to one or more of throttle device 220, brake device 230, and steering device 240 to navigate vehicle 200 (e.g., by causing acceleration, turning, lane change, etc.). Further, System 100 may receive an input indicating the operating state of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.) from one or more of throttle device 220, brake device 230, and steering device 240. Further details are provided below in connection with FIGS. 4-7.

[0143] As shown in FIG. 3A, vehicle 200 may also include a user interface 170 for interacting with the driver or passengers of vehicle 200. For example, the user interface 170 of the vehicle application may include a touch screen 320, a knob 330, a button 340, and a microphone 350. The driver or passengers of vehicle 200 may also use a steering wheel (e.g., located on or near the steering column of vehicle 200 and including, for example, a turn signal lever) and buttons (e.g., located on the steering wheel of vehicle 200) to interact with system 100. In some embodiments, microphone 350 may be disposed adjacent to rearview mirror 310. Similarly, in some embodiments, image capture device 122 may be disposed near rearview mirror 310. In some embodiments, the user interface 170 may also include one or more speakers 360 (e.g., speakers of the vehicle audio system). For example, system 100 may provide various notifications (e.g., alerts) via speakers 360.

[0144] Figures 3B - 3D are diagrams of an exemplary camera mount 370 configured to be disposed in contact with a vehicle's windshield behind a rearview mirror (e.g., rearview mirror 310) without conflicting with the disclosed embodiments. As shown in Figure 3B, camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be disposed behind glare shield 380, which may be directly affixed to the vehicle's windshield and may include a composition of film material and / or anti - reflective material. For example, glare shield 380 may be disposed such that it contacts and aligns with the vehicle's windshield having the same inclination. In some embodiments, each of image capture devices 122, 124, and 126 may be disposed behind glare shield 380, as shown, for example, in Figure 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. Figure 3C is a front - view of camera mount 370 shown in Figure 3B.

[0145] As will be appreciated by those skilled in the art benefiting from the present disclosure, numerous modifications and / or changes can be made to the foregoing disclosed embodiments. For example, not all components are essential for the operation of system 100. Further, any component may be disposed in any suitable part of system 100, and these components may provide the functionality of the disclosed embodiments and may be rearranged in various configurations. Accordingly, the foregoing configurations are examples, and regardless of the above - described configurations, system 100 can provide a wide range of functionality to analyze what is around vehicle 200 and navigate vehicle 200 in response to that analysis.

[0146] As will be discussed in more detail below and without conflicting with the various embodiments disclosed, system 100 can provide various functions related to autonomous driving and / or driver assistance technologies. For example, system 100 can analyze image data, location data (e.g., location information by GPS), map data, speed data, and / or data from sensors included in vehicle 200. System 100 can collect data for analysis from, for example, image acquisition unit 120, location sensor 130, and other sensors. Further, system 100 can analyze the collected data to determine whether vehicle 200 should perform a particular action, and then automatically perform the determined action without human intervention. For example, when vehicle 200 navigates without human intervention, system 100 can automatically control the brakes, acceleration, and / or steering of vehicle 200 (e.g., by sending control signals to one or more of throttle device 220, brake device 230, and steering device 240). Further, system 100 can analyze the collected data and issue warnings and / or alerts to the vehicle occupants based on the analysis of the collected data. Further details regarding the various embodiments provided by system 100 are provided below.

[0147] [Front Multi-imaging System]

[0148] As described above, the system 100 can provide a driving assistance function using a multi-camera system. The multi-camera system may use one or more cameras facing the forward direction of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side or the rear of the vehicle. In one embodiment, for example, the 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 arranged at the front and / or both side surfaces of the vehicle (e.g., vehicle 200). The first camera may have a field of view larger than that of the second camera, a field of view smaller than that of the second camera, or a field of view that partially overlaps with that of the second camera. Further, the first camera may be connected to a first image processor that performs monocular image analysis of the image provided by the first camera, and the second camera may be connected to a second image processor that performs monocular image analysis of the image provided by the second camera. The outputs (e.g., processed information) of the first image processor and the second image processor may be combined. In some embodiments, the second image processor may receive images from both the first camera and the second camera and perform stereo analysis. In another embodiment, the system 100 may use a three-camera imaging system in which each of the plurality of cameras has a different field of view. Thus, in such a system, determinations can be made based on information obtained from objects located at various distances with respect to both the front and both side portions of the vehicle. Reference to monocular image analysis may mean performing image analysis based on an image captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may mean performing image analysis based on two or more images captured with one or more changes in image capture parameters. For example, suitable captured images for performing stereo image 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, and the like.

[0149] For example, in one embodiment, system 100 may implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees, or other values selected from the range of about 20 to 45 degrees), image capture device 124 may provide a wide field of view (e.g., 150 degrees, or other values selected from the range of about 100 to about 180 degrees), and image capture device 126 may provide an intermediate field of view (e.g., 46 degrees, or other values selected from the range of about 35 to about 60 degrees). In some embodiments, image capture device 126 may serve as the main camera or primary camera. Image capture devices 122, 124, and 126 may be disposed behind rearview mirror 310 and may be disposed substantially side by side (e.g., 6 cm apart). Further, in some embodiments as described above, one or more of image capture devices 122, 124, and 126 may be attached behind glare shield 380 that is in the same plane as the front windshield of vehicle 200. Such a shield may act to minimize any reflection effects from the inside of the vehicle on image capture devices 122, 124, and 126.

[0150] In another embodiment, as described above in connection with FIGS. 3B and 3C, a wide field of view camera (e.g., image capture device 124 in the above example) may be mounted lower than a narrow field of view camera and a main field of view camera (e.g., image devices 122 and 126 in the above example). This configuration may provide a clear line of sight from the wide field of view camera. To reduce reflections, the camera may be mounted close to the front windshield of vehicle 200, and the camera may include a polarizing plate to attenuate reflected light.

[0151] A three-camera system can provide certain performance characteristics. For example, some embodiments may include the function of confirming the detection of an object by one camera based on the detection results of another camera. In the three-camera configuration described above, the processing unit 110 may include, for example, three processing devices (such as three processor chips of the EyeQ series as described above), and each processing device is specialized in processing images captured by one or more of the image capture devices 122, 124, and 126.

[0152] In a three-camera system, the first processing device receives images from both the main camera and the narrow field of view camera, performs vision processing by the narrow FOV camera, and may detect, for example, other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. Further, the first processing device may calculate the pixel disparity between the images from the main camera and the narrow field of view camera, and create a 3D reconstruction of the environment of the 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.

[0153] The second processing device receives an image from the main camera, performs vision processing, and may detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. Further, the second processing device may calculate the camera displacement, and based on the displacement, calculate the pixel disparity between consecutive images to create a 3D reconstruction of the scene (such as structure from motion: SfM). The second processing device may send the SfM-based 3D reconstruction combined with the stereo 3D image to the first processing device.

[0154] The third processing device receives an image from the wide FOV camera, processes the image, and may detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. The third processing device may further execute additional processing instructions and analyze the image to identify moving objects within the image, such as vehicles changing lanes, pedestrians, etc.

[0155] In some embodiments, opportunities may be provided for the system to have redundancy by enabling a stream of image-based information to be independently captured and processed. Such redundancy may include, for example, verifying and / or supplementing information obtained by capturing and processing image information from at least a second image capture device using a first image capture device and processed images from that device.

[0156] In some embodiments, when providing navigation assistance to vehicle 200, system 100 may use two image capture devices (e.g., image capture devices 122 and 124), and may also 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 to navigate vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and validity of information obtained based on images captured from image capture device 122 and / or image capture device 124. That is, image capture device 126 (and corresponding processing device) may be considered to provide a redundancy subsystem for providing a check against the analysis obtained from image capture devices 122 and 124 (e.g., providing an automatic emergency braking (AEB) system). Further, in some embodiments, the redundancy and validity of received data may be supplemented based on information received from one or more sensors (e.g., radar, LIDAR, acoustic sensors, information received from one or more transceivers outside the vehicle, etc.).

[0157] Those skilled in the art will recognize that the above camera configurations, camera arrangements, number of cameras, camera positions, etc. are merely examples. These components and the like described for the overall system may be configured and used in various different configurations without departing from the scope of the disclosed embodiments. Further details regarding the use of a multi-camera system to provide driver assistance and / or autonomous vehicle functions follow.

[0158] FIG. 4 is an exemplary functional block diagram of memory 140 and / or 150, which may be stored / programmed with instructions for performing one or more operations consistent with the disclosed embodiments. Although reference is made below to memory 140, those skilled in the art will recognize that the instructions may be stored in memory 140 and / or 150.

[0159] As shown in FIG. 4, memory 140 may store a monocular image analysis module 402, a stereo image analysis module 404, a speed acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Further, 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 description may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, each stage of any of the following processes may be performed by one or more processing devices.

[0160] In one embodiment, the monocular image analysis module 402 may store instructions (such as computer vision software), which, when executed by the processing unit 110, perform monocular image analysis on a set of images acquired by one of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may perform monocular image analysis by combining information from the set of images with additional perceptual information (e.g., information from radar, LIDAR, etc.). As described below in connection with FIGS. 5A-5D, the monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as, for example, lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic signals, hazards, and any other features related to the environment of the vehicle. Based on the analysis, the system 100 (e.g., the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as, for example, turning, lane changes, and changes in acceleration, as discussed below in connection with the navigation response module 408.

[0161] In one embodiment, the stereo image analysis module 404 may store instructions (such as computer vision software), which, when executed by the processing unit 110, perform stereo image analysis on a first set and a second set of images acquired by a combination of image capture devices selected from among image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first set and the second set of images with additional perceptual information (such as information from radar) to perform stereo image analysis. For example, the stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. As will be described below in connection with FIG. 6, the stereo image analysis module 404 may include instructions for detecting a set of features such as, for example, lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic signals, and hazards within the first set and the second set of images. Based on the analysis, the processing unit 110 may cause one or more navigation responses in vehicle 200, such as turning, lane changes, and acceleration changes, as will be discussed below in connection with the navigation response module 408. Further, in some embodiments, the stereo image analysis module 404 may implement techniques related to a trained system (such as a neural network or a deep neural network) or an untrained system (such as a system configured to detect and / or label objects in an environment where perceptual information is captured and processed using computer vision algorithms). In one embodiment, the stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of a trained system and an untrained system.

[0162] In one embodiment, the speed acceleration module 406 may store software configured to analyze data received from one or more computing electromechanical devices within the vehicle 200 that are configured to cause a change in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 may execute instructions related to the speed acceleration module 406 and calculate a target speed of the vehicle 200 based on data obtained from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, a target position, speed and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road features, and the position information of the vehicle 200 relative to the lane markings of the road. Further, the processing unit 110 may calculate the target speed of the vehicle 200 based on the perception input (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle device 220, the brake device 230, and / or the steering device 240 of the vehicle 200. Based on the calculated target speed, the processing unit 110 may send an electronic signal to the throttle device 220, the brake device 230, and / or the steering device 240 of the vehicle 200 to cause a change in speed and / or acceleration, for example, by physically depressing the brake of the vehicle 200 or releasing the accelerator.

[0163] In one embodiment, the navigation response module 408 may store software executable to determine a desired navigation response based on data obtained from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404 by the processing unit 110. Such data may include position information and speed information related to nearby vehicles, pedestrians, and road features, as well as target position information of the vehicle 200. Further, in some embodiments, the navigation response may be (partially or fully) based on map data, a predetermined position of the vehicle 200, and / or a relative speed or relative acceleration between the vehicle 200 and one or more objects detected from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may determine a desired navigation response based on perceptual input (e.g., information from radar) and input from other systems of the vehicle 200 (such as the throttle device 220, the brake device 230, and / or the steering device 240 of the vehicle 200). Based on the desired navigation response, the processing unit 110 may transmit an electronic signal to the throttle device 220, the brake device 230, and the steering device 240 of the vehicle 200, and cause the desired navigation response, for example, by turning the steering wheel of the vehicle 200 to achieve a rotation of a predetermined angle. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as an input for executing the speed acceleration module 406 to calculate a change in the speed of the vehicle 200.

[0164] Furthermore, any of the modules disclosed herein (e.g., modules 402, 404, and 406) may implement techniques related to a trained system (such as a neural network or a deep neural network) or an untrained system.

[0165] FIG. 5A is a flowchart showing an exemplary process 500A for generating one or more navigation responses based on monocular image analysis that is consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via a data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera included in the image acquisition unit 120 (such as the image capture device 122 having a field of view 202) may capture a plurality of images of an area in front of the vehicle 200 (or, for example, to the side or rear of the vehicle), and these images may be transmitted to the processing unit 110 via a data connection (such as digital, wired, USB, wireless, Bluetooth, etc.). The processing unit 110 may, at step 520, execute the monocular image analysis module 402 to analyze the plurality of images, as will be described in more detail below with reference to FIGS. 5B-5D. By performing the analysis, the processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, and traffic signals, etc.

[0166] At step 520, the processing unit 110 may execute the monocular image analysis module 402 to detect various road obstacles such as, for example, a part of a truck tire, a fallen road sign, a loose cargo, and small animals. Since road obstacles can differ in structure, shape, size, and color, detecting such risk factors can be more difficult. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on the plurality of images to detect road obstacles. For example, the processing unit 110 may estimate the movement of the camera between consecutive image frames, calculate the pixel parallax between the frames to construct a 3D map of the road. The processing unit 110 may then use the 3D map to detect the road surface and risk factors present on the road surface.

[0167] In stage 530, the processing unit 110 may execute the navigation response module 408 to generate one or more navigation responses in the vehicle 200 based on the analysis performed in stage 520 and the techniques described above in connection with FIG. 4. The navigation responses may include, for example, turning, lane changes, and acceleration changes. In some embodiments, the processing unit 110 may use data obtained from the execution of the speed acceleration module 406 to generate one or more navigation responses. Further, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 may move the vehicle 200 across one lane and then accelerate it by sequentially transmitting control signals to, for example, the steering device 240 and the throttle device 220 of the vehicle 200. Alternatively, the processing unit 110 may move the vehicle 200 in a lane while applying brakes to the vehicle 200 by simultaneously transmitting control signals to, for example, the brake device 230 and the steering device 240 of the vehicle 200.

[0168] FIG. 5B is a flowchart illustrating an exemplary process 500B for detecting one or more vehicles and / or one or more pedestrians included in a set of images that is consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500B. At step 540, the processing unit 110 may determine a set of candidate objects representing potential vehicles and / or pedestrians. For example, the processing unit 110 may scan one or more images, compare the images with one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or parts thereof). The predetermined patterns may be designed in a manner that achieves a high probability of "false hits" and a low probability of "misses". For example, the processing unit 110 may use a low similarity threshold with the predetermined patterns to identify candidate objects as potential vehicles or pedestrians. By doing so, it may be possible to reduce the probability that the processing unit 110 misses (e.g., fails to identify) candidate objects representing vehicles or pedestrians.

[0169] At step 542, the processing unit 110 may filter the set of candidate objects to exclude certain candidates (e.g., objects that are irrelevant or have little relevance) based on classification criteria. Such criteria may be derived from various characteristics related to the type of objects stored in a database (e.g., a database stored in the memory 140). These characteristics may include object shape, dimensions, texture, and position (e.g., position relative to the vehicle 200). Thus, the processing unit 110 may use one or more sets of criteria to exclude incorrect candidates from the set of candidate objects.

[0170] In stage 544, the processing unit 110 may analyze a plurality of frames of an image to determine whether an object included in the set of candidate objects represents a vehicle and / or a pedestrian. For example, the processing unit 110 may track the detected candidate objects throughout a series of consecutive frames and accumulate frame-by-frame data (e.g., size, position relative to the vehicle 200, etc.) associated with the detected objects. Further, the processing unit 110 may estimate the parameters of the detected objects and compare the position data for each frame of the object with the predicted position.

[0171] In stage 546, the processing unit 110 may construct a set of measurements of the detected objects. Such measurements may include, for example, the position, velocity, and acceleration values associated with the detected objects (relative to the vehicle 200). In some embodiments, the processing unit 110 may construct the measurements based on an estimation technique that uses a series of time-based observations such as a Kalman filter or linear quadratic estimation (LQE), and / or based on modeled data available for various object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter may be based on measurements of the scale of the object, and the scale measurements are proportional to the time until collision (e.g., the time until the vehicle 200 reaches the object). Thus, by performing stages 540 - 546, the processing unit 110 can identify vehicles and pedestrians that appear within the set of captured images and obtain information related to those vehicles and pedestrians (e.g., position, velocity, size). Based on this identification and the information obtained, the processing unit 110 can generate one or more navigation responses in the vehicle 200 as described above in connection with FIG. 5A.

[0172] In stage 548, the processing unit 110 may perform optical flow analysis of one or more images in order to reduce the probability of detecting "false detection" and the probability of missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, the analysis of the motion pattern of the vehicle 200 in one or more images related to other vehicles and pedestrians, and this motion pattern is different from the motion of the road surface. The processing unit 110 may calculate the motion of the candidate object by observing the various positions of the object throughout a plurality of image frames captured at different times. The processing unit 110 may use the position and time values as inputs to a mathematical model that calculates the motion of the candidate object. Therefore, optical flow analysis may provide another method for detecting vehicles and pedestrians near the vehicle 200. The processing unit 110 may perform optical flow analysis in combination with stages 540-546 to provide redundancy in the detection of vehicles and pedestrians and enhance the reliability of the system 100.

[0173] FIG. 5C is a flowchart showing an exemplary process 500C for detecting road markings and / or lane geometric structure information included in a set of images that is not inconsistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500C. In stage 550, the processing unit 110 may detect a set of objects by scanning one or more images. In order to detect lane markings, lane geometric structure information, and segments of other related road markings, the processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., small depressions, small stones, etc.). In stage 552, the processing unit 110 may group together segments belonging to the same road marking or lane marking detected in stage 550. Based on this grouping, the processing unit 110 may develop a model such as a mathematical model representing the detected segments.

[0174] In step 554, the processing unit 110 may construct a set of measurement values related to the detected segment. In some embodiments, the processing unit 110 may create a projection of the detected segment from the image plane onto the actual plane. This projection may be characterized by using a cubic polynomial having coefficients corresponding to physical characteristics such as the position, slope, curvature, and curvature derivative of the detected road. When generating the projection, the processing unit 110 may consider changes in the road surface and pitch and roll rates associated with the vehicle 200. Further, the processing unit 110 may model the road elevation by analyzing the position and motion cues present on the road surface. Further, the processing unit 110 may estimate the pitch and roll rates associated with the vehicle 200 by tracking a set of feature points within one or more images.

[0175] In step 556, the processing unit 110 may perform multi-frame analysis, for example, by tracking the detected segment throughout a sequence of consecutive image frames and accumulating frame-by-frame data related to the detected segment. When the processing unit 110 performs multi-frame analysis, the set of measurement values constructed in step 554 will become more reliable and will gradually be associated with a higher confidence level. Thus, by performing steps 550, 552, 554, and 556, the processing unit 110 can identify road markings appearing within the set of captured images and obtain lane geometric structure information. Based on this identification and the information obtained, the processing unit 110 can generate one or more navigation responses in the vehicle 200 as described above in connection with FIG. 5A.

[0176] In stage 558, the processing unit 110 may consider additional information sources to further develop the safety model of the vehicle 200 in relation to what is around it. The processing unit 110 may use the safety model to define situations in which the system 100 can perform the automatic control of the vehicle 200 in a safe manner. To develop the safety model, in some embodiments, the processing unit 110 may consider the positions and movements of other vehicles, detected road edges and road barriers, and / or general road shape descriptions extracted from map data (such as the data in the map database 160). By considering additional information sources, the processing unit 110 can provide redundancy in the detection of road markings and lane geometries, and can enhance the reliability of the system 100.

[0177] FIG. 5D is a flowchart showing an exemplary process 500D for detecting a traffic signal included in a set of images, which is consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500D. In stage 560, the processing unit 110 may scan the set of images to identify objects that appear at positions within the images that may contain a traffic signal. For example, the processing unit 110 may filter the identified objects to construct a set of candidate objects and exclude objects that are unlikely to correspond to a traffic signal. This filtering may be performed based on various characteristics related to traffic signals, such as shape, dimensions, texture, and position (e.g., position relative to the vehicle 200). Such characteristics may be based on multiple examples of traffic signals and traffic control signals and may be stored in a database. In some embodiments, the processing unit 110 may perform multi-frame analysis on the set of candidate objects that reflect possible traffic signals. For example, the processing unit 110 may track the candidate objects throughout consecutive image frames, estimate the actual positions of the candidate objects, and exclude objects that are moving (objects that are unlikely to be traffic signals). In some embodiments, the processing unit 110 may perform color analysis on the candidate objects and identify the relative positions of the detected colors that appear inside the possible traffic signals.

[0178] In stage 562, the processing unit 110 may analyze the geometric structure of the intersection. This analysis may be based on any combination of (i) the number of lanes detected on both sides of the vehicle 200, (ii) signs detected on the road (such as arrow signs), and (iii) a description of the intersection extracted from map data (such as data in the map database 160). The processing unit 110 may perform the analysis using the information obtained from the execution of the monocular analysis module 402. Further, the processing unit 110 may identify the correspondence between the traffic signal detected in stage 560 and the lanes appearing near the vehicle 200.

[0179] As the vehicle 200 approaches the intersection, in stage 564, the processing unit 110 may update the reliability associated with the analyzed geometric structure of the intersection and the detected traffic signal. For example, the number of traffic signals estimated to appear at the intersection may affect the reliability when compared to the actual number of traffic signals appearing at the intersection. Thus, based on the reliability, the processing unit 110 may delegate control authority to the driver of the vehicle 200 to improve safety conditions. By performing stages 560, 562, and 564, the processing unit 110 may identify the traffic signals appearing in the set of captured images and analyze the geometric structure information of the intersection. Based on this identification and analysis, the processing unit 110 may generate one or more navigation responses in the vehicle 200 as described above in connection with FIG. 5A.

[0180] FIG. 5E is a flowchart showing an exemplary process 500E for generating one or more navigation responses in the vehicle 200 based on a vehicle route, which is not inconsistent with the disclosed embodiments. In stage 570, the processing unit 110 may construct an initial vehicle route associated with the vehicle 200. This vehicle route may be represented using a set of points expressed in coordinates (x, z), and the distance d between two points within this set of points imay be included in the range of 1 to 5 meters. In one embodiment, the processing unit 110 may construct an initial vehicle path using two polynomials, for example, left and right road polynomials. The processing unit 110 may calculate the geometric midpoint between the two polynomials and, if there is an offset (a zero offset may correspond to driving in the center of the lane), shift each point included in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset). This offset may exist in a direction perpendicular to the segment between any two points within the vehicle path. In another embodiment, the processing unit 110 may use one polynomial and the estimated lane width to shift each point of the vehicle path by an amount obtained by adding a predetermined offset (e.g., a smart lane offset) to half of the estimated lane width.

[0181] In step 572, the processing unit 110 may update the vehicle path constructed in step 570. The processing unit 110 may reconstruct the vehicle path constructed in step 570 using a high resolution, whereby the distance d between two points within the set of points representing the vehicle path k is the distance d described above i becomes smaller. For example, the distance d k may be included in the range of 0.1 to 0.3 meters. The processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, whereby 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) may be obtained.

[0182] In step 574, the processing unit 110, based on the updated vehicle path constructed in step 572, (coordinates (x l , z l) may determine a look-ahead point expressed as). The processing unit 110 may extract a look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance may have a lower limit value in the 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, when the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower limit value). The look-ahead time may be in the range of 0.5 to 1.5 seconds and may be inversely proportional to the gain of one or more control loops (such as an azimuth error tracking control loop) associated with generating a navigation response in the vehicle 200. For example, the gain of the azimuth error tracking control loop may depend on the bandwidth of the yaw rate loop, the steering actuator loop, and the lateral dynamics of the vehicle, etc. Therefore, the higher the gain of the azimuth error tracking control loop, the shorter the look-ahead time.

[0183] In step 576, the processing unit 110 may determine an azimuth error and a yaw rate command based on the look-ahead point determined in step 574. The processing unit 110 may determine the azimuth error by calculating the arctangent of the look-ahead point, e.g., arctan(x l / z l ). The processing unit 110 may determine the yaw rate command as the product of the azimuth error and a high-level control gain. The high-level control gain may be equal to (2 / [look-ahead time]) when the look-ahead distance is not at the lower limit value. Otherwise, the high-level control gain may be equal to (2×[speed of vehicle 200] / [look-ahead distance]).

[0184] FIG. 5F is a flowchart showing an exemplary process 500F for determining whether a leading vehicle is changing lanes, which is not inconsistent with the disclosed embodiments. At step 580, the processing unit 110 may identify navigation information associated with the leading vehicle (e.g., a vehicle traveling in front of vehicle 200). For example, the processing unit 110 may determine the position, speed (e.g., direction and speed), and / or acceleration of the leading vehicle using the techniques described above in connection with FIGS. 5A and 5B. The processing unit 110 may determine one or more road polynomials, a look-ahead point (associated with vehicle 200), and / or a snail trail (e.g., a set of points describing the path traveled by the leading vehicle) using the techniques described above in connection with FIG. 5E.

[0185] In stage 582, the processing unit 110 may analyze the navigation information identified in stage 580. In one embodiment, the processing unit 110 may calculate the distance (e.g., along the trail) between the snail trail and the road polynomial. If the variance of this distance along the trail exceeds a predetermined threshold (e.g., 0.1 - 0.2 meters for a straight road, 0.3 - 0.4 meters for a gently curved road, and 0.5 - 0.6 meters for a sharp curved road), the processing unit 110 may determine that the leading vehicle is probably changing lanes. If it is detected that a plurality of vehicles are traveling in front of vehicle 200, the processing unit 110 may compare the snail trails associated with each vehicle. Based on this comparison, the processing unit 110 may determine that a vehicle whose snail trail does not match the snail trails of other vehicles is probably changing lanes. The processing unit 110 may further compare the curvature of the snail trail (associated with the leading vehicle) with the expected curvature of the road segment on which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., data from the map database 160), the road polynomial, the snail trails of other vehicles, and prior knowledge about the road. If the difference between the curvature of the snail trail and the expected curvature of the road segment exceeds a predetermined threshold, the processing unit 110 may determine that the leading vehicle is probably changing lanes.

[0186] In another embodiment, the processing unit 110 may compare the instantaneous position of the leading vehicle with the look-ahead point (associated with the vehicle 200) over a specific period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the leading vehicle and the look-ahead point changes during the specific period and the cumulative total of the change amount exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a gently curved road, and 1.3 to 1.7 meters on a sharp curved road), the processing unit 110 may determine that the leading vehicle is probably changing lanes. In another embodiment, the processing unit 110 may analyze the geometric structure of the snail trail by comparing the lateral movement distance along the trail with the expected curvature of the snail trail. The expected radius of curvature may be obtained according to the calculation of (δ z 2 +δ x 2 ) / 2 / (δ x ). Here, δ x represents the lateral movement distance, and δ 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 to 700 meters), the processing unit 110 may determine that the leading vehicle is probably changing lanes. In another embodiment, the 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 is superimposed on the road polynomial), the processing unit 110 may then determine that the leading vehicle is probably changing lanes. In the case of the position of the leading vehicle where another vehicle is detected in front of the leading vehicle and the snail trails of the two vehicles are not parallel, the processing unit 110 may determine that the (nearer) leading vehicle is probably changing lanes.

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

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

[0189] In stage 620, the processing unit 110 executes the stereo image analysis module 404 to perform stereo image analysis on the first and second plurality of images, create a 3D map of the road ahead of the vehicle, and detect features in these images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. The stereo image analysis may be performed in a manner similar to the stages described above in connection with FIGS. 5A - 5D. For example, the processing unit 110 executes the stereo image analysis module 404 to detect candidate objects (such as vehicles, pedestrians, road signs, traffic lights, road obstacles, etc.) in the first and second plurality of images, exclude a subset of the candidate objects based on various criteria, further perform multi-frame analysis, construct measurements, and identify the reliability of the remaining candidate objects. When performing the above stages, the processing unit 110 may consider information from both the first and second plurality of images rather than just information from one set of images. For example, the processing unit 110 may analyze the differences in pixel-level data of candidate objects (or other data subsets of the two streams of the captured images) that appear in both the first and second plurality of images. As another example, the processing unit 110 may estimate the position and / or velocity of a candidate object (e.g., with respect to vehicle 200) by observing that the object appears in one of the plurality of images but not in the others, and estimate it in comparison with other differences that may exist in relation to the objects that appear when there are two image streams. For example, the position, velocity, and / or acceleration with respect to vehicle 200 may be determined based on the trajectories, positions, motion characteristics, etc. of the features associated with the objects that appear in one or both of the two image streams.

[0190] In step 630, the processing unit 110 may execute the navigation response module 408 to generate one or more navigation responses in the vehicle 200 based on the analysis performed in step 620 and the techniques described above in connection with FIG. 4. The navigation responses may include, for example, turning, lane changes, acceleration changes, speed changes, and braking. In some embodiments, the processing unit 110 may use data obtained from the execution of the speed acceleration module 406 to generate one or more navigation responses. Further, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof.

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

[0192] At stage 720, processing unit 110 may analyze the first, second, and third plurality of images to detect features within these images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. This analysis may be performed in a manner similar to the stages described above in connection with FIGS. 5A-5D and FIG. 6. For example, processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., by execution of monocular image analysis module 402 and based on the stages 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., by execution of stereo image analysis module 404 and based on the stages described above in connection with FIG. 6). The 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., by execution of monocular image analysis module 402) and perform stereo image analysis on the second and third plurality of images (e.g., by execution of stereo image analysis module 404). The configurations 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.

[0193] In some embodiments, the processing unit 110 may perform tests on the system 100 based on the images acquired and analyzed in stages 710 and 720. Such tests may provide an indication of the overall performance of the system 100 for a particular configuration of the image capture devices 122, 124, and 126. For example, the processing unit 110 may determine the rates of "false detection" (e.g., when the system 100 incorrectly determines the presence of a vehicle or pedestrian) and "miss".

[0194] In stage 730, the processing unit 110 may generate one or more navigation responses in the vehicle 200 based on information obtained from two of the first, second, and third plurality of images. The selection of two of the first, second, and third plurality of images may depend on various factors such as the number, type, and size of the objects detected in each of the plurality of images. The processing unit 110 may make the selection based on image quality and resolution, the effective field of view reflected in the image, the number of frames captured, the extent to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which the object appears, the percentage of objects appearing in such each frame), etc.

[0195] In some embodiments, the processing unit 110 may select information obtained from two of the first, second, and third plurality of images by determining the degree to which information obtained from one image source matches information obtained from another image source. For example, the processing unit 110 may combine the processed information obtained from each of the image capture devices 122, 124, and 126 (whether by monocular analysis, stereo analysis, or any combination of these two) to identify visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic signals, etc.) that are consistent across the images captured from each of the image capture devices 122, 124, and 126. The processing unit 110 may exclude information that is not consistent across the captured images (e.g., a vehicle changing lanes, a lane model indicating a vehicle that is too close to vehicle 200, etc.). Thus, the processing unit 110 may select information obtained from two of the first, second, and third plurality of images based on the determination of consistent and inconsistent information.

[0196] Navigation responses may include, for example, turning, lane changes, and acceleration changes. The processing unit 110 may generate one or more navigation responses based on the analysis performed at stage 720 and the techniques described above in connection with FIG. 4. The processing unit 110 may generate one or more navigation responses using data obtained from the execution of the speed acceleration module 406. In some embodiments, the processing unit 110 may generate one or more navigation responses based on the relative position, relative speed, and / or relative acceleration of vehicle 200 and an object detected in any of the first, second, and third plurality of images. The plurality of navigation responses may be performed simultaneously, sequentially, or any combination thereof.

[0197] [Sparse Road Model for Autonomous Vehicle Navigation]

[0198] 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 a road segment. For example, the sparse map can provide sufficient information to navigate an autonomous vehicle without storing and / or updating large amounts of data. As discussed in more detail below, an autonomous vehicle can use the sparse map to navigate one or more roads based on one or more stored trajectories.

[0199] [Sparse Map for Autonomous Vehicle Navigation]

[0200] In some embodiments, the disclosed systems and methods may generate a sparse map for autonomous vehicle navigation. For example, the sparse map can provide sufficient information for navigation without requiring excessive data storage or data transfer rates. As discussed in more detail below, a vehicle (which may be an autonomous vehicle) can use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map may include data related to roads and possibly landmarks along the road, which may be sufficient for vehicle navigation but also indicates a small data footprint. For example, a sparse data map, described in detail below, may require significantly less storage area and data transfer bandwidth compared to a digital map that includes detailed map information (such as image data collected along the road).

[0201] For example, instead of storing a detailed representation of a road segment, the sparse data map can store a three-dimensional polynomial representation of a preferred vehicle route along the road. These routes may require little data storage space. Further, in the sparse data map described, landmarks may be identified and included in the sparse map road model to assist navigation. These landmarks may be placed at any interval suitable for enabling vehicle navigation, but in some cases, it may not be necessary to identify such landmarks or include them in the model at high density and narrow intervals. Rather, in some cases, navigation may be enabled based on landmarks placed at intervals of at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers. As will be discussed in more detail in other sections, the sparse map may be generated based on data collected or measured by various sensors and devices on a vehicle as the vehicle travels along a roadway, such as an image capture device, a sensor for a global positioning system, a motion sensor, etc. In some cases, the sparse map may be generated based on data collected from multiple drives of one or more vehicles along a particular roadway. Generating a sparse map using multiple drives of one or more vehicles is sometimes referred to as "crowdsourcing" of the sparse map.

[0202] Without conflicting with the disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed systems and methods may distribute a sparse map to generate a road navigation model for an autonomous vehicle, and use the sparse map and / or the generated road navigation model to navigate an autonomous vehicle along a road segment. A sparse map that does not conflict with the present disclosure may include one or more three-dimensional contour maps that may represent a predetermined trajectory that an autonomous vehicle may traverse as it moves along a related road segment.

[0203] A sparse map that does not conflict with the present disclosure may also include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and any other road-related features useful for navigating a vehicle. The sparse map that does not conflict with the present disclosure may enable automatic navigation of a vehicle based on a relatively small amount of data included in the sparse map. For example, embodiments of the disclosed sparse map do not include a detailed representation of the road, such as data detailing road edges, road curvature, images associated with road segments, or other physical features associated with road segments, but rather may require relatively little storage area (and relatively little bandwidth if each part of the sparse map is transferred to the vehicle), yet still be able to provide sufficient automated vehicle navigation. As discussed in more detail below, the small data footprint of the disclosed sparse map can be achieved in some embodiments by storing a representation of road-related elements that requires relatively little data yet still enables automatic navigation.

[0204] For example, the disclosed sparse map may store a polynomial representation of one or more trajectories along which a vehicle can travel rather than a detailed representation of various aspects of the road. Thus, to enable navigation along a road, rather than storing (or having to transfer) details regarding the physical nature of the road, using the disclosed sparse map may, in some cases, obviate the need to interpret the physical aspects of the road and instead align the vehicle's travel path with a trajectory (e.g., a polynomial spline) along a particular road segment to navigate the vehicle along the particular road segment. In this way, the vehicle may be navigated primarily based on the stored trajectory (e.g., a polynomial spline), which requires much less storage area than approaches that require storage of lane images, road parameters, road layouts, etc.

[0205] In addition to the stored polynomial representation of the trajectory along the road segment, the disclosed sparse map may also include small data objects that can represent road features. In some embodiments, the small data objects may include digital signatures, which are obtained from digital images (or digital signals) acquired by sensors (such as cameras or other sensors like suspension sensors) mounted on vehicles traveling along the road segment. The digital signature may be small in size compared to the signal acquired by the sensor. In some embodiments, the digital signature may be created to be compatible with, for example, a classifier function configured to detect and identify road features from signals acquired by the sensor during a subsequent drive. In some embodiments, the digital signature has as small a footprint as possible and is created to retain the function of associating or matching road features to the stored signature based on an image of the road features (or, if the stored signature is not image-based and / or includes other data, a digital signal generated by the sensor) captured by a camera mounted on a vehicle traveling along the same road segment at a next opportunity.

[0206] In some embodiments, the size of the data object may further be related to the uniqueness of the road feature. For example, for road features detectable by a camera mounted on a vehicle, if the vehicle-mounted camera system is coupled to a classifier that can distinguish image data corresponding to the road feature as being related to a particular type of road feature (such as a road sign), and such road signs are locally unique in the area (e.g., no exactly the same road sign or the same type of road sign is nearby), it may be sufficient to store data indicating the type and location of the road feature.

[0207] As will be 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 features with a relatively small number of bytes, while at the same time providing sufficient information to recognize and use such features for navigation. In one example, a road sign may be identified as a recognized landmark on which vehicle navigation can be based. The representation of the road sign may be stored in a sparse map, which may include, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign), and a few bytes of data indicating the location of the landmark (e.g., coordinates). Navigating based on such a lightweight data representation of the landmark (e.g., using the representation sufficient to perform location identification, recognition, and navigation based on the landmark) can provide the desired level of navigation functionality associated with the sparse map without significantly increasing the data overhead associated with the sparse map. This efficient representation of landmarks (and other road features) may utilize sensors and processors mounted on a vehicle configured to detect, identify, and / or classify specific road features.

[0208] For example, in a given area, if a sign or even a particular type of sign is locally unique (e.g., there are no other signs or no other signs of the same type), the sparse map may use data indicating the type of landmark (the sign or the particular type of sign). During navigation (e.g., autonomous navigation), when a camera mounted on an autonomous vehicle captures an image of an area that includes the sign (or the particular type of sign), the processor may process the image, detect the sign (if it actually exists in the image), classify the image as the sign (or as the particular type of sign), and associate the location of the image with the location of the sign stored in the sparse map.

[0209] The sparse map may include any suitable representation of an object identified along a road segment. In some cases, the object may be referred to as a semantic object or a non-semantic object. A semantic object may include, for example, an object associated with a given type classification. This type classification may be useful in reducing the amount of data required to describe the semantic objects recognized in the environment, which can be beneficial both during the collection stage (e.g., reducing the cost associated with the use of bandwidth for transferring drive information from multiple collection vehicles to a server) and during the navigation stage (e.g., by reducing the map data, the transfer of map tiles from the server to the navigating vehicle can be accelerated, and the cost associated with the use of bandwidth for such transfer can also be reduced). The semantic object classification type may be assigned to any type of object or feature expected to be encountered along the roadway.

[0210] Semantic objects may further be divided into two or more logical groups. For example, in some cases, one group of semantic object types may be related to a given dimension. Such semantic objects may include specific speed limit signs, priority road signs, merge signs, stop signs, traffic lights, lane direction arrows, manhole covers, or any other type of object that may be related to a standardized size. One benefit provided by such semantic objects may be that little data may be needed to represent / fully define the object. For example, if the standardized size of the speed limit size is known, then the collection vehicle may then only need to identify the presence of the detected speed limit sign (by analysis of the captured image) along with an indication of the location of the detected speed limit sign (e.g., the 2D position of the center of the sign or a particular corner of the sign in the captured image (or, alternatively, the 3D position in actual coordinates)) in order to provide sufficient information for map generation on the server side. When the 2D image position is transmitted to the server, the server may be able to determine the actual position of the sign (e.g., via the structure in a motion technique using multiple images captured from one or more collection vehicles), so the position where the sign was detected in relation to the captured image may also be transmitted. Even with this limited information (which only requires a few bytes to define each detected object), the server may construct a map that includes speed limit signs fully represented based on the type classification (representing speed limit signs) received along with the location information of the detected signs from one or more collection vehicles.

[0211] Semantic objects may also include other recognized objects or feature types that are not related to specific standardized characteristics. Such objects or features may include holes in the road, tar seams, street light poles, non-standardized signals, curbs, trees, tree branches, or any other type of recognized object with one or more variable characteristics (e.g., variable dimensions). In such cases, in addition to sending an indication of the detected object or feature type (e.g., a hole in the road, a pole, etc.) and the location information of the detected object or feature to the server, the collection vehicle may also send an indication of the size of the object or feature. The size may be represented in 2D image dimensions (e.g., with a bounding box, or one or more dimension values), or in actual dimensions (specified through a structure in a motion calculation based on the output of a LIDAR or RADAR system, the output of a trained neural network, etc.).

[0212] Non-semantic objects or features may include any detectable object or feature that is outside the recognized types or categories but can still provide valuable information in map generation. In some cases, such non-semantic features may include detected corners of a building or corners of detected window glass of a building, unique stones or objects near a roadway, concrete splatters on a road shoulder, or any other detectable object or feature. When detecting such an object or feature, one or more collection vehicles may send the positions of one or more points (2D image points or 3D real-world points) associated with the detected object / feature to a map generation server. Further, for the region of the captured image containing the detected object or feature, a compressed or simplified image segment (e.g., an image hash) may be generated. This image hash may be calculated based on a predetermined image processing algorithm and may form an effective signature for the detected non-semantic object or feature. Vehicles traversing the roadway may apply an algorithm similar to the one used to generate the image hash to verify / validate the presence of non-semantic features or objects mapped in the captured image, so such signatures may be useful for navigation related to a sparse map containing non-semantic features or objects. By using this approach, non-semantic features may add richness to the sparse map without adding significant data overhead (and may, for example, improve their utility in navigation).

[0213] As mentioned, the target trajectories may be stored in the sparse map. These target trajectories (e.g., 3D splines) may represent preferred or recommended routes for each available lane of the roadway, for each valid route through an intersection, for merge points and exits, etc. In addition to the target trajectories, other road features may also be detected, collected, and incorporated into the sparse map in the form of representative splines. Such features may include, for example, road edges, lane markings, curbs, guardrails, or any other object or feature extending along a lane or road segment.

[0214] [Generation of Sparse Map]

[0215] In some embodiments, the sparse map may include at least one line representation of road surface features extending along a road segment and a plurality of landmarks associated with the road segment. In certain aspects, the sparse map may be generated by image analysis of a plurality of images obtained, for example, via "crowdsourcing" as one or more vehicles traverse the road segment.

[0216] FIG. 8 shows a sparse map 800 that may be accessed by one or more vehicles, such as vehicle 200 (which may be an autonomous vehicle), to provide autonomous vehicle navigation. The sparse map 800 may be stored in a memory such as memory 140 or 150. Such a memory device may include any type of non-transitory storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 may include a hard drive, a compact disk, a flash memory, a magnetic-based memory device, an optical-based memory device, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., map database 160) that may be stored in memory 140 or 150, or other types of storage devices.

[0217] In some embodiments, the sparse map 800 may be stored in a storage device or non-transitory computer-readable medium mounted on the vehicle 200 (e.g., a storage device included in a navigation system mounted on the vehicle 200). A processor provided in the vehicle 200 (e.g., the processing unit 110) may access the sparse map 800 stored in a storage device or computer-readable medium mounted on the vehicle 200 to generate navigation instructions for guiding the vehicle when the autonomous vehicle 200 traverses a road segment.

[0218] However, the sparse map 800 need not be stored locally with respect to the vehicle. In some embodiments, the sparse map 800 may be stored in a storage device or computer-readable medium provided in a remote server that communicates with the vehicle 200 or a device associated with the vehicle 200. A processor provided in the vehicle 200 (e.g., the processing unit 110) may receive data included in the sparse map 800 from the remote server and may execute this data to guide the autonomous operation of the vehicle 200. In such embodiments, the remote server may store all or only a portion of the sparse map 800. In response thereto, a storage device or computer-readable medium mounted on the vehicle 200 and / or mounted on one or more additional vehicles may store one or more remaining portions of the sparse map 800.

[0219] Furthermore, in such embodiments, a plurality of vehicles (e.g., dozens, hundreds, thousands, or millions of vehicles, etc.) passing through various road segments may be enabled to access the sparse map 800. It should also be noted that the sparse map 800 may include a plurality of submaps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, millions, or more submaps (e.g., map tiles) that can be used when navigating a vehicle. Such submaps may sometimes be referred to as local maps or map tiles, and a vehicle traveling along a roadway may access any number of local maps related to the location where the vehicle is traveling. The local map areas of the sparse map 800 may be stored together with a global navigation satellite system (GNSS) key as an index to the sparse map 800's database. Thus, the calculation of the steering angle for navigating a host vehicle in this system may be performed without relying on the GNSS position, road features, or landmarks of the host vehicle, although such GNSS information may be used to search for relevant local maps.

[0220] Generally, the sparse map 800 may be generated based on data (e.g., drive information) collected from one or more vehicles as they travel along a roadway. For example, sensors (e.g., cameras, speedometers, GPS, accelerometers, etc.) mounted on one or more vehicles can be used to record the trajectory of one or more vehicles as they travel along a roadway, and a polynomial representation of the preferred trajectory of vehicles that will subsequently move along this roadway can be determined based on the trajectories traveled and collected by the one or more vehicles. Similarly, data collected by one or more vehicles can help identify potential landmarks along a particular roadway. Data collected from passing vehicles may also be used to identify road profile information, e.g., road width profile, road roughness profile, lane spacing profile, road conditions, etc. Using the collected information, the sparse map 800 can be generated for use in navigating one or more autonomous vehicles and may be distributed (e.g., for local storage or via on-the-fly data transmission). However, in some embodiments, map generation may not end with the initial generation of the map. As will be discussed in more detail below, the sparse map 800 may be constantly or periodically updated based on data collected from a vehicle as the vehicle continues to travel on a roadway included in the sparse map 800.

[0221] The data recorded in the sparse map 800 may include location information based on global positioning system (GPS) data. For example, the location information may be included in the sparse map 800 for various map elements including, for example, the location of landmarks, the location of road profiles, etc. The location of the map elements included in the sparse map 800 may be obtained using GPS data collected from vehicles passing through the lanes. For example, a vehicle passing through an identified landmark may use the GPS location information associated with the vehicle and the determination of the location of the identified landmark relative to the vehicle (e.g., based on image analysis of data collected from one or more cameras mounted on the vehicle) to determine the location of the identified landmark. Such determination of the location of the identified landmark (or any other feature included in the sparse map 800) may be repeated each time a further vehicle passes through the identified landmark. Some or all of the further determinations may be used to fine-tune the location information regarding the identified landmark stored in the sparse map 800. For example, in some embodiments, multiple location measurements regarding a particular feature stored in the sparse map 800 may be averaged together. However, any other mathematical operation may be used to fine-tune the location of the stored map elements based on multiple locations determined for the map elements.

[0222] In a particular example, the collection vehicle may pass through a particular road segment. Each collection vehicle captures an image of its respective environment. The images may be collected at any suitable frame capture rate (e.g., 9 Hz, etc.). One or more image analysis processors mounted on each collection vehicle analyze the captured images to detect the presence of semantic and / or non-semantic features / objects. At a high level, the collection vehicle sends an indication of the detection of semantic and / or non-semantic objects / features to the mapping server, along with the locations associated with these objects / features. More specifically, type indicators, dimension indicators, etc. may be sent together with the location information. The location information may include any information suitable to enable the mapping server to aggregate the detected objects / features into a sparse map useful in navigation. In some cases, the location information may include one or more 2D image locations (e.g., X-Y pixel locations) in the captured image where semantic or non-semantic features / objects were detected. Such image locations may correspond to the center, corners, etc. of the feature / object. In this scenario, each collection vehicle may also provide the server with the location (e.g., GPS location) where each image was captured, to assist the mapping server in reconstructing the drive information and aligning the drive information from multiple collection vehicles.

[0223] In other cases, the collection vehicle may provide the server with one or more 3D real-world points associated with the detected object / feature. Such 3D points may be related to a predetermined origin (such as the origin of the drive segment) and may be specified by any suitable method. In some cases, the structure in the motion method may be used to identify the 3D real-world position of the detected object / feature. For example, in two or more captured images, a particular object such as a specific speed limit sign may be detected. By using information such as the observed changes in the speed limit sign in the captured images (changes in X-Y pixel position, changes in size, etc.) along with the known ego-motion (speed, trajectory, GPS position, etc.) of the collection vehicle between multiple captured images, the actual position of one or more points associated with the speed limit sign is identified and may be passed to the mapping server. Such a method is optional as it requires more computation in a part of the collection vehicle system. The sparse map of the disclosed embodiments may enable automatic navigation of the 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 the target trajectory, landmarks, and any other stored road features) of less than 2MB per kilometer of road, less than 1MB per kilometer of road, less than 500kB per kilometer of road, or less than 100kB per kilometer of road. In some embodiments, the data density of the sparse map 800 may be less than 10kB per kilometer of road or even less than 2kB per kilometer of road (e.g., 1.6kB per kilometer), less than or equal to 10kB per kilometer of road, or less than or equal to 20kB per kilometer of road. In some embodiments, most, if not all, of the lanes in the United States can be autonomously navigated using a sparse map having a total data of 4GB or less. These data density values may represent the average for the entire sparse map 800, the average for the local maps within the sparse map 800, and / or the average for a particular road segment within the sparse map 800.

[0224] As mentioned above, the sparse map 800 may include a representation 810 of a plurality of target trajectories for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as 3D splines. The target trajectories stored in the sparse map 800 may be determined, for example, based on two or more reconstructed trajectories regarding previous passages of a vehicle along a particular road segment. A road segment may be associated with a single target trajectory or a plurality of target trajectories. For example, in a two-lane road, a first target trajectory may be stored to represent a target route traveling in a first direction along the road, and a second target trajectory may be stored to represent a target route traveling in another direction (e.g., opposite to the first direction) along the road. For a particular road segment, additional target trajectories may be stored. For example, in a multi-lane road, one or more target trajectories may be stored to represent target driving routes for a plurality of vehicles in one or more lanes associated with the multi-lane road. In some embodiments, each lane of a multi-lane road may be associated with its own target trajectory. In other embodiments, fewer target trajectories than the lanes present in the multi-lane road may be stored. In such a case, a vehicle navigating the multi-lane road may use any of the stored plurality of target trajectories to guide navigation, taking into account the lane offset amount from the lane in which the target trajectory is stored (e.g., if the vehicle is traveling in the leftmost lane of a three-lane highway and only the target trajectory for the middle lane of the highway is stored, the vehicle may navigate using the target trajectory of the middle lane by taking into account the lane offset amount between the middle lane and the leftmost lane when generating a navigation command).

[0225] In some embodiments, the target trajectory may represent an ideal path that the vehicle should follow when it is driving. The target trajectory may be located, for example, approximately at the center of the driving lane. In other cases, the target trajectory may be located elsewhere with respect 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, the navigation based on the target trajectory may include a determined offset amount that is maintained with respect to the position of the target trajectory. Further, in some embodiments, the determined offset amount maintained with respect to the position of the target trajectory may vary based on the type of vehicle (e.g., a passenger vehicle including two axles may have a different offset than a truck including more than two axles along at least a portion of the target trajectory).

[0226] The sparse map 800 may also include data related to a plurality of predetermined landmarks 820 associated with a particular road segment, local map, etc. As will be discussed in more detail below, these landmarks may be used for the navigation of the autonomous vehicle. For example, in some embodiments, these landmarks may be used to determine the current position of the vehicle with respect to the stored target trajectory. Using this position information, the autonomous vehicle may be able to adjust its traveling direction to match the direction of the target trajectory at the determined position.

[0227] The plurality of landmarks 820 may be identified at any suitable interval and stored in the sparse map 800. In some embodiments, the landmarks may be stored at a relatively high density (e.g., every few meters, or even more densely). However, in some embodiments, significantly large landmark interval values may be used. For example, in the sparse map 800, the identified landmarks may be arranged at intervals of 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers. In some cases, the identified landmarks may even be arranged at distances exceeding 2 kilometers apart.

[0228] During the determination of the vehicle position relative to landmarks and thus the target trajectory, the vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to identify its ego motion and estimates its position relative to the target trajectory. Since errors can accumulate in dead reckoning navigation, over time, the accuracy of the position determination relative to the target trajectory may gradually decrease. The vehicle can use the landmarks (and their known positions) present in the sparse map 800 to remove the errors due to dead reckoning in position determination. Thus, the identified landmarks included in the sparse map 800 can serve as an essential part of navigation that can determine the accurate position of the vehicle relative to the target trajectory. Since a certain amount of error may be acceptable in position search, the identified landmarks do not necessarily have to be available to the autonomous vehicle. Rather, suitable navigation may be possible even based on landmark intervals of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or even longer as described above. In some embodiments, a density of one identified landmark per 1 km of road may be sufficient to maintain the longitudinal position determination accuracy within 1 m. Therefore, it is not necessary to store every possible landmark that appears along the road segment in the sparse map 800.

[0229] Furthermore, in some embodiments, lane markings may be used to identify the vehicle's position between landmarks. By using lane markings between landmarks, the accumulation of errors during dead reckoning navigation can be minimized.

[0230] 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 describing the left and right sides of the road with a three-dimensional polynomial. Such polynomials representing the left and right sides of a single lane are shown in FIG. 9A. Regardless of how many lanes a road may have, the road can be represented using polynomials 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 markings representing lane boundaries, solid yellow lines representing boundaries between lanes traveling in different directions, etc.) may also be represented using polynomials as shown in FIG. 9A.

[0231] As shown in FIG. 9A, lane 900 may be represented using a polynomial (e.g., a first-degree, second-degree, third-degree, or polynomial of any suitable degree). For the sake of explanation, lane 900 is shown as a two-dimensional lane and the polynomial is shown as a two-dimensional polynomial. 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 the position of each side of the road or the lane boundary. For example, each of the left side 910 and the right side 920 may be represented by a plurality of polynomials of any suitable length. In some cases, these polynomials may have a length of about 100 m, but other lengths longer or shorter than 100 m may also be used. Further, such polynomials may overlap each other to facilitate seamless transition when navigating based on the polynomial that the host vehicle encounters next as it travels along the lane. For example, each of the left side 910 and the right side 920 may be represented by a plurality of third-degree polynomials that are divided into segments of a length of about 100 meters (an example of a first predetermined range) and overlap each other by about 50 meters. The polynomials representing the left side 910 and the right side 920 may or may not be of the same degree. For example, in some embodiments, some of the polynomials may be second-degree polynomials, some may be third-degree polynomials, and some may be fourth-degree polynomials.

[0232] In the example shown in FIG. 9A, the left side 910 of lane 900 is represented by two groups of cubic 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 and extend along the positions on each side of the road. The polynomial segments 911, 912, 913, 914, 915, and 916 are about 100 meters in length and overlap continuously with adjacent segments by about 50 meters. However, as described above, polynomials of different lengths and different amounts of overlap may also be used. For example, the polynomials may be 500 m, 1 km, or even longer, and the amount of overlap may vary from 0 to 50 m, 50 m to 100 m, or more than 100 m. Further, although FIG. 9A is shown as representing polynomials extending in a 2D space (e.g., on a paper surface), it should be understood that these polynomials represent curves extending in three dimensions (e.g., including a height component) and may represent elevation variations of the road segment in addition to the curvature of the X-Y plane. In the example shown in FIG. 9A, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922, and 923 and a second group having polynomial segments 924, 925, and 926.

[0233] Returning to the target trajectory of the sparse map 800, FIG. 9B shows a three-dimensional polynomial representing the target trajectory of a vehicle traveling along a particular road segment. The target trajectory represents not only the path in the X-Y plane that the host vehicle should travel along a particular road segment, but also the elevation variations that the host vehicle experiences as it travels along the road segment. Thus, each target trajectory included in the sparse map 800 may be represented by one or more three-dimensional polynomials, such as the three-dimensional polynomial 950 shown in FIG. 9B. The sparse map 800 may include a plurality of trajectories (e.g., millions or billions or more trajectories representing the trajectories of vehicles along various road segments along lanes around the world). In some embodiments, each target trajectory may correspond to a spline connecting three-dimensional polynomial segments.

[0234] Regarding the data footprint of the polynomial curves stored in the sparse map 800, in some embodiments, each cubic polynomial may be represented by four parameters, and each parameter requires 4 bytes of data. A cubic polynomial that requires approximately 192 bytes of data per 100 m can be used to obtain a suitable representation. This may correspond to a data utilization / transfer requirement of approximately 200 kB per hour for a host vehicle traveling at approximately 100 km / hr.

[0235] The sparse map 800 may describe a network of lanes using a combination of geometric structure descriptors and metadata. The geometric structure may be described by the polynomials or splines 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 indicators may be very small.

[0236] Thus, a sparse map according to an embodiment of the present disclosure may include at least one line representation of a road surface feature extending along a road segment, and each line representation represents a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as described above, 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. Further, as discussed below with respect to "crowdsourcing", the road surface feature may be identified by image analysis of a plurality of images obtained when one or more vehicles pass through the road segment.

[0237] As described above, the sparse map 800 may include a plurality of predetermined landmarks associated with a road segment. Instead of storing actual images of the landmarks and utilizing image recognition analysis based on, for example, the captured images and the stored images, each landmark included in the sparse map 800 can be represented and recognized using less data than would be required if actual images were stored. Nevertheless, the data representing the landmark can include sufficient information to describe or identify the landmark along the road. By storing data that describes the characteristics of the landmark rather than the actual image of the landmark, the size of the sparse map 800 can be reduced.

[0238] FIG. 10 shows an example of the types of landmarks that can be represented in the sparse map 800. These landmarks can include any visible and distinguishable object along the road segment. The landmarks may be selected to be fixed and not subject to frequent changes in their position and / or content. The landmarks included in the sparse map 800 can help determine the position of the vehicle 200 with respect to the target trajectory when the vehicle traverses a particular road segment. Examples of landmarks can include traffic signs, direction signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., streetlight poles, reflectors, etc.), and any other suitable types. In some embodiments, lane markings on the road may also be included as landmarks in the sparse map 800.

[0239] Examples of landmarks shown in FIG. 10 include traffic signs, direction signs, roadside fixtures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), priority road signs (e.g., priority road sign 1005), route number signs (e.g., route number sign 1010), traffic signal signs (e.g., traffic signal sign 1015), stop signs (e.g., stop sign 1020). Direction signs may include signs that include one or more arrows indicating one or more directions to different locations. For example, direction signs may include highway sign 1025 having an arrow guiding a vehicle to a different road or location, exit sign 1030 having an arrow guiding a vehicle to get off the road, and the like. Thus, at least one of the plurality of landmarks may include a road sign.

[0240] General signs may be unrelated to traffic. For example, general signs may include billboards used for advertising, or welcome boards adjacent to the boundaries of two countries, states, counties, cities, or towns. FIG. 10 shows a general sign 1040 (“Joe's Restaurant”). General sign 1040 may be rectangular in shape as shown in FIG. 10, but general sign 1040 may also be other shapes such as square, circular, triangular, and the like.

[0241] Landmarks may also include roadside fixtures. A roadside fixture may be an object that is not a sign and may be unrelated to traffic or direction. For example, roadside fixtures may include street lamp posts (e.g., street lamp post 1035), utility poles, traffic signal poles, and the like.

[0242] Landmarks may include beacons that can be specially designed for use in an autonomous vehicle navigation system. For example, such beacons may include stand-alone structures arranged at predetermined intervals to assist in navigating the host vehicle. Such beacons may also include visual / graphic information (e.g., icons, emblems, barcodes, etc.) added to existing road signs 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 identification information and / or landmark location information that can be used when the host vehicle determines its position along a target trajectory.

[0243] In some embodiments, the landmarks included in the sparse map 800 may be represented by data objects of a predetermined size. The data representing the landmarks may include any parameters suitable for identifying a particular landmark. For example, in some embodiments, the landmarks stored in the sparse map 800 may include the physical size of the landmark (e.g., for assisting in estimating the distance to the landmark based on a known size / scale), the distance to the previous landmark, the lateral offset, the height, the type code (e.g., the type of the landmark, i.e., what type of directional sign, traffic sign, etc.), GPS coordinates (e.g., for assisting in wide-area positioning), and any other suitable parameters. Each parameter may be associated with a data size. For example, the size of the landmark may be stored using 8 bytes of data. The distance to the previous landmark, the lateral offset, and the height may be specified using 12 bytes of data. The type code associated with a landmark such as a directional sign or a traffic sign may require approximately 2 bytes of data. For a general sign, an image signature enabling identification of the general sign may be stored using 50 bytes of data storage. The GPS position of the landmark may be associated with 16 bytes of data storage. These data sizes for each parameter are merely examples, and other data sizes may also be used. By representing the landmarks in the sparse map 800 in this way, an efficient solution for efficiently representing the landmarks in a database can be provided. In some embodiments, an object may be referred to as a standard semantic object or a non-standard semantic object. Standard semantic objects may include any class of objects having a standardized set of characteristics (e.g., speed limit signs, warning signs, directional signs, traffic lights, etc. having known dimensions or other characteristics). Non-standard semantic objects may include any objects not associated with a standardized set of characteristics (e.g., general advertising signs, signs identifying a company, holes in the road, trees, etc. that may have variable dimensions).Each non-standard and semantic object may be represented by 38 bytes of data (e.g., 8 bytes for size, 12 bytes for distance to the previous landmark, lateral offset and height, 2 bytes for type code, 16 bytes for position coordinates). Since the mapping server may not require the size information to fully represent the objects in the sparse map, standard and semantic objects may be represented using even less data.

[0244] The sparse map 800 may represent the type of landmark using a tag system. In some cases, each traffic sign or direction sign may be associated with a unique tag, which may be stored in the database as part of the landmark identification information. For example, the database may include about 1000 different tags to represent various traffic signs and about 10000 different tags to represent direction signs. Of course, any suitable number of tags may be used, and additional tags may be created as needed. In some embodiments, general-purpose signs may be represented using less than about 100 bytes (e.g., about 86 bytes including 8 bytes for size, 12 bytes for distance to the previous landmark, lateral offset, and height, 50 bytes for image signature, 16 bytes for GPS coordinates).

[0245] Thus, for semantic road signs that do not require image signatures, the impact on the data density of the sparse map 800 can be on the order of about 760 bytes per kilometer (e.g., [20 landmarks per km] × [38 bytes per landmark] = 760 bytes), even at a relatively high landmark density of about one per 50 m. Even for general-purpose signs that include image signature components, the impact on the data density is about 1.72 kB per km (e.g., [20 landmarks per km] × [86 bytes per landmark] = 1,720 bytes). For semantic road signs, this impact corresponds to a data usage of about 76 kB per hour for a vehicle traveling at 100 km / hr. For general-purpose signs, this impact corresponds to about 170 kB per hour for a vehicle traveling at 100 km / hr. It should be noted that in some environments (e.g., urban environments), the detected objects available for use due to what is included in the sparse map can be present at a fairly high density (presumably more than one per meter). In some embodiments, generally rectangular objects, such as rectangular signs, may be represented in the sparse map 800 with data of 100 bytes or less. The representation of generally rectangular objects (e.g., general sign 1040) in the sparse map 800 may include a reduced image signature or image hash (e.g., reduced image signature 1045) associated with the generally rectangular object. This reduced image signature / image hash can be determined by using any suitable image hash algorithm, and using this reduced image signature / image hash can help, for example, identify general-purpose signs as recognized landmarks. Such a reduced image signature (e.g., image information obtained from the actual image data representing an object) can eliminate the need to store the actual image of the object and the need for comparative image analysis on the actual image to recognize landmarks.

[0246] Referring to FIG. 10, the sparse map 800 may include or store a shortened image signature 1045 associated with the general label 1040, rather than an actual image of the general label 1040. For example, after an image capture device (e.g., image capture devices 122, 124, or 126) captures an image of the general label 1040, a processor (e.g., an image processor 190 or any other processor that can process images, mounted on the host vehicle or located remotely with respect to the host vehicle) may perform image analysis to extract / create a shortened image signature 1045 that includes a unique signature or pattern associated with the general label 1040. In one embodiment, the shortened image signature 1045 may include a shape, a color pattern, a brightness pattern, or any other feature for describing the general label 1040 that can be extracted from an image of the general label 1040.

[0247] For example, in FIG. 10, the circles, triangles, and stars shown in the shortened image signature 1045 may represent regions of different colors. The patterns represented by the circles, triangles, and stars may be stored in the sparse map 800, for example, within 50 bytes as specified to include an image signature. In particular, the circles, triangles, and stars do not necessarily mean that such shapes are stored as part of the image signature. Rather, these shapes are intended to conceptually represent recognizable regions having other variations of distinguishable color differences, texture regions, graphic shapes, or characteristics associated with general labels. Using such a shortened image signature, landmarks can be identified in the form of general labels. For example, using the shortened image signature, an identification analysis can be performed based on a comparison between the stored shortened image signature and, for example, image data captured using a camera mounted on an autonomous vehicle.

[0248] Accordingly, a plurality of landmarks may be identified by image analysis of a plurality of images acquired as one or more vehicles traverse a road segment. As will be described below with respect to "crowdsourcing", in some embodiments, the image analysis for identifying a plurality of landmarks 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. Further, in some embodiments, the image analysis for identifying a plurality of landmarks may include excluding 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.

[0249] When the host vehicle returns to a target trajectory that can be used to navigate a particular road segment, FIG. 11A shows a polynomial representation of the trajectory captured in the process of constructing or maintaining the sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 may be determined based on two or more reconstructed trajectories regarding previous traversals of vehicles along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be an aggregate of two or more reconstructed trajectories regarding previous traversals of vehicles along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be an average of two or more reconstructed trajectories regarding previous traversals of vehicles along the same road segment. Other mathematical operations may also be used to construct a target trajectory along a road route based on reconstructed trajectories collected from vehicles traversing along a road segment.

[0250] As shown in FIG. 11A, in road segment 1100, multiple vehicles 200 may travel at different times. Each vehicle 200 may collect data related to the route that the vehicle has traveled along the road segment. The route that a particular vehicle travels may be determined based on, among other possible sources of information, camera data, accelerometer information, speed sensor information, and / or GPS information. Using such data, the trajectories of the vehicles traveling along the road segment can be reconstructed, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) can be determined for a particular road segment. Such a target trajectory may represent the preferred route of the vehicle (e.g., guided by an automatic navigation system) when the host vehicle travels along the road segment.

[0251] In the example shown in FIG. 11A, a first reconstructed trajectory 1101 may be determined based on data received from a first vehicle passing through road segment 1100 during a first period (e.g., day of the week 1), a second reconstructed trajectory 1102 may be obtained from a second vehicle passing through road segment 1100 during a second period (e.g., day of the week 2), and a third reconstructed trajectory 1103 may be obtained from a third vehicle passing through road segment 1100 during a third period (e.g., day of the week 3). Each of the trajectories 1101, 1102, and 1103 may be represented by a polynomial such as a three-dimensional polynomial. Note that in some embodiments, any of the reconstructed trajectories may be compiled within a vehicle passing through road segment 1100.

[0252] Furthermore, or alternatively, such a reconstructed trajectory may be determined on the server side based on information received from vehicles passing through road segment 1100. For example, in some embodiments, vehicle 200 may transmit data related to the movement of the vehicle along road segment 1100 (e.g., in particular, steering angle, direction of travel, time, position, speed, detected road geometry, and / or detected landmarks) to one or more servers. The server may reconstruct the trajectory of vehicle 200 based on the received data. The server may also generate a target trajectory for guiding the navigation of an autonomous vehicle traveling along the same road segment 1100 later, based on the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. The target trajectory may be associated with a single previous passage of the road segment, but in some embodiments, each target trajectory included in the sparse map 800 may be determined based on two or more reconstructed trajectories of vehicles passing through 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 the average of the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 may be a collection (e.g., a weighted combination) of two or more reconstructed trajectories.

[0253] In the mapping server, the server may receive actual trajectories for a specific road segment from a plurality of collection vehicles passing through the road segment. The received actual trajectories may be aligned to generate target trajectories for each available route along the road segment (e.g., each lane, each driving direction, each route passing through an intersection, etc.). The alignment process may include using detected objects / features identified along the road segment, along with the collected positions of those detected objects / features, to associate the actually collected trajectories with each other. Once aligned, an average or "best fit" target trajectory for each available lane, etc., may be aggregated and determined based on the associated / aligned actual trajectories.

[0254] Figures 11B and 11C further illustrate the concept of target trajectories associated with road segments existing in the geographical area 1111. As shown in Figure 11B, the first road segment 1120 within the geographical area 1111 may include a multi-lane road, which includes two lanes 1122 designated for vehicle travel in the first direction and two additional lanes 1124 designated for vehicle travel in the second direction opposite to the first direction. Lanes 1122 and 1124 may be separated by a double yellow line 1123. The geographical area 1111 may also include a branch road segment 1130 intersecting the road segment 1120. The road segment 1130 may include a two-lane road, with each lane designated for travel in a different direction. The geographical area 1111 may also include other road features, such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0255] As shown in FIG. 11C, the sparse map 800 may include a local map 1140 that includes a road model for assisting vehicles within the geographical area 1111 with automatic navigation. For example, the local map 1140 may include target trajectories of one or more lanes associated with road segments 1120 and / or 1130 within the geographical area 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that are accessible or available when the autonomous vehicle passes through lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that are accessible or available when the autonomous vehicle passes through lane 1124. Further, the local map 1140 may include target trajectories 1145 and / or 1146 that are accessible or available when the autonomous vehicle passes through road segment 1130. The target trajectory 1147 may represent a preferred route to proceed when the autonomous vehicle transitions from lane 1120 (specifically, corresponding to the target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (specifically, corresponding to the target trajectory 1145 associated with the first side of road segment 1130). Similarly, the target trajectory 1148 represents a preferred route to proceed when the autonomous vehicle transitions from road segment 1130 (specifically, corresponding to the target trajectory 1146) to a portion of road segment 1124 (specifically, corresponding to the target trajectory 1143 associated with the left lane of lane 1124 as shown).

[0256] 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 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 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 the current position of the vehicle relative to any of the shown target trajectories. Thereby, the vehicle can adjust its traveling direction to match the direction of the target trajectory at its determined position.

[0257] In some embodiments, the sparse map 800 may also include a road signature profile. Such a road signature profile may be associated with any distinguishable / measurable change in at least one parameter related to the road. For example, in some cases, such a profile may be associated with changes in road surface information, such as changes in road surface unevenness of a particular road segment, changes in road width of an entire particular road segment, changes in the distance between dashed lines painted along a particular road segment, changes in road curvature along a particular road segment, and the like. FIG. 11D shows an example of a road signature profile 1160. The profile 1160 may represent any of the parameters described above, but in one example, the profile 1160 may represent measured values of road surface unevenness obtained by monitoring one or more sensors that provide an output indicating the amount of suspension displacement when the vehicle travels on a particular road segment.

[0258] Alternatively, or simultaneously, profile 1160 may represent a change in road width, which is identified based on image data obtained by a camera mounted on a vehicle traveling on a particular road segment. Such a profile may be useful, for example, in determining a particular position of an autonomous vehicle relative to a particular target trajectory. That is, when an autonomous vehicle traverses a road segment, it may measure a profile related to one or more parameters associated with the road segment. If the measured profile can be associated with / match a predetermined profile that plots the change in parameters with respect to the position along the road segment, then the measured profile and the predetermined profile may be used (e.g., by overlaying corresponding portions of the measured profile and the predetermined profile) to determine the current position along the road segment and thus the current position relative to the target trajectory of the road segment.

[0259] In some embodiments, sparse map 800 may include various trajectories based on various characteristics associated with a user of the autonomous vehicle, environmental conditions, and / or other parameters related to driving. For example, in some embodiments, various trajectories may be generated based on various user preferences and / or profiles. A sparse map 800 including such various trajectories may be provided to various autonomous vehicles of various 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 there is a toll road on the route. The disclosed system may generate various sparse maps having various trajectories based on such various user preferences or profiles. As another example, some users may prefer to drive in the high-speed lane, while other users may prefer to always keep their position in the middle lane.

[0260] Various trajectories may be generated based on various environmental conditions such as snow, rain, fog, etc. during the day and at night and may be included in the sparse map 800. An autonomous vehicle traveling under various environmental conditions may be provided with the sparse map 800 generated based on such various environmental conditions. In some embodiments, a camera provided on the autonomous vehicle may detect the environmental conditions and provide such information back to a server that generates and provides the sparse map. For example, the server may generate the sparse map 800 to include trajectories that may be less suitable or safe for autonomous driving under the detected environmental conditions, or may update the already generated sparse map 800. The update of the sparse map 800 based on the environmental conditions may be performed dynamically when the autonomous vehicle is traveling along the road.

[0261] Various other parameters related to driving may also be used as a basis for generating various sparse maps and providing this to various autonomous vehicles. For example, when an autonomous vehicle is traveling at high speed, turns may become tighter. When an autonomous vehicle is proceeding along a particular trajectory, a trajectory associated with a particular lane rather than the road may be included in the sparse map 800 so that the vehicle can maintain a particular lane. When an image captured by a camera mounted on the autonomous vehicle indicates that the vehicle has moved out of a lane (e.g., crossed a lane marking), an operation to return the vehicle to the designated lane according to a particular trajectory may be activated within the vehicle.

[0262] [Cloud Sourcing of Sparse Map]

[0263] The disclosed sparse maps may be efficiently (and passively) generated by the power of crowdsourcing. For example, any passenger or commercial vehicle equipped with a camera (e.g., a simple low-resolution camera that is routinely included as an OEM device in current vehicles), and an appropriate image analysis processor can serve as a collection vehicle. No special equipment (e.g., high-resolution imaging and / or positioning systems) is required. As a result of the disclosed crowdsourcing approach, the generated sparse maps can be extremely accurate and can include extremely fine-tuned position information (enabling navigation error limits of 10 cm or less) without requiring any special-purpose imaging or sensing devices as inputs to the map generation process. Since the mapping server system can always utilize new drive information from any road traveled by a passenger or commercial vehicle minimally equipped to also serve as a collection vehicle, crowdsourcing also enables much faster (and less expensive) updates to the generated map. The designated vehicles do not need to be equipped with high-resolution imaging and mapping sensors. Thus, the costs associated with building such special-purpose vehicles can be avoided. Further, updates to the currently disclosed sparse maps can be done much faster than systems that utilize dedicated special-purpose mapping vehicles (which, due to their cost and special equipment, are typically limited to a fleet of special-purpose vehicles that is much smaller than the number of passenger or commercial vehicles already available to perform the disclosed collection methods).

[0264] The disclosed sparse map generated by crowdsourcing can be highly accurate as it can be generated based on multiple inputs from a plurality of (dozens, hundreds, millions, etc.) collection vehicles having drive information collected along a particular road segment. For example, for each collection vehicle driving along a particular road segment, its actual trajectory may be recorded and the location information related to the objects / features detected along the road segment may be identified. This information is passed from the plurality of collection vehicles to a server. The actual trajectories are aggregated and a target trajectory fine-tuned for each valid driving route along the road segment is generated. Further, the location information of each of the (semantic or non-semantic) objects / features detected along the road segment, collected from the plurality of collection vehicles, can also be aggregated. As a result, the mapped locations of each detected object / feature may constitute the average of hundreds, thousands or millions of locations individually identified for each detected object / feature. Such an approach can result in highly accurately mapped locations for the detected objects / features.

[0265] In some embodiments, the disclosed systems and methods may generate a sparse map for autonomous vehicle navigation. For example, the disclosed systems and methods may use crowdsourced data in generating a sparse map that can be used for navigating one or more autonomous vehicles along a road of a system. As used herein, "crowdsourcing" means receiving data from various vehicles (e.g., autonomous vehicles) traveling on a certain road segment at different times, and such data is used to generate and / or update a road model including sparse map tiles. This model, or any of its multiple sparse map tiles, may then be transmitted to the vehicle or other vehicles that will later travel along the road segment to assist in autonomous vehicle navigation. The road model may include a plurality of target trajectories representing preferred trajectories for an autonomous vehicle to follow when passing through a certain road segment. These target trajectories may be the same as those reconstructed from the actual trajectories collected from vehicles passing through the road segment, and the collected actual trajectories may be transmitted from the vehicle to the server. In some embodiments, the target trajectories may be different from the actual trajectories previously traveled when one or more vehicles passed through the road segment. The target trajectories may be generated based on the actual trajectories (e.g., by averaging or any other suitable operation).

[0266] The vehicle trajectory data that a vehicle can upload to the server may correspond to the actual reconstructed trajectory of the vehicle or to a recommended trajectory. The recommended trajectory may be based on or related to the actual reconstructed trajectory of the vehicle, but may be different from the actual reconstructed trajectory. For example, the vehicle may change its actual reconstructed trajectory and submit (e.g., recommend) the changed actual trajectory to the server. The road model may use the recommended changed trajectory as a target trajectory for the autonomous navigation of other vehicles.

[0267] In addition to the trajectory information, other information that may be used when constructing the sparse data map 800 may include information related to potential landmark candidates. For example, through cloud sourcing of information, the disclosed systems and methods can identify potential landmarks in the environment and fine-tune the positions of the landmarks. These landmarks may be used for an autonomous vehicle's navigation system to determine and / or adjust the position of the vehicle along a target trajectory.

[0268] The reconstructed trajectory that the vehicle may generate when traveling along a road may be obtained in any suitable manner. In some embodiments, for example, by using ego-motion estimation (e.g., 3D translation and 3D rotation of a camera and thus the vehicle body), multiple parts of the vehicle's movement can be connected together to develop the reconstructed trajectory. The estimation of rotation and translation may be determined based on the result of analyzing images captured by one or more image capture devices together with information from other sensors or devices (such as inertial sensors and speed sensors). For example, the inertial sensor may include an accelerometer or other suitable sensor configured to measure changes in the vehicle body's translation and / or rotation. The vehicle may include a speed sensor for measuring the speed of the vehicle.

[0269] In some embodiments, the ego-motion of the camera (and thus the vehicle body) may be estimated based on optical flow analysis of the captured images. In the optical flow analysis of a series of images, the movement of the pixels in the series of images is identified, and based on the identified movement, the movement of the vehicle is specified. The ego-motion may be accumulated along the road segment over time to reconstruct a trajectory associated with the road segment that the vehicle has traveled.

[0270] Data (e.g., reconstructed trajectories) collected by multiple vehicles during multiple drives at different times along a road segment may be used to construct a road model (e.g., including a target trajectory, etc.) included in the sparse data map 800. Data collected by multiple vehicles during multiple drives at different times along a road segment may be averaged to improve the accuracy of the model. In some embodiments, data regarding the geometry of the road and / or landmarks may be received from multiple vehicles passing through a common road segment at different times. Such data received from different vehicles may be combined for generating and / or updating the road model.

[0271] The geometry of the reconstructed trajectory along the road segment (as well as the geometry of the target trajectory) may be represented by a curve in three-dimensional space, and this curve may be a spline connecting three-dimensional polynomials. The curve of the reconstructed trajectory may be obtained from the analysis of a video stream or multiple images captured by a camera installed in the vehicle. In some embodiments, the position is identified in each frame or image several meters ahead of the current position of the vehicle. This position is where the vehicle is expected to travel after a predetermined period. This operation may be repeated for each frame, and at the same time, the vehicle may calculate the ego motion (rotation and translation) of the camera. In each frame or image, a short-distance model of the desired path is generated by the vehicle within a reference frame attached to the camera. Multiple short-distance models may be joined together to obtain a three-dimensional model of the road in some coordinate frame, and this coordinate frame may be any coordinate frame or a predetermined coordinate frame. The three-dimensional model of the road may then be fitted to a spline, and this spline may include one or more polynomials of a suitable degree or connect these polynomials.

[0272] To complete the short - distance road model in each frame, one or more detection modules may be used. For example, a bottom - up lane detection module may be used. The bottom - up lane detection module can be useful when lane markings are drawn on the road. This module may search for edges in the image and compile these edges together 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, and this deep neural network may be trained to predict an accurate short - distance route from the input image. In either module, the road model may be detected in the image coordinate frame and converted to a three - dimensional space that can be virtually attached to the camera.

[0273] In the method of modeling the reconstructed trajectory, the accumulation of long - term ego - motion may result in the accumulation of errors that may include noise components. However, such errors may not be important because the generated model may provide sufficient accuracy for navigation at the regional scale. Furthermore, it is possible to offset the accumulated error by using external information sources such as satellite images or geodetic surveys. For example, the disclosed systems and methods may use a GNSS receiver to offset the accumulated error. However, GNSS positioning signals may not always be available and accurate. The disclosed systems and methods may enable steering applications that are less 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 system may use GNSS signals only for the purpose of indexing a database.

[0274] In some embodiments, the distance range (e.g., regional scale) that may be suitable for a steering application of an autonomous vehicle navigation may be on the order of 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances may be used because the geometric road model is used mainly for two purposes: to pre-plan a trajectory and to identify the position of the vehicle with the road model. In some embodiments, the planning task may use a model over a typical range of 40 meters ahead (or any other suitable forward distance, e.g., 20 meters, 30 meters, 50 meters), and at this time the control algorithm steers the vehicle according to a target point located 1.3 seconds ahead (or any other time, e.g., 1.5 seconds, 1.7 seconds, 2 seconds, etc.). The position identification task uses a road model over a typical range of 60 meters behind the vehicle (or any other suitable distance, e.g., 50 meters, 100 meters, 150 meters, etc.) according to a method called "tail alignment" which will be described in more detail in another section. The disclosed system and method may generate a geometric model with sufficient accuracy over a specific range such as 100 meters so that the planned trajectory does not deviate more than 30 cm from the center of the lane, for example.

[0275] As described above, a 3D road model may be constructed by detecting short-distance portions and connecting them together. This connection may be made possible by calculating a six-stage ego-motion model using images and / or pictures captured by a camera, data from an inertial sensor reflecting the movement of the vehicle, and the speed signal of the host vehicle. The cumulative error may be small enough on the scale of a certain local range, such as on the order of 100 meters. All of this may be completed in one drive of a specific road segment.

[0276] In some embodiments, multiple drives may be used to average the resulting models to further improve accuracy. The same vehicle may drive the same route multiple times, or multiple vehicles may each transmit the model data they collected to a central server. In any case, a matching procedure may be performed so that overlapping models can be identified and averaged to generate a target trajectory. Once the constructed model (e.g., including the target trajectory) meets the convergence criteria, it may be used for steering. Subsequent drives may be used for further model improvement and to adapt to infrastructure changes.

[0277] Sharing of driving experiences (such as detection data) among multiple vehicles becomes possible when these vehicles are connected to a central server. Each vehicle client may store a partial copy of the general road model that may be related to its respective current position. A two-way update procedure between the vehicle and the server may be performed by the vehicle and the server. Due to the small footprint concept described above, the disclosed system and method can perform two-way updates using a very small bandwidth.

[0278] Information related to possible landmarks may also be identified and transferred to the central server. For example, the disclosed system and method may identify one or more physical characteristics of a possible landmark based on one or more images including the landmark. These 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 the landmark, the identification of text related to the landmark, etc. For example, the vehicle may analyze one or more images captured by a camera to detect possible landmarks such as speed limit signs.

[0279] The vehicle may determine the distance from the vehicle to a landmark or the position associated with a landmark (e.g., any semantic or non-semantic object or feature along a road segment) based on the analysis of one or more images. In some embodiments, this distance may be determined based on the analysis of the image of the landmark using a suitable image analysis method such as a scaling method and / or an optical flow method. As described above, the position of the object / feature may include the 2D image position of one or more points associated with the object / feature (e.g., the X-Y pixel position in one or more captured images), or may include the 3D actual position of one or more points (determined through the structure in a motion / optical flow approach, such as LIDAR or RADAR information). In some embodiments, the disclosed systems and methods may be configured to determine the possible type or classification of a landmark. If the vehicle determines that a particular possible 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 type or classification of the landmark to the server along with the position of the landmark. The server may store such an indication. Later, during navigation, the navigating vehicle may capture an image containing a representation of this landmark, process the image (e.g., using a classifier), and compare the resulting landmark to verify the detection of the mapped landmark and to use the mapped landmark when identifying the position of the navigating vehicle relative to the sparse map.

[0280] In some embodiments, multiple autonomous vehicles traveling on a certain road segment may communicate with a server. The vehicle (or client) may generate a curve depicting the drive of the vehicle (e.g., by integration of ego motion) in an arbitrary coordinate frame. The vehicle may detect landmarks and place the landmarks in the same frame. The vehicle may upload the curve and the landmarks to the server. The server may collect data from multiple drives from the vehicles and generate an integrated road model. For example, as discussed below with respect to FIG. 19, the server may generate a sparse map with an integrated road model using the uploaded curves and landmarks.

[0281] The server may distribute this model to clients (e.g., vehicles). For example, the server may distribute the sparse map to one or more vehicles. When the server receives new data from a vehicle, the server may update the model always or periodically. For example, the server may process the new data and evaluate whether the data contains information that should trigger an update of the data or the creation of new data at the server. The server may distribute the updated model or update information to the vehicle to provide autonomous vehicle navigation.

[0282] The server may use one or more criteria to determine whether the new data received from the vehicle should trigger an update of the model or the creation of new data. For example, if the new data indicates that a landmark previously recognized at a specific location no longer exists or has been replaced by another landmark, the server may determine that the new data should trigger an update of the model. As another example, if the new data indicates that a certain road segment is closed and this is corroborated by data received from other vehicles, the server may determine that the new data should trigger an update of the model.

[0283] The server may distribute the updated model (or the updated part of the model) to one or more vehicles traveling on the road segment associated with the update of the model. The server may also distribute the updated model to vehicles that are scheduled to travel on the road segment associated with the update of the model, or vehicles for which the road segment is included in the vehicle's movement plan. For example, while an autonomous vehicle is traveling along another road segment before reaching a road segment associated with a certain update, the server may distribute the update information or the updated model to the autonomous vehicle before the vehicle reaches this road segment.

[0284] In some embodiments, the 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 road graph and the most likely route at each intersection or connection point of the road segment. For example, the remote server may align these trajectories to generate a sparse map by cloud-sourcing from the collected trajectories.

[0285] The server may average the characteristics of landmarks received from multiple vehicles traveling along a common road segment, such as the distance between a landmark and another landmark (e.g., the landmark immediately ahead along the road segment) measured by the multiple vehicles, to obtain an arc length parameter, and assist in position identification and speed calibration along the route for each client vehicle. The server may average the physical dimensions of landmarks measured by multiple vehicles traveling along a common road segment and recognizing the same landmarks. The averaged physical dimensions may be used to assist in distance estimation such as the distance from the vehicle to the landmark. The server may average the lateral position of a landmark (e.g., the position from the lane in which the vehicle is traveling to the landmark) measured by multiple vehicles traveling along a common road segment and recognizing the same landmarks. The averaged lateral position may be used to assist in lane designation. The server may average the GPS coordinates of a landmark measured by multiple vehicles traveling along the same road segment and recognizing the same landmarks. The averaged GPS coordinates of the landmark may be used to assist in broad position identification or positioning of the landmark in the road model.

[0286] In some embodiments, the server may identify changes to the model, such as construction, detours, new signs, sign removals, etc., based on data received from the vehicles. The server may update the model always or periodically or immediately when new data is received from the vehicles. The server may distribute the updated information or the updated model of the model to the vehicles to provide automatic navigation. For example, as further discussed below, the server may use crowd-sourced data to exclude "ghost" landmarks detected by the vehicles.

[0287] In some embodiments, the server may analyze the driver's intervention during autonomous driving. The server may analyze the data received from the vehicle at the time and location where the intervention occurred, and / or the data received before the time when the intervention occurred. The server may identify a certain portion of the data that caused or is closely related to the intervention, for example, data indicating a temporary lane closure setting, data indicating the presence of pedestrians on the road. The server may update the model based on the identified data. For example, the server may change one or more trajectories stored in the model.

[0288] FIG. 12 is a schematic diagram of a system that generates a sparse map using crowdsourcing (and distributes the sparse map by crowdsourcing and uses it for navigation). FIG. 12 shows a road segment 1200 including one or more lanes. A plurality of vehicles 1205, 1210, 1215, 1220, and 1225 (although shown in FIG. 12 as simultaneously appearing in the road segment 1200) may travel on the road segment 1200 either simultaneously or at different times. At least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. For the sake of simplicity of this example, it is assumed that all of the vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0289] Each vehicle may be similar to the vehicles disclosed in other embodiments (e.g., vehicle 200), and may include components or devices included in or related to the vehicles disclosed in other embodiments. Each vehicle may include an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle may communicate with a remote server 1230 via one or more networks (e.g., via a cellular network and / or the Internet, etc.) through a wireless communication path 1235 shown by a dashed line. Each vehicle may send data to the server 1230 and receive data from the server 1230. For example, the server 1230 may collect data from a plurality of vehicles traveling on a road segment 1200 at different times, process the collected data, and generate an autonomous vehicle-oriented road navigation model or an update to the model. The server 1230 may send the autonomous vehicle-oriented road navigation model or an update to the model to the vehicle that sent data to the server 1230. The server 1230 may send the autonomous vehicle-oriented road navigation model or an update to the model to other vehicles that will later travel on the road segment 1200.

[0290] When vehicles 1205, 1210, 1215, 1220, and 1225 travel on road segment 1200, navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 may be transmitted to server 1230. In some embodiments, the navigation information may be associated with a common road segment 1200. The navigation information may include a trajectory associated with each of vehicles 1205, 1210, 1215, 1220, and 1225 when each vehicle travels on road segment 1200. In some embodiments, the trajectory may be reconstructed based on data detected by various sensors and devices provided in vehicle 1205. For example, the trajectory may be reconstructed based on at least one of accelerometer data, speed data, landmark data, road geometry or profile data, vehicle positioning data, and ego-motion data. In some embodiments, the trajectory may be reconstructed based on data from an inertial sensor such as an accelerometer and the speed of vehicle 1205 detected by a speed sensor. Further, in some embodiments, the trajectory may be determined (e.g., by a processor mounted on each of vehicles 1205, 1210, 1215, 1220, and 1225) based on the detected ego-motion of a camera that may indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The ego-motion of the camera (and thus the vehicle body) may be identified from the analysis of one or more images captured by the camera.

[0291] In some embodiments, the trajectory of vehicle 1205 may be determined by a processor mounted on vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 may receive data detected by various sensors and devices provided in vehicle 1205 and determine a trajectory based on the data received from vehicle 1205.

[0292] In some embodiments, the 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 configuration and / or landmarks. The lane configuration may include the total number of lanes in road segment 1200, the type of lanes (e.g., one-way lanes, two-way lanes, driving lanes, passing lanes, etc.), markings on the lanes, the width of the lanes, and the like. In some embodiments, the navigation information may include lane designation, e.g., which of a plurality of lanes the vehicle will travel in. For example, the lane designation may be associated with a numerical value, where "3" indicates that the vehicle will travel in the third lane from the left or right. As another example, the lane designation may be associated with a text value, where "center lane" indicates that the vehicle will travel in the center lane.

[0293] Server 1230 may store the navigation information in a non-transitory computer-readable medium, such as a hard drive, compact disk, tape, memory, etc. Server 1230 may generate (e.g., by a processor included in server 1230) at least a part of a road navigation model for autonomous vehicles for a common road segment 1200 based on the navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225, and may store this model as part of a sparse map. Server 1230 may determine a trajectory associated with each lane based on crowdsourcing data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling in the lanes of the road segment at different times. Server 1230 may generate an autonomous vehicle road navigation model or a part of the model (e.g., an updated part) based on multiple trajectories determined based on crowdsourcing navigation data. Server 1230 may send the model or the updated part of the model to one or more of the autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or any other autonomous vehicle that will later travel on the road segment, in order to update an existing autonomous vehicle road navigation model provided to the navigation system of the vehicle. The autonomous vehicle road navigation model may be used when an autonomous vehicle autonomously navigates along the common road segment 1200.

[0294] As described above, the road navigation model for an autonomous vehicle may be included in a sparse map (e.g., the sparse map 800 shown in FIG. 8). The sparse map 800 may include a sparse record of data related to the geometric structure of the road and / or landmarks along the road, which can provide sufficient information to guide the autonomous navigation of the autonomous vehicle and, moreover, does not require excessive data storage. In some embodiments, the road navigation model for an autonomous vehicle may be stored separately from the sparse map 800 and may use the map data from the sparse map 800 when the model is executed for navigation. In some embodiments, the road navigation model for an autonomous vehicle may determine a target trajectory along the road segment 1200 using the map data included in the sparse map 800 to guide the autonomous navigation of the autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles that will later travel along the road segment 1200. For example, when the road navigation model for an autonomous vehicle is executed by a processor included in the navigation system of the vehicle 1205, the model may cause the processor to compare a trajectory determined based on the navigation information received from the vehicle 1205 with a predetermined trajectory included in the sparse map 800 to confirm and / or correct the current driving course of the vehicle 1205.

[0295] In a road navigation model for an autonomous vehicle, the geometric structure of a road feature or a target trajectory may be encoded by a curve in a three-dimensional space. In one embodiment, this curve may be a three-dimensional spline that includes one or more connected three-dimensional polynomials. As would be understood by those skilled in the art, a spline may be a numerical function that is defined piecewise by a series of polynomials for fitting data. Splines for fitting three-dimensional geometric structure data of a road may include linear splines (first order), quadratic splines (second order), cubic splines (third order), or any other splines (other orders), or a combination thereof. A spline may include one or more three-dimensional polynomials of various orders that connect (e.g., fit) data points of the three-dimensional geometric structure data of the road. In some embodiments, a road navigation model for an autonomous vehicle may include a three-dimensional spline corresponding to a common road segment (e.g., road segment 1200) or a target trajectory along a lane of road segment 1200.

[0296] As described above, the road navigation model for autonomous vehicles included in the sparse map may include other information, for example, identification information 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) installed in each of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 may capture an image of the landmark. A processor (e.g., processor 180, 190, or processing unit 110) provided in vehicle 1205 may process the image of the landmark to extract the identification information of the landmark. Rather than the actual image of the landmark, the identification information of the landmark may be stored in sparse map 800. The identification information of the landmark may require much less storage space than the actual image. Other sensors or systems (e.g., GPS system) may also provide specific identification information of the landmark (e.g., the location of the landmark). The landmark may include at least one of traffic signs, arrow markings, lane markings, broken-line lane markings, traffic lights, stop lines, direction signs (e.g., highway exit signs with arrows indicating directions, highway signs with arrows pointing to another direction or location), landmark beacons, or street light poles. 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. When the vehicle passes by this device, the beacon received by the vehicle and the location of the device (e.g., determined from the GPS location of the device) may be used as a landmark to be included in the road navigation model for autonomous vehicles and / or sparse map 800.

[0297] The identification information of at least one landmark may include the position of at least one landmark. The position of the landmark may be determined based on a positioning method performed using sensor systems (e.g., a global positioning system, an inertia-based positioning system, a landmark beacon, etc.) associated with a plurality of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the position of the landmark may be determined by averaging position measurements detected, collected, or received by the sensor systems of different vehicles 1205, 1210, 1215, 1220, and 1225 over a plurality of drives. For example, vehicles 1205, 1210, 1215, 1220, and 1225 may transmit data of the position measurements to server 1230, and the server may average the position measurements and use the averaged position measurements as the position of the landmark. The position of the landmark may be constantly fine-tuned by measurements received from the vehicle during subsequent drives.

[0298] The identification information of a landmark may include the size of the landmark. A processor provided in a vehicle (e.g., 1205) may estimate the physical size of the landmark based on the analysis of an image. The server 1230 may receive a plurality of estimated values regarding the physical size of the same landmark from different vehicles driven by different drivers. The server 1230 may average the various estimated values to arrive at the physical size of the landmark and store the size of the landmark in the road model. The estimated values of the physical size may further be used to determine or estimate the distance from the vehicle to the landmark. The distance to the landmark may be estimated based on the current speed of the vehicle and the extended scale based on the position of the landmark appearing in the image with respect to the extended focus of the camera. For example, the distance to the landmark may be estimated by Z = V×dt×R / D, where V is the speed of the vehicle, R is the distance in the image from the landmark to the extended focus at time t1, D is the change in the distance for the landmark in the image from t1 to t2, and dt represents (t2 - t1). For example, the distance to the landmark may be estimated by Z = V×dt×R / D, where V is the speed of the vehicle, R is the distance in the image between the landmark and the extended focus, dt is the time interval, and D is the image displacement of the landmark along the epipolar line. Other equations equivalent to the above equation, such as Z = V×ω / Δω, may be used to estimate the distance to the landmark. Here, V is the vehicle speed, ω is the image length (such as the object width), and Δω is the change in the image length per unit time.

[0299] When the physical size of the landmark is known, the distance to the landmark may also be determined based on the following equation, Z = f×W / ω. Here, f is the focal length, W is the size of the landmark (e.g., height or width), and ω is the number of pixels when the landmark leaves the image. From the above equation, the change in the distance Z is ΔZ = f×W×Δω / ω 2It may be calculated using +f×ΔW / ω. Here, ΔW decays to zero by averaging, and Δω is the number of pixels representing the bounding box accuracy of the image. The value for estimating the physical size of the landmark may be calculated by averaging a plurality of observation results on the server side. The error resulting from distance estimation can be very small. There are two sources of error that may occur when using the above formula. That is, ΔW and Δω. The respective contributions to the distance error are ΔZ = f×W×Δω / ω 2 given by +f×ΔW / ω. However, since ΔW decays to zero by averaging, ΔZ is determined by Δω (e.g., the inaccuracy of the image's bounding box).

[0300] In the case of a landmark of unknown dimensions, the distance to the landmark may be estimated by tracking feature points on the landmark over consecutive frames. For example, specific features appearing on a speed limit sign may be tracked over two or more image frames. Based on these tracked features, a distribution of distances for each feature point may be generated. The 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 average of the distance distribution may be used as the distance estimate.

[0301] FIG. 13 shows an exemplary road navigation model for an autonomous vehicle represented by a plurality of 3D 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 3D polynomials connecting a plurality of data points 1310. Each polynomial may be a first-degree polynomial, a second-degree polynomial, a third-degree polynomial, or any suitable combination of polynomials having different degrees. 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 a landmark (e.g., size, location, and identification information of the landmark) and / or a road signature profile (e.g., road geometry, road bump profile, road curvature profile, road width profile). In some embodiments, some of the data points 1310 may be associated with data related to landmark-associated data and some may be associated with data related to road-signature-profile-associated data.

[0302] FIG. 14 shows the raw position data 1410 (e.g., GPS data) received from five separate drives. A drive may be separated from another drive if separate vehicles pass simultaneously, if the same vehicle passes at different times, or if separate vehicles pass at different times. To account for errors in the position data 1410 and the different positions of multiple vehicles within the same lane (e.g., one vehicle may be driving closer to the left side of the lane than another vehicle), the server 1230 may generate a map framework 1420 using one or more statistical techniques and determine whether changes in the raw position data 1410 represent actual differences or statistical errors. Each path included in the map framework 1420 may be newly associated with the raw data 1410 that formed that path. For example, the path between A and B included in the map framework 1420 is associated with the raw data 1410 from drives 2, 3, 4, and 5 but not with the raw data from drive 1. The framework 1420 may not be as detailed as would be used for vehicle navigation (e.g., to combine drives from multiple lanes of the same road), but it can provide useful topological information and can be used to define intersections.

[0303] FIG. 15 shows an example in which further details can be generated for the sparse map included in the segments of the map framework (e.g., segments A - B included in the framework 1420). As shown in FIG. 15, data (e.g., ego - motion data, road - sign data, etc.) may be shown according to the position S (or S1 or S2) along the drive. The server 1230 may identify landmarks for the sparse map by identifying unique matches between the landmarks 1501, 1503, and 1505 of the drive 1510 and the landmarks 1507 and 1509 of the drive 1520. Such a matching algorithm may result in the identification of landmarks 1511, 1513, and 1515. However, one of ordinary skill in the art will recognize that other matching algorithms may be used. For example, instead of, or in combination with, unique matches, probability optimization may be used. The server 1230 may align each drive longitudinally and align the matched landmarks. For example, the server 1230 may select one drive (e.g., drive 1520) as a reference drive and then move and / or elastically stretch one or more other drives (e.g., drive 1510) to align them.

[0304] FIG. 16 shows an example in which landmark data is aligned for use in a sparse map. In the example of FIG. 16, landmark 1610 includes road signs. The example of FIG. 16 further shows data from a plurality of drives 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the example of FIG. 16, the data from drive 1613 is composed of “ghost” landmarks, and server 1230 may identify this data as such. Because none of drives 1601, 1603, 1605, 1607, 1609, and 1611 include landmark identification information near the landmarks identified by drive 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.

[0305] FIG. 17 shows a system 1700 for generating drive data that can be used to crowdsource a sparse map. As shown in FIG. 17, system 1700 may include a camera 1701 and a location device 1703 (e.g., a GPS locator). Camera 1701 and location device 1703 may be attached to a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). Camera 1701 may generate multiple types of data, such as ego-motion data, traffic sign data, or road data. The camera data and location data may be divided into a plurality of drive segments 1705. For example, each of the plurality of drive segments 1705 may have camera data and location data from a drive of less than 1 km.

[0306] In some embodiments, system 1700 may remove the redundancy of drive segment 1705. For example, if a landmark appears in multiple images from camera 1701, system 1700 may remove redundant data such that drive segment 1705 contains only one instance of the position of the landmark and any metadata associated with the landmark. As a further example, if lane markings appear in multiple images from camera 1701, system 1700 may remove redundant data such that drive segment 1705 contains only one instance of the position of the lane markings and any metadata associated with the lane markings.

[0307] System 1700 also includes a server (e.g., server 1230). Server 1230 may receive drive segments 1705 from the vehicle and recombine these drive segments 1705 into one drive 1707. In such a manner, it is possible to reduce the bandwidth requirements when transferring data between the vehicle and the server, and it may also be possible for the server to store data related to the entire drive.

[0308] FIG. 18 shows system 1700 of FIG. 17 further configured to crowdsource a sparse map. As in FIG. 17, system 1700 includes vehicle 1810, which captures drive data using, for example, a camera (which generates, for example, egomotion data, traffic sign data, or road data) and a positioning device (e.g., a GPS locator). As in FIG. 17, vehicle 1810 divides the collected data into a plurality of drive segments (shown as "DS1 1", "DS2 1", "DSN 1" in FIG. 18). Server 1230 then receives the drive segments and reconstructs one drive (shown as "Drive 1" in FIG. 18) from these received segments.

[0309] As further shown in FIG. 18, system 1700 also receives data from additional vehicles. For example, vehicle 1820 also captures drive data using, for example, cameras (which generate, for example, ego motion data, traffic sign data, or road data) and location devices (e.g., GPS locators). Similar to vehicle 1810, vehicle 1820 divides the collected data into a plurality of drive segments (shown as "DS1 2", "DS2 2", "DSN 2" in FIG. 18). Server 1230 then receives the drive segments and reconstructs one drive (shown as "Drive 2" in FIG. 18) from these received segments. Any number of additional vehicles may be used. For example, FIG. 18 also includes vehicle N, which captures drive data, divides the data into a plurality of drive segments (shown as "DS1 N", "DS2 N", "DSN N" in FIG. 18), and transmits these to server 1230 for reconstruction into one drive (shown as "Drive N" in FIG. 18).

[0310] As shown in FIG. 18, server 1230 may construct a sparse map (shown as "Map") using the reconstructed drives (e.g., "Drive 1", "Drive 2", and "Drive N") collected from a plurality of vehicles (e.g., "Automobile 1" (also shown as vehicle 1810), "Automobile 2" (also shown as vehicle 1820), and "Automobile N").

[0311] FIG. 19 is a flowchart showing an exemplary 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.

[0312] Process 1900 may include a step (step 1905) of receiving a plurality of images acquired when one or more vehicles pass through a road segment. Server 1230 may receive images from a camera included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 may capture one or more images regarding the environment surrounding vehicle 1205 when vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 may also receive, as described above with respect to FIG. 17, image data excluding the redundant parts and with redundancy removed by a processor mounted on vehicle 1205.

[0313] Process 1900 may further include a step (step 1910) of identifying at least one line representation of a road surface feature extending along the road segment based on the plurality of images. 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 image received from camera 122, identify a road edge or lane marking, and determine a trajectory of travel along road segment 1200 associated with the road edge or lane marking. In some embodiments, the trajectory (or line representation) may include a spline, polynomial representation, or curve. Server 1230 may determine the trajectory of travel of vehicle 1205 based on the ego-motion of the camera (e.g., three-dimensional translational motion and / or three-dimensional rotational motion) received in step 1905.

[0314] Process 1900 may also include a step (step 1915) of identifying a plurality of landmarks associated with a road segment based on a plurality of images. For example, server 1230 may analyze the environmental images received from camera 122 and identify one or more landmarks such as road signs along road segment 1200. Server 1230 may identify the landmarks using the analysis of a plurality of images acquired when one or more vehicles pass through the road segment. To enable crowdsourcing, the analysis may include rules regarding accepting and rejecting potential landmarks related to the road segment. For example, the analysis may include a step of accepting a potential landmark if the ratio of the images in which the landmark appears to the images in which the landmark does not appear exceeds a threshold, and / or a step of rejecting a potential landmark if the ratio of the images in which the landmark does not appear to the images in which the landmark appears exceeds a threshold.

[0315] 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 a step of server 1230 clustering vehicle trajectories related to a plurality of vehicles traveling on the road segment and determining a target trajectory based on the clustered vehicle trajectories, as discussed in more detail below. The step of clustering vehicle trajectories may include server 1230 clustering a plurality of trajectories related to vehicles traveling on the road segment into a plurality of clusters based on at least one of the absolute traveling direction of the vehicle or the lane designation of the vehicle. The step of generating a target trajectory may include server 1230 averaging the clustered trajectories. As a further example, process 1900 may include a step of aligning the data received in step 1905. Other processes or steps performed by server 1230 may also be included in process 1900 as described above.

[0316] 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 represent data in world coordinates. For example, coordinates based on the longitude and latitude of the earth's surface may be used. The host vehicle may determine its position and orientation relative to the map for use in maneuvering the map. To position the vehicle on the map and to determine the rotational transformation between the body reference frame and the world reference frame (e.g., north, east, and south), it seems natural to use the onboard GPS device. Once the body reference frame is aligned with the map reference frame, the desired route can then be represented in the body reference frame, and steering commands can be calculated or generated.

[0317] The disclosed systems and methods may enable autonomous vehicle navigation (e.g., steering control) using a low footprint model, which may be collected by the autonomous vehicle itself without the aid of expensive surveying equipment. To assist in autonomous navigation (e.g., steering applications), the road model may include a sparse map having the geometric structure of the road, its lane configuration, and landmarks that can be used to determine the position or positions of the vehicle along the trajectory included in the model. As described above, the generation of the sparse map may be performed by a remote server that communicates with and receives data from vehicles traveling on the road. This data may include sensed data, trajectories reconstructed based on the sensed data, and / or recommended trajectories that may represent changes to the reconstructed trajectories. As discussed below, the server may retransmit the model to the vehicle or other vehicles that will later travel on the road for use in autonomous navigation.

[0318] FIG. 20 shows a block diagram of server 1230. Server 1230 may include a communication unit 2005, which may include both hardware components (e.g., communication control circuits, switches, and antennas) and software components (e.g., communication protocols, computer code). For example, communication unit 2005 may include at least one network interface. Server 1230 may communicate with vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. For example, server 1230 may receive navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. Server 1230 may distribute an autonomous vehicle road navigation model to one or more autonomous vehicles via communication unit 2005.

[0319] Server 1230 may include at least one non-transitory storage medium 2010, such as a hard drive, compact disk, tape, etc. Storage device 1410 may be configured to store data such as navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225, and / or an autonomous vehicle road navigation model generated by server 1230 based on the navigation information. Storage device 2010 may be configured to store any other information, such as a sparse map (e.g., sparse map 800 described above with respect to FIG. 8).

[0320] In addition to, or instead of, the storage device 2010, the server 1230 may include a memory 2015. The memory 2015 may be the same as, or different from, the memories 140 or 150. The memory 2015 may be a non-transitory memory such as flash memory, random access memory, etc. The memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., processor 2020), map data (e.g., data of the sparse map 800), a road navigation model for an autonomous vehicle, and / or navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225.

[0321] The server 1230 may include at least one processing device 2020 configured to perform various functions by executing computer code or instructions stored in the memory 2015. For example, the processing device 2020 may analyze navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225 and generate a road navigation model for an autonomous vehicle based on this analysis. The processing device 2020 may control the communication unit 1405 to distribute the road navigation model for an autonomous vehicle to one or more autonomous vehicles (e.g., one or more of the vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicle that will later travel on the road segment 1200). The processing device 2020 may be the same as, or different from, the processors 180, 190, or the processing unit 110.

[0322] FIG. 21 shows a block diagram of a memory 2015, which may store computer code or instructions for performing one or more operations to generate a road navigation model for use in autonomous vehicle navigation. As shown in FIG. 21, the memory 2015 may store one or more modules for performing operations to process vehicle navigation information. For example, the memory 2015 may include a model generation module 2105 and a model distribution module 2110. A processor 2020 may execute instructions stored in either of the modules 2105 and 2110 included in the memory 2015.

[0323] The model generation module 2105 may store instructions that, when executed by the processor 2020, may generate at least a portion of a road navigation model for an autonomous vehicle for a common road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, when generating a road navigation model for an autonomous vehicle, the processor 2020 may cluster vehicle trajectories along the common road segment 1200 into various clusters. The processor 2020 may determine a target trajectory along the common road segment 1200 based on the clustered vehicle trajectories of each of the various clusters. Such operations may include, in each cluster, determining an average trajectory of the clustered vehicle trajectories (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.

[0324] A road model and / or a sparse map may store trajectories associated with road segments. These trajectories, which may be called target trajectories, are provided to an 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 always be updated (e.g., averaged) using new trajectories received from other vehicles.

[0325] A vehicle traveling on a road segment may collect data with various sensors. The data may include landmarks, road signature profiles, vehicle movement (e.g., accelerometer data, speed data), vehicle position (e.g., GPS data), and may either reconstruct the actual trajectory itself or send the data to a server, which will reconstruct the actual trajectory for the vehicle. In some embodiments, the vehicle may send data related to a trajectory (e.g., a curve in any reference frame), landmark data, and lane designations along the driving route to server 1230. Various vehicles traveling on multiple drives along the same road segment may have separate trajectories. Server 1230 may identify routes or trajectories associated with each lane from the trajectories received from vehicles through a clustering process.

[0326] Figure 22 shows a process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine a target trajectory of a common road segment (e.g., road segment 1200). The target trajectory or target trajectories determined from the clustering process may be included in an autonomous vehicle road navigation model or a sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 may transmit a plurality of trajectories 2200 to server 1230. In some embodiments, server 1230 may generate trajectories based on landmarks, road geometry, and vehicle movement information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate an autonomous vehicle road navigation model, server 1230 may cluster vehicle trajectories 1600 into a plurality of clusters 2205, 2210, 2215, 2220, 2225, and 2230 as shown in Figure 22.

[0327] Clustering may be performed using various criteria. In some embodiments, all drives included in a cluster may be similar with respect to the absolute direction of travel along road segment 1200. The absolute direction of travel may be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the absolute direction of travel may be obtained using dead reckoning. Dead reckoning, as would be understood by one of ordinary skill in the art, may be used to determine the current position and thus the direction of travel of vehicles 1205, 1210, 1215, 1220, and 1225 using previously determined positions, estimated speeds, and the like. Trajectories clustered by the absolute direction of travel may help identify routes along the lanes.

[0328] In some embodiments, all of the drives included in a cluster may be similar with respect to lane designations (e.g., the same lane before and after an intersection) along the drive of the road segment 1200. The trajectories clustered by lane designation may help to identify the lanes along the roadway. In some embodiments, both criteria (e.g., absolute direction of travel and lane designation) may be used for clustering.

[0329] In each of the clusters 2205, 2210, 2215, 2220, 2225, and 2230, these trajectories may be averaged to obtain a target trajectory associated with a particular cluster. For example, trajectories from multiple drives associated with the same lane cluster may be averaged. The averaged trajectory may be a target trajectory associated with a particular lane. To average the trajectories of a cluster, the server 1230 may select a reference frame for any one of the trajectories C0. For all of the other trajectories (C1, …, Cn), the server 1230 may determine a rigid transformation that maps Ci to C0. Here, i = 1, 2, …, n, and n is a positive integer corresponding to the total number of trajectories included in the cluster. The server 1230 may calculate an average curve or trajectory in the C0 reference frame.

[0330] In some embodiments, landmarks may define matching arc lengths between different drives, which may be used to align the trajectories and lanes. In some embodiments, lane markings before and after an intersection may be used to align the trajectories and lanes.

[0331] To compose lanes from these trajectories, the server 1230 may select a reference frame for any one of the lanes. The server 1230 may map the partially overlapping lanes to the selected reference frame. The server 1230 may continue the mapping until all of the lanes are in the same reference frame. Adjacent lanes may be aligned as if they were the same lane, and later shifted horizontally.

[0332] Landmarks recognized along a road segment may first be mapped to a common reference frame at the lane level and then at the intersection level. For example, the same landmark may be recognized multiple times by multiple vehicles in multiple drives. Data regarding the same landmark received in different drives may be slightly different. Such data may be averaged and mapped to the same reference frame, such as a C0 reference frame. Additionally or alternatively, the variance of data for the same landmark received in multiple drives may be calculated.

[0333] In some embodiments, each lane of road segment 120 may be associated with a target trajectory and specific landmarks. This target trajectory or such target trajectories may be included in a road navigation model for an autonomous vehicle and may be used later by other autonomous vehicles traveling along the same road segment 1200. While vehicles 1205, 1210, 1215, 1220, and 1225 are traveling along road segment 1200, the landmarks identified by these vehicles may be recorded along with the target trajectory. The data for the target trajectory and landmarks may be constantly or periodically updated with new data received from other vehicles in subsequent drives.

[0334] For the purpose of identifying the position of an autonomous vehicle, the disclosed system and method may use an extended Kalman filter. The position of the vehicle may be determined based on three-dimensional position data and / or three-dimensional orientation data, and the prediction of the future position in front of the current position of the vehicle by integrating ego motion. The position identification of the vehicle may be corrected or adjusted by the image observation of landmarks. For example, when the vehicle detects a landmark in the image captured by the camera, the landmark may be compared with the known landmarks stored in the road model or the sparse map 800. The known landmarks have known positions (e.g., GPS data) along the target trajectory stored in the road model and / or the sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark can be estimated. The position of the vehicle 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 the sparse map 800). The position / location data of the landmarks stored in the road model and / or the sparse map 800 (e.g., the average value from multiple drives) may be assumed to be accurate.

[0335] In some embodiments, the disclosed system may form a closed-loop subsystem, in which the position estimation of the six degrees of freedom of the vehicle (e.g., three-dimensional position data and three-dimensional orientation data) is used to navigate (e.g., steer the steering wheel of the autonomous vehicle) the autonomous vehicle so that it can reach a desired point (e.g., 1.3 seconds ahead of the stored point). Next, the six-degree-of-freedom position may be estimated using the data measured from the steering and the actual navigation.

[0336] In some embodiments, poles along a road, such as street light poles and poles for power transmission lines or cable lines, may be used as landmarks for identifying the position of a vehicle. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along a road segment, may also be used as landmarks for identifying the position of a vehicle. When using a pole for positioning, rather than the y-direction observation of the pole (i.e., the distance to the pole), the x-direction observation (i.e., the viewing angle from the vehicle) may be used. This is because the lower part of the pole may be blocked and, in some cases, the pole may not be on the road surface.

[0337] FIG. 23 shows a vehicle navigation system, which may be used for automatic navigation using a sparse map by crowdsourcing. For the sake of explanation, the vehicle is referred to as vehicle 1205. The vehicle shown in FIG. 23 may be any other vehicle disclosed herein, for example, vehicles 1210, 1215, 1220, and 1225, and vehicle 200 shown in other embodiments may be included. As shown in FIG. 12, vehicle 1205 may communicate with server 1230. Vehicle 1205 may include an image capture device 122 (e.g., camera 122). Vehicle 1205 may include a navigation system 2300 configured to provide navigation guidance for vehicle 1205 to travel on a road (e.g., road segment 1200). Vehicle 1205 may also include other sensors such as speed sensor 2320 and accelerometer 2325. Speed sensor 2320 may be configured to detect the speed of vehicle 1205. Accelerometer 2325 may be configured to detect the acceleration or deceleration of vehicle 1205. The vehicle 1205 shown in FIG. 23 may be an autonomous vehicle, and navigation system 2300 may be used to provide navigation guidance for autonomous driving. Alternatively, vehicle 1205 may be a non-autonomous, human-controlled vehicle, and navigation system 2300 may still be used to provide navigation guidance.

[0338] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 via 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, which is configured to process data such as GPS signals, map data from the sparse map 800 (this data may be stored in a storage device mounted on the vehicle 1205 and / or received from the server 1230), the geometry of the road detected by the road profile sensor 2330, the images captured by the camera 122, and / or the road navigation model for autonomous vehicles 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 unevenness, road width, road elevation, road curvature, etc. For example, the road profile sensor 2330 may include a device for measuring the movement of the suspension of the vehicle 2305 to obtain the road unevenness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor for measuring the distance from the vehicle 1205 to the roadside (e.g., the roadside barrier), whereby the width of the road is measured. In some embodiments, the road profile sensor 2330 may include a device configured to measure the rise and fall of the road elevation. In some embodiments, the road profile sensor 2330 may include a device configured to measure the road curvature. For example, a camera (e.g., the camera 122 or another camera) may be used to capture an image of the road indicating the road curvature. The vehicle 1205 may detect the road curvature using such an image.

[0339] At least one processor 2315 may be programmed to receive at least one environmental image related to vehicle 1205 from camera 122. At least one processor 2315 may analyze the at least one environmental image to identify navigation information related to vehicle 1205. The navigation information may include a trajectory related to the travel of vehicle 1205 along road segment 1200. At least one processor 2315 may determine the trajectory based on the movement of camera 122 (and thus the vehicle), for example, 3D translational motion and 3D rotational motion. In some embodiments, at least one processor 2315 may identify the translational and rotational motion of camera 122 based on the analysis of a plurality of images acquired by camera 122. In some embodiments, the navigation information may include lane designation information (e.g., which lane vehicle 1205 is traveling in along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 may be used for server 1230 to generate and / or update a road navigation model for an autonomous vehicle, and this information may be transmitted again from server 1230 to vehicle 1205 to provide automatic navigation guidance to vehicle 1205.

[0340] At least one processor 2315 may also be programmed to transmit navigation information from vehicle 1205 to server 1230. In some embodiments, the navigation information may be transmitted to server 1230 along with road information. The road location information may include at least one of the GPS signals received by the GPS unit 2310, landmark information, the geometry of the road, lane information, and the like. At least one processor 2315 may receive from server 1230 an autonomous vehicle road navigation model or a portion of the model. The autonomous vehicle road navigation model received from server 1230 may include at least one update based on the navigation information transmitted from vehicle 1205 to server 1230. A portion of the model transmitted from server 1230 to vehicle 1205 may include the updated portion of the model. At least one processor 2315 may generate at least one navigation operation (e.g., maneuvers such as making a turn, applying brakes, accelerating, passing another vehicle, etc.) by vehicle 1205 based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0341] At least one processor 2315 may be configured to communicate with various sensors and components included in vehicle 1205, and such sensors and components include communication unit 1705, GPS unit 2315, camera 122, speed sensor 2320, accelerometer 2325, and road profile sensor 2330. At least one processor 2315 may collect information or data from the various sensors and components and transmit the information or data to server 1230 via communication unit 2305. Alternatively, or in addition, the various sensors or components of vehicle 1205 may also communicate with server 1230 to transmit the data or information collected by the sensors or components to server 1230.

[0342] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may communicate with each other and may share navigation information with each other. Thereby, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 may generate a road navigation model for an autonomous vehicle using crowdsourcing, for example, based on information shared by other vehicles. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may share navigation information with each other, and each vehicle may update the road navigation model for its own autonomous vehicle provided to each vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (for example, vehicle 1205) may function as a hub vehicle. At least one processor 2315 of the hub vehicle (for example, vehicle 1205) may perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle may communicate with other vehicles and receive navigation information from other vehicles. At least one processor 2315 of the hub vehicle may generate a road navigation model for an autonomous vehicle or an update to the model based on the shared information received from other vehicles. At least one processor 2315 of the hub vehicle may transmit the road navigation model for an autonomous vehicle or the update to the model to other vehicles to provide automated navigation guidance.

[0343] [Navigation Based on Sparse Map]

[0344] As described above, a road navigation model for an autonomous vehicle including a sparse map 800 may include a plurality of mapped lane markings and a plurality of mapped objects / features associated with a road segment. As discussed in more detail below, these mapped lane markings, objects, and features may be used when an autonomous vehicle navigates. For example, in some embodiments, the mapped objects and features may be used to identify the position of the host vehicle relative to the map (e.g., relative to the mapped target trajectory). The mapped lane markings may be used (e.g., as a check) to determine the lateral position and / or orientation relative to a planned trajectory or target trajectory. Using this position information, the autonomous vehicle may be able to adjust its travel direction to match the direction of the target trajectory at the determined position.

[0345] Vehicle 200 may be configured to detect lane markings in a given road segment. A road segment may include any markings on the road for guiding vehicle traffic in a lane. For example, a lane marking may be a solid or dashed line that defines the edge of a driving lane. Lane markings may include, for example, double lines such as double solid lines, double dashed lines, or a combination of solid and dashed lines indicating whether passing is permitted in an adjacent lane. Lane markings may also include highway entrance and exit markings, which may indicate, for example, a deceleration lane for an exit ramp, or a dotted line indicating that a lane is for turning only or that a lane ends. These markings may further indicate a work zone, a temporary lane shift, a route through an intersection, a median strip, a dedicated lane (e.g., a bicycle lane, an HOV lane, etc.), or various other markings (e.g., a crosswalk, a speed bump for vehicles, a railroad crossing, a stop line, etc.).

[0346] Vehicle 200 may capture images of surrounding lane markings using cameras such as image capture devices 122 and 124 included in image acquisition unit 120. Vehicle 200 may analyze these images to detect the positions of points related to lane markings based on features identified in one or more of the captured images. The positions of these points may be uploaded to a server to represent lane markings in sparse map 800. Depending on the positions and fields of view of the cameras, lane markings on both sides of the vehicle may be detected simultaneously from a single image. In other embodiments, various cameras attached to multiple surfaces of the vehicle may be used to capture images. Rather than uploading actual images of lane markings, these markings may be stored in sparse map 800 as splines or a series of points, thus reducing the size of sparse map 800 and / or the data that the vehicle needs to upload remotely.

[0347] Figures 24A - 24D show exemplary point positions for representing specific lane markings that can be detected by vehicle 200. Similar to the landmarks described above, vehicle 200 may use various image recognition algorithms or software to identify the positions of points within the captured images. For example, vehicle 200 may recognize a series of edge points, corner points, or various other point positions associated with a specific lane marking. Figure 24A shows a solid - line lane marking 2410 that can be detected by vehicle 200. The lane marking 2410 represents the outer edge of the lane and may be represented by a solid white line. As shown in Figure 24A, vehicle 200 may be configured to detect a plurality of edge - position points 2411 along the lane marking. These position points 2411 may be collected to represent the lane marking at any interval sufficient to create a lane marking mapped in a sparse map. For example, the lane marking may be represented by one point per meter of the detected edge, one point per five meters of the detected edge, or other suitable intervals. In some embodiments, this interval may be determined by other factors rather than a predetermined interval, such as, for example, based on the points having the highest confidence - ranking regarding the position of the detection points by vehicle 200. Figure 24A shows edge - position points on the inner edge of lane marking 2410, but the points may be collected on the outer edge of the line or along both edges. Further, although Figure 24A shows one line, similar edge points may be detected for double solid lines. For example, points 2411 may be detected along one or both edges of the solid line.

[0348] Vehicle 200 may represent different lane markings according to the type or shape of the lane markings. FIG. 24B shows an exemplary dashed lane marking 2420 that can be detected by vehicle 200. Rather than identifying edge points as in FIG. 24A, the vehicle may detect a series of corner points 2421 that represent the corners of the lane dashes that define the entire boundary of the dashed line. FIG. 24B shows that each corner of a given dashed marking is located, but vehicle 200 may detect and / or upload a subset of these points shown in the figure. For example, vehicle 200 may detect the leading edge or leading corner of a given dashed marking, or may detect the two corner points closest to the inside of the lane. Further, not all dashed markings need to be captured. For example, vehicle 200 may capture and / or record points that represent samples of the dashed markings (e.g., every other one, every third one, every fifth one, etc.), or points that represent the dashed markings at a predetermined interval (e.g., every meter, every five meters, every ten meters, etc.). Corner points may also be detected for similar lane markings, such as markings indicating that a certain lane is for an exit ramp, markings indicating the end of a particular lane, or various other lane markings that may have detectable corner points. Corner points may also be detected for lane markings composed of double dashed lines or combinations of solid and dashed lines.

[0349] In some embodiments, the points uploaded to the server to generate the mapped lane markings may represent other points in addition to the detected edge points or corner points. FIG. 24C shows a series of points that may represent the centerline of a given lane marking. For example, the solid line lane 2410 may be represented by centerline points 2441 along the centerline 2440 of the lane marking. In some embodiments, the vehicle 200 may be configured to detect these center points using various image recognition techniques, such as convolutional neural networks (CNNs), scale-invariant feature transform (SIFT), histogram of oriented gradients (HOG) features, or other techniques. Alternatively, the vehicle 200 may detect other points, such as the edge points 2411 shown in FIG. 24A, and may calculate the centerline points 2441, for example, by detecting points along each edge and determining the midpoint between the edge points. Similarly, the dashed line lane marking 2420 may be represented by centerline points 2451 along the centerline 2450 of the lane marking. The centerline points may be located at the edges of the dashed lines as shown in FIG. 24C, or at various other locations along the centerline. For example, each dashed line may be represented by one point at the geometric center of the dashed line. Each point may be spaced at a predetermined interval along the centerline (e.g., every 1 meter, every 5 meters, every 10 meters, etc.). The centerline points 2451 may be directly detected by the vehicle 200, or may be calculated based on other detected reference points, such as the corner points 2421 as shown in FIG. 24B. A centerline may be used to represent other lane marking types, such as double lines, using a similar technique as described above.

[0350] In some embodiments, vehicle 200 may identify points that represent other features, such as an intersection between two intersecting lane markings. FIG. 24D shows an exemplary point representing an intersection between two lane markings 2460 and 2465. Vehicle 200 may calculate an intersection point 2466 that represents the intersection between the two lane markings. For example, one of lane markings 2460 or 2465 may represent an intersection area of a train or other intersection area within a road segment. Lane markings 2460 and 2465 are shown as intersecting perpendicular to each other, but various other configurations may be detected. For example, lane markings 2460 and 2465 may intersect at other angles, and one or both of these lane markings may end at intersection point 2466. A similar approach may be applied to intersections between dashed lines or other lane marking types. In addition to intersection point 2466, various other points 2467 may be detected that provide additional information regarding the orientation of lane markings 2460 and 2465.

[0351] Vehicle 200 may associate actual coordinates with each detection point of the lane markings. For example, it may generate a position identifier including the coordinates of each point and upload it to a server for mapping the lane markings. The position identifier may further include other identification information regarding these points, such as whether these points represent corner points, edge points, center points, etc. Thus, vehicle 200 may be configured to determine the actual position of each point based on the analysis of the image. For example, vehicle 200 may detect other features in the image, such as various landmarks described above, to identify the actual position of the lane markings. This may include determining the position of the lane markings in the image relative to the detected landmarks, or determining the position of the vehicle based on the detected landmarks and then determining the distance from the vehicle (or the target trajectory of the vehicle) to the lane markings. If no landmarks are available, the position of the lane marking points may be determined relative to the position of the vehicle determined based on dead reckoning. The actual coordinates included in the position identifier may be represented as absolute coordinates (e.g., coordinates by latitude / longitude), or may be related to other features, such as based on the longitudinal position along the target trajectory and the lateral distance from the target trajectory. The position identifier may then be uploaded to a server to generate a mapped lane marking in a navigation model (such as sparse map 800). In some embodiments, the server may construct a spline representing the lane markings of a road segment. Alternatively, vehicle 200 may generate a spline and upload it to the server so that this spline is recorded in the navigation model.

[0352] FIG. 24E shows an exemplary navigation model or sparse map of a corresponding road segment that includes the mapped lane markings. The sparse map may include a target trajectory 2475 for the vehicle to travel along the road segment. As described above, the target trajectory 2475 may represent an ideal path that the vehicle passes through when traveling on the corresponding road segment and may be located at other locations on the road (e.g., the center line of the road, etc.). The target trajectory 2475 may be calculated in various ways as described above, based on, for example, a set (e.g., a weighted combination) of two or more reconstructed trajectories of vehicles passing through the same road segment.

[0353] In some embodiments, the target trajectory may be generated equally for all vehicle types and all road, vehicle, and / or environmental conditions. However, in other embodiments, various other factors or variables may also be considered when generating the target trajectory. Different target trajectories may be generated for different types of vehicles (e.g., passenger cars, light trucks, and full trailers). For example, a target trajectory with a relatively small turning radius may be generated for a small passenger car rather than a large semi-trailer truck. In some embodiments, the road, vehicle, and environmental conditions may also be considered. For example, different target trajectories may be generated for different road conditions (e.g., wet, snowy, frozen, dry, etc.), vehicle conditions (e.g., tire condition or estimated tire condition, brake condition or estimated brake condition, fuel remaining, etc.), or environmental factors (e.g., time, visibility, weather, etc.). The target trajectory may also depend on one or more aspects or features of a particular road segment (e.g., speed limit, frequency and size of turns, gradient, etc.). In some embodiments, various user settings such as a set driving mode (e.g., desired driving aggressiveness, economy mode, etc.) may also be used to determine the target trajectory.

[0354] The sparse map may also include mapped lane markings 2470 and 2480 representing lane markings along a road segment. The mapped lane markings may be represented by a plurality of position identifiers 2471 and 2481. As described above, the position identifier may include the position at the actual coordinates of the point associated with the detected lane marking. Similar to the target trajectory in the model, the lane marking may also include elevation data and may be represented as a curve in three-dimensional space. For example, this curve may be a spline connecting three-dimensional polynomials of a suitable degree, and this curve may be calculated based on the position identifier. The mapped lane markings may also include other information or metadata regarding the lane markings, such as an identifier of the type of lane marking (e.g., between two lanes in the same driving direction, between two lanes in opposite driving directions, the edge of a lane, etc.) and / or other characteristics of the lane marking (e.g., solid line, dashed line, single line, double line, yellow line, white line, etc.). In some embodiments, the mapped lane markings may be constantly updated in the model, for example, using a crowdsourcing approach. The same vehicle may upload position identifiers on multiple occasions of driving on the same road segment, or data may be selected from multiple vehicles (such as 1205, 1210, 1215, 1220, and 1225) driving on the road segment at different times. The sparse map 800 may then be updated or fine-tuned based on subsequent position identifiers received from the vehicle and stored in the system. When the mapped lane markings are updated and fine-tuned, the updated road navigation model and / or sparse map may be distributed to a plurality of autonomous vehicles.

[0355] The generation of the mapped lane markings in the sparse map may also include detection and / or mitigation of errors based on anomalies included in the image or the actual lane markings themselves. FIG. 24F shows exemplary anomalies 2495 associated with the detection of lane markings 2490. Anomalies 2495 may appear in the images captured by the vehicle 200, for example, due to an object blocking the camera's field of view with respect to the lane markings, dust adhering to the lens, etc. In some cases, the anomaly may be due to the lane markings themselves, where the lane markings are damaged or worn, or are partially covered, for example, by dirt, dust, water, snow, or other substances on the road. Due to the anomalies 2495, incorrect points 2491 may be detected by the vehicle 200. The sparse map 800 may correct the mapped lane markings and eliminate the errors. In some embodiments, the vehicle 200 may detect the incorrect points 2491, for example, by detecting the anomalies 2495 in the image or by identifying the errors based on the lane marking points detected before and after the anomaly. Based on the detection of the anomaly, the vehicle may exclude the point 2491 or adjust this point to follow other detected points. In other embodiments, after this point is uploaded, for example, based on other points uploaded during the same movement or based on an aggregate of data from previous movements along the same road segment, the error may be corrected by determining that this point deviates from the expected threshold.

[0356] Lane markings mapped in the navigation model and / or the sparse map may also be used for the navigation of an autonomous vehicle passing through the corresponding lane. For example, a vehicle navigating along a target trajectory may periodically use the lane markings mapped in the sparse map to align the lane markings themselves with the target trajectory. As described above, between landmarks, the vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to identify its ego motion and estimate its position relative to the target trajectory. Since errors can accumulate over time, the accuracy of the vehicle's positioning relative to the target trajectory may gradually decrease. Therefore, the vehicle can use the lane markings (and their known positions) present in the sparse map 800 to reduce the errors due to dead reckoning in positioning. In this way, the identified lane markings included in the sparse map 800 can serve as an essential part of navigation that can determine the accurate position of the vehicle relative to the target trajectory.

[0357] FIG. 25A shows an exemplary image 2500 of the vehicle's surrounding environment that can be used for navigation based on the mapped lane markings. The image 2500 may be captured by the vehicle 200 via, for example, the image capture devices 122 and 124 included in the image acquisition unit 120. The image 2500 may include an image of at least one lane marking 2510, as shown in FIG. 25A. The image 2500 may also include one or more landmarks 2521, such as road signs used for the above-described navigation. Some of the elements shown in FIG. 25A, such as the elements 2511, 2530, and 2520 detected and / or identified by the vehicle 200 but not appearing in the captured image 2500, are also shown for reference.

[0358] Using the various techniques described above with respect to FIGS. 24A-24D and 24F, the vehicle may analyze the image 2500 and identify the lane markings 2510. Various points 2511 corresponding to features of the lane markings within the image may be detected. For example, the points 2511 may correspond to the edges of the lane markings, the corners of the lane markings, the midpoints of the lane markings, the intersections of two intersecting lane markings, or various other features or locations. Points 2511 corresponding to the positions of points stored in the navigation model received from the server may be detected. For example, if a sparse map including points representing the centerline of the mapped lane markings is received, the points 2511 may also be detected based on the centerline of the lane markings 2510.

[0359] The vehicle may also determine a longitudinal position represented by element 2520 and located along the target trajectory. The longitudinal position 2520 may be determined from the image 2500, for example, by detecting landmarks 2521 within the image 2500 and comparing the measured positions to the positions of known landmarks stored in the road model or sparse map 800. The position of the vehicle along the target trajectory may then be determined based on the distance to the landmark and the known position of the landmark. The longitudinal position 2520 may also be determined from an image other than the image used to determine the position of the lane markings. For example, the longitudinal position 2520 may be determined by detecting landmarks included in an image that captured the image 2500 simultaneously or substantially simultaneously from another camera within the image acquisition unit 120. In some cases, the vehicle may not be near any landmarks or other reference points for determining the longitudinal position 2520. In such cases, the vehicle may navigate based on dead reckoning and thus may use sensors to identify its ego motion and estimate the longitudinal position 2520 relative to the target trajectory. The vehicle may also determine a distance 2530 representing the actual distance between the vehicle and the lane markings 2510 observed in one or more captured images. Camera angle, vehicle speed, vehicle width, or various other factors may be considered when determining the distance 2530.

[0360] FIG. 25B shows the correction of the lateral position identification of the vehicle based on the mapped lane markings in the road navigation model. As described above, the vehicle 200 may determine the distance 2530 between the vehicle 200 and the lane marking 2510 using one or more images captured by the vehicle 200. The vehicle 200 may also have access to a road navigation model such as the sparse map 800 that may include the mapped lane markings 2550 and the target trajectory 2555. The mapped lane markings 2550 may be modeled using the methods described above, for example, using location identifiers obtained by crowdsourcing captured by a plurality of vehicles. The target trajectory 2555 may be generated using various methods described above. The vehicle 200 may also determine or estimate the longitudinal position 2520 along the target trajectory 2555 as described above with respect to FIG. 25A. The vehicle 200 may then determine the expected distance 2540 based on the lateral distance between the target trajectory 2555 and the mapped lane markings 2550 corresponding to the longitudinal position 2520. The lateral position identification of the vehicle 200 may be corrected or adjusted by comparing the actual distance 2530 measured using one or more captured images with the expected distance 2540 from the model.

[0361] Figures 25C and 25D provide diagrams related to another example of identifying the position of a host vehicle based on mapped landmarks / objects / features in a sparse map during navigation. Figure 25C conceptually represents a series of images captured from a vehicle navigating along road segment 2560. In this example, road segment 2560 includes a straight portion of a two-lane highway described by road edges 2561 and 2562 and center lane markings 2563. As shown, the host vehicle is navigating along lane 2564 associated with mapped target trajectory 2565. Thus, in an ideal situation (and in the absence of influencers such as the presence of the target vehicle or object in the lane), the host vehicle should track the mapped target trajectory 2565 closely as it navigates along lane 2564 of road segment 2560. In reality, the host vehicle may experience drift as it navigates along the mapped target trajectory 2565. For effective and safe navigation, this drift should be maintained within acceptable limits (e.g., a lateral displacement of + / - 10 cm from the target trajectory 2565, or any other suitable threshold). To periodically account for the drift and make any necessary course corrections to ensure that the host vehicle progresses along the target trajectory 2565, the disclosed navigation system may be able to identify the position of the host vehicle along the target trajectory 2565 (e.g., identify the lateral and longitudinal positions of the host vehicle relative to the target trajectory 2565) using one or more mapped features / objects included in the sparse map.

[0362] As a simple example, FIG. 25C shows a speed limit sign 2566 that may appear in five different images sequentially captured as the host vehicle navigates along road segment 2560. For example, at the first time, t0, the sign 2566 may appear near the horizontal line in the captured image. As the host vehicle approaches the sign 2566, in the images captured at subsequent times t1, t2, t3, and t4, the sign 2566 will appear at different 2D X-Y pixel positions in the captured image. For example, in the captured image space, the sign 2566 will move downward and to the right along curve 2567 (e.g., a curve extending through the center of the sign in each of the five captured image frames). The sign 2566 may also appear to grow in size as the host vehicle approaches (i.e., it will occupy a greater number of pixels in the next captured image).

[0363] These changes in the image space representation of an object such as sign 2566 may be utilized to determine the position of the host vehicle at a particular position along the target trajectory. For example, as described in the present disclosure, any detectable object or feature, such as a semantic feature like sign 2566 or a detectable and non-semantic feature, may be identified by one or more collection vehicles that have traversed a previous road segment (e.g., road segment 2560). A mapping server may collect drive information collected from multiple vehicles, aggregate and correlate that information, and generate a sparse map that includes, for example, a target trajectory 2565 for lane 2564 of road segment 2560. The sparse map may also store the position of sign 2566 (along with type information, etc.). During navigation (e.g., before entering road segment 2560), the host vehicle may be provided with a map tile that includes the sparse map for road segment 2560. To navigate in lane 2564 of road segment 2560, the host vehicle may proceed along the mapped target trajectory 2565.

[0364] The mapped representation of the identifier 2566 may be used by the host vehicle to identify its own position relative to the target trajectory. For example, a camera on the host vehicle will capture an image 2570 of the host vehicle's environment, and the captured image 2570 may include an image representation of the identifier 2566 having a specific size and a specific X-Y image position, as shown in FIG. 25D. This size and X-Y image position can be used to identify the position of the host vehicle relative to the target trajectory 2565. For example, based on a sparse map including the representation of the identifier 2566, the host vehicle's navigation processor can determine that, in response to the host vehicle traveling along the target trajectory 2565, the representation of the identifier 2566 should appear to move along line 2567 (within the image space) in the captured image. If a captured image such as image 2570 shows a center (or other reference point) shifted from line 2567 (e.g., the expected image space trajectory), then the host vehicle navigation system can then determine that it was not positioned on the target trajectory 2565 at the time of the captured image. However, the navigation processor can determine appropriate navigation corrections from the image to return the host vehicle to the target trajectory 2565. For example, if the analysis results show an image position of the identifier 2566 shifted by a distance 2572 to the left of the expected image space position on line 2567 in the image, the navigation processor may then cause the host vehicle to make a course change (e.g., change the steering angle of the steering wheel) to move the host vehicle to the left by a distance 2573. Thus, each captured image can be used as part of a feedback loop process, such that the difference between the observed image position of the identifier 2566 and the expected image trajectory 2567 is minimized, ensuring that the host vehicle continues along the target trajectory 2565 with little deviation.Of course, the more mapped objects are available, the more frequently the described location identification method can be used, which can reduce or eliminate the deviation due to the drift from the target trajectory 2565.

[0365] The above-described process may be useful for detecting the lateral orientation or displacement of the host vehicle related to the target trajectory. The location identification of the host vehicle related to the target trajectory 2565 may also include determining the longitudinal position of the target vehicle along the target trajectory. For example, the captured image 2570 includes a representation of the sign 2566 having a specific image size (e.g., a 2D X-Y pixel region). Since it travels through the image space along the line 2567 (e.g., as shown in FIG. 25C, the size of the sign gradually increases), this size can be compared with the expected image size of the mapped sign 2566. Based on the image size of the sign 2566 in the image 2570 and based on the expected size progression in the image space related to the mapped target trajectory 2565, the host vehicle can identify the longitudinal position relative to the target trajectory 2565 (at the time when the image 2570 was captured). This longitudinal position, combined with any lateral displacement relative to the target trajectory 2565, as described above, enables the overall location identification of the host vehicle related to the target trajectory 2565 since the host vehicle navigates along the road 2560.

[0366] FIGS. 25C and 25D provide merely an example of the disclosed location identification method using one mapped object and one target trajectory. In other examples, there may be many more target trajectories (e.g., one target trajectory for each possible lane of a multi-lane highway, urban streets, complex intersections, etc.), and there may be many more mapped objects available for location identification. For example, a sparse map representing an urban environment may include a large number of objects available for location identification every one meter.

[0367] FIG. 26A is a flowchart showing an exemplary process 2600A for mapping lane markings for use in an autonomous vehicle navigation that is not inconsistent with the disclosed embodiments. At step 2610, process 2600A may include receiving two or more location identifiers associated with the detected lane markings. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifier may include the location at the actual coordinates of the points associated with the detected lane markings, as described above with respect to FIG. 24E. In some embodiments, the location identifier may also include other data, such as additional information regarding the road segment or lane marking. Additional data, such as accelerometer data, speed data, landmark data, road geometry or profile data, vehicle positioning data, ego motion data, or various other forms of data described above, may also be received at step 2610. The location identifier may be generated by vehicles such as vehicles 1205, 1210, 1215, 1220, and 1225 based on an image captured by this vehicle. For example, the identifier may be determined based on the acquisition of at least one image representing the environment of the host vehicle from a camera associated with the host vehicle, the analysis of at least one image for detecting lane markings included in the environment of the host vehicle, and the analysis of at least one image for determining the position of the detected lane markings relative to the position associated with the host vehicle. As described above, the lane markings may include various different marking types, and the location identifier may correspond to various points associated with the lane markings. For example, if the detected lane marking is part of a dashed line marking representing a lane boundary, these points may correspond to the corners of the detected lane marking. If the detected lane marking is part of a solid line marking representing a lane boundary, these points may correspond to the edges of the detected lane marking detected at various intervals described above. In some embodiments, these points may also correspond to the centerline of the detected lane marking, as shown in FIG. 24C, or may correspond to the intersection of two intersecting lane markings and at least two other points associated with at least one of the intersecting lane markings, as shown in FIG. 24D.

[0368] In stage 2612, process 2600A may include associating the detected lane markings with the corresponding road segment. For example, server 1230 may analyze the actual coordinates or other information received in stage 2610 and compare this coordinate or other information with the position information stored in the road navigation model for autonomous vehicles. Server 1230 may determine the road segment in the model corresponding to the actual road segment where the lane markings are detected.

[0369] In stage 2614, process 2600A may include updating the road navigation model for autonomous vehicles associated with the corresponding road segment based on two or more position identifiers associated with the detected lane markings. For example, the autonomous road navigation model may be the sparse map 800, and server 1230 may update the sparse map to include or adjust the mapped lane markings in the model. Server 1230 may update the model based on various methods or processes described above with respect to FIG. 24E. In some embodiments, updating the road navigation model for autonomous vehicles may include storing one or more indicators of the position at the actual coordinates of the detected lane markings. The road navigation model for autonomous vehicles may also include at least one target trajectory for the vehicle to travel along the corresponding road segment, as shown in FIG. 24E.

[0370] In stage 2616, process 2600A may include distributing the updated road navigation model for autonomous vehicles to a plurality of autonomous vehicles. For example, server 1230 may distribute the updated road navigation model for autonomous vehicles to vehicles 1205, 1210, 1215, 1220, and 1225 that can use this model for navigation. The road navigation model for autonomous vehicles may be distributed via one or more networks (e.g., using a cellular network and / or the Internet, etc.) through the wireless communication path 1235, as shown in FIG. 12.

[0371] In some embodiments, the lane markings may be mapped using data received from multiple vehicles, such as with a crowdsourcing technique, as described above with respect to FIG. 24E. For example, process 2600A may include receiving, from a first host vehicle, a first communication including a position identifier associated with a detected lane marking, and receiving, from a second host vehicle, a second communication including an additional position identifier associated with the detected lane marking. For example, the second communication may be received from a subsequent vehicle traveling on the same road segment, or may be received from the same vehicle during a subsequent movement along the same road segment. Process 2600A may further include refining the determination of at least one position associated with the detected lane marking based on the position identifier received in the first communication and based on the additional position identifier received in the second communication. This step may include using an average of the multiple position identifiers and / or excluding “ghost” identifiers that may not reflect the actual position of the lane marking.

[0372] FIG. 26B is a flowchart showing an exemplary process 2600B for autonomously navigating a host vehicle along a road segment using the mapped lane markings. Process 2600B may be performed, for example, by the processing unit 110 of the autonomous vehicle 200. At step 2620, process 2600B may include receiving a road navigation model for an autonomous vehicle from a server-based system. In some embodiments, the road navigation model for an autonomous vehicle may include a target trajectory for the host vehicle along the road segment and a position identifier associated with one or more lane markings associated with the road segment. For example, vehicle 200 may receive a sparse map 800 developed using process 2600A or another road navigation model. In some embodiments, the target trajectory may be represented as a three-dimensional spline, as shown, for example, in FIG. 9B. As described above with respect to FIGS. 24A-24F, the position identifier may include the position in the actual coordinates of a point associated with a lane marking (e.g., a corner point of a dashed lane marking, an edge point of a solid lane marking, an intersection of two intersecting lane markings and other points associated with the intersecting lane markings, a center line associated with the lane marking, etc.).

[0373] At step 2621, process 2600B may include receiving at least one image representing the environment of the vehicle. This image may be received from an image capture device of the vehicle, such as via the image capture devices 122 and 124 included in the image acquisition unit 120. This image may include an image of one or more lane markings, similar to the image 2500 described above.

[0374] At step 2622, process 2600B may include determining the longitudinal position of the host vehicle along the target trajectory. As described above with respect to FIG. 25A, this may be based on other information (e.g., landmarks, etc.) included in the captured image or by the estimated dead reckoning of the vehicle between the detected landmarks.

[0375] In stage 2623, process 2600B may include determining an expected lateral distance to a lane marking based on a determined longitudinal position of the host vehicle along a target trajectory and based on two or more position identifiers associated ...

Claims

1. 1. A navigation system for a host vehicle, comprising: receiving at least one captured center image from a center camera in the host vehicle, the captured center image including a representation of at least a portion of the host vehicle's environment; receiving at least one captured left surround image from a left surround camera in the host vehicle, the captured left surround image including a representation of at least a portion of the host vehicle's environment; and receiving at least one captured right surround image from a right surround camera in the host vehicle, the field of view of the center camera at least partially overlapping with both the field of view of the left surround camera and the field of view of the right surround camera; providing the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image to an analysis module configured to generate an output related to the at least one captured central image based on an analysis of the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image, the generated output including pixel-by-pixel depth information for at least one region of the captured central image; and causing at least one navigation action by the host vehicle based on the generated output including the pixel-by-pixel depth information for the at least one region of the captured central image. At least one processor programmed to: The analysis module includes at least one trained model trained based on training data including a combination of a plurality of images captured by a plurality of cameras having at least partially overlapping fields of view and LIDAR point cloud information corresponding to at least a portion of the plurality of images. Navigation system.

2. the at least one trained model comprises a neural network; The navigation system of claim 1 .

3. The LIDAR point cloud information is treated as reference depth information or actual depth values ​​for training the neural network.

3. The navigation system according to claim 2.

4. the generated output includes pixel-by-pixel depth information for all regions of the captured central image; A navigation system according to any one of claims 1 to 3.

5. two or more of the center camera, the left surround camera and the right surround camera have different fields of view; A navigation system according to any one of claims 1 to 4.

6. two or more of the center camera, the left surround camera and the right surround camera have different focal lengths; A navigation system according to any one of claims 1 to 5.

7. the center camera, the left surround camera, and the right surround camera are included in a first camera group, and the host vehicle has at least a second camera group also including a center camera, a left surround camera, and a right surround camera; A navigation system according to any one of claims 1 to 6.

8. the analysis module is further configured to generate another output related to the at least one center image captured by the center camera of the second camera group based on an analysis of the at least one captured center image, the at least one captured left surround image, and the at least one captured right surround image received from the center camera, the left surround camera, and the right surround camera of the second camera group; the other output generated includes pixel-by-pixel depth information for at least one region of the central image captured by the central camera of the second camera group.

8. The navigation system according to claim 7.

9. the analysis module is configured to generate pixel-by-pixel depth information for at least one image captured by at least one camera in each of the first camera group and the at least second camera group to provide a 360 degree imaging point cloud surrounding the vehicle.

9. A navigation system according to claim 7 or 8.

10. the first camera group and the at least second camera group share at least one camera; A navigation system according to any one of claims 7 to 9.

11. the right surround camera of the first camera group serves as the left surround camera of the second camera group, and the left surround camera of the first camera group serves as the right surround camera of a third camera group; A navigation system according to any one of claims 7 to 10.

12. At least one of the left surround camera or the right surround camera of the first camera group serves as a central camera for camera groups other than the first camera group. A navigation system according to any one of claims 7 to 11.

13. the at least one navigation operation includes at least one of accelerating, braking, or turning the host vehicle; A navigation system according to any one of the preceding claims.

14. The at least one processor is further programmed to determine the at least one navigation operation based on a combination of the pixel-by-pixel depth information for the at least one region of the captured central image and point cloud information received from a LIDAR system in the host vehicle. A navigation system according to any one of claims 1 to 13.

15. the per-pixel depth information for the at least one region of the captured central image provides depth information for one or more objects represented in the captured central image; the one or more objects are not in contact with the ground; A navigation system according to any one of the preceding claims.

16. the one or more objects are carried by a target vehicle; 16. The navigation system of claim 15.

17. The ground surface includes a road surface. A navigation system according to claim 15 or 16.

18. the per-pixel depth information for the at least one region of the captured central image provides depth information for a surface of at least one object represented in the captured central image; the surface of the at least one object includes a reflection of one or more other objects; A navigation system according to any one of the preceding claims.

19. the per-pixel depth information for the at least one region of the captured central image provides depth information related to objects that are at least partially obscured from view in one or more of the at least one captured central image, the at least one captured left surround image, or the at least one captured right surround image. A navigation system according to any one of the preceding claims.

20. Each of the training data includes three images, each captured by one of a group of cameras including the center camera, the left surround camera, and the right surround camera. A navigation system according to any one of the preceding claims.

21. 1. A method for identifying navigation operations by a host vehicle, comprising: receiving at least one captured center image from a center camera in the host vehicle, the captured center image including a representation of at least a portion of the host vehicle's environment, receiving at least one captured left surround image from a left surround camera in the host vehicle, the captured left surround image including a representation of at least a portion of the host vehicle's environment, and receiving at least one captured right surround image from a right surround camera in the host vehicle, the field of view of the center camera at least partially overlapping with both the field of view of the left surround camera and the field of view of the right surround camera; providing the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image to an analysis module configured to generate an output related to the at least one captured central image based on an analysis of the at least one captured central image, the at least one captured left surround image, and the at least one captured right surround image, the generated output including pixel-by-pixel depth information for at least one region of the captured central image; causing at least one navigation action by the host vehicle based on the generated output including the pixel-by-pixel depth information for the at least one region of the captured central image; Equipped with The analysis module includes at least one trained model trained based on training data including a combination of a plurality of images captured by a plurality of cameras having at least partially overlapping fields of view and LIDAR point cloud information corresponding to at least a portion of the plurality of images. method.

Images