System and method for vehicle navigation

Abstract

Systems and methods for vehicle navigation are provided. In one embodiment, at least one processor may receive at least one image captured from a camera of a vehicle from an environment of the vehicle. The processor may analyze the at least one captured image to identify road topology features in the environment of the vehicle represented in the at least one image and at least one point associated with the at least one image. Based on the identified road topology features, the processor may determine an estimated path in the environment of the vehicle associated with the at least one point. The processor may also cause the vehicle to perform a navigation action based on the estimated path.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority to U.S. Provisional Application No. 62 / 853,300, filed May 28, 2019, U.S. Provisional Application No. 62 / 853,305, filed May 28, 2019, U.S. Provisional Application No. 62 / 853,832, filed May 29, 2019, U.S. Provisional Application No. 62 / 875,226, filed July 17, 2019, U.S. Provisional Application No. 63 / 005,736, filed April 6, 2020, and U.S. Provisional Application No. 63 / 006,340, filed April 7, 2020. The above applications are incorporated herein by reference in their entirety. Technical Field

[0003] The present disclosure generally relates to autonomous vehicle navigation. Background Art

[0004] As technology continues to advance, the goal of fully autonomous vehicles capable of navigating roads is imminent. Autonomous vehicles may need to consider a wide variety of factors and make appropriate decisions based on those factors to safely and accurately reach their intended destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., captured from cameras), information from radar or lidar, and may also use information obtained from other sources (e.g., GPS devices, speed sensors, accelerometers, suspension sensors, etc.). Furthermore, to navigate to their destination, autonomous vehicles may also need to identify their position within a specific road (e.g., a specific lane in a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and navigate from one road to another at appropriate intersections or junctions. Harnessing and interpreting the vast amount of information collected by an autonomous vehicle as it navigates to its destination presents numerous design challenges. The vast amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that autonomous vehicles may need to analyze, access, and / or store creates challenges that can actually limit or even negatively impact autonomous navigation. Furthermore, if autonomous vehicles rely on traditional mapping technologies to navigate, the massive amounts of data required to store and update maps will pose a significant challenge. Summary of the Invention

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

[0006] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one image captured from a camera of the vehicle's environment; analyze the at least one image to identify road topology features in the vehicle's environment represented in the at least one image and at least one point associated with the at least one image. The processor may also be programmed to determine an estimated path associated with the at least one point in the vehicle's environment based on the identified road topology features; and cause the vehicle to perform a navigation action based on the estimated path.

[0007] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one image captured from a camera of the vehicle's environment; and analyze the at least one image to identify one or more road topology features in the vehicle's environment represented in the at least one image. The processor may also be programmed to, for each of a plurality of segments of the at least one image and based on the identified one or more road topology features, determine an estimated path at a location in the vehicle's environment corresponding to one of the plurality of segments. The processor may also cause the vehicle to perform a navigation action based on at least one of the predicted paths associated with the plurality of segments of the at least one image.

[0008] In one embodiment, a navigation system for a host vehicle may include at least one processor. The processor may be programmed to receive at least one image captured from a camera of the host vehicle from an environment of the host vehicle; analyze the at least one image to identify a representation of a lane of travel of the vehicle along a road segment and a representation of at least one additional lane of travel along the road segment. The processor may also be programmed to analyze the at least one image to identify attributes associated with the at least one additional lane of travel; and determine information indicative of a representation of the at least one additional lane of travel based on the attributes. The processor may be programmed to transmit the information indicative of the representation of the at least one additional lane of travel to a server for use in updating a road navigation model.

[0009] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that are executed by at least one processing device and may perform any of the methods described herein.

[0010] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments. In the drawings:

[0012] Figure 1 is a pictorial representation of an exemplary system consistent with the disclosed embodiments.

[0013] Figure 2A is a diagrammatic side view representation of an exemplary vehicle incorporating systems consistent with the disclosed embodiments.

[0014] Figure 2B yes Figure 2A A diagrammatic top view representation of a vehicle and systems consistent with the disclosed embodiments is shown in FIG.

[0015] Figure 2C is a diagrammatic top view representation of another embodiment of a vehicle incorporating a system consistent with the disclosed embodiments.

[0016] Figure 2D is a diagrammatic top view representation of yet another embodiment of a vehicle incorporating a system consistent with the disclosed embodiments.

[0017] Figure 2E is a diagrammatic top view representation of yet another embodiment of a vehicle incorporating a system consistent with the disclosed embodiments.

[0018] Figure 2F is a pictorial representation of an exemplary vehicle control system consistent with the disclosed embodiments.

[0019] Figure 3A is a pictorial representation of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system, consistent with the disclosed embodiments.

[0020] Figure 3B is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield, consistent with the disclosed embodiments.

[0021] Figure 3C yes Figure 3B , which is an illustration of a camera installation consistent with the disclosed embodiments from different perspectives.

[0022] Figure 3D is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield, consistent with the disclosed embodiments.

[0023] Figure 4 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations, consistent with the disclosed embodiments.

[0024] Figure 5A is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on monocular image analysis, consistent with the disclosed embodiments.

[0025] Figure 5B is a flow chart illustrating an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images, consistent with the disclosed embodiments.

[0026] Figure 5C is a flow chart illustrating an exemplary process for detecting road signs and / or lane geometry information in a set of images consistent with the disclosed embodiments.

[0027] Figure 5D is a flow chart illustrating an exemplary process for detecting traffic lights in a set of images, consistent with the disclosed embodiments.

[0028] Figure 5E is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on a vehicle path, consistent with the disclosed embodiments.

[0029] Figure 5F is a flow chart illustrating an exemplary process for determining whether a leading vehicle is changing lanes, consistent with the disclosed embodiments.

[0030] Figure 6 is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on stereo image analysis, consistent with the disclosed embodiments.

[0031] Figure 7 is a flow chart illustrating an exemplary process for eliciting one or more navigational responses based on analysis of three sets of images, consistent with the disclosed embodiments.

[0032] Figure 8 A sparse map for providing autonomous vehicle navigation consistent with the disclosed embodiments is shown.

[0033] Figure 9A A polynomial representation of a portion of a road segment consistent with disclosed embodiments is shown.

[0034] Figure 9B A curve representing a target trajectory of a vehicle for a particular road segment in three-dimensional space contained in a sparse map consistent with disclosed embodiments is shown.

[0035] Figure 10Example landmarks that may be included in a sparse map consistent with the disclosed embodiments are shown.

[0036] Figure 11A Polynomial representations of trajectories consistent with the disclosed embodiments are shown.

[0037] Figure 11B and Figure 11C A target trajectory along a multi-lane road is shown consistent with the disclosed embodiments.

[0038] Figure 11D Example road signature profiles consistent with disclosed embodiments are shown.

[0039] Figure 12 is a schematic illustration of a system for autonomous vehicle navigation using crowdsourcing data received from multiple vehicles, consistent with the disclosed embodiments.

[0040] Figure 13 An example autonomous vehicle road navigation model represented by a plurality of three-dimensional splines is shown, consistent with the disclosed embodiments.

[0041] Figure 14 A map skeleton generated from combining positioning information from multiple drives is shown, consistent with the disclosed embodiments.

[0042] Figure 15 An example of a longitudinal alignment of two vehicles with example markings as landmarks is shown, consistent with the disclosed embodiments.

[0043] Figure 16 An example of a longitudinal alignment of multiple vehicles with example signs serving as landmarks is shown, consistent with the disclosed embodiments.

[0044] Figure 17 is a schematic illustration of a system for generating driving data using a camera, a vehicle, and a server, consistent with the disclosed embodiments.

[0045] Figure 18 is a schematic illustration of a system for crowdsourcing sparse maps consistent with the disclosed embodiments.

[0046] Figure 19 is a flow chart illustrating an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment, consistent with the disclosed embodiments.

[0047] Figure 20 A block diagram of a server consistent with the disclosed embodiments is shown.

[0048] Figure 21 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0049] Figure 22 A process for clustering vehicle trajectories associated with vehicles consistent with the disclosed embodiments is shown.

[0050] Figure 23 A vehicle navigation system that may be used for autonomous navigation consistent with the disclosed embodiments is shown.

[0051] Figure 24A 、 Figure 24B 、 Figure 24C and Figure 24D Exemplary lane markings that may be detected consistent with the disclosed embodiments are shown.

[0052] Figure 24E Exemplary mapped lane markings consistent with the disclosed embodiments are shown.

[0053] Figure 24F Exemplary anomalies associated with detecting lane markings consistent with the disclosed embodiments are shown.

[0054] Figure 25A Exemplary images of a vehicle's surroundings for navigation based on mapped lane markings, consistent with the disclosed embodiments, are shown.

[0055] Figure 25B Vehicle lateral positioning correction based on mapped lane markings in a road navigation model is shown, consistent with the disclosed embodiments.

[0056] Figure 26A is a flow chart illustrating an exemplary process for mapping lane markings for autonomous vehicle navigation consistent with the disclosed embodiments.

[0057] Figure 26B is a flow chart illustrating an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings, consistent with the disclosed embodiments.

[0058] Figure 27 Illustration of example images captured by a host vehicle consistent with disclosed embodiments.

[0059] Figure 28 is an illustration of another example image with additional example road topology features that may be detected by a host vehicle, consistent with the disclosed embodiments.

[0060] Figure 29 is an illustration of an example vector field overlaid on an image, consistent with the disclosed embodiments.

[0061] Figure 30Example predicted paths that may be determined consistent with the disclosed embodiments are shown.

[0062] Figure 31 is a flow chart illustrating an example process for navigating a host vehicle based on a vector field, consistent with the disclosed embodiments.

[0063] Figure 32 is a flow chart illustrating an example process for navigating a host vehicle based on a vector field, consistent with the disclosed embodiments.

[0064] Figure 33 is an illustration of example images that may be captured by a host vehicle for lane analysis consistent with the disclosed embodiments.

[0065] Figure 34 Example attributes that may be identified by a host vehicle to determine lane characterizations consistent with the disclosed embodiments are shown.

[0066] Figure 35 is an illustration of an example road segment on which road characterization may be performed consistent with the disclosed embodiments.

[0067] Figure 36 is a flow chart illustrating an example process for navigating a host vehicle based on semantic road features, consistent with the disclosed embodiments. DETAILED DESCRIPTION

[0068] The following detailed description refers to the accompanying drawings. Whenever possible, the same reference numerals are used in the drawings and the following description to refer to the same or similar parts. Although several illustrative embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, replacements, additions, or modifications may be made to the components shown in the drawings, and the illustrative methods described herein may be modified by replacing, reordering, removing, or adding steps to the disclosed methods. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the proper scope is defined by the appended claims.

[0069] Autonomous Vehicle Overview

[0070] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that is capable of implementing at least one navigation change without driver input. A "navigation change" refers to one or more changes in the steering, braking, or acceleration of the vehicle. To be autonomous, a vehicle need not be fully automatic (e.g., fully operable without a driver or without driver input). Rather, autonomous vehicles include those that are capable of operating under driver control during certain time periods and operating without driver control during other time periods. Autonomous vehicles may also include vehicles that only control some aspects of vehicle navigation, such as steering (e.g., maintaining the vehicle's route between vehicle lane limits), but may leave other aspects to the driver (e.g., braking). In some cases, an autonomous vehicle may handle some or all aspects of the vehicle's braking, speed control, and / or steering.

[0071] Because human drivers typically rely on visual cues and observations to control vehicles, traffic infrastructure has been built accordingly, with lane markings, traffic signs, and traffic lights all designed to provide visual information to drivers. Given these design characteristics of the traffic infrastructure, autonomous vehicles can include cameras and processing units that analyze visual information captured from the vehicle's environment. Visual information can include, for example, components of the traffic infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) that are observable by the driver, as well as other obstacles (e.g., other vehicles, pedestrians, debris, etc.). In addition, autonomous vehicles can also use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, a vehicle can use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information about its environment while the vehicle is traveling, and the vehicle (and other vehicles) can use this information to locate itself on the model.

[0072] In some embodiments of the present disclosure, an autonomous vehicle may use information obtained while navigating (from cameras, GPS devices, accelerometers, velocity sensors, suspension sensors, etc.). In other embodiments, an autonomous vehicle may use information obtained from past navigations of the vehicle (or other vehicles) while navigating. In other embodiments, an autonomous vehicle may use a combination of information obtained while navigating and information obtained from past navigations. The following sections provide an overview of a system consistent with the disclosed embodiments, followed by an overview of a forward imaging system and method consistent with the system. The following sections disclose systems and methods for building, using, and updating sparse maps for autonomous vehicle navigation.

[0073] System Overview

[0074] Figure 1is a block diagram illustrating system 100 consistent with the disclosed exemplary embodiments. System 100 may include various components depending on the requirements of a particular implementation. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a location sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. Processing unit 110 may include one or more processing devices. In some embodiments, processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements of a particular application. In some embodiments, image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 may also communicatively connect processing device 110 to a data interface 128 of image capture device 120. For example, the data interface 128 may include any wired and / or wireless link or links for transmitting image data acquired by the image acquisition device 120 to the processing unit 110 .

[0075] The wireless transceiver 172 may include one or more devices configured to exchange transmissions over an air interface to one or more networks (e.g., cellular, Internet, etc.) using radio frequencies, infrared frequencies, magnetic fields, or electric fields. The wireless transceiver 172 may transmit and / or receive data using any known standard (e.g., Wi-Fi, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications from the host vehicle to one or more remotely located servers. Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to coordinate navigation of the host vehicle with respect to or in conjunction with target vehicles in the host vehicle's environment), or even broadcast transmissions to unspecified recipients in the vicinity of the transmitting vehicle.

[0076] Both the application processor 180 and the image processor 190 may include various types of hardware-based processing devices. For example, either or both of the application processor 180 and the image processor 190 may include a microprocessor, a preprocessor (such as an image preprocessor), a graphics processor, a central processing unit (CPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for running applications and suitable for 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. Various processing devices may be used, including, for example, processors such as Processors available from manufacturers such as GPUs are available from manufacturers such as wait).

[0077] In some embodiments, the application processor 180 and / or the image processor 190 may include a processor that can be Any of the EyeQ series processor chips available. These processor designs each contain multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors and may also include video output capabilities. In one example, 90 nanometer-micron technology operating at 332 MHz is used. The architecture consists of two floating-point hyperthreaded 32-bit RISC CPUs ( cores), five visual computing engines (VCEs), and three vector microcode processors The MIPS34K CPU manages the five VCEs, three VMPs, and a series of peripherals. TM and DMA, a second MIPS34K CPU and multi-channel DMA and other peripherals. These five VCEs, three and MIPS34K CPU can perform the intensive visual calculations required for multi-function bundled applications. In another example, a third generation processor and a processor larger than Six times stronger In other examples, the disclosed embodiments may be used and / or Of course, any updated or future EyeQ processing devices may also be used with the disclosed embodiments.

[0078] Any of the processing devices disclosed herein can be configured to perform certain functions. Configuring a processing device (such as any described EyeQ processor or other controller or microprocessor) to perform certain functions can include programming computer-executable instructions and making these instructions available to the processing device for execution during operation of the processing device. In some embodiments, configuring the processing device can include programming the processing device directly using architecture instructions. For example, a processing device such as a field programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc. can be configured using, for example, one or more hardware description languages ​​(HDLs).

[0079] In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible to the processing device during operation. For example, the processing device may access the memory during operation to obtain and execute the stored instructions. In either case, the 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.

[0080] Although Figure 1 Two separate processing devices are depicted as being 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 perform the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by more than two processing devices. Furthermore, in some embodiments, system 100 may include one or more of processing units 110 without including other components, such as image acquisition unit 120.

[0081] The processing unit 110 may include various types of devices. For example, the processing unit 110 may include various devices such as a controller, an image preprocessor, a central processing unit (CPU), a graphics processing unit (GPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device used for image processing and analysis. The image preprocessor may include a video processor for capturing, digitizing, and processing images from the 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 include any number of circuits known in the art, including caches, power supplies, clocks, and input / output circuits. The memory may store software that, when executed by the processor, controls the operation of the system. The memory may include 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 devices, tape storage devices, removable storage devices, and other types of storage devices. In one embodiment, the memory may be separate from the processing unit 110. In another embodiment, the memory may be integrated into the processing unit 110.

[0082] Each memory 140, 150 may contain software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. These memory units may contain various databases and image processing software, as well as trained systems such as neural networks or, for example, deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage devices, tape storage devices, removable storage devices, and / or any other type of storage device. In some embodiments, the memory units 140, 150 may be separate from the application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into the application processor 180 and / or image processor 190.

[0083] Position sensor 130 may include any type of device suitable for determining a location associated with at least one component of system 100. In some embodiments, position sensor 130 may include a GPS receiver. Such a receiver may determine user location and velocity by processing signals broadcast by global positioning system satellites. Position information from position sensor 130 may be made available to application processor 180 and / or image processor 190.

[0084] In some embodiments, system 100 may include components such as a speed sensor (eg, tachometer, speedometer) for measuring the speed of vehicle 200 and / or an accelerometer (single-axis or multi-axis) for measuring the acceleration of vehicle 200 .

[0085] The user interface 170 may include any device suitable for providing information to or receiving input from one or more users of the system 100. In some embodiments, the user interface 170 may include a user input device, including, for example, a touch screen, a microphone, a keyboard, a pointing device, a tracking wheel, a camera, knobs, buttons, etc. Using such input devices, a user can provide information input or commands to the system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, a pointer, or eye tracking capabilities, or by any other suitable technique for communicating information to the system 100.

[0086] The user interface 170 may be equipped with one or more processing devices configured to provide and receive information to and from a user, and to process the information for use by, for example, the application processor 180. In some embodiments, such processing devices may execute instructions for recognizing and tracking eye movements, receiving and interpreting voice commands, recognizing and interpreting touches and / or gestures made on a touch screen, responding to keyboard input or menu selections, etc. In some embodiments, the user interface 170 may include a display, a speaker, a haptic device, and / or any other device for providing output information to a user.

[0087] The map database 160 may comprise any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 may comprise data relating to the location of various items in a reference coordinate system, including roads, water features, geographic features, commercial areas, points of interest, restaurants, gas stations, and the like. The map database 160 may store not only the locations of such items, but also descriptors associated with such items, including, for example, names associated with any stored features. In some embodiments, the map database 160 may be physically located with the other components of the system 100. Alternatively or additionally, the map database 160 or a portion thereof may be remotely located relative to the other components of the system 100 (e.g., the processing unit 110). In such embodiments, information from the map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, the map database 160 may store a sparse data model comprising a polynomial representation of certain road features (e.g., lane markings) or a target trajectory of the host vehicle. Figures 8 to 19 Systems and methods for generating such maps are discussed.

[0088] Image capture devices 122, 124, and 126 may each comprise any type of device suitable for capturing at least one image from the environment. Furthermore, any number of image capture devices may be used to acquire images for input to the image processor. Some embodiments may comprise only a single image capture device, while other embodiments may comprise two, three, or even four or more image capture devices. Figures 2B to 2E Image capture devices 122, 124, and 126 are further described.

[0089] The system 100 or its various components may be incorporated into a variety of different platforms. In some embodiments, the system 100 may be included in a vehicle 200, such as Figure 2A For example, the vehicle 200 may be equipped with Figure 1 The processing unit 110 and any other components of the system 100 are described. Although in some embodiments, the vehicle 200 may be equipped with only a single image capture device (e.g., a camera), in other embodiments, such as a combination of Figure 2B-2E As discussed above, multiple image capture devices may be used. For example, Figure 2A As shown, either of the image capture devices 122 and 124 of the vehicle 200 may be part of an ADAS (Advanced Driver Assistance System) imaging suite.

[0090] The image capture device included on the vehicle 200 as part of the image acquisition unit 120 may be positioned in any suitable location. In some embodiments, such as Figure 2A-2E as well as Figure 3A-3C As shown, the image capture device 122 can be located near the rearview mirror. This location can provide a line of sight similar to that of the driver of the vehicle 200, which can help determine what is visible and invisible to the driver. The image capture device 122 can be positioned anywhere near the rearview mirror, and placing the image capture device 122 on the driver's side of the mirror can further help obtain an image representative of the driver's field of view and / or line of sight.

[0091] Other positioning options are also possible for the image capture devices of image acquisition unit 120. For example, image capture device 124 can be located on or in the bumper of vehicle 200. Such positioning may be particularly suitable for image capture devices with a wide field of view. The line of sight of an image capture device located in the bumper may differ from the line of sight of the driver, and therefore, the bumper image capture device and the driver may not always see the same objects. Image capture devices (e.g., image capture devices 122, 124, and 126) can also be located in other positions. For example, the image capture device can be located on or in one or both of the sideview mirrors of vehicle 200, on the roof of vehicle 200, on the hood of vehicle 200, on the trunk of vehicle 200, on the side of vehicle 200, mounted on any window of vehicle 200, positioned behind any window of vehicle 200, or positioned in front of any window of vehicle 200, mounted in or near a light fixture on the front and / or rear of vehicle 200, and the like.

[0092] In addition to the image capture device, vehicle 200 may also include various other components of system 100. For example, processing unit 110 may be included on vehicle 200, either integrated with or separate from the vehicle's engine control unit (ECU). Vehicle 200 may also be equipped with a location sensor 130, such as a GPS receiver, and may also include a map database 160 and memory units 140 and 150.

[0093] As discussed earlier, the wireless transceiver 172 can transmit and / or receive data over one or more networks (e.g., a cellular network, the Internet, etc.). For example, the wireless transceiver 172 can upload data collected by the system 100 to one or more servers and download data from one or more servers. For example, via the wireless transceiver 172, the system 100 can receive periodic or on-demand updates to the data stored in the map database 160, the memory 140, and / or the storage 150. Similarly, the wireless transceiver 172 can upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, the vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0094] The system 100 can upload data to a server (e.g., to the cloud) based on a privacy level setting. For example, the system 100 can implement a privacy level setting to specify or limit the type of data (including metadata) that can be transmitted to the server that can uniquely identify the vehicle and / or the driver / owner of the vehicle. Such settings can be set by the user via, for example, the wireless transceiver 172, can be initialized by factory default settings, or by data received by the wireless transceiver 172.

[0095] In some embodiments, the system 100 may upload data according to a "high" privacy level, and, if set, the system 100 may transmit data (e.g., location information related to the route, captured images, etc.) without any details about a specific vehicle and / or driver / owner. For example, when uploading data according to the "high" privacy setting, the system 100 may not include the vehicle identification number (VIN) or the name of the driver or owner of the vehicle, and may instead transmit data such as captured images and / or limited location information related to the route.

[0096] Other privacy levels are contemplated. For example, the system 100 may transmit data to a server according to an "intermediate" privacy level and may include additional information that is not included at a "high" privacy level, such as the make and / or model of the vehicle and / or the type of vehicle (e.g., passenger car, sport utility vehicle, truck, etc.). In some embodiments, the system 100 may upload data according to a "low" privacy level. With the "low" privacy level set, the system 100 may upload data and include information sufficient to uniquely identify a specific vehicle, owner / driver, and / or a portion or the entire route traveled by the vehicle. Such "low" privacy level data may include one or more of the following: for example, the VIN, the driver / owner's name, the vehicle's point of origin prior to departure, the vehicle's intended destination, the vehicle's make and / or model, the vehicle type, etc.

[0097] Figure 2A is a diagrammatic side view representation of an exemplary vehicle imaging system consistent with the disclosed embodiments. Figure 2B yes Figure 2A A diagrammatic top view of the embodiment shown in FIG. Figure 2B As shown, the disclosed embodiments may include a vehicle 200 including a system 100 within its body having a first image capture device 122 positioned near a rearview mirror of the vehicle 200 and / or near a driver, a second image capture device 124 positioned on or in a bumper area (e.g., one of the bumper areas 210 ) of the vehicle 200 , and a processing unit 110 .

[0098] like Figure 2C As shown, both image capture devices 122 and 124 may be positioned near the rearview mirror of vehicle 200 and / or near the driver. Figure 2B and Figure 2C Two image capture devices 122 and 124 are shown, but it should be understood that other embodiments may include more than two image capture devices. Figure 2D and 2E In the illustrated embodiment, a first image capture device 122 , a second image capture device 124 , and a third image capture device 126 are included in the system 100 of a vehicle 200 .

[0099] like Figure 2D As shown, image capture device 122 may be positioned near a rearview mirror of vehicle 200 and / or near the driver, and image capture devices 124 and 126 may be positioned on or in a bumper area (e.g., one of bumper areas 210) of vehicle 200. Figure 2E As shown, image capture devices 122, 124, and 126 can be positioned near the rearview mirror and / or near the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices can be positioned in any suitable location within or on vehicle 200.

[0100] It should be understood that the disclosed embodiments are not limited to vehicles and can be applied in other scenarios. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200 and can be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0101] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280×960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included, for example, to provide the image capture device with a desired focal length and field of view. In some embodiments, the image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, as Figure 2DAs shown, the image capture device 122 can be configured to capture images with a desired field of view (FOV) 202. For example, the image capture device 122 can be configured to have a conventional FOV, such as in the range of 40 degrees to 56 degrees, including a 46-degree FOV, a 50-degree FOV, a 52-degree FOV, or a larger FOV. Alternatively, the image capture device 122 can be configured to have a narrow FOV in the range of 23 degrees to 40 degrees, such as a 28-degree FOV or a 36-degree FOV. In addition, the image capture device 122 can be configured to have a wide FOV in the range of 100 degrees to 180 degrees. In some embodiments, the image capture device 122 can include a wide-angle bumper camera or a camera with a FOV of up to 180 degrees. In some embodiments, the image capture device 122 can be a 7.2 Mpixel image capture device with an aspect ratio of approximately 2:1 (e.g., HxV = 3800×1900 pixels) with a horizontal FOV of approximately 100 degrees. Such an image capture device can be used in place of a three-image capture device configuration. Due to significant lens distortion, in embodiments where the image capture device uses a radially symmetric lens, the vertical FOV of such an image capture device can be significantly less than 50 degrees. For example, such a lens may not be radially symmetric, which would allow a vertical FOV greater than 50 degrees with a 100-degree horizontal FOV.

[0102] The first image capture device 122 can acquire a plurality of first images of a scene associated with the vehicle 200. Each of the plurality of first images can be acquired as a series of image scan lines, which can be captured using a rolling shutter. Each scan line can contain a plurality of pixels.

[0103] The first image capture device 122 may have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate may refer to the rate at which the image sensor may acquire image data associated with each pixel contained in a particular scan line.

[0104] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, including, for example, CCD sensors or CMOS sensors. In one embodiment, a CMOS image sensor may be employed with a rolling shutter, such that each pixel in a row is read one at a time, and the rows are scanned on a row-by-row basis until the entire image frame has been captured. In some embodiments, the rows may be captured sequentially from top to bottom relative to the frame.

[0105] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) may constitute a high-resolution imager and may have a resolution greater than 5 M pixels, 7 M pixels, 10 M pixels, or more.

[0106] The use of a rolling shutter may cause pixels in different rows to be exposed and captured at different times, which may cause skew and other image artifacts in the captured image frame. On the other hand, when image capture device 122 is configured to operate with a global or synchronized shutter, all pixels may be exposed for the same amount of time and during a common exposure period. As a result, the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a particular time. In contrast, in a rolling shutter application, each row in the frame is exposed and data is captured at a different time. As a result, moving objects may appear distorted in an image capture device with a rolling shutter. This phenomenon will be described in more detail below.

[0107] Second image capture device 124 and third image capture device 126 can be any type of image capture device. Similar to first image capture device 122, each of image capture devices 124 and 126 can include an optical axis. In one embodiment, each of image capture devices 124 and 126 can include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of image capture devices 124 and 126 can include a rolling shutter. Similar to image capture device 122, image capture devices 124 and 126 can be configured to include various lenses and optical elements. In some embodiments, the lenses associated with image capture devices 124 and 126 can provide a FOV (such as FOVs 204 and 206) that is equal to or narrower than the FOV associated with image capture device 122 (such as FOV 202). For example, image capture devices 124 and 126 can have a FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0108] Image capture devices 124 and 126 may capture a plurality of second and third images of a scene associated with vehicle 200. Each of the plurality of second and third images may be captured as second and third series of image scan lines, which may be captured using a rolling shutter. Each scan line or row may have a plurality of pixels. Image capture devices 124 and 126 may have second and third scan rates associated with the capture of each image scan line included in the second and third series.

[0109] Each image capture device 122, 124, and 126 can be positioned at any suitable location and orientation relative to vehicle 200. The relative positions of image capture devices 122, 124, and 126 can 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 FOV 204) may partially or completely overlap with the FOV associated with image capture device 122 (e.g., FOV 202) and the FOV associated with image capture device 126 (e.g., FOV 206).

[0110] Image capture devices 122, 124, and 126 may be located at any suitable relative heights on vehicle 200. In one example, there may be height differences between image capture devices 122, 124, and 126 that may provide sufficient parallax information to enable stereo analysis. Figure 2A As shown, the two image capture devices 122 and 124 are at different heights. For example, there may also be a lateral displacement difference between the image capture devices 122, 124, and 126 to provide additional parallax information for the stereo analysis of the processing unit 110. The difference in lateral displacement can be represented by dx, as Figure 2C and Figure 2D In some embodiments, there may be a forward or backward displacement (e.g., a range displacement) between image capture devices 122, 124, and 126. For example, image capture device 122 may be positioned 0.5 to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of displacement may enable one image capture device to cover a potential blind spot of the other image capture device(s).

[0111] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with image capture device 122 may be higher, lower, or the same as the resolution of the image sensor(s) associated with image capture devices 124 and 126. In some embodiments, the image sensor(s) associated with image capture device 122 and / or image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0112] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame before continuing to capture pixel data associated with the next image frame) can be controllable. The frame rate associated with image capture device 122 can be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 can depend on various factors that may affect the timing of the frame rates. For example, one or more of image capture devices 122, 124, and 126 can include a selectable pixel delay period that is applied before or after acquiring image data associated with one or more pixels of the image sensors in image capture devices 122, 124, and / or 126. Typically, image data corresponding to each pixel can be acquired based on the clock rate used for the device (e.g., one pixel per clock cycle). Furthermore, in embodiments incorporating a rolling shutter, one or more of image capture devices 122, 124, and 126 may include a selectable horizontal blanking period that is applied before or after acquiring image data associated with a row of pixels of an image sensor in image capture devices 122, 124, and / or 126. Furthermore, one or more of image capture devices 122, 124, and / or 126 may include a selectable vertical blanking period that is applied before or after acquiring image data associated with an image frame of image capture devices 122, 124, and 126.

[0113] These timing controls can enable synchronization of the frame rates associated with image capture devices 122, 124, and 126, even if the line scan rate of each is different. Furthermore, as will be discussed in more detail below, these selectable timing controls, along with other factors (e.g., image sensor resolution, maximum line scan rate, etc.), can enable synchronization of image capture from areas where the FOV of image capture device 122 overlaps with one or more of the FOVs of image capture devices 124 and 126, even if the field of view of image capture device 122 is different from the FOVs of image capture devices 124 and 126.

[0114] The frame rate timing in image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, assuming similar line scan rates for both devices, if one device includes an image sensor with a resolution of 640×480 and the other device includes an image sensor with a resolution of 1280×960, more time will be required to acquire a frame of image data from the sensor with the higher resolution.

[0115] Another factor that can affect the timing of image data acquisition in image capture devices 122, 124, and 126 is the maximum line scan rate. For example, a certain minimum amount of time will be required to acquire a line of image data from the image sensors included in image capture devices 122, 124, and 126. Assuming no pixel delay period is added, this minimum amount of time for acquiring a line of image data will be related to the maximum line scan rate for the particular device. Devices that provide higher maximum line scan rates have the potential to provide higher frame rates than devices with lower maximum line scan rates. In some embodiments, one or more of image capture devices 124 and 126 can have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 can be 1.25, 1.5, 1.75, or 2 times, or more, the maximum line scan rate of image capture device 122.

[0116] In another embodiment, image capture devices 122, 124, and 126 may have the same maximum line rate, but image capture device 122 may operate at a scan rate less than or equal to its maximum line rate. The system may be configured such that one or more of image capture devices 124 and 126 operate at a line rate equal to the line rate of image capture device 122. In other examples, the system may be configured such that the line rate of image capture device 124 and / or image capture device 126 may be 1.25, 1.5, 1.75, or 2 or more times the line rate of image capture device 122.

[0117] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric. In other words, they may include cameras with different fields of view (FOVs) and focal lengths. For example, the fields of view of image capture devices 122, 124, and 126 may include any desired area of ​​the environment surrounding vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, behind vehicle 200, to the sides of vehicle 200, or a combination thereof.

[0118] Furthermore, the focal length associated with each image capture device 122, 124, and / or 126 can be selectable (e.g., by including an appropriate lens, etc.) so that each device captures images of objects at a desired range of distances relative to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 can capture images of objects that are within a few meters of the vehicle. The image capture devices 122, 124, and 126 can also be configured to capture images of objects at greater ranges from the vehicle (e.g., 25 meters, 50 meters, 100 meters, 150 meters, or more). In addition, the focal lengths of image capture devices 122, 124, and 126 may be selected so that one image capture device (e.g., image capture device 122) may capture images of objects that are relatively close to the vehicle (e.g., within 10 meters or within 20 meters), while other image capture devices (e.g., image capture devices 124 and 126) may capture images of objects that are farther away from the vehicle 200 (e.g., greater than 20 meters, 50 meters, 100 meters, 150 meters, etc.).

[0119] According to some embodiments, the FOV of one or more image capture devices 122, 124, and 126 may have a wide angle. For example, having a FOV of 140 degrees may be advantageous, particularly for image capture devices 122, 124, and 126 that may be used to capture images of areas near vehicle 200. For example, image capture device 122 may be used to capture images of areas to the right or left of vehicle 200, and in such embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0120] The field of view associated with each of image capture devices 122, 124, and 126 may depend on the corresponding focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0121] Image capture devices 122, 124, and 126 can be configured to have any suitable field of view. In one specific example, image capture device 122 can have a horizontal FOV of 46 degrees, image capture device 124 can have a horizontal FOV of 23 degrees, and image capture device 126 can have a horizontal FOV between 23 degrees and 46 degrees. In one specific example, image capture device 122 can have a horizontal FOV of 52 degrees, image capture device 124 can have a horizontal FOV of 26 degrees, and image capture device 126 can 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 can vary from 1.5 to 2.0. In other embodiments, the ratio can vary between 1.25 and 2.25.

[0122] System 100 can be configured such that the field of view of image capture device 122 at least partially or completely overlaps the field of view of image capture device 124 and / or image capture device 126. In some embodiments, system 100 can be configured such that the fields of view of image capture devices 124 and 126, for example, fall within (e.g., are narrower than) the field of view of image capture device 122 and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 can capture adjacent FOVs or can have partial overlap in their FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 can be aligned such that the center of the narrower FOV image capture devices 124 and / or 126 can be located in the lower half of the field of view of the wider FOV device 122.

[0123] Figure 2F is a diagrammatic representation of an exemplary vehicle control system consistent with the disclosed embodiments. Figure 2F As indicated, the vehicle 200 may include a throttle regulation system 220, a braking system 230, and a steering system 240. The system 100 may provide input (e.g., control signals) to one or more of the throttle regulation system 220, the braking system 230, and the steering system 240 via one or more data links (e.g., any wired and / or wireless links for transmitting data). For example, based on analysis of images acquired by the image capture devices 122, 124, and / or 126, the system 100 may provide control signals to one or more of the throttle regulation system 220, the braking system 230, and the steering system 240 to navigate the vehicle 200 (e.g., by causing acceleration, steering, lane shifting, etc.). In addition, the system 100 may receive input from one or more of the throttle regulation system 220, the braking system 230, and the steering system 240 that indicates an operating condition of the vehicle 200 (e.g., speed, whether the vehicle 200 is braking and / or steering, etc.). The following is in conjunction with Figures 4 to 7 Provide further details.

[0124] like Figure 3AAs shown, vehicle 200 may also include a user interface 170 for interacting with the driver or passengers of vehicle 200. For example, user interface 170 in a vehicle application may include a touch screen 320, a knob 330, buttons 340, and a microphone 350. The driver or passengers of vehicle 200 may also interact with system 100 using handles (e.g., located on or near the steering column of vehicle 200, including, for example, a turn signal handle), buttons (e.g., located on the steering wheel of vehicle 200), and the like. In some embodiments, microphone 350 may be positioned adjacent to rearview mirror 310. Similarly, in some embodiments, image capture device 122 may be located near rearview mirror 310. In some embodiments, user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, system 100 may provide various notifications (e.g., alarms) via speakers 360.

[0125] Figures 3B to 3D is an illustration of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and against a vehicle windshield, consistent with the disclosed embodiments. Figure 3B As shown, camera mount 370 can include image capture devices 122, 124, and 126. Image capture devices 124 and 126 can be positioned behind a sun visor 380, which can be flush with the vehicle windshield and include a film and / or a composite of anti-reflective materials. For example, sun visor 380 can be positioned so that the visor is aligned relative to the vehicle windshield with a matching bevel. In some embodiments, each of image capture devices 122, 124, and 126 can be positioned behind sun visor 380, for example, Figure 3D The disclosed embodiments are not limited to any particular configuration of image capture devices 122 , 124 , and 126 , camera mount 370 , and light shield 380 . Figure 3C yes Figure 3B An illustration of camera mount 370 is shown from a front perspective.

[0126] As will be appreciated by those skilled in the art having the benefit of this disclosure, numerous variations and / or modifications may be made to the aforementioned disclosed embodiments. For example, not all components are necessary for the operation of system 100. Furthermore, any component may be located in any suitable portion of system 100 and components may be rearranged into various configurations while providing the functionality of the disclosed embodiments. Therefore, the aforementioned configurations are exemplary, and regardless of the configurations discussed above, system 100 may provide a wide range of functionality for analyzing the surroundings of vehicle 200 and navigating vehicle 200 in response to that analysis.

[0127] As discussed in greater detail below and in accordance with various disclosed embodiments, system 100 can provide various features related to autonomous driving and / or driver assistance technologies. For example, system 100 can analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 can collect data for analysis from, for example, image acquisition unit 120, location sensor 130, and other sensors. Furthermore, system 100 can analyze the collected data to determine whether vehicle 200 should take a certain action and then automatically take the determined action without human intervention. For example, while vehicle 200 is navigating without human intervention, system 100 can automatically control braking, acceleration, and / or steering of vehicle 200 (e.g., by transmitting control signals to one or more of throttle control system 220, braking system 230, and steering system 240). Furthermore, system 100 can analyze the collected data and, based on the analysis of the collected data, issue warnings and / or alerts to vehicle occupants. Additional details regarding various embodiments provided by system 100 are provided below.

[0128] Forward multi-imaging system

[0129] As discussed above, system 100 can provide driver assistance functionality using a multi-camera system. A multi-camera system can use one or more cameras facing the front of the vehicle. In other embodiments, the multi-camera system can include one or more cameras facing the sides or rear of the vehicle. In one embodiment, for example, system 100 can use a dual-camera imaging system, wherein a first camera and a second camera (e.g., image capture devices 122 and 124) can be positioned in front of and / or to the sides of a vehicle (e.g., vehicle 200). The first camera can have a field of view that is larger than, smaller than, or partially overlaps with the field of view of the second camera. In addition, the first camera can be connected to a first image processor to perform monocular image analysis of the image provided by the first camera, and the second camera can be connected to a second image processor to perform monocular image analysis of the image provided by the second camera. The outputs of the first and second image processors (e.g., processed information) can be combined. In some embodiments, the second image processor can receive images from both the first and second cameras to perform stereo analysis. In another embodiment, system 100 can use a three-camera imaging system, wherein each camera has a different field of view. Thus, such a system can make decisions based on information derived from objects located at different distances in front of and to the side of the vehicle. References to monocular image analysis can refer to instances where image analysis is performed based on images captured from a single viewpoint (e.g., from a single camera). Stereoscopic image analysis can refer to instances where image analysis is performed based on two or more images captured using one or more variations of image capture parameters. For example, captured images suitable for stereoscopic image analysis can include images captured from two or more different positions, from different fields of view, using different focal lengths, and with disparity information, etc.

[0130] 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 another value selected from a range of approximately 20 degrees to 45 degrees), image capture device 124 may provide a wide field of view (e.g., 150 degrees or another value selected from a range of approximately 100 degrees to approximately 180 degrees), and image capture device 126 may provide an intermediate field of view (e.g., 46 degrees or another value selected from a range of approximately 35 degrees to approximately 60 degrees). In some embodiments, image capture device 126 may serve as the primary or base camera. Image capture devices 122, 124, and 126 may be positioned behind rearview mirror 310 and positioned substantially side-by-side (e.g., 6 centimeters apart). Furthermore, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 may be mounted behind sun visor 380 flush with the windshield of vehicle 200. Such shielding may be used to minimize the effect of any reflections from the interior of the vehicle on image capture devices 122 , 124 , and 126 .

[0131] In another embodiment, as above combined Figure 3B and Figure 3C As discussed, the wide field of view camera (e.g., image capture device 124 in the above example) can be mounted lower than the narrow field of view camera and the main field of view camera (e.g., image capture devices 122 and 126 in the above example). This configuration can provide a clear line of sight from the wide field of view camera. To reduce reflections, the camera can be mounted closer to the windshield of vehicle 200, and a polarizer can be included on the camera to dampen reflected light.

[0132] A three-camera system can provide certain performance characteristics. For example, some embodiments may include the ability for one camera to verify the detection of an object based on the detection results from another camera. In the three-camera configuration discussed above, the processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), where each processing device is dedicated to processing images captured by one or more of the image capture devices 122, 124, and 126.

[0133] In a three-camera system, the first processing device can receive images from both the main camera and the narrow field of view camera and perform vision processing for the narrow FOV camera, for example, to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Furthermore, the first processing device can calculate the disparity of pixels between the images from the main camera and the narrow camera and create a 3D reconstruction of the vehicle 200's environment. The first processing device can then combine the 3D reconstruction with 3D map data, or with 3D information calculated based on information from another camera.

[0134] The second processing device can receive images from the primary camera and perform visual processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Furthermore, the second processing device can calculate camera displacement and, based on this displacement, calculate the disparity of pixels between consecutive images and create a 3D reconstruction of the scene (e.g., structure from motion). The second processing device can transmit the structure from motion based on the 3D reconstruction to the first processing device for combination with the stereoscopic 3D image.

[0135] The third processing device may receive images from the wide FOV camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device may further execute additional processing instructions to analyze the images to identify moving objects in the images, such as vehicles changing lanes, pedestrians, etc.

[0136] In some embodiments, having streams of image-based information captured and processed independently can provide an opportunity to provide redundancy in the system. Such redundancy can include, for example, using a first image capture device and images processed from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0137] In some embodiments, system 100 may use two image capture devices (e.g., image capture devices 122 and 124) to provide navigation assistance for vehicle 200, and use a third image capture device (e.g., image capture device 126) to provide redundancy and validate 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 performed by system 100 for navigating vehicle 200, while image capture device 126 may provide images for monocular analysis performed by system 100 to provide redundancy and validate information derived from images captured by image capture device 122 and / or image capture device 124. In other words, image capture device 126 (and a corresponding processing device) may be considered to provide a redundant subsystem for providing a check on the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Additionally, in some embodiments, redundancy and validation of received data 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.).

[0138] Those skilled in the art will recognize that the above-described camera configurations, camera placements, number of cameras, camera positioning, etc. are merely examples. These components and other components described with respect to the overall system can be assembled and used in a variety of different configurations without departing from the scope of the disclosed embodiments. Further details regarding the use of a multi-camera system to provide driver assistance and / or autonomous vehicle functionality are as follows.

[0139] Figure 4 1 is an exemplary functional block diagram of memory 140 and / or memory 150, which may be stored / programmed with instructions for performing one or more operations consistent with embodiments of the present disclosure. Although the following refers to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0140] like Figure 4 As shown, memory 140 may store a monocular image analysis module 402, a stereo image analysis module 404, a velocity and acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of modules 402, 404, 406, and 408 contained in memory 140. Those skilled in the art will appreciate that references to processing unit 110 in the following discussion may refer separately or collectively to application processor 180 and image processor 190. Accordingly, any of the steps of the following processes may be performed by one or more processing devices.

[0141] In one embodiment, the monocular image analysis module 402 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform monocular image analysis on a set of images acquired by one of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. 5A to 5D As described, the monocular image analysis module 402 may include instructions for detecting a set of features within a set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other features associated with the vehicle's environment. Based on this analysis, the system 100 (e.g., via the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, acceleration changes, etc., as discussed below in conjunction with the navigation response module 408.

[0142] In one embodiment, stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform stereo image analysis on a first set of images and a second set of images acquired by a combination of image capture devices selected from any of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from the first set of images and the second set of images with additional sensory information (e.g., information from radar) to perform stereo image analysis. For example, stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. As described below in conjunction with Figure 6 As described, stereo image analysis module 404 may include instructions for detecting a set of features within the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and the like. Based on this analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, such as steering, lane changes, changes in acceleration, and the like, as discussed below in conjunction with navigation response module 408. Furthermore, in some embodiments, stereo image analysis module 404 may implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems, such as systems that may be configured to use computer vision algorithms to detect and / or label objects in an environment from which sensory information is captured and processed. In one embodiment, stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0143] In one embodiment, the speed and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in the vehicle 200 that are configured to cause changes in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 may execute instructions associated with the speed and acceleration module 406 to calculate a target speed for the vehicle 200 based on data derived from executing the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, speed, and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, position information of the vehicle 200 relative to lane markings on the road, etc. Additionally, the processing unit 110 may calculate the target speed for the vehicle 200 based on sensory input (e.g., information from radar) and input from other systems of the vehicle 200, such as the throttle control system 220, the braking system 230, and / or the steering system 240. Based on the calculated target speed, the processing unit 110 can transmit an electrical signal to the throttle regulation system 220, the braking system 230 and / or the steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration by, for example, physically pressing the brake or releasing the accelerator of the vehicle 200.

[0144] In one embodiment, the navigation response module 408 may store software that is executable by the processing unit 110 to determine a desired navigation response based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include position and velocity information associated with nearby vehicles, pedestrians, and road objects, target position information for the vehicle 200, and the like. Furthermore, in some embodiments, the navigation response may be based (in part or in whole) on map data, a predetermined position of the vehicle 200, and / or a relative velocity or 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 also determine the desired navigation response based on sensory input (e.g., information from radar) and input from other systems of the vehicle 200, such as the throttle control system 220, the braking system 230, and the steering system 240 of the vehicle 200. Based on the desired navigation response, the processing unit 110 may transmit electrical signals to the throttle adjustment system 220, the braking system 230, and the steering system 240 of the vehicle 200 to trigger the desired navigation response by, for example, turning the steering wheel of the vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as input to execute the speed and acceleration module 406 to calculate the change in the speed of the vehicle 200.

[0145] Furthermore, any modules disclosed herein (e.g., modules 402, 404, and 406) may implement techniques associated with trained systems (such as neural networks or deep neural networks) or untrained systems.

[0146] Figure 5A is a flow chart illustrating an exemplary process 500A for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via the data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera (such as the image capture device 122 having the field of view 202) included in the image acquisition unit 120 may capture a plurality of images of an area in front of the vehicle 200 (e.g., or to the side or rear of the vehicle) and transmit them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). At step 520, the processing unit 110 may execute the monocular image analysis module 402 to analyze the plurality of images, as described below in conjunction with Figures 5B to 5D By performing this analysis, processing unit 110 can detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0147] At step 520, the processing unit 110 may also execute the monocular image analysis module 402 to detect various road hazards, such as, for example, parts of a truck tire, fallen road signs, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of such hazards more difficult. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road hazards. For example, the processing unit 110 may estimate the camera motion between consecutive image frames and calculate the disparity in pixels between 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 the hazards present on the road surface.

[0148] At step 530, the processing unit 110 may execute the navigation response module 408 to perform the navigation response based on the analysis performed at step 520 and the above combination. Figure 4The techniques described herein are used to cause one or more navigation responses. The navigation responses may include, for example, steering, lane changing, braking, changes in acceleration, etc. In some embodiments, the processing unit 110 may use data derived from the execution speed and acceleration module 406 to cause the one or more navigation responses. In addition, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 may cause the vehicle 200 to change lanes and then accelerate by, for example, transmitting control signals to the steering system 240 and the throttle adjustment system 220 of the vehicle 200 in sequence. Alternatively, the processing unit 110 may cause the vehicle 200 to brake while changing lanes by, for example, transmitting control signals to the braking system 230 and the steering system 240 of the vehicle 200 simultaneously.

[0149] Figure 5B is a flow chart illustrating an exemplary process 500B for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to implement process 500B. At step 540, processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 may scan one or more images, compare the images to one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or portions thereof). The predetermined patterns may be designed in such a way as to achieve a high "false hit" rate and a low "miss" rate. For example, processing unit 110 may apply a low similarity threshold to the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. Doing so may allow processing unit 110 to reduce the likelihood of missing (e.g., failing to identify) candidate objects representing vehicles or pedestrians.

[0150] At step 542, processing unit 110 may filter the set of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria may be derived from various attributes associated with object type categories stored in a database (e.g., a database stored in memory 140). Attributes may include object shape, size, texture, location (e.g., relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to reject false candidates from the set of candidate objects.

[0151] At step 544, processing unit 110 may analyze multiple frames of imagery to determine whether an object in the set of candidate objects represents a vehicle and / or a pedestrian. For example, processing unit 110 may track detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to vehicle 200, etc.). In addition, processing unit 110 may estimate parameters of the detected object and compare the frame-by-frame position data of the object with the predicted position.

[0152] At step 546, processing unit 110 may construct a set of measurements for the detected object. Such measurements may include, for example, position, velocity, and acceleration values ​​associated with the detected object (relative to vehicle 200). In some embodiments, processing unit 110 may construct the measurements based on estimation techniques such as a Kalman filter or linear quadratic estimation (LQE) using a series of time-based observations and / or based on modeling data available for different object categories (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter may be based on a measure of the scale of the object, where the measure of scale is proportional to the time to collision (e.g., the amount of time it takes for vehicle 200 to reach the object). Thus, by performing steps 540 to 546, processing unit 110 may identify vehicles and pedestrians that appear within the set of captured images and derive information associated with the vehicles and pedestrians (e.g., position, velocity, size). Based on this identification and the derived information, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in conjunction with Figure 5A described.

[0153] At step 548, the processing unit 110 may perform an optical flow analysis on the one or more images to reduce the likelihood of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing motion patterns relative to the vehicle 200, associated with other vehicles and pedestrians, and distinct from the motion of the road surface in one or more images. The processing unit 110 may calculate the motion of the candidate objects by observing the different positions of the objects across multiple image frames captured at different times. The processing unit 110 may use the position and time values ​​as input to a mathematical model for calculating the motion of the candidate objects. Therefore, optical flow analysis may provide another method for detecting vehicles and pedestrians near the vehicle 200. The processing unit 110 may perform optical flow analysis in conjunction with steps 540 to 546 to provide redundancy for detecting vehicles and pedestrians and improve the reliability of the system 100.

[0154] Figure 5Cis a flow chart illustrating an exemplary process 500C for detecting road signs and / or lane geometry information in a set of images consistent with the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to implement process 500C. At step 550, processing unit 110 may detect a set of objects by scanning one or more images. In order to detect road segments of lane signs, lane geometry information, and other relevant road signs, processing unit 110 may filter the set of objects to exclude objects determined to be irrelevant (e.g., small potholes, small rocks, etc.). At step 552, processing unit 110 may group together road segments detected in step 550 that belong to the same road sign or lane marking. Based on the grouping, processing unit 110 may generate a model, such as a mathematical model, representing the detected road segments.

[0155] At step 554, the processing unit 110 may construct a set of measurements associated with the detected road segment. In some embodiments, the processing unit 110 may create a projection of the detected road segment from the image plane onto the real-world plane. The projection may be characterized using a cubic polynomial having coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivatives of the detected road. When generating the projection, the processing unit 110 may take into account changes in the road surface, as well as the pitch and roll rates associated with the vehicle 200. In addition, the processing unit 110 may model the road elevation by analyzing position and motion cues present on the road surface. Furthermore, the processing unit 110 may estimate the pitch and roll rates associated with the vehicle 200 by tracking a set of feature points in one or more images.

[0156] At step 556, processing unit 110 may perform a multi-frame analysis by, for example, tracking the detected road segments across consecutive image frames and accumulating frame-by-frame data associated with the detected road segments. As processing unit 110 performs multi-frame analysis, the set of measurements constructed at step 554 may become more reliable and associated with increasingly higher confidence levels. Thus, by performing steps 550, 552, 554, and 556, processing unit 110 may identify road signs appearing in the set of captured images and derive lane geometry information. Based on this identification and the derived information, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in conjunction with Figure 5A described.

[0157] At step 558, processing unit 110 may consider additional information sources to further generate a safety model of vehicle 200 in its surrounding environment. Processing unit 110 may use the safety model to define a context in which system 100 can safely perform autonomous control of vehicle 200. To generate this safety model, in some embodiments, processing unit 110 may consider the position and motion of other vehicles, detected curbs and guardrails, and / or a general road shape description extracted from map data (such as data from map database 160). By considering additional information sources, processing unit 110 can provide redundancy for detecting road signs and lane geometry and increase the reliability of system 100.

[0158] Figure 5D is a flow chart illustrating an exemplary process 500D for detecting traffic lights in a set of images consistent with the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to implement process 500D. At step 560, processing unit 110 may scan the set of images and identify objects appearing in the images at locations that may contain traffic lights. For example, processing unit 110 may filter the identified objects to construct a set of candidate objects, excluding those that are unlikely to correspond to traffic lights. Filtering may be performed based on various attributes associated with traffic lights, such as shape, size, texture, position (e.g., relative to vehicle 200), etc. Such attributes may be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, processing unit 110 may perform a multi-frame analysis of the set of candidate objects that reflect possible traffic lights. For example, processing unit 110 may track candidate objects across consecutive image frames, estimate the real-world positions of the candidate objects, and filter out objects that are moving (and therefore unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects and identify the relative locations of the detected colors that appear within possible traffic lights.

[0159] At step 562, processing unit 110 may analyze the geometry of the intersection. The analysis may be based on any combination of: (i) the number of lanes detected on either side of vehicle 200, (ii) detected signs (e.g., arrow signs) on the road, and (iii) a description of the intersection extracted from map data (e.g., data from map database 160). Processing unit 110 may use information derived from executing monocular analysis module 402 to perform the analysis. In addition, processing unit 110 may determine the correspondence between the traffic lights detected at step 560 and the lanes present near vehicle 200.

[0160] At step 564, as the vehicle 200 approaches the intersection, the processing unit 110 may update the confidence level associated with the analyzed intersection geometry and detected traffic lights. For example, the number of traffic lights estimated to be present at the intersection compared to the number of traffic lights actually present at the intersection may affect the confidence level. Therefore, based on the confidence level, the processing unit 110 may delegate control to the driver of the vehicle 200 in order to improve safety conditions. By performing steps 560, 562, and 564, the processing unit 110 may identify the traffic lights that appear within the set of captured images and analyze the intersection geometry information. Based on this identification and analysis, the processing unit 110 may cause one or more navigation responses in the vehicle 200, as described above in conjunction with Figure 5A described.

[0161] Figure 5E is a flow chart illustrating an exemplary process 500E for inducing one or more navigation responses in vehicle 200 based on a vehicle path consistent with the disclosed embodiments. At step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path may be represented by a set of points expressed in coordinates (x, z), and a distance d between two points in the set of points. i May fall within the range of 1 to 5 meters. In one embodiment, the processing unit 110 may construct an initial vehicle path using two polynomials, such as a left road polynomial and a right road polynomial. The processing unit 110 may calculate the geometric midpoint between the two polynomials and offset each point included in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset), if any (a zero offset may correspond to driving in the middle of the lane). The offset may be in a direction perpendicular to the road segment between any two points in the vehicle path. In another embodiment, the processing unit 110 may use a polynomial and an estimated lane width to offset each point of the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0162] At step 572, the processing unit 110 may update the vehicle path constructed at step 570. The processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution so that the d between two points in the set of points representing the vehicle path is k Less than the distance d as mentioned above i For example, the distance dk may fall within the range of 0.1 to 0.3 meters. The processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may generate a cumulative distance vector S corresponding to the total length of the vehicle path (i.e., based on the set of points representing the vehicle path).

[0163] At step 574, the processing unit 110 may determine a look-ahead point (expressed in coordinates (x l , z l )). The processing unit 110 can extract a look-ahead point from the accumulated distance vector S, and the look-ahead point can be associated with a look-ahead distance and a look-ahead time. The look-ahead distance can have a lower limit ranging from 10 meters to 20 meters and can be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, as the speed of the vehicle 200 decreases, the look-ahead distance can also decrease (e.g., until it reaches the lower limit). The look-ahead time can range from 0.5 to 1.5 seconds and can be inversely proportional to the gain of one or more control loops associated with causing a navigation response in the vehicle 200, such as a heading error tracking control loop. For example, the gain of the heading error tracking control loop can depend on the bandwidth of the yaw rate loop, the steering actuator loop, the lateral dynamics of the vehicle, etc. Therefore, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0164] At step 576, the processing unit 110 may determine the heading error and yaw rate command based on the foresight point determined at step 574. The processing unit 110 may calculate the arc tangent of the foresight point, such as arctan(x l / z l ) to determine the heading error. The processing unit 110 may determine the yaw rate command as the product of the heading error and the high-level control gain. If the look-ahead distance is not at the lower limit, the high-level control gain may be equal to: (2 / look-ahead time). Otherwise, the high-level control gain may be equal to: (2×vehicle 200 speed / look-ahead distance).

[0165] Figure 5F FIGURE 5 is a flow chart illustrating an exemplary process 500F for determining whether a leading vehicle is changing lanes consistent with the disclosed embodiments. At step 580, the processing unit 110 may determine navigation information associated with a leading vehicle (e.g., a vehicle traveling in front of the vehicle 200). For example, the processing unit 110 may use the above combined Figure 5A and Figure 5B The described techniques can be used to determine the position, velocity (e.g., direction and speed), and / or acceleration of the vehicle ahead. The processing unit 110 can also use the above combined Figure 5E The described techniques determine one or more road polynomials, forward view points (associated with vehicle 200 ), and / or tracking trajectories (eg, a set of points describing a path taken by a leading vehicle).

[0166] At step 582, processing unit 110 may analyze the navigation information determined in step 580. In one embodiment, processing unit 110 may calculate the distance between the tracking trajectory and the road polynomial (e.g., along the trajectory). If the change in this distance along the trajectory exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a sharply curved road), processing unit 110 may determine that the leading vehicle is likely changing lanes. In the event that multiple vehicles are detected traveling ahead of vehicle 200, processing unit 110 may compare the tracking trajectory associated with each vehicle. Based on this comparison, processing unit 110 may determine that a vehicle whose tracking trajectory does not match the tracking trajectory of the other vehicles is likely changing lanes. Processing unit 110 may also compare the curvature of the tracking trajectory (associated with the leading vehicle) with the expected curvature of the road segment in which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., data from map database 160), from a road polynomial, from tracked trajectories of other vehicles, from prior knowledge about the road, etc. If the difference between the curvature of the tracked trajectory and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely changing lanes.

[0167] In another embodiment, the processing unit 110 may compare the instantaneous position of the preceding vehicle with a forward sight point (associated with the vehicle 200) over a specific time period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the preceding vehicle and the forward sight point changes during the specific time period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a sharply curved road), the processing unit 110 may determine that the preceding vehicle is likely changing lanes. In another embodiment, the processing unit 110 may analyze the geometry of the tracking trajectory by comparing the lateral distance traveled along the tracking trajectory with the expected curvature of the tracking path. The expected radius of curvature may be determined based on the calculation: (δ z 2 +δ x 2 ) / 2 / (δ x ), where δ x represents the lateral travel distance and δ zThe longitudinal distance traveled is represented by the curvature. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 can determine that the leading vehicle is likely to be changing lanes. In another embodiment, the processing unit 110 can analyze the position of the leading vehicle. If the position of the leading vehicle obscures the road polynomial (e.g., the leading vehicle is overlaid on top of the road polynomial), the processing unit 110 can determine that the leading vehicle is likely to be changing lanes. In the event that the position of the leading vehicle is such that another vehicle is detected in front of the leading vehicle and the tracking trajectories of the two vehicles are not parallel, the processing unit 110 can determine that the (closer) leading vehicle is likely to be changing lanes.

[0168] At step 584, processing unit 110 may determine whether leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make this determination based on a weighted average of the individual analyses performed at step 582. Under such an approach, for example, a determination by processing unit 110 that a leading vehicle is likely changing lanes based on a particular type of analysis may be assigned a value of "1" (and "0" may be used to indicate a determination that a leading vehicle is unlikely to be changing lanes). Different analyses performed at step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0169] Figure 6 6 is a flow chart illustrating an exemplary process 600 for eliciting one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments. At step 610, processing unit 110 may receive a first and second plurality of images via data interface 128. For example, cameras included in image acquisition unit 120 (such as image capture devices 122 and 124 having fields of view 202 and 204) may capture a first and second plurality of images of an area in front of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive the first and second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0170] At step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis on the first and second plurality of images to create a 3D map of the road ahead of the vehicle and detect features within the image, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. Figures 5A to 5DStereo image analysis can be performed in a manner similar to the steps described above. For example, processing unit 110 can execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) within the first and second pluralities of images, filter out a subset of candidate objects based on various criteria, perform multi-frame analysis, construct measurements, and determine confidence levels for the remaining candidate objects. When performing the above steps, processing unit 110 can consider information from both the first and second pluralities of images, rather than just one set of images. For example, processing unit 110 can analyze differences in pixel-level data (or other subsets of data from the two streams of captured images) for candidate objects appearing in both the first and second pluralities of images. As another example, processing unit 110 can estimate the position and / or velocity of a candidate object (e.g., relative to vehicle 200) by observing whether an object appears in one of the multiple images but not in the other, or other possible differences relative to objects appearing in the two image streams. For example, the position, velocity, and / or acceleration relative to vehicle 200 can be determined based on features such as trajectory, position, movement characteristics, etc. associated with the object appearing in one or both image streams.

[0171] At step 630, the processing unit 110 may execute the navigation response module 408 to perform the navigation response based on the analysis performed at step 620 and the above combination. Figure 4 The described techniques may be used to cause one or more navigation responses in the vehicle 200. The navigation responses may include, for example, steering, changing lanes, changes in acceleration, changes in speed, braking, etc. In some embodiments, the processing unit 110 may use data derived from executing the speed and acceleration module 406 to cause the one or more navigation responses. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0172] Figure 7is a flow chart illustrating an exemplary process 700 for inducing one or more navigation responses based on analysis of three sets of images, consistent with the disclosed embodiments. At step 710, processing unit 110 may receive first, second, and third pluralities of images via data interface 128. For example, cameras included in image acquisition unit 120 (such as image capture devices 122, 124, and 126 having fields of view 202, 204, and 206) may capture first, second, and third pluralities of images of areas in front of and / or to the sides of vehicle 200 and transmit them to processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, processing unit 110 may receive the first, second, and third pluralities of images via three or more data interfaces. For example, each of image capture devices 122, 124, 126 may have an associated data interface for communicating data to processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0173] At step 720, the processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. This analysis may be performed similarly to the above combined Figures 5A-5D and Figure 6 For example, the processing unit 110 may perform a monocular image analysis on each of the first, second, and third plurality of images (e.g., via execution of the monocular image analysis module 402 and based on the above combination). 5A to 5D Alternatively, the processing unit 110 may perform stereoscopic image analysis on the first and second pluralities of images, the second and third pluralities of images, and / or the first and third pluralities of images (e.g., via execution of the stereoscopic image analysis module 404 and based on the above combination). Figure 6 4 and 5. The processing unit 110 may perform a combination of monocular and stereo image analysis. For example, the processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via execution by the monocular image analysis module 402) and stereo image analysis on the second and third pluralities of images (e.g., via execution by the stereo image analysis module 404). The configuration of the image capture devices 122, 124, and 126—including their respective positioning and fields of view 202, 204, and 206—may affect the type of analysis performed on the first, second, and third pluralities of images. The disclosed embodiments are not limited to a particular configuration of the image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third pluralities of images.

[0174] In some embodiments, processing unit 110 may test system 100 based on the images acquired and analyzed in steps 710 and 720. Such testing may provide an indicator of the overall performance of system 100 for certain configurations of image acquisition devices 122, 124, and 126. For example, processing unit 110 may determine the proportion of "false hits" (e.g., instances where system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses."

[0175] At step 730, the processing unit 110 may cause one or more navigation responses in the vehicle 200 based on information derived from two of the first, second, and third pluralities of images. The selection of two of the first, second, and third pluralities of images may depend on various factors, such as, for example, the number, type, and size of objects detected in each of the plurality of images. The processing unit 110 may also make the selection based on image quality and resolution, the effective field of view reflected in the image, the number of frames captured, the degree to which one or more objects of interest actually appear in the frames (e.g., the percentage of frames in which the objects appear, the proportion of the objects appearing in each such frame), etc.

[0176] In some embodiments, processing unit 110 may select information derived from two of the first, second, and third pluralities of images by determining how consistent the information derived from one image source is with information derived from the other image sources. For example, processing unit 110 may combine processed information derived from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination thereof) and determine visual indicators (e.g., lane markings, detected vehicles and their locations and / or paths, detected traffic lights, etc.) that are consistent between each captured image from image capture devices 122, 124, and 126. Processing unit 110 may also exclude information that is inconsistent between the captured images (e.g., vehicles changing lanes, lane models indicating that a vehicle is too close to vehicle 200, etc.). Thus, processing unit 110 may select information derived from two of the first, second, and third pluralities of images based on determining consistent and inconsistent information.

[0177] The navigation response may include, for example, steering, lane changing, braking, acceleration change, etc. The processing unit 110 may make a decision based on the analysis performed in step 720 and the above combination. Figure 4The processing unit 110 may also use data derived from executing the speed and acceleration module 406 to cause one or more navigation responses. In some embodiments, the processing unit 110 may cause one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration between the vehicle 200 and an object detected within any of the first, second, and third pluralities of images. The multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0178] Sparse road models for autonomous vehicle navigation

[0179] In some embodiments, the disclosed systems and methods can utilize sparse maps for autonomous vehicle navigation. In particular, sparse maps can be used for autonomous vehicle navigation along road segments. For example, sparse maps can provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed in greater detail below, an autonomous vehicle can use a sparse map to navigate one or more roads based on one or more stored trajectories.

[0180] Sparse maps for autonomous vehicle navigation

[0181] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, a 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 can be an autonomous vehicle) can use a sparse map to navigate one or more roads. For example, in some embodiments, a sparse map can contain data related to roads and potential landmarks along the roads that may be sufficient for vehicle navigation but also exhibit a small data footprint. For example, the sparse data maps described in detail below may require significantly less storage space and data transfer bandwidth than digital maps that contain detailed map information (such as image data collected along the roads).

[0182] For example, a sparse data map can store a three-dimensional polynomial representation of a preferred vehicle path along a road, rather than storing a detailed representation of a road segment. These paths may require very little data storage space. In addition, in the described sparse data map, landmarks can be identified and included in the sparse map road model to assist navigation. These landmarks can be located at any spacing suitable for enabling vehicle navigation, but in some cases, these landmarks do not need to be identified and included in the model at high density and short spacing. On the contrary, in some cases, navigation based on landmarks that are at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart is possible. As will be discussed in more detail in other sections, a sparse map can be generated based on data collected or measured by a vehicle equipped with various sensors and devices (such as image capture devices, global positioning system sensors, motion sensors, etc.) as the vehicle travels along the road. In some cases, a sparse map can be generated based on data collected during multiple drives of one or more vehicles along a specific road. Generating a sparse map using multiple drives of one or more vehicles can be referred to as a "crowdsourced" sparse map.

[0183] Consistent with the disclosed embodiments, an autonomous vehicle system can use a sparse map for navigation. For example, the disclosed systems and methods can allocate a sparse map for generating a road navigation model for an autonomous vehicle, and can use the sparse map and / or the generated road navigation model to navigate the autonomous vehicle along a road segment. A sparse map consistent with the present disclosure can include one or more three-dimensional contours that can represent predetermined trajectories that autonomous vehicles can traverse as they move along the associated road segment.

[0184] Sparse maps consistent with the present disclosure may also include data representing one or more road features. Such road features may include recognizable landmarks, road signature outlines, and any other road-related features useful in vehicle navigation. Sparse maps consistent with the present disclosure may enable autonomous navigation of a vehicle based on a relatively small amount of data contained in the sparse map. For example, the disclosed embodiments of the sparse map may require a relatively small amount of storage space (and relatively small bandwidth when portions of the sparse map are transmitted to the vehicle), but may still adequately provide autonomous vehicle navigation, rather than including detailed representations of roads, such as curbs, road curvature, images associated with road segments, or data detailing other physical features associated with the road segments. In some embodiments, the small data footprint of the disclosed sparse maps may be achieved by storing representations of road-related elements that require a small amount of data but still enable autonomous navigation, which will be discussed in further detail below.

[0185] For example, the disclosed sparse map may store a polynomial representation of one or more trajectories that a vehicle may follow along a road, rather than storing a detailed representation of various aspects of the road. Thus, using the disclosed sparse map, a vehicle may be navigated along a particular road segment, rather than storing (or having to transmit) details about the physical properties of the road to enable navigation along the road, in some cases without having to account for the physical aspects of the road, but rather by aligning the path it travels with a trajectory (e.g., a polynomial spline) along the particular road segment. In this way, a vehicle may be navigated primarily based on stored trajectories (e.g., polynomial splines), which may require significantly less storage space than approaches involving storage of road images, road parameters, road layouts, etc.

[0186] In addition to the stored polynomial representations of trajectories along a 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 a digital signature derived from a digital image (or digital signal) obtained by a sensor (e.g., a camera or other sensor, such as a suspension sensor) on a vehicle traveling along the road segment. The digital signature may have a reduced size relative to the signal obtained by the sensor. In some embodiments, the digital signature may be created to be compatible with a classifier function configured to detect and identify road features from the signal obtained by the sensor, for example, during subsequent driving. In some embodiments, the digital signature may be created so that the digital signature has the smallest possible footprint while retaining the ability to associate or match road features with stored signatures based on an image of the road feature (or a digital signal generated by the sensor if the stored signature is not image-based and / or contains other data) captured by a camera on a subsequent vehicle traveling along the same road segment.

[0187] In some embodiments, the size of the data object can be further correlated with the uniqueness of the road feature. For example, for a road feature that is detectable by a camera on a vehicle, and where the camera system on the vehicle is coupled to a classifier that is capable of distinguishing image data corresponding to the road feature as being associated with a particular type of road feature (e.g., a road sign), and where such a road sign is locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), storing data indicating the type of road feature and its location may be sufficient.

[0188] As will be discussed in further detail below, road features (e.g., landmarks along a road segment) can be stored as small data objects that can represent road features in relatively few bytes while providing sufficient information for identifying and navigating using such features. In one example, road signs can be identified as recognizable landmarks on which a vehicle's navigation can be based. Representations of road signs can be stored in a sparse map to include, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign) and a few bytes of data indicating the landmark's location (e.g., coordinates). Navigation based on such data-light representations of landmarks (e.g., using representations sufficient to locate, identify, and navigate based on the landmarks) can provide the desired level of navigation functionality associated with sparse maps without significantly increasing the data overhead associated with sparse maps. Such condensed representations of landmarks (and other road features) can utilize sensors and processors included on such vehicles that are configured to detect, identify, and / or classify specific road features.

[0189] For example, when a landmark or even a particular type of landmark in a given area is locally unique (e.g., when there are no other landmarks or no other landmarks of the same type), the sparse map can use data indicating the type of landmark (a landmark or a particular type of landmark), and during navigation (e.g., autonomous navigation) when a camera on an autonomous vehicle captures an image of an area containing a landmark (or a particular type of landmark), the processor can process the image, detect the landmark (if indeed present in the image), classify the image as a landmark (or a particular type of landmark), and associate the location of the image with the location of the landmark stored in the sparse map.

[0190] Generate sparse maps

[0191] 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 some aspects, the sparse map may be generated via "crowd sourcing," for example, by performing image analysis on a plurality of images acquired as one or more vehicles traverse the road segment.

[0192] Figure 8A sparse map 800 is shown that one or more vehicles, such as vehicle 200 (which may be an autonomous vehicle), may access for use in providing 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, an optical disk, flash memory, a magnetic-based storage device, an optical-based storage device, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150 or another type of storage device.

[0193] In some embodiments, sparse map 800 may be stored on a storage device or non-transitory computer-readable medium provided on vehicle 200 (e.g., a storage device included in a navigation system on vehicle 200). A processor provided on vehicle 200 (e.g., processing unit 110) may access sparse map 800 stored on the storage device or computer-readable medium provided on vehicle 200 to generate navigation instructions for guiding autonomous vehicle 200 when the vehicle traverses a road segment.

[0194] However, the sparse map 800 does not need to be stored locally with respect to the vehicle. In some embodiments, the sparse map 800 may be stored on a storage device or computer-readable medium that is provided on a remote server that communicates with the vehicle 200 or a device associated with the vehicle 200. A processor provided on the vehicle 200 (e.g., processing unit 110) may receive the data contained in the sparse map 800 from the remote server and may execute the data for guiding autonomous driving of the vehicle 200. In such an embodiment, the remote server may store all or only a portion of the sparse map 800. Accordingly, a storage device or computer-readable medium provided on the vehicle 200 and / or on one or more additional vehicles may store the remaining portion(s) of the sparse map 800.

[0195] In addition, in such an embodiment, the sparse map 800 can be accessed by multiple vehicles (e.g., tens, hundreds, thousands, or millions of vehicles, etc.) traveling through different road segments. It should also be noted that the sparse map 800 can contain multiple sub-maps. For example, in some embodiments, the sparse map 800 can contain hundreds, thousands, millions, or more sub-maps that can be used to navigate the vehicle. Such sub-maps can be referred to as local maps, and a vehicle traveling along the road can access any number of local maps related to the location where the vehicle is traveling. The local map portion of the sparse map 800 can be stored together with a global navigation satellite system (GNSS) key as an index to a database of the sparse map 800. Therefore, although the calculation of the steering angle for navigating the main vehicle in the present system can be performed without relying on the GNSS position of the main vehicle, road features, or landmarks, such GNSS information can be used to retrieve relevant local maps.

[0196] In general, the sparse map 800 can be generated based on data collected from one or more vehicles as they travel along a road. For example, using sensors on one or more vehicles (e.g., cameras, speedometers, GPS, accelerometers, etc.), the trajectories of one or more vehicles traveling along a road can be recorded, and a polynomial representation of the preferred trajectory of the vehicle for subsequent trips along the road can be determined based on the collected trajectories traveled by the one or more vehicles. Similarly, data collected by one or more vehicles can help identify potential landmarks along a particular road. Data collected from passing vehicles can also be used to identify road profile information, such as road width profiles, road roughness profiles, traffic line spacing profiles, road conditions, etc. Using the collected information, the sparse map 800 can be generated and distributed (e.g., for local storage or via in-flight data transmission) for use in navigating one or more autonomous vehicles. However, in some embodiments, map generation may not end at the initial generation of the map. As will be discussed in more detail below, the sparse map 800 can be continuously or periodically updated based on data collected from the vehicles as they continue to traverse the roads included in the sparse map 800.

[0197] The data recorded in sparse map 800 may include location information based on Global Positioning System (GPS) data. For example, location information may be included in sparse map 800 for various map elements, including, for example, landmark locations, road delineation locations, and the like. The locations of map elements included in sparse map 800 may be obtained using GPS data collected from vehicles traversing the road. For example, a vehicle passing by an identified landmark may determine the location of the identified landmark using GPS location information associated with the vehicle and a determination of the location of the identified landmark relative to the vehicle (e.g., based on image analysis of data collected from one or more cameras on the vehicle). This location determination for the identified landmark (or any other feature included in sparse map 800) may be repeated as additional vehicles pass by the location of the identified landmark. Some or all of the additional location determinations may be used to refine the location information stored in sparse map 800 relative to the identified landmark. For example, in some embodiments, multiple location measurements relative to a particular feature stored in sparse map 800 may be averaged together. However, any other mathematical operation may also be used to refine the stored location of a map element based on multiple determined locations of the map element.

[0198] The sparse map of the disclosed embodiment can use a relatively small amount of stored data to enable autonomous navigation of a vehicle. In some embodiments, the sparse map 800 can have a data density (e.g., comprising data representing target track, 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 can be less than 10kB per kilometer of road, or even less than 2kB per kilometer of road (e.g., 1.6kB per kilometer), or no more than 10kB per kilometer of road, or no more than 20kB per kilometer of road. In some embodiments, the sparse map with 4GB or less data can also be used to autonomously navigate most of the roads (if not all) of the United States. These data density values ​​can represent the average on the specific road segments in the local map and / or sparse map 800 of the entire sparse map 800, the sparse map 800, and / or the sparse map 800.

[0199] As described above, the sparse map 800 may include representations 810 of multiple target trajectories for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as three-dimensional splines. For example, the target trajectories stored in the sparse map 800 may be determined based on two or more reconstructed trajectories of a vehicle's previous traversal along a particular road segment. A road segment may be associated with a single target trajectory or multiple target trajectories. For example, on a two-lane road, a first target trajectory may be stored to represent an intended path for traveling along the road in a first direction, and a second target trajectory may be stored to represent an intended path for traveling along the road in another direction (e.g., opposite to the first direction). Additional target trajectories may be stored for a particular road segment. For example, on a multi-lane road, one or more target trajectories may be stored that represent the intended path for traveling of a vehicle 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, there may be fewer target trajectories stored than there are lanes on the multi-lane road. In this case, a vehicle navigating on a multi-lane road can use any stored target trajectory to guide its navigation by taking into account lane offsets from the lane in which the target trajectory is stored (e.g., if a vehicle is traveling in the leftmost lane of a three-lane highway and target trajectories are stored only for the middle lane of the highway, the vehicle can navigate using the target trajectory for the middle lane by taking into account the lane offset between the middle lane and the leftmost lane when generating navigation instructions).

[0200] In some embodiments, the target trajectory can represent the ideal path that the vehicle should take when traveling. The target trajectory can be located at the approximate center of the lane of travel, for example. In other cases, the target trajectory can be located at other places relative to the road section. For example, the target trajectory can approximately coincide with the center of the road, the edge of the road, or the edge of the lane. In this case, navigation based on the target trajectory can include a definite offset maintained relative to the positioning of the target trajectory. In addition, in some embodiments, the definite offset maintained relative to the positioning of the target trajectory can be different based on the type of vehicle (for example, along at least a portion of the target trajectory, a passenger car comprising two axles can have different offsets from a truck comprising more than two axles).

[0201] The sparse map 800 may also include data related to a plurality of predetermined landmarks 820, which are associated with specific road segments, local maps, and the like. As discussed in more detail below, these landmarks can be used for navigation of the autonomous vehicle. For example, in some embodiments, the landmarks can be used to determine the current position of the vehicle relative to a stored target track. Using this position information, the autonomous vehicle can adjust its heading to match the direction of the target track at the determined location.

[0202] A plurality of landmarks 820 can be identified and stored in the sparse map 800 at any suitable spacing. In some embodiments, landmarks can be stored at a relatively high density (e.g., every few meters or more). However, in some embodiments, significantly larger landmark spacing values ​​can be used. For example, in the sparse map 800, the identified (or recognized) landmarks can be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, the identified landmarks can be located at a distance of even more than 2 kilometers apart.

[0203] Between landmarks, and therefore between determinations of the vehicle's position relative to the target trajectory, the vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to determine its ego motion and estimate its position relative to the target trajectory. Because errors can accumulate during navigation via dead reckoning, the position determination relative to the target trajectory may become increasingly inaccurate over time. The vehicle can use the landmarks present in sparse map 800 (and their known positions) to eliminate errors in position determination caused by dead reckoning. In this way, the identified landmarks contained in sparse map 800 can serve as navigation anchors from which the vehicle's accurate position relative to the target trajectory can be determined. Because a certain amount of error in position fixes may be acceptable, identified landmarks need not always be available to the autonomous vehicle. Instead, suitable navigation can even be based on landmark spacings of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more, as described above. In some embodiments, a density of one identified landmark per 1 kilometer of road is sufficient to maintain longitudinal position determination accuracy within 1 meter. Therefore, it is not necessary to store every potential landmark that occurs along a road segment in the sparse map 800 .

[0204] Furthermore, in some embodiments, lane markings may be used to localize the vehicle during landmark intervals. By using lane markings during landmark intervals, accumulation during navigation by dead reckoning may be minimized.

[0205] In addition to target tracks and identified landmarks, the sparse map 800 may contain information related to various other road features. For example, Figure 9A A representation of a curve along a particular road segment is shown that may be stored in the sparse map 800. In some embodiments, a single lane of a road may be modeled by a three-dimensional polynomial description of the left and right sides of the road. Figure 9A Such polynomials representing the left and right sides of a single lane are shown in . Regardless of how many lanes a road may have, the road may be represented by a polynomial similar to Figure 9A For example, the left and right edges of a multi-lane road can be represented by polynomials similar to Figure 9A The polynomials shown in FIG. 1 and the intermediate lane markings included on multi-lane roads (e.g., dashed line markings indicating lane boundaries, solid yellow lines indicating boundaries between lanes traveling in different directions, etc.) may also be represented using a polynomial such as Figure 9A The polynomial shown is used to represent .

[0206] like Figure 9A As shown, lane 900 may be represented using a polynomial (e.g., a first order, second order, third order, or any suitable order polynomial). For illustration, lane 900 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. Figure 9A As shown, lane 900 includes a left edge 910 and a right edge 920. In some embodiments, more than one polynomial may be used to represent the location of each side of the road or lane boundary. For example, each of left edge 910 and right edge 920 may be represented by multiple polynomials of any suitable length. In some cases, the polynomials may have a length of approximately 100 meters, although other lengths greater or less than 100 meters may also be used. Furthermore, the polynomials may overlap with each other to facilitate seamless transitions in navigation based on subsequently encountered polynomials as the host vehicle travels along the road. For example, each of left edge 910 and right edge 920 may be represented by multiple third-order polynomials, which are divided into segments of approximately 100 meters (an example of a first predetermined range) and overlap each other by approximately 50 meters. The polynomials representing left edge 910 and right edge 920 may or may not be of the same order. For example, in some embodiments, some polynomials may be second-order polynomials, some may be third-order polynomials, and some may be fourth-order polynomials.

[0207] exist Figure 9A In the example shown, the left side 910 of lane 900 is represented by two sets of third-order polynomials. The first set contains polynomial segments 911, 912, and 913. The second set contains polynomial segments 914, 915, and 916. These two sets, although substantially parallel to each other, follow the positioning of their respective road sides. Polynomial segments 911, 912, 913, 914, 915, and 916 have a length of approximately 100 meters and overlap with adjacent segments in the series by approximately 50 meters. However, as previously mentioned, polynomials of different lengths and different amounts of overlap may also be used. For example, the polynomials may have a length of 500m, 1km, or longer, and the amount of overlap may vary from 0 to 50m, 50m to 100m, or more than 100m. In addition, although Figure 9A are shown as representing polynomials extending in 2D space (e.g., on the surface of paper), but it will be appreciated that these polynomials may represent curves extending in three dimensions (e.g., containing a height component) to represent elevation changes in a road segment in addition to XY curvature. Figure 9AIn the example shown, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921 , 922 , and 923 and a second group having polynomial segments 924 , 925 , and 926 .

[0208] Returning to the target trajectory of the sparse map 800, Figure 9B 3D polynomials representing target trajectories for a vehicle traveling along a particular road segment are shown. The target trajectory represents not only the XY path that the host vehicle should travel along the particular road segment, but also the elevation changes that the host vehicle will experience while traveling along that road segment. Thus, each target trajectory in the sparse map 800 can be represented by one or more 3D polynomials, such as Figure 9B The sparse map 800 may contain a plurality of trajectories (e.g., millions or billions or more to represent the trajectories of vehicles along various road segments along roads around the world). In some embodiments, each target trajectory may correspond to a spline connecting the segments of the 3D polynomial.

[0209] Regarding the data footprint of the polynomial curves stored in the sparse map 800, in some embodiments, each cubic polynomial can be represented by four parameters, each requiring four bytes of data. A suitable representation can be achieved using a cubic polynomial requiring approximately 192 bytes of data per 100 meters. For a host vehicle traveling approximately 100 km / hr, this translates to a data usage / transmission requirement of approximately 200 kB per hour.

[0210] The sparse map 800 can use a combination of geometric descriptors and metadata to describe the lane network. The geometry can be described using polynomials or splines as described above. The metadata can describe the number of lanes, special characteristics (such as shared lanes), and possibly other sparse labels. The total footprint of such indicators may be negligible.

[0211] Accordingly, 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, each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as described above, the at least one line representation of a road surface feature may include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature may include at least one of a curb or a lane marking. Furthermore, as discussed below with respect to "crowdsourcing," road surface features may be identified by image analysis of multiple images acquired as one or more vehicles traverse the road segment.

[0212] As previously described, the sparse map 800 can include multiple predetermined landmarks associated with road segments. Instead of storing actual images of the landmarks and relying on image recognition analysis based on captured and stored images, each landmark in the sparse map 800 can be represented and identified using less data than would be required. The data representing the landmarks can still contain sufficient information to describe or identify the landmarks along the road. Storing data describing the characteristics of the landmarks, rather than actual images of the landmarks, can reduce the size of the sparse map 800.

[0213] Figure 10 Examples of the types of landmarks that can be represented in the sparse map 800 are shown. Landmarks can include any visible and identifiable object along a road segment. Landmarks can be selected so that they are fixed and do not change frequently with respect to their positioning and / or content. The landmarks included in the sparse map 800 are useful in determining the positioning of the vehicle 200 relative to the target trajectory as the vehicle traverses a particular road segment. Examples of landmarks can include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lamp posts, reflectors, etc.), and any other suitable categories. In some embodiments, lane markings on the road can also be included in the sparse map 800 as landmarks.

[0214] Figure 10 Examples of landmarks shown in FIG. 1 include traffic signs, directional signs, roadside fixtures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), yield signs (e.g., yield sign 1005), route number signs (e.g., route number sign 1010), traffic light signs (e.g., traffic light sign 1015), and stop signs (e.g., stop sign 1020). Directional signs may include signs that include one or more arrows indicating one or more directions to different locations. For example, directional signs may include highway signs 1025 with arrows for directing vehicles to different roads or locations, exit signs 1030 with arrows for directing vehicles off a road, and so on. Accordingly, at least one of the plurality of landmarks may include a road sign.

[0215] General signs may not be related to transportation. For example, general signs may include billboards used for advertising or welcome boards near the border between two countries, states, counties, cities, or towns. Figure 10 A general sign 1040 ("Joe's Restaurant") is shown. Although the general sign 1040 may have a rectangular shape, such as Figure 10 As shown, however, generally the logo 1040 can have other shapes, such as square, circle, triangle, etc.

[0216] Landmarks may also include roadside fixtures. Roadside fixtures may not be signs and may not be related to traffic or directions. For example, roadside fixtures may include lamp posts (e.g., lamp post 1035), power line posts, traffic light posts, etc.

[0217] Landmarks may also include beacons specifically designed for use with autonomous vehicle navigation systems. For example, such beacons may include independent structures placed at predetermined intervals to assist in navigating the host vehicle. Such beacons may also include visual / graphic information (e.g., icons, emblems, bar codes, etc.) added to existing road signs that can be recognized or identified by vehicles traveling along the 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 and / or landmark location information that the host vehicle may use when determining its position along the target trajectory.

[0218] In some embodiments, the landmarks included in the sparse map 800 can be represented by data objects of a predetermined size. The data representing the landmark can include any suitable parameters for identifying a particular landmark. For example, in some embodiments, the landmarks stored in the sparse map 800 can include parameters such as the physical size of the landmark (e.g., to support estimation of the distance to the landmark based on a known size / scale), the distance to the previous landmark, the lateral offset, the altitude, the type code (e.g., the landmark type - what type of directional sign, traffic sign, etc.), GPS coordinates (e.g., to support global positioning), and any other suitable parameters. Each parameter can be associated with a data size. For example, 8 bytes of data can be used to store the landmark size. 12 bytes of data can be used to specify the distance to the previous landmark, the lateral offset, and the altitude. The type code associated with a landmark such as a directional sign or traffic sign can require approximately 2 bytes of data. For general landmarks, a 50-byte data storage device can be used to store an image signature that enables identification of general landmarks. The GPS location of a landmark can be associated with a 16-byte data storage device. These data sizes for each parameter are examples only, and other data sizes can also be used.

[0219] Representing landmarks in the sparse map 800 in this way can provide a streamlined solution for efficiently representing landmarks in a database. In some embodiments, signs can be referred to as semantic signs and non-semantic signs. Semantic signs can include any category of signs with standardized meanings (e.g., speed limit signs, warning signs, directional signs, etc.). Non-semantic signs can include any sign that is not associated with a standardized meaning (e.g., general advertising signs, signs identifying commercial establishments, etc.). For example, each semantic sign can be represented by 38 bytes of data (e.g., 8 bytes for size; 12 bytes for distance, lateral offset, and altitude to the previous landmark; 2 bytes for type code; and 16 bytes for GPS coordinates). The sparse map 800 can use a tag system to represent landmark types. In some cases, each traffic sign or directional sign can be associated with its own tag, which can be stored in the database as part of the landmark identification. For example, the database can contain approximately 1,000 different tags to represent various traffic signs, and approximately 10,000 different tags to represent directional signs. Of course, any suitable number of tags can be used, and additional tags can be created as needed. In some embodiments, a general-purpose marker may use less than about 100 bytes (e.g., about 86 bytes, including 8 bytes for size; 12 bytes for distance, lateral offset, and altitude to a previous landmark; 50 bytes for an image signature; and 16 bytes for GPS coordinates).

[0220] Thus, for semantic road signs that do not require image signatures, even at a relatively high landmark density of approximately 1 per 50 meters, the data density impact on the sparse map 800 can be approximately 760 bytes per kilometer (e.g., 20 landmarks per kilometer x 38 bytes per landmark = 760 bytes). Even for general purpose signs that include an image signature component, the data density impact is approximately 1.72 kilobytes per kilometer (e.g., 20 landmarks per kilometer x 86 bytes per landmark = 1,720 bytes). For semantic road signs, this equates to approximately 76kB of data usage per hour for a vehicle traveling 100 km / hr. For general purpose signs, this equates to approximately 170kB of data usage per hour for a vehicle traveling 100 km / hr.

[0221] In some embodiments, a generally rectangular object, such as a rectangular sign, can be represented in the sparse map 800 by no more than 100 bytes of data. The representation of a generally rectangular object (e.g., the general sign 1040) in the sparse map 800 can include a condensed image signature (e.g., the compressed image signature 1045) associated with the generally rectangular object. This compressed image signature can be used, for example, to assist in the identification of the general sign, such as as a recognizable landmark. This compressed image signature (e.g., image information derived from actual image data representing the object) can avoid the need to store the actual image of the object, or avoid the need to perform comparative image analysis on the actual image to identify the landmark.

[0222] refer to Figure 10 , the sparse map 800 may include or store a compressed image signature 1045 associated with the generic sign 1040, rather than an actual image of the generic sign 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of the generic sign 1040, a processor (e.g., image processor 190 or any other processor that can process the image, which is onboard or remotely located relative to the host vehicle) may perform image analysis to extract / create a compressed image signature 1045 that includes a unique signature or pattern associated with the generic sign 1040. In one embodiment, the compressed image signature 1045 may include a shape, a color pattern, a brightness pattern, or any other feature that can be extracted from the image of the generic sign 1040 to describe the generic sign 1040.

[0223] For example, in Figure 10 , the circles, triangles, and stars shown in the compressed image signature 1045 can represent areas of different colors. The patterns represented by the circles, triangles, and stars can be stored in the sparse map 800, for example, within the 50 bytes designated as containing the image signature. It is worth noting that the circles, triangles, and stars are not necessarily intended to indicate that these shapes are stored as part of the image signature. Instead, these shapes are intended to conceptually represent recognizable areas with discernible color differences, text areas, graphic shapes, or other variations of characteristics that can be associated with a general sign. Such a compressed image signature can be used to identify a landmark in the form of a general sign. For example, the compressed image signature can be used to perform the same or different analysis based on a comparison of the stored compressed image signature with image data captured, for example, using a camera on an autonomous vehicle.

[0224] Accordingly, multiple landmarks can be identified by performing image analysis on multiple images acquired as one or more vehicles traverse a road segment. As explained below with respect to "crowdsourcing," in some embodiments, image analysis to identify multiple landmarks can include accepting a potential landmark when the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold. Furthermore, in some embodiments, image analysis to identify multiple landmarks can include rejecting a potential landmark when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

[0225] Returning to the target trajectory that the host vehicle can use to navigate a specific road segment, Figure 11A A polynomial representation of a trajectory captured in the process of building or maintaining a sparse map 800 is shown. The polynomial representation of a target trajectory contained in the sparse map 800 can be determined based on two or more reconstructed trajectories of a vehicle previously traversed along the same road segment. In some embodiments, the polynomial representation of a target trajectory contained in the sparse map 800 can be an aggregation of two or more reconstructed trajectories of a vehicle previously traversed along the same road segment. In some embodiments, the polynomial representation of a target trajectory contained in the sparse map 800 can be an average of two or more reconstructed trajectories of a vehicle previously traversed along the same road segment. Other mathematical operations can also be used to construct a target trajectory along a road path based on the reconstructed trajectories collected from vehicles traversing along a road segment.

[0226] like Figure 11A As shown, a road segment 1100 can be traveled by multiple vehicles 200 at different times. Each vehicle 200 can collect data related to the path taken by the vehicle along the road segment. The path traveled by a particular vehicle can be determined based on camera data, accelerometer information, speed sensor information, and / or GPS information, among other potential sources. This data can be used to reconstruct the trajectory of the vehicle traveling along the road segment, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) can be determined for the particular road segment. This target trajectory can represent a preferred path for the host vehicle (e.g., as guided by an autonomous navigation system) as it travels along the road segment.

[0227] exist Figure 11AIn the example shown, a first reconstructed trajectory 1101 can be determined based on data received from a first vehicle traversing road segment 1100 during a first time period (e.g., day one), a second reconstructed trajectory 1102 can be obtained from a second vehicle traversing road segment 1100 during a second time period (e.g., day two), and a third reconstructed trajectory 1103 can be obtained from a third vehicle traversing road segment 1100 during a third time period (e.g., day three). Each trajectory 1101, 1102, and 1103 can be represented by a polynomial, such as a three-dimensional polynomial. It should be noted that in some embodiments, any reconstructed trajectory can be assembled on a vehicle traversing road segment 1100.

[0228] Additionally or alternatively, such a reconstructed trajectory may be determined on the server side based on information received from vehicles traversing the road segment 1100. For example, in some embodiments, the vehicles 200 may transmit data related to their movement along the road segment 1100 (e.g., steering angle, heading, time, location, speed, sensed road geometry and / or sensed landmarks, etc.) to one or more servers. The server may reconstruct the trajectory of the vehicle 200 based on the received data. The server may also generate a target trajectory for guiding navigation of an autonomous vehicle that will travel along the same road segment 1100 at a later time based on the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. Although a target trajectory may be associated with a single previous traversal of a road segment, in some embodiments, each target trajectory contained in the sparse map 800 may be determined based on two or more reconstructed trajectories of vehicles traversing the same road segment. Figure 11A , the target track is represented by 1110. In some embodiments, the target track 1110 may be generated based on the average of the first track 1101, the second track 1102, and the third track 1103. In some embodiments, the target track 1110 included in the sparse map 800 may be an aggregation (e.g., a weighted combination) of two or more reconstructed tracks.

[0229] Figure 11B and Figure 11C The concept of target trajectories associated with road segments existing within the geographic area 1111 is further illustrated. Figure 11BAs shown, a first road segment 1120 within geographic area 1111 may include a multi-lane road comprising two lanes 1122 designated for vehicle travel in a first direction and two additional lanes 1124 designated for vehicle travel in a second direction opposite the first direction. Lanes 1122 and 1124 may be separated by a double yellow line 1123. Geographic area 1111 may also include a branch road segment 1130 intersecting road segment 1120. Road segment 1130 may include a two-lane road, with each lane designated for a different direction of travel. Geographic area 1111 may also include other road features such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0230] like Figure 11C As shown, sparse map 800 may include local map 1140, which includes a road model for facilitating autonomous navigation of a vehicle within geographic area 1111. For example, local map 1140 may include target trajectories for one or more lanes associated with road segments 1120 and / or 1130 within geographic area 1111. For example, local map 1140 may include target trajectories 1141 and / or 1142 that the autonomous vehicle may access or rely on when traversing lane 1122. Similarly, local map 1140 may include target trajectories 1143 and / or 1144 that the autonomous vehicle may access or rely on when traversing lane 1124. Furthermore, local map 1140 may include target trajectories 1145 and / or 1146 that the autonomous vehicle may access or rely on when traversing road segment 1130. Target trajectory 1147 represents the preferred path that the autonomous vehicle should follow when transitioning from lane 1120 (specifically, relative to target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (specifically, relative to target trajectory 1145 associated with the first side of road segment 1130). Similarly, target trajectory 1148 represents the preferred path that the autonomous vehicle should follow when transitioning from road segment 1130 (specifically, relative to target trajectory 1146) to a portion of road segment 1124 (specifically, as shown, relative to target trajectory 1143 associated with the left lane of lane 1124).

[0231] Sparse map 800 may also include representations of other road-related features associated with geographic area 1111. For example, sparse map 800 may also include representations of one or more landmarks identified in geographic area 1111. These landmarks may include a first landmark 1150 associated with stop line 1132, a second landmark 1152 associated with stop sign 1134, a third landmark associated with speed limit sign 1154, and a fourth landmark 1156 associated with hazard sign 1138. Such landmarks may be used, for example, to help the autonomous vehicle determine its current location relative to any shown target track so that the vehicle can adjust its heading to match the direction of the target track at the determined location.

[0232] In some embodiments, the sparse map 800 may also include road signature profiles. Such road signature profiles may be associated with any discernible / measurable change in at least one parameter associated with a road. For example, in some cases, such profiles may be associated with changes in road surface information, such as changes in surface roughness of a particular road segment, changes in road width along a particular road segment, changes in the distance between dashed lines drawn along a particular road segment, changes in road curvature along a particular road segment, and the like. Figure 11D An example of a road signature profile 1160 is shown. While profile 1160 may represent any of the above parameters or other parameters, in one example, profile 1160 may represent a measurement of road surface roughness, e.g., as obtained by monitoring one or more sensors that provide outputs indicative of an amount of suspension displacement as a vehicle travels on a particular road segment.

[0233] Alternatively or concurrently, profile 1160 can represent changes in road width, as determined based on image data obtained via a camera on a vehicle traveling on a particular road segment. For example, such a profile can be useful in determining a particular positioning of an autonomous vehicle relative to a particular target track. That is, as it traverses a road segment, the autonomous vehicle can measure a profile associated with one or more parameters associated with the road segment. If the measured profile can be correlated / matched with a predetermined profile that maps parameter changes relative to position along the road segment, the measured and predetermined profiles can be used (e.g., by overlaying corresponding portions of the measured and predetermined profiles) to determine the current position along the road segment, and therefore the current position of the target track relative to the road segment.

[0234] In some embodiments, the sparse map 800 may include different trajectories based on different characteristics associated with users of the autonomous vehicles, environmental conditions, and / or other parameters related to driving. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or profiles. A sparse map 800 containing such different trajectories may be provided to different autonomous vehicles of different users. For example, some users may prefer to avoid toll roads, while other users may prefer to take the shortest or fastest route, regardless of whether there are toll roads on the route. The disclosed system may generate different sparse maps with different trajectories based on such different user preferences or profiles. As another example, some users may prefer to drive in a fast-moving lane, while other users may prefer to always maintain a position in the center lane.

[0235] Based on different environmental conditions, such as day and night, snow, rain, fog, etc., different trajectories can be generated and included in the sparse map 800. Autonomous vehicles traveling under different environmental conditions can be provided with sparse maps 800 generated based on such different environmental conditions. In some embodiments, cameras provided on autonomous vehicles can detect environmental conditions and provide such information back to a server that generates and provides sparse maps. For example, the server can generate or update an already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. As the autonomous vehicle travels along the road, updates to the sparse map 800 based on environmental conditions can be performed dynamically.

[0236] Other different parameters related to driving can also be used as a basis for generating different sparse maps and providing different sparse maps to different autonomous vehicles. For example, when the autonomous vehicle is traveling at high speeds, turns may be tighter. Tracks associated with specific lanes rather than roads can be included in the sparse map 800 so that the autonomous vehicle can maintain itself within a specific lane when the vehicle follows a specific track. When images captured by a camera on the autonomous vehicle indicate that the vehicle has drifted outside of the lane (e.g., crossed a lane marking), an action can be triggered within the vehicle to bring the vehicle back into the designated lane according to the specific track.

[0237] Crowdsourced sparse maps

[0238] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, the disclosed systems and methods can use crowdsourced data to generate a sparse map that one or more autonomous vehicles can use to navigate along a system of roads. As used herein, "crowdsourcing" means receiving data from various vehicles (e.g., autonomous vehicles) traveling on a road segment at different times, and this data is used to generate and / or update a road model. The model can be transmitted to vehicles or other vehicles traveling later along the road segment to assist in autonomous vehicle navigation. The road model can include multiple target trajectories that represent preferred trajectories that the autonomous vehicle should follow when traversing the road segment. The target trajectory can be the same as the reconstructed actual trajectory collected from vehicles traversing the road segment, which can be transmitted from the vehicle to a server. In some embodiments, the target trajectory can be different from the actual trajectory previously adopted by one or more vehicles when traversing the road segment. The target trajectory can be generated based on the actual trajectory (e.g., by averaging or any other suitable operation).

[0239] The vehicle trajectory data that a vehicle may upload to a server may correspond to the vehicle's actual reconstructed trajectory, or may correspond to a recommended trajectory that may be based on or related to the vehicle's actual reconstructed trajectory, but may differ from the actual reconstructed trajectory. For example, a vehicle may modify its actual reconstructed trajectory and submit (e.g., recommend) the modified actual trajectory to the server. The road model may use the recommended, modified trajectory as a target trajectory for autonomous navigation of other vehicles.

[0240] In addition to trajectory information, other information potentially used in constructing the sparse data map 800 can include information related to potential landmark candidates. For example, by crowdsourcing information, the disclosed systems and methods can identify potential landmarks in the environment and refine the landmark locations. The autonomous vehicle's navigation system can use these landmarks to determine and / or adjust the vehicle's position along the target trajectory.

[0241] The reconstructed trajectory that can be generated as the vehicle travels along the road can be obtained by any suitable method. In some embodiments, the reconstructed trajectory can be generated by stitching together segments of the vehicle's motion using, for example, ego-motion estimates (e.g., three-dimensional translation and three-dimensional rotation of the camera (and thus the vehicle body)). The rotation and translation estimates can be determined based on analysis of images captured by one or more image capture devices and information from other sensors or devices (such as inertial sensors and speed sensors). For example, the inertial sensors can include accelerometers or other suitable sensors configured to measure changes in vehicle body translation and / or rotation. The vehicle can include a speed sensor that measures the vehicle's speed.

[0242] In some embodiments, the camera's (and thus the vehicle's) ego-motion can be estimated based on optical flow analysis of the captured images. Optical flow analysis of an image sequence identifies the movement of pixels in the image sequence and, based on the identified movement, determines the vehicle's motion. The ego-motion can be integrated over time and along a road segment to reconstruct a trajectory associated with the road segment that the vehicle has followed.

[0243] Data collected at different times along a road segment by multiple vehicles in multiple drives (e.g., reconstructed trajectories) can be used to construct a road model (e.g., including target trajectories, etc.) included in the sparse data map 800. Data collected at different times along a road segment by multiple vehicles in multiple drives can also be averaged to improve the accuracy of the model. In some embodiments, data about road geometry and / or landmarks can be received from multiple vehicles traveling through a public road segment at different times. Such data received from different vehicles can be combined to generate and / or update a road model.

[0244] The geometry of the reconstructed trajectory (and target trajectory) along the road segment can be represented by a curve in three-dimensional space, which can be a spline connecting three-dimensional polynomials. The reconstructed trajectory curve can be determined by analyzing a video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a position is identified in each frame or image a few meters ahead of the vehicle's current position. The position is the position where the vehicle is expected to travel within a predetermined time period. This operation can be repeated frame by frame, and at the same time, the vehicle can calculate the camera's ego motion (rotation and translation). In each frame or each image, the vehicle generates a short-range model of the expected path in a reference frame attached to the camera. The short-range models can be stitched together to obtain a three-dimensional model of the road in a certain coordinate system, which can be an arbitrary or predetermined coordinate system. The three-dimensional model of the road can then be fitted by a spline, which can contain or connect one or more polynomials of appropriate order.

[0245] In order to summarize the short-range road model at each frame, one or more detection modules can be used. For example, a bottom-up lane detection module can be used. The bottom-up lane detection module can be useful when mapping lane markings on the road. This module can find edges in the image and assemble them together to form lane markings. A second module can be used together with the bottom-up lane detection module. The second module is an end-to-end deep neural network that can be trained to predict the correct short-range path from the input image. In both modules, the road model can be detected in the image coordinate system and transformed into a three-dimensional space that can be virtually attached to the camera.

[0246] Although the reconstructed trajectory modeling method may introduce an accumulation of errors due to the integration of self-motion over long periods of time, which may contain noise components, such errors may be insignificant because the generated model can provide sufficient accuracy for navigation on a local scale. In addition, the integration error can also be eliminated by using external information sources such as satellite imagery or geodetic measurements. For example, the disclosed system and method can use a GNSS receiver to eliminate cumulative errors. However, GNSS positioning signals may not always be available and accurate. The disclosed system and method can enable steering applications that are weakly dependent on the availability and accuracy of GNSS positioning. In such a system, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed system may use GNSS signals only for database indexing purposes.

[0247] In some embodiments, the range scale (e.g., local scale) relevant to autonomous vehicle navigation and steering applications can be approximately 50 meters, 100 meters, 200 meters, 300 meters, etc. This range can be used because the geometric road model is primarily used for two purposes: planning a forward trajectory and localizing the vehicle on the road model. In some embodiments, when the control algorithm steers the vehicle based on a target point located 1.3 seconds ahead (or any other time, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.), the planning task can use the model within a typical range of 40 meters ahead (or any other suitable forward distance, such as 20 meters, 30 meters, 50 meters). The localization task uses the road model within a typical range of 60 meters behind the vehicle (or any other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.). According to a method called "tail alignment" described in more detail in another section, the disclosed systems and methods can generate a geometric model with sufficient accuracy over a specific range (such as 100 meters) so that the planned trajectory does not deviate from the center of the lane by more than, for example, 30 centimeters.

[0248] As described above, a 3D road model can be constructed by detecting short-range segments and stitching them together. Stitching can be enabled by computing a six-degree ego-motion model using video and / or images captured by a camera, data from inertial sensors reflecting the vehicle's motion, and the host vehicle's speed signal. The accumulated error can be sufficiently small over a certain local scale (such as approximately 100 meters). All of this can be accomplished in a single drive on a specific road segment.

[0249] In some embodiments, multiple drives can be used to average the resulting model and further improve its accuracy. The same car can drive the same route multiple times, or multiple cars can transmit their collected model data to a central server. In any case, a matching process can be performed to identify overlapping models and enable averaging to generate a target trajectory. Once the convergence criteria are met, the constructed model (e.g., containing the target trajectory) can be used for steering. Subsequent drives can be used for further model improvement and adaptation to infrastructure changes.

[0250] If multiple vehicles are connected to a central server, sharing driving experience (such as sensed data) between them becomes feasible. Each vehicle client can store a partial copy of the general road model, which can be related to its current location. A bidirectional update process between the vehicle and the server can be performed by the vehicle and the server. The small footprint concept discussed above enables the disclosed system and method to perform bidirectional updates using very little bandwidth.

[0251] Information related to potential landmarks can also be determined and forwarded to the central server. For example, the disclosed systems and methods can determine one or more physical attributes of a potential landmark based on one or more images containing the landmark. The physical attributes can include the physical size of the landmark (e.g., height, width), the distance from the vehicle to the landmark, the distance between the landmark and previous landmarks, the lateral position of the landmark (e.g., the position of the landmark relative to the lane of travel), the GPS coordinates of the landmark, the type of landmark, text identification on the landmark, etc. For example, the vehicle can analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

[0252] A vehicle can determine the distance from the vehicle to a landmark based on an analysis of one or more images. In some embodiments, the distance can be determined based on an analysis of an image of the landmark using a suitable image analysis method, such as a scaling method and / or an optical flow method. In some embodiments, the disclosed systems and methods can be configured to determine the type or classification of a potential landmark. In the event that a vehicle determines that a potential landmark corresponds to a predetermined type or classification stored in a sparse map, it is sufficient for the vehicle to communicate an indication of the type or classification of the landmark along with its location to a server. The server can store such an indication. At a later time, another vehicle can capture an image of the landmark, process the image (e.g., using a classifier), and compare the results of processing the image with the indication of the landmark type stored in the server. There can be various types of landmarks, and different types of landmarks can be associated with different types of data uploaded to and stored in the server. Different processing on the vehicle can detect the landmark and communicate information about the landmark to the server, and systems on the vehicle can receive the landmark data from the server and use the landmark data to identify the landmark in autonomous navigation.

[0253] In some embodiments, multiple autonomous vehicles driving on a road segment can communicate with a server. A vehicle (or client) can generate a curve describing its driving in an arbitrary coordinate system (e.g., by integrating ego motion). The vehicle can detect landmarks and locate them in the same frame. The vehicle can upload the curve and landmarks to the server. The server can collect data from the vehicles over multiple driving cycles and generate a unified road model. Or, for example, as shown below with reference to Figure 19 As discussed, the server can generate a sparse map with a unified road model using the uploaded curves and landmarks.

[0254] The server may also distribute the model to clients (e.g., vehicles). For example, the server may distribute a sparse map to one or more vehicles. The server may continuously or periodically update the model as new data is received from the vehicles. For example, the server may process the new data to evaluate whether the data contains information that should trigger an update or creation of new data on the server. The server may distribute the updated model or updates to the vehicles for use in providing autonomous vehicle navigation.

[0255] The server can use one or more criteria to determine whether new data received from a vehicle should trigger an update to the model or the creation of new data. For example, the server can determine that the new data should trigger an update to the model when the new data indicates that a previously identified landmark at a particular location no longer exists or has been replaced by another landmark. As another example, the server can determine that the new data should trigger an update to the model when the new data indicates that a road segment has been closed, and this has been confirmed by data received from other vehicles.

[0256] The server can distribute the updated model (or updated portion of the model) to one or more vehicles traveling on the road segment associated with the model update. The server can also distribute the updated model to vehicles that will be traveling on the road segment, or whose planned trips include the road segment associated with the model update. For example, if the autonomous vehicle travels along another road segment before reaching the road segment associated with the update, the server can distribute the update or updated model to the autonomous vehicle before the vehicle reaches the road segment.

[0257] In some embodiments, a remote server can collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a public road segment). The server can use the landmarks to match curves and create an average road model based on the trajectories collected from multiple vehicles. The server can also calculate a graph of the road and the most likely path at each node or connection of the road segment. For example, the remote server can align the trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0258] The server may average landmark attributes received from multiple vehicles traveling along a public road segment, such as the distance from one landmark to another (e.g., the previous landmark along the road segment) measured by multiple vehicles, to determine arc length parameters and support positioning and speed calibration of each client vehicle along the path. The server may average the physical dimensions of landmarks measured by multiple vehicles traveling along the public road segment and identifying the same landmark. The averaged physical dimensions may be used to support distance estimation, such as the distance from the vehicle to the landmark. The server may average the lateral positions of the landmarks (e.g., from the lane the vehicle is traveling in to the position of the landmark) measured by multiple vehicles traveling along the public road segment and identifying the same landmark. The averaged lateral positions may be used to support lane assignment. The server may average the GPS coordinates of the landmarks measured by multiple vehicles traveling along the same road segment and identifying the same landmark. The averaged GPS coordinates of the landmarks may be used to support global positioning (localization) or positioning (positioning) of the landmarks in the road model.

[0259] In some embodiments, based on data received from the vehicle, the server can identify model changes, such as construction, detours, new signs, removal of signs, etc. The server can continuously, periodically, or instantaneously update the model as new data is received from the vehicle. The server can distribute updates to the model or the updated model to the vehicle for use in providing autonomous navigation. For example, as discussed further below, the server can use crowdsourced data to filter out "ghost" landmarks detected by the vehicle.

[0260] In some embodiments, the server can analyze driver interventions during autonomous driving. The server can analyze data received from the vehicle at the time and location of the intervention, and / or data received before the time of the intervention. The server can identify certain portions of the data that caused or were closely related to the intervention, such as data indicating a temporary lane closure or data indicating a pedestrian on the road. The server can update the model based on the identified data. For example, the server can modify one or more trajectories stored in the model.

[0261] Figure 12 is a schematic diagram of a system for generating sparse maps using crowdsourcing (and for sparse map distribution and navigation using crowdsourcing). Figure 12 A road segment 1200 is shown that includes one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 may be traveling on the road segment 1200 at the same time or at different times (although Figure 121200 at the same time). At least one of vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. To simplify this example, it is assumed that all vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0262] Each vehicle may be similar to a vehicle disclosed in other embodiments (e.g., vehicle 200) and may include components or devices included in or associated with vehicles disclosed in other embodiments. Each vehicle may be equipped with an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle may communicate with a remote server 1230 via one or more networks (e.g., via a cellular network and / or the internet, etc.) via a wireless communication path 1235, as shown by a dashed line. Each vehicle may transmit data to and receive data from server 1230. For example, server 1230 may collect data from multiple vehicles traveling on road segment 1200 at different times and may process the collected data to generate an autonomous vehicle road navigation model, or updates to the model. Server 1230 may transmit the autonomous vehicle road navigation model or updates to the model to the vehicle that transmitted the data to server 1230. Server 1230 may also transmit the autonomous vehicle road navigation model or updates to the model to other vehicles traveling on road segment 1200 at a later time.

[0263] As 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, navigation information may be associated with public road segment 1200. The navigation information may include a trajectory associated with each vehicle 1205, 1210, 1215, 1220, and 1225 as each vehicle travels on road segment 1200. In some embodiments, the trajectory may be reconstructed based on data sensed by various sensors and devices provided on vehicle 1205. For example, the trajectory may be reconstructed based on at least one of accelerometer data, velocity data, landmark data, road geometry or contour data, vehicle position 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 velocity of vehicle 1205 sensed by a velocity sensor. Furthermore, in some embodiments, the trajectory can be determined (e.g., by a processor on each of vehicles 1205, 1210, 1215, 1220, and 1225) based on sensed camera ego motion, which can indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The camera (and thus the vehicle body) ego motion can be determined by analyzing one or more images captured by the camera.

[0264] In some embodiments, the trajectory of the vehicle 1205 may be determined by a processor provided on the vehicle 1205 and transmitted to the server 1230. In other embodiments, the server 1230 may receive data sensed by various sensors and devices provided in the vehicle 1205 and determine the trajectory based on the data received from the vehicle 1205.

[0265] 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, lane types (e.g., single lane, dual lane, driving lane, passing lane, etc.), lane markings, lane width, etc. In some embodiments, the navigation information may include a lane assignment, e.g., which lane of a plurality of lanes the vehicle is traveling in. For example, a lane assignment may be associated with a numerical value of "3," indicating that the vehicle is traveling in the third lane from the left or right. As another example, a lane assignment may be associated with a text value of "center lane," indicating that the vehicle is traveling in the center lane.

[0266] Server 1230 may store navigation information on a non-transitory computer-readable medium, such as a hard drive, optical disk, tape, memory, or the like. Server 1230 may generate (e.g., via a processor included in server 1230) at least a portion of an autonomous vehicle road navigation model for public road segment 1200 based on navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225, and may store the model as part of a sparse map. Server 1230 may determine a track associated with each lane based on crowdsourced data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling on lanes of the road segment at different times. Server 1230 may generate an autonomous vehicle road navigation model, or a portion (e.g., an updated portion) of the model, based on the multiple tracks determined from the crowdsourced navigation data. Server 1230 can transmit the model, or an updated portion of the model, to one or more of autonomous vehicles 1205, 1210, 1215, 1220, and 1225 traveling on road segment 1200, or any other autonomous vehicles traveling on the road segment at a later time, for use in updating the existing autonomous vehicle road navigation model provided in the vehicle's navigation system. The autonomous vehicle road navigation model can be used by the autonomous vehicle for autonomous navigation along public road segment 1200.

[0267] As mentioned above, the autonomous vehicle road navigation model can be included in the sparse map (e.g. Figure 8 sparse map 800). Sparse map 800 may contain a sparse record of data related to road geometry and / or landmarks along a road, which may provide sufficient information for guiding autonomous vehicle navigation without requiring excessive data storage. In some embodiments, an autonomous vehicle road navigation model may be stored separately from sparse map 800, and when the model is executed for navigation, map data from sparse map 800 may be used. In some embodiments, the autonomous vehicle road navigation model may use the map data contained in sparse map 800 to determine a target trajectory along road segment 1200 for guiding autonomous navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles that later travel along road segment 1200. For example, when the autonomous vehicle road navigation model is executed by a processor included in a navigation system of vehicle 1205, the model may cause the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory included in sparse map 800 to verify and / or correct the current route of vehicle 1205.

[0268] In the autonomous vehicle road navigation model, the geometry of the road features or target trajectory can be encoded by a curve in three-dimensional space. In one embodiment, the curve can be a three-dimensional spline, comprising one or more connected three-dimensional polynomials. As understood by those skilled in the art, a spline can be a numerical function for fitting data defined piecewise by a series of polynomials. The spline used to fit the three-dimensional geometric structure data of the road can include a linear spline (first order), a quadratic spline (second order), a cubic spline (third order), or any other spline (other orders), or a combination thereof. The spline can include one or more three-dimensional polynomials of different orders that connect (e.g., fit) the data points of the three-dimensional geometric structure data of the road. In some embodiments, the autonomous vehicle road navigation model can include a three-dimensional spline corresponding to the target trajectory along a public road segment (e.g., road segment 1200) or a lane of road segment 1200.

[0269] As described above, the autonomous vehicle road navigation model included in the sparse map may include other information, such as the identification of at least one landmark along road segment 1200. The landmark may be visible within the field of view of a camera (e.g., camera 122) mounted on each of vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 may capture an image of the landmark. A processor provided on vehicle 1205 (e.g., processors 180, 190, or processing unit 110) may process the image of the landmark to extract identification information for the landmark. The landmark identification information, rather than the actual image of the landmark, may be stored in sparse map 800. Landmark identification information may require significantly less storage space than actual images. Other sensors or systems (e.g., a GPS system) may also provide certain identification information for the landmark (e.g., the location of the landmark). The landmark may include at least one of a traffic sign, an arrow sign, a lane marker, a dashed lane marker, a traffic light, a stop line, a directional sign (e.g., a highway exit sign with an arrow indicating a direction, a highway sign with an arrow pointing in a different direction or location), a landmark beacon, or a lamppost. 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 on a vehicle so that when the vehicle passes by the device, the beacon received by the vehicle and the location of the device (e.g., determined from the device's GPS location) can be used as a landmark to be included in the autonomous vehicle road navigation model and / or sparse map 800.

[0270] The identification of at least one landmark may include the location of the at least one landmark. The location of the landmark may be determined based on position measurements performed using sensor systems (e.g., global positioning systems, inertial positioning systems, landmark beacons, etc.) associated with multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of the landmark may be determined by averaging position measurements detected, collected, or received by sensor systems on different vehicles 1205, 1210, 1215, 1220, and 1225 over multiple drives. For example, vehicles 1205, 1210, 1215, 1220, and 1225 may transmit position measurements to server 1230, which may average the position measurements and use the averaged position measurement as the location of the landmark. The location of the landmark may be continuously refined using measurements received from vehicles on subsequent drives.

[0271] The identification of the landmark may include the size of the landmark. A processor provided on the vehicle (e.g., 1205) may estimate the physical size of the landmark based on analysis of the image. Server 1230 may receive multiple estimates of the physical size of the same landmark from different vehicles over different drives. Server 1230 may average the different estimates to derive the physical size of the landmark and store the landmark size in the road model. The physical size estimate may be used to further determine or estimate the distance from the vehicle to the landmark. The distance to the landmark may be estimated based on the current speed of the vehicle and based on the extended ratio of the position of the landmark appearing in the image relative 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 from the landmark at time t1 to the extended focus in the image, and D is the change in distance of the landmark from t1 to t2 in the image. dt represents (t2-t1). For example, the distance to a landmark can be estimated by Z = V * dt * R / D, where V is the vehicle's speed, R is the distance between the landmark and the expanded focus in the image, 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, can be used to estimate the distance to the landmark. Here, V is the vehicle's speed, ω is the image length (similar to the object width), and Δω is the change in image length per unit time.

[0272] When the physical size of a landmark is known, the distance to the landmark can also be determined based on the following equation: Z = f*W / ω, where f is the focal length, W is the size of the landmark (such as height or width), and ω is the number of pixels when the landmark is out of the image. Based on the above equation, ΔZ = f*W*Δω / ω can be used 2+f*ΔW / ω to calculate the change in distance Z, where ΔW decays to zero by averaging, and where Δω is the number of pixels representing the accuracy of the bounding box in the image. The value of the estimated physical size of the landmark can be calculated by averaging multiple observations on the server side. The final error in the distance estimate can be very small. When using the above equation, two error sources may appear, namely ΔW and Δω. Their contribution to the distance error is given by ΔZ = f*W*Δω / ω 2 +f*ΔW / ω. However, ΔW decays to zero by averaging; therefore ΔZ is determined by Δω (e.g., the inaccuracy of the bounding box in the image).

[0273] For landmarks of unknown size, the distance to the landmark can be estimated by tracking feature points on the landmark between consecutive frames. For example, certain features appearing on a speed limit sign can be tracked between two or more image frames. Based on these tracked features, a distance distribution for each feature point can be generated. A distance estimate can be extracted from the distance distribution. For example, the most frequently occurring distance in the distance distribution can be used as the distance estimate. As another example, the average of the distance distribution can be used as the distance estimate.

[0274] Figure 13 An example autonomous vehicle road navigation model represented by a plurality of three-dimensional splines 1301 , 1302 , and 1303 is shown. Figure 13 Curves 1301, 1302, and 1303 are shown for illustration purposes only. Each spline may comprise one or more three-dimensional polynomials connecting a plurality of data points 1310. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or any combination of suitable polynomials of varying orders. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to a landmark (e.g., the size, location, and identification information of the landmark) and / or a road signature profile (e.g., road geometry, road roughness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 may be associated with data related to the landmark, while other data points may be associated with data related to the road signature profile.

[0275] Figure 141 shows raw positioning data 1410 (e.g., GPS data) received from five separate drives. A drive can be separated from another drive if the separated vehicle is crossed at the same time, by the same vehicle at separate times, or by the separated vehicles at separate times. To account for errors in positioning data 1410 and different positioning of vehicles in the same lane (e.g., one vehicle may be closer to the left side of the lane than another), server 1230 can use one or more statistical techniques to generate a map skeleton 1420 to determine whether changes in raw positioning data 1410 represent actual deviations or statistical errors. Each path within skeleton 1420 can be linked back to the raw data 1410 that formed the path. For example, the path between A and B within skeleton 1420 is linked to raw data 1410 from drives 2, 3, 4, and 5, but not from drive 1. Skeleton 1420 may not be detailed enough to navigate a vehicle (e.g., because, unlike the spline described above, skeleton 1420 combines drives from multiple lanes on the same road), but it can provide useful topological information and can be used to define intersections.

[0276] Figure 15 An example is shown by which additional detail can be generated for a sparse map within a segment of a map skeleton (e.g., segment A to segment B within skeleton 1420). Figure 15 As shown, data (e.g., ego-motion data, road sign data, etc.) can be shown as a function of position S (or S1 or S2) along the driving. Server 1230 can identify landmarks of the sparse map by identifying unique matches between landmarks 1501, 1503, and 1505 of driving 1510 and landmarks 1507 and 1509 of driving 1520. This matching algorithm can obtain the identification of landmarks 1511, 1513, and 1515. However, those skilled in the art will recognize that other matching algorithms can be used. For example, probabilistic optimization can be used instead of unique matching or in combination with unique matching. Server 1230 can align driving longitudinally to align matching landmarks. For example, server 1230 can select one driving (e.g., driving 1520) as a reference driving, and then shift and / or elastically stretch (multiple) other drivings (e.g., driving 1510) for alignment.

[0277] Figure 16 An example of aligned landmark data used in a sparse map is shown. Figure 16 In the example shown in FIG. 1 , landmark 1610 includes a road sign. Figure 16 The example further depicts data from multiple drivers 1601, 1603, 1605, 1607, 1609, 1611, and 1613. Figure 16In the example shown in FIG16 , the data from drive 1613 contains a "ghost" landmark, and server 1230 may identify it as such because drives 1601, 1603, 1605, 1607, 1609, and 1611 do not contain identifications of landmarks near the landmark identified in drive 1613. Accordingly, server 1230 may accept a potential landmark when the ratio of images in which the landmark does appear to images in which the landmark does not appear exceeds a threshold, and / or may reject a potential landmark when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

[0278] Figure 17 A system 1700 for generating driving data is depicted that can be used to crowdsource sparse maps. Figure 17 As shown, system 1700 may include a camera 1701 and a positioning device 1703 (e.g., a GPS locator). Camera 1701 and positioning device 1703 may be mounted on a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). Camera 1701 may generate a plurality of data types, such as ego-motion data, traffic sign data, road data, etc. The camera data and positioning data may be segmented into driving segments 1705. For example, driving segments 1705 may each include camera data and positioning data from less than 1 kilometer of driving.

[0279] In some embodiments, system 1700 can remove redundancy in driving segment 1705. For example, if a landmark appears in multiple images from camera 1701, system 1700 can remove the redundant data so that driving segment 1705 only contains one copy of the landmark's location and any metadata associated with the landmark. As a further example, if a lane marking appears in multiple images from camera 1701, system 1700 can remove the redundant data so that driving segment 1705 only contains one copy of the lane marking's location and any metadata associated with the lane marking.

[0280] System 1700 also includes a server (e.g., server 1230). Server 1230 can receive drive segments 1705 from the vehicle and reassemble the drive segments 1705 into a single drive 1707. This arrangement can reduce bandwidth requirements when transmitting data between the vehicle and the server, while also allowing the server to store data related to the entire drive.

[0281] Figure 18 Describes a method that is further configured to crowdsource sparse maps. Figure 17 System 1700. Figure 17As shown, system 1700 includes a vehicle 1810 that captures driving data using, for example, a camera (which generates, for example, ego-motion data, traffic sign data, road data, etc.) and a positioning device (e.g., a GPS locator). Figure 17 As shown, the vehicle 1810 segments the collected data into driving segments (in Figure 18 The server 1230 then receives the driving segments and reconstructs the driving (in Figure 18 described as "driving 1" in [1].

[0282] like Figure 18 As further depicted in FIG, system 1700 also receives data from additional vehicles. For example, vehicle 1820 also uses, for example, a camera (which generates, for example, ego-motion data, traffic sign data, road data, etc.) and a positioning device (e.g., a GPS locator) to capture driving data. Similar to vehicle 1810, vehicle 1820 segments the collected data into driving segments (in Figure 18 The server 1230 then receives the driving segments and reconstructs the driving (in Figure 18 Any number of additional vehicles may be used. For example, Figure 18 Also included is "Car N", which captures driving data and segments it into driving segments (in Figure 18 and transmit it to the server 1230 for reconstruction into a driving Figure 18 depicted as "Driving N").

[0283] like Figure 18 As shown, server 1230 can build a sparse map (depicted as “Map”) using reconstructed drives (e.g., “Drive 1,” “Drive 2,” and “Drive N”) collected from multiple vehicles (e.g., “Car 1” (also labeled as Vehicle 1810), “Car 2” (also labeled as Vehicle 1820), and “Car N”).

[0284] Figure 19 19 is a flow chart illustrating an example process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 may be performed by one or more processing devices included in server 1230.

[0285] Process 1900 may include receiving a plurality of images captured as one or more vehicles traverse a road segment (step 1905). Server 1230 may receive images from cameras included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, as vehicle 1205 travels along road segment 1200, camera 122 may capture one or more images of the environment surrounding vehicle 1205. In some embodiments, server 1230 may also receive image data that has been stripped down by a processor on vehicle 1205 to remove redundancy, as described above with reference to FIG. Figure 17 discussed.

[0286] Process 1900 may further include identifying at least one line representation of a road surface feature extending along the road segment based on the plurality of images (step 1910). Each line representation may represent a path along the road segment that substantially corresponds to the road surface feature. For example, server 1230 may analyze the environmental imagery received from camera 122 to identify a curb or lane marking and determine a travel trajectory along road segment 1200 associated with the curb or lane marking. In some embodiments, the trajectory (or line representation) may include a spline, a polynomial representation, or a curve. Server 1230 may determine the travel trajectory of vehicle 1205 based on the camera ego-motion (e.g., three-dimensional translation and / or three-dimensional rotational motion) received at step 1905.

[0287] Process 1900 may also include identifying a plurality of landmarks associated with the road segment based on the plurality of images (step 1910). For example, server 1230 may analyze the environmental images received from camera 122 to identify one or more landmarks, such as road signs along road segment 1200. Server 1230 may identify the landmarks using an analysis of a plurality of images acquired as one or more vehicles traverse the road segment. To enable crowdsourcing, the analysis may include rules for accepting and rejecting possible landmarks associated with the road segment. For example, the analysis may include accepting a potential landmark when the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark when the ratio of images in which the landmark does not appear to images in which the landmark does appear exceeds a threshold.

[0288] 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 traveling along a road segment, and process 1900 may include clustering, by server 1230, vehicle trajectories associated with a plurality of vehicles traveling on the road segment and determining a target trajectory based on the clustered vehicle trajectories, as discussed in further detail below. Clustering the vehicle trajectories may include clustering, by server 1230, the plurality of trajectories associated with vehicles traveling on the road segment into a plurality of clusters based on at least one of the absolute headings of the vehicles or the lane assignments of the vehicles. Generating the target trajectory may include averaging the clustered trajectories by server 1230. As a further example, process 1900 may include aligning the data received in step 1905. As described above, other processes or steps performed by server 1230 may also be included in process 1900.

[0289] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates rather than global coordinates. For autonomous driving, some systems may present data in world coordinates. For example, longitude and latitude coordinates on the surface of the earth may be used. In order to use a map for steering, the host vehicle may determine its position and orientation relative to the map. It seems natural to use a GPS device on the vehicle in order to locate the vehicle on the map and to find a rotational transformation between the body reference frame and the world reference frame (e.g., north, east, and down). Once the body reference frame is aligned with the map reference frame, the desired route can be expressed in the body reference frame and steering commands can be calculated or generated.

[0290] The disclosed systems and methods can enable autonomous vehicle navigation (e.g., steering control) with low-footprint models that can be collected by the autonomous vehicle itself without the assistance of expensive surveying instruments. To support autonomous navigation (e.g., steering applications), a road model can include a sparse map having the geometry of the road, its lane structure, and landmarks that can be used to determine the location or position of the vehicle along a trajectory contained in the model. As described above, the generation of the sparse map can be performed by a remote server that communicates with and receives data from vehicles traveling on the road. The data can include sensed data, trajectories reconstructed based on the sensed data, and / or recommended trajectories that can represent modified reconstructed trajectories. As described below, the server can transmit the model back to the vehicle or other vehicles traveling on the road later to assist in autonomous navigation.

[0291] Figure 2012 shows a block diagram of a server. Server 1230 may include a communication unit 2005, which may include hardware components (e.g., communication control circuitry, 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 autonomous vehicle road navigation models to one or more autonomous vehicles via communication unit 2005.

[0292] The server 1230 may include at least one non-transitory storage medium 2010, such as a hard drive, an optical disk, a magnetic tape, etc. The storage device 1410 may be configured to store data, such as navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225 and / or an autonomous vehicle road navigation model generated by the server 1230 based on the navigation information. The storage device 2010 may be configured to store any other information, such as a sparse map (e.g., as described above with reference to FIG. Figure 8 The sparse map 800 discussed).

[0293] In addition to or in place of storage device 2010, server 1230 may include memory 2015. Memory 2015 may be similar to or different from memory 140 or 150. Memory 2015 may be a non-transitory memory, such as flash memory, random access memory, etc. Memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., processor 220), map data (e.g., data of sparse map 800), autonomous vehicle road navigation models, and / or navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225.

[0294] Server 1230 may include at least one processing device 2020 configured to execute computer code or instructions stored in memory 2015 to perform various functions. For example, processing device 2020 may analyze navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and generate an autonomous vehicle road navigation model based on the analysis. Processing device 2020 may control communication unit 1405 to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles (e.g., one or more of vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicle that later travels on road segment 1200). Processing device 2020 may be similar to or different from processors 180, 190, or processing unit 110.

[0295] Figure 21 2 shows a block diagram of a memory 2015 that can store computer code or instructions for performing one or more operations for generating a road navigation model for autonomous vehicle navigation. Figure 21 As shown, the memory 2015 may store one or more modules for performing operations for processing vehicle navigation information. For example, the memory 2015 may include a model generation module 2105 and a model assignment module 2110. The processor 2020 may execute instructions stored in any of the modules 2105 and 2110 included in the memory 2015.

[0296] Model generation module 2105 may store instructions that, when executed by processor 2020, may generate at least a portion of an autonomous vehicle road navigation model for a public road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, when generating the autonomous vehicle road navigation model, processor 2020 may cluster vehicle trajectories along public road segment 1200 into different clusters. Processor 2020 may determine a target trajectory along public road segment 1200 based on the clustered vehicle trajectories for each different cluster. Such an operation may include finding a mean or average trajectory of the clustered vehicle trajectories within each cluster (e.g., by averaging data representing the clustered vehicle trajectories). In some embodiments, the target trajectory may be associated with a single lane of public road segment 1200.

[0297] The road model and / or sparse map can store trajectories associated with road segments. These trajectories can be referred to as target trajectories, which are provided to the autonomous vehicle for autonomous navigation. The target trajectories can be received from multiple vehicles or generated based on actual trajectories received from multiple vehicles or recommended trajectories (with some modifications to the actual trajectories). The target trajectories contained in the road model or sparse map can be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0298] Vehicles traveling on a road segment can collect data through various sensors. This data can include landmarks, road signature profiles, vehicle motion (e.g., accelerometer data, speed data), vehicle location (e.g., GPS data), and can reconstruct the actual trajectory itself or transmit the data to a server, which will reconstruct the actual trajectory of the vehicle. In some embodiments, the vehicle can transmit data related to the trajectory (e.g., curves in an arbitrary reference frame), landmark data, and lane assignments along the travel path to the server 1230. Various vehicles traveling along the same road segment in various driving styles can have different trajectories. The server 1230 can identify the route or trajectory associated with each lane from the trajectories received from the vehicles through a clustering process.

[0299] Figure 22 A process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 for determining a target trajectory for a public road segment (e.g., road segment 1200) is shown. The target trajectory or multiple target trajectories determined from the clustering process can be included in the autonomous vehicle road navigation model or sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 can transmit multiple trajectories 2200 to server 1230. In some embodiments, server 1230 can generate trajectories based on landmarks, road geometry, and vehicle motion information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate the autonomous vehicle road navigation model, server 1230 can cluster vehicle trajectories 1600 into multiple clusters 2205, 2210, 2215, 2220, 2225, and 2230, as shown in FIG. Figure 22 shown.

[0300] Clustering can be performed using various criteria. In some embodiments, all of the vehicles in a cluster may be similar in terms of their absolute heading along road segment 1200. Absolute heading can be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, absolute heading can be obtained using dead reckoning. As will be appreciated by those skilled in the art, dead reckoning can be used to determine the current position and, therefore, the heading of vehicles 1205, 1210, 1215, 1220, and 1225 using previously determined positions, estimated speeds, and the like. Clustering tracks by absolute heading can be helpful in identifying routes along the road.

[0301] In some embodiments, all drives in a cluster may be similar with respect to lane assignment along the drive on road segment 1200 (e.g., in the same lane before and after an intersection). Trajectories clustered by lane assignment may be helpful in identifying lanes along the road. In some embodiments, both criteria (e.g., absolute heading and lane assignment) may be used for clustering.

[0302] In each cluster 2205, 2210, 2215, 2220, 2225 and 2230, the trajectories can be averaged to obtain a target trajectory associated with a particular cluster. For example, trajectories from multiple drives associated with the same lane cluster can be averaged. The average trajectory can be a target trajectory associated with a particular lane. To average a set of trajectories, the server 1230 can select a reference frame for an arbitrary trajectory C0. For all other trajectories (C1, ..., Cn), the server 1230 can find a rigid transformation that maps Ci to C0, where i = 1, 2, ..., n, where n is a positive integer corresponding to the total number of trajectories contained in the cluster. The server 1230 can calculate a mean curve or trajectory in the C0 reference frame.

[0303] In some embodiments, landmarks can define arc length matching between different drives, which can be used to align the trajectory with the lane. In some embodiments, lane markings before and after the intersection can be used to align the trajectory with the lane.

[0304] To assemble lanes from the trajectory, server 1230 can select a reference frame for any lane. Server 1230 can map partially overlapping lanes to the selected reference frame. Server 1230 can continue mapping until all lanes are in the same reference frame. Adjacent lanes can be aligned as if they were the same lane, and they can laterally shift.

[0305] Landmarks identified along a road segment can be mapped to a common reference frame, first at the lane level and then at the intersection level. For example, the same landmark may be identified multiple times by multiple vehicles across multiple drives. The data received for the same landmark in different drives may vary slightly. This data can be averaged and mapped to a common reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of the data received for the same landmark across multiple drives can be calculated.

[0306] In some embodiments, each lane of road segment 120 can be associated with a target track and certain landmarks. The target track or multiple such target tracks can be included in the autonomous vehicle road navigation model, which can later be used by other autonomous vehicles traveling along the same road segment 1200. As the vehicles travel along road segment 1200, landmarks recognized by vehicles 1205, 1210, 1215, 1220, and 1225 can be recorded in association with the target track. The target track and landmark data can be continuously or periodically updated using new data received from other vehicles during subsequent drives.

[0307] For the positioning of autonomous vehicles, the disclosed systems and methods can use an extended Kalman filter. The positioning of the vehicle can be determined based on three-dimensional position data and / or three-dimensional orientation data, by predicting the future position ahead of the current position of the vehicle through the integration of self-motion. The positioning of the vehicle can be corrected or adjusted by observing the image of a landmark. For example, when the vehicle detects a landmark within an image captured by a camera, the landmark can be compared with known landmarks stored in the road model or sparse map 800. The known landmark can have a known position (e.g., GPS data) along the target trajectory stored in the road model and / or sparse map 800. Based on the current speed and image of the landmark, the distance from the vehicle to the landmark can be estimated. The positioning of the vehicle along the target trajectory can be adjusted based on the distance to the landmark and the known position of the landmark (stored in the road model or sparse map 800). The position / position data of the landmark stored in the road model and / or sparse map 800 (e.g., an average from multiple driving) can be assumed to be accurate.

[0308] In some embodiments, the disclosed system can form a closed-loop subsystem in which an estimate of the vehicle's six-degree-of-freedom positioning (e.g., three-dimensional position data plus three-dimensional orientation data) can be used to navigate the autonomous vehicle (e.g., steering the autonomous vehicle's wheels) to reach a desired point (e.g., stored 1.3 seconds ahead). Conversely, data measured from steering and actual navigation can be used to estimate the six-degree-of-freedom positioning.

[0309] In some embodiments, poles along the road, such as lampposts and power or cable poles, can be used as landmarks for locating the vehicle. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along the road segment, can also be used as landmarks for locating the vehicle. When poles are used for positioning, the x-view of the pole (i.e., from the vehicle's perspective) can be used instead of the y-view (i.e., distance to the pole) because the base of the pole may be obscured and sometimes not in the plane of the road.

[0310] Figure 23 A navigation system for a vehicle is shown that can be used for autonomous navigation using a crowdsourced sparse map. For illustration, the vehicle is referred to as vehicle 1205. Figure 23 The vehicle shown in FIG may be any other vehicle disclosed herein, including, for example, vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 shown in other embodiments. Figure 12 As shown, vehicle 1205 can communicate with server 1230. Vehicle 1205 can include image capture device 122 (e.g., camera 122). Vehicle 1205 can include navigation system 2300, which is configured to provide navigation guidance for vehicle 1205 traveling on a road (e.g., road segment 1200). Vehicle 1205 can also include other sensors, such as speed sensor 2320 and accelerometer 2325. Speed ​​sensor 2320 can be configured to detect the speed of vehicle 1205. Accelerometer 2325 can be configured to detect acceleration or deceleration of vehicle 1205. Figure 23 The vehicle 1205 shown in FIG2 can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, the vehicle 1205 can also be a non-autonomous, human-controlled vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0311] Navigation system 2300 may include a communication unit 2305 configured to communicate with server 1230 via communication path 1235. Navigation system 2300 may also include a GPS unit 2310 configured to receive and process GPS signals. Navigation system 2300 may also include at least one processor 2315 configured to process data such as GPS signals, map data from sparse map 800 (which may be stored on a storage device provided on vehicle 1205 and / or received from server 1230), road geometry sensed by road profile sensor 2330, images captured by camera 122, and / or autonomous vehicle road navigation models received from server 1230. Road profile sensor 2330 may include different types of devices for measuring different types of road profiles, such as road surface roughness, road width, road height, road curvature, etc. For example, road profile sensor 2330 may include a device that measures the motion of vehicle suspension 2305 to derive a road roughness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor to measure the distance from the vehicle 1205 to the side of the road (e.g., an obstacle on the side of the road), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the upper and lower elevations of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the curvature of the road. For example, a camera (e.g., camera 122 or another camera) may be used to capture an image of the road showing the curvature of the road. The vehicle 1205 may use such an image to detect the curvature of the road.

[0312] At least one processor 2315 may be programmed to receive at least one environmental image associated with vehicle 1205 from camera 122. At least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with vehicle 1205. The navigation information may include a trajectory associated with vehicle 1205 traveling along road segment 1200. At least one processor 2315 may determine the trajectory based on the motion of camera 122 (and thus the vehicle), such as three-dimensional translation and three-dimensional rotation. In some embodiments, at least one processor 2315 may determine the translation and rotation of camera 122 based on an analysis of multiple images captured by camera 122. In some embodiments, the navigation information may include lane assignment information (e.g., which lane vehicle 1205 is traveling in along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 may be used by server 1230 to generate and / or update an autonomous vehicle road navigation model, which may be transmitted from server 1230 back to vehicle 1205 for use in providing autonomous navigation guidance for vehicle 1205.

[0313] The at least one processor 2315 may also be programmed to transmit navigation information from the vehicle 1205 to the server 1230. In some embodiments, the navigation information may be transmitted to the server 1230 along with road information. The road positioning information may include at least one of GPS signals received by the GPS unit 2310, landmark information, road geometry, lane information, and the like. The at least one processor 2315 may receive an autonomous vehicle road navigation model or a portion of the model from the server 1230. The autonomous vehicle road navigation model received from the server 1230 may include at least one update based on the navigation information transmitted from the vehicle 1205 to the server 1230. The portion of the model transmitted from the server 1230 to the vehicle 1205 may include an updated portion of the model. The at least one processor 2315 may cause at least one navigation maneuver (e.g., steering, such as turning, braking, accelerating, passing another vehicle, etc.) of the vehicle 1205 based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0314] At least one processor 2315 may be configured to communicate with various sensors and components included in vehicle 1205, including 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 additionally, various sensors or components of vehicle 1205 may also communicate with server 1230 and transmit data or information collected by the sensors or components to server 1230.

[0315] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can communicate with each other and share navigation information with each other, so that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 can, for example, use crowdsourcing to generate an autonomous vehicle road navigation model based on information shared by other vehicles. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 can share navigation information with each other, and each vehicle can update the autonomous vehicle road navigation model provided in its own vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) can serve as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) can perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle can communicate with other vehicles and receive navigation information from them. The at least one processor 2315 of the hub vehicle may generate an autonomous vehicle road navigation model or updates to the model based on the shared information received from the other vehicles. The at least one processor 2315 of the hub vehicle may transmit the autonomous vehicle road navigation model or updates to the model to the other vehicles to provide autonomous navigation guidance.

[0316] Mapped lane markings and navigation based on mapped lane markings

[0317] As previously mentioned, the autonomous vehicle road navigation model and / or sparse map 800 may include a plurality of mapped lane markers associated with road segments. As discussed in more detail below, these mapped lane markers may be used when the autonomous vehicle is navigating. For example, in some embodiments, the mapped lane markers may be used to determine the lateral position and / or orientation relative to the planned trajectory. Using this position information, the autonomous vehicle may adjust its heading to match the direction of the target trajectory at the determined location.

[0318] Vehicle 200 can be configured to detect lane markings in a given road segment. A road segment can include any markings on a road used to direct vehicular traffic on the road. For example, a lane marking can be a solid or dashed line that distinguishes the edge of a travel lane. Lane markings can also include double lines, such as double solid lines, double dashed lines, or a combination of solid and dashed lines, to indicate, for example, whether overtaking is allowed in an adjacent lane. Lane markings can also include highway entrance and exit signs indicating, for example, deceleration lanes for exit ramps, or dashed lines indicating that a lane is a turn-only lane or is about to end. Signs can also indicate work zones, temporary lane changes, travel paths through intersections, medians, dedicated lanes (e.g., bicycle lanes, HOV lanes, etc.), or various other markings (e.g., crosswalks, speed bumps, railroad crossings, stop lines, etc.).

[0319] The vehicle 200 may use a camera, such as the image capture devices 122 and 124 included in the image acquisition unit 120, to capture images of surrounding lane markings. The vehicle 200 may analyze the images based on features identified in one or more captured images to detect point locations associated with the lane markings. These point locations may be uploaded to a server to represent the lane markings in the sparse map 800. Depending on the position and field of view of the camera, lane markings on both sides of the vehicle may be detected simultaneously from a single image. In other embodiments, different cameras may be used to capture images on multiple sides of the vehicle. Instead of uploading actual images of the markings, the lane markings may be stored as splines or a series of points in the sparse map 800, thereby reducing the size of the sparse map 800 and / or the data that must be uploaded remotely by the vehicle.

[0320] Figures 24A-24D Example point locations that can be detected by vehicle 200 to represent a particular lane marking are shown. Similar to the landmarks described above, vehicle 200 can use various image recognition algorithms or software to identify point locations within the captured image. For example, vehicle 200 can identify a series of edge points, corner points, or various other point locations associated with a particular lane marking. Figure 24A 2 shows a solid lane marker 2410 that can be detected by the vehicle 200. The lane marker 2410 can represent the outside edge of the road and is represented by a solid white line. Figure 24AAs shown, the vehicle 200 can be configured to detect a plurality of edge positioning points 2411 along the lane markings. The positioning points 2411 can be collected to represent the lane markings at any interval sufficient to create mapped lane markings in the sparse map. For example, the lane markings can be represented by one point every meter of the detected edge, one point every five meters of the detected edge, or at other suitable spacings. In some embodiments, the spacing can be determined by other factors rather than set intervals, such as, for example, based on the point at which the vehicle 200 has the highest confidence ranking for the location of the detected point. Although Figure 24A Edge positioning points on the inner edge of lane marking 2410 are shown, these points can be collected on the outer edge of the line or along both edges. Figure 24A A single line is shown in FIG, but similar edge points can be detected for double solid lines. For example, point 2411 can be detected along the edge of one or two solid lines.

[0321] Vehicle 200 may also represent lane markings differently depending on the type or shape of the lane markings. Figure 24B An exemplary dashed lane marking 2420 is shown that can be detected by the vehicle 200. The vehicle can detect a series of corner points 2421 representing the corners of the lane dash to define the complete boundary of the dashed line, rather than as Figure 24A Identify edge points as in Figure 24B Each corner of a given dotted line marker being located is shown, but the vehicle 200 can detect or upload a subset of the points shown in the figure. For example, the vehicle 200 can detect the leading edge or leading corner of a given dotted line marker, or can detect the two corner points closest to the interior of the lane. In addition, not every dotted line marker can be captured, for example, the vehicle 200 can capture and / or record points representing samples of dotted line markers (e.g., every other, every three, every five, etc.), or points representing dotted line markers at predetermined intervals (e.g., every meter, every five meters, every ten meters, etc.). Corner points of similar lane markers (such as signs indicating that a lane is for an exit ramp, signs indicating that a particular lane is about to end, or various other lane markers that may have detectable corner points) can also be detected. Corner points of lane markers consisting of double dashed lines or a combination of solid and dashed lines can also be detected.

[0322] In some embodiments, the points uploaded to the server to generate mapped lane markings may represent points other than detected edge points or corner points. Figure 24CA series of points that can represent the centerline of a given lane marking are shown. For example, a solid lane 2410 can be represented by a centerline point 2441 along the centerline 2440 of the lane marking. In some embodiments, the vehicle 200 can be configured to detect these centerpoints using various image recognition techniques such as convolutional neural networks (CNNs), scale-invariant feature transforms (SIFTs), histograms of oriented gradients (HOG) features, or other techniques. Alternatively, the vehicle 200 can detect other points such as Figure 24A The edge points 2411 shown are shown, and the centerline points 2441 can be calculated, for example, by detecting points along each edge and determining the midpoint between the edge points. Similarly, the dashed lane marker 2420 can be represented by a centerline point 2451 along the centerline 2450 of the lane marker. The centerline points can be located at the edges of the dashed lines, as shown in Figure 24C, or at various other locations along the centerline. For example, each dashed line can be represented by a single point at the geometric center of the dashed line. The points can also be spaced at predetermined intervals along the centerline (e.g., every meter, every 5 meters, every 10 meters, etc.). The centerline points 2451 can be detected directly by the vehicle 200, or can be calculated based on other detected reference points (such as corner points 2421), as shown in Figure 24C. Figure 24B Using similar techniques to those described above, center lines can also be used to represent other lane marking types, such as double lines.

[0323] In some embodiments, vehicle 200 may identify points representing other features, such as a vertex between two intersecting lane markings. Figure 24D Example points representing an intersection between two lane markers 2460 and 2465 are shown. Vehicle 200 can calculate a vertex 2466 representing the intersection between the two lane markers. For example, one of lane markers 2460 or 2465 can represent a train crossing area or other intersection area in the road segment. Although lane markers 2460 and 2465 are shown as crossing each other perpendicularly, various other configurations can be detected. For example, lane markers 2460 and 2465 can cross at other angles, or one or both lane markers can terminate at vertex 2466. Similar techniques can also be applied to intersections between dashed lines or other lane marking types. In addition to vertex 2466, various other points 2467 can also be detected to provide further information about the orientation of lane markers 2460 and 2465.

[0324] Vehicle 200 can associate real-world coordinates with each detected point of a lane marker. For example, a location identifier (including the coordinates of each point) can be generated and uploaded to a server for use in mapping lane markers. The location identifier can also include other identifying information about the point, including whether the point represents a corner point, an edge point, a center point, etc. Therefore, vehicle 200 can be configured to determine the real-world location of each point based on analysis of the image. For example, vehicle 200 can detect other features in the image (such as the various landmarks described above) to locate the real-world location of the lane marker. This can include determining the location of the lane marker in the image relative to a detected landmark, or determining the vehicle's position based on the detected landmark and then determining the distance from the vehicle (or the vehicle's target trajectory) to the lane marker. When landmarks are unavailable, the location of the lane marker point can be determined relative to the vehicle's position determined based on dead reckoning. The real-world coordinates included in the location identifier can be expressed as absolute coordinates (e.g., latitude / longitude coordinates) or relative to other features, such as based on a longitudinal position along the target trajectory and a lateral distance from the target trajectory. The position identifiers can then be uploaded to a server for use in generating mapped lane markings in a navigation model, such as the sparse map 800. In some embodiments, the server can construct splines representing lane markings for a road segment. Alternatively, the vehicle 200 can generate the splines and upload them to the server for recording in the navigation model.

[0325] Figure 24E An exemplary navigation model or sparse map of a corresponding road segment including mapped lane markings is shown. The sparse map may include a target trajectory 2475 for the vehicle to follow along the road segment. As described above, the target trajectory 2475 may represent an ideal path for the vehicle to take when traveling along the corresponding road segment, or may be located elsewhere on the road (e.g., the centerline of the road, etc.). The target trajectory 2475 may be calculated using various methods as described above, for example, by aggregating (e.g., weighted combining) two or more reconstructed trajectories of the vehicle passing through the same road segment.

[0326] In some embodiments, target tracks can be generated equally for all vehicle types and for all roads, vehicles and / or environmental conditions. However, in other embodiments, various other factors or variables can also be considered when generating the target track. Different target tracks can be generated for different types of vehicles (e.g., private cars, light trucks and full trailers). For example, a target track with a relatively small turning radius can be generated for a small private car compared to a larger semi-trailer truck. In some embodiments, roads, vehicles and environmental conditions can also be considered. For example, different target tracks can be generated for different road conditions (e.g., wet, snowy, icy, dry, etc.), vehicle conditions (e.g., tire conditions or estimated tire conditions, braking conditions or estimated braking conditions, remaining fuel amount, etc.), or environmental factors (e.g., time of day, visibility, weather, etc.). The target track can also depend on one or more aspects or features (e.g., speed limit, frequency and size of turns, slope, etc.) of a specific road section. In some embodiments, various user settings can also be used to determine the target track, such as the driving mode set (e.g., desired driving positivity, economy mode, etc.).

[0327] The sparse map may also include mapped lane markers 2470 and 2480 representing lane markers along the road segment. The mapped lane markers may be represented by multiple location identifiers 2471 and 2481. As described above, the location identifier may include the location of the point associated with the detected lane marker in real-world coordinates. Similar to the target trajectory in the model, the lane marker may also include elevation data and may be represented as a curve in three-dimensional space. For example, the curve may be a spline connecting three-dimensional polynomials of appropriate order. The curve may be calculated based on the location identifier. The mapped lane markers may also include other information or metadata about the lane markers, such as an identifier of the type of lane marker (e.g., a lane marker between two lanes traveling in the same direction, a lane marker between two lanes traveling in opposite directions, a curb, etc.) and / or other characteristics of the lane marker (e.g., solid line, dashed line, single line, double line, yellow, white, etc.). In some embodiments, for example, crowdsourcing technology may be used to continuously update the mapped lane markers within the model. The same vehicle may upload a location identifier during multiple occasions while traveling the same road segment, or data may be selected from multiple vehicles (such as 1205, 1210, 1215, 1220, and 1225) traveling the road segment at different times. The sparse map 800 may then be updated or refined based on subsequent location identifiers received from the vehicle and stored in the system. As the mapped lane markings are updated and refined, the updated road navigation model and / or sparse map may be distributed to multiple autonomous vehicles.

[0328] Generating mapped lane markings in a sparse map may also include detecting and / or mitigating errors based on anomalies in the image or in the actual lane markings themselves. Figure 24F An exemplary anomaly 2495 associated with detected lane marking 2490 is shown. Anomaly 2495 may appear in an image captured by vehicle 200 due to, for example, an object obstructing the camera's view of the lane marking, debris on the lens, and the like. In some cases, the anomaly may be caused by the lane marking itself, which may be damaged or worn, or partially covered by dirt, debris, water, snow, or other material on the road. Anomaly 2495 may result in an erroneous point 2491 detected by vehicle 200. Sparse map 800 can provide correctly mapped lane markings and eliminate errors. In some embodiments, vehicle 200 may detect erroneous point 2491, for example, by detecting anomaly 2495 in an image or by identifying an error based on detected lane marking points before and after the anomaly. Based on the detected anomaly, the vehicle may omit point 2491 or adjust it to be consistent with other detected points. In other embodiments, the error may be corrected after the point has been uploaded, for example, by determining that the point is outside an expected threshold based on other points uploaded during the same trip or based on aggregation of data from previous trips along the same road segment.

[0329] The mapped lane markers in the navigation model and / or sparse map can also be used for navigation of autonomous vehicles passing through the corresponding roads. For example, a vehicle navigating along a target trajectory can periodically use the mapped lane markers in the sparse map to align itself with the target trajectory. As described above, between landmarks, the vehicle can navigate based on dead reckoning, where the vehicle uses sensors to determine its own motion and estimate its position relative to the target trajectory. Errors may accumulate over time, and the position determination of the vehicle relative to the target trajectory may become increasingly inaccurate. Accordingly, the vehicle can use the lane markers (and their known positioning) that appear in the sparse map 800 to reduce errors caused by dead reckoning in position determination. In this way, the identified lane markers included in the sparse map 800 can be used as navigation anchors, from which the exact position of the vehicle relative to the target trajectory can be determined.

[0330] Figure 25A An exemplary image 2500 of a vehicle's surroundings that can be used for navigation based on mapped lane markings is shown. Image 2500 can be captured, for example, by vehicle 200 using image capture devices 122 and 124 included in image acquisition unit 120. Image 2500 can include an image of at least one lane marking 2510, such as Figure 25A The image 2500 may also include one or more landmarks 2521, such as road signs, for use in navigation as described above. Figure 25ASome elements shown in 2500 that do not appear in captured image 2500 but are detected and / or determined by vehicle 200 (such as elements 2511 , 2530 , and 2520 ) are also shown for reference.

[0331] Use the reference above Figures 24A-24D and Figure 24F Using various techniques described above, a vehicle can analyze image 2500 to identify lane markings 2510. Various points 2511 corresponding to features of lane markings in the image can be detected. For example, point 2511 can correspond to an edge of a lane marking, a corner of a lane marking, a midpoint of a lane marking, a vertex between two intersecting lane markings, or various other features or locations. Point 2511 can be detected as a location corresponding to a point stored in a navigation model received from a server. For example, if a sparse map containing points representing the centerlines of mapped lane markings is received, point 2511 can also be detected based on the centerlines of lane markings 2510.

[0332] The vehicle can also determine a longitudinal position, represented by element 2520, located along the target trajectory. For example, longitudinal position 2520 can be determined from image 2500 by detecting landmarks 2521 within image 2500 and comparing the measured positions with known landmark positions stored in the road model or sparse map 800. The vehicle's position along the target trajectory can then be determined based on the distance to the landmarks and the known positions of the landmarks. Longitudinal position 2520 can also be determined from images other than those used to determine the positions of lane markings. For example, longitudinal position 2520 can be determined by detecting landmarks in images from other cameras within image acquisition unit 120 that were captured simultaneously or nearly simultaneously with image 2500. In some cases, the vehicle may not be near any landmarks or other reference points used to determine longitudinal position 2520. In such cases, the vehicle can navigate based on dead reckoning and, therefore, use sensors to determine its ego-motion and estimate longitudinal position 2520 relative to the target trajectory. The vehicle can also determine distance 2530, which represents the actual distance between the vehicle and lane marking 2510 as observed in the captured image(s). The camera angle, the speed of the vehicle, the width of the vehicle, or various other factors may be considered when determining the distance 2530 .

[0333] Figure 25BA lateral positioning correction of a vehicle based on mapped lane markings in a road navigation model is shown. As described above, the vehicle 200 can use one or more images captured by the vehicle 200 to determine the distance 2530 between the vehicle 200 and the lane marking 2510. The vehicle 200 can also access a road navigation model (such as a sparse map 800), which can include mapped lane markings 2550 and a target trajectory 2555. The mapped lane markings 2550 can be modeled using the techniques described above, such as using crowdsourced positioning identifiers captured by multiple vehicles. The target trajectory 2555 can also be generated using the various techniques previously described. The vehicle 200 can also determine or estimate the longitudinal position 2520 along the target trajectory 2555, as described above with reference to FIG. Figure 25A The vehicle 200 can then determine an expected distance 2540 based on the lateral distance between the target track 2555 and the mapped lane marker 2550, corresponding to the longitudinal position 2520. The lateral positioning of the vehicle 200 can be corrected or adjusted by comparing the actual distance 2530 measured using the captured image(s) to the expected distance 2540 from the model.

[0334] Figure 26A 2 is a flow chart illustrating an exemplary process 2600A for mapping lane markings for autonomous vehicle navigation consistent with the disclosed embodiments. At step 2610, process 2600A may include receiving two or more location identifiers associated with detected lane markings. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifiers may include the locations of points associated with the detected lane markings in real-world coordinates, as described above with reference to FIG. Figure 24EIn some embodiments, the location identifier may also include other data, such as additional information about road segments or lane markings. Additional data, such as accelerometer data, speed data, landmark data, road geometry or contour data, vehicle location data, ego-motion data, or various other forms of data as described above, may also be received during step 2610. The location identifier may be generated by a vehicle (such as vehicles 1205, 1210, 1215, 1220, and 1225) based on images captured by the vehicle. For example, the identifier may be determined based on acquiring at least one image representing the host vehicle's environment from a camera associated with the host vehicle, analyzing the at least one image to detect lane markings in the host vehicle's environment, and analyzing the at least one image to determine the position of the detected lane markings relative to a location associated with the host vehicle. As described above, lane markings may include a variety of different marking types, and the location identifiers may correspond to various points relative to the lane markings. For example, if the detected lane marking is part of a dashed line marking a lane boundary, the points may correspond to detected corners of the lane marking. If the detected lane marking is part of a solid line marking a lane boundary, the points may correspond to detected edges of the lane marking at various spacings as described above. In some embodiments, these points may correspond to the center lines of detected lane markings, such as Figure 24C As shown, or may correspond to at least one of a vertex between two intersecting lane markers and two other points associated with the intersecting lane markers, such as Figure 24D shown.

[0335] At step 2612, process 2600A may include associating the detected lane marking with a corresponding road segment. For example, server 1230 may analyze the real-world coordinates or other information received during step 2610 and compare the coordinates or other information with positioning information stored in the autonomous vehicle road navigation model. Server 1230 may determine a road segment in the model that corresponds to the real-world road segment at which the lane marking was detected.

[0336] At step 2614, process 2600A may include updating the autonomous vehicle road navigation model with respect to the corresponding road segment based on the two or more positioning identifiers associated with the detected lane markings. For example, the autonomous road navigation model may be the sparse map 800, and the server 1230 may update the sparse map to include or adjust the mapped lane markings in the model. The server 1230 may update the sparse map based on the above reference. Figure 24EIn some embodiments, updating the autonomous vehicle road navigation model may include storing one or more position indicators of detected lane markings in real-world coordinates. The autonomous vehicle road navigation model may also include at least one target trajectory followed by the vehicle along the corresponding road segment, such as Figure 24E shown.

[0337] At step 2616, process 2600A may include distributing the updated autonomous vehicle road navigation model to a plurality of autonomous vehicles. For example, server 1230 may distribute the updated autonomous vehicle road navigation model to vehicles 1205, 1210, 1215, 1220, and 1225, which may use the model for navigation. The autonomous vehicle road navigation model may be distributed via one or more networks (e.g., via a cellular network and / or the Internet, etc.) via wireless communication paths 1235, such as Figure 12 shown.

[0338] In some embodiments, lane markings may be mapped using data received from multiple vehicles (such as through crowdsourcing techniques), as described above with reference to Figure 24E As described. For example, process 2600A may include receiving a first communication from a first host vehicle including a location identifier associated with a detected lane marking, and receiving a second communication from a second host vehicle including an additional location 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 from the same vehicle on a subsequent trip along the same road segment. Process 2600A may also include refining the determination of at least one location associated with the detected lane marking based on the location identifier received in the first communication and based on the additional location identifier received in the second communication. This may include using an average of multiple location identifiers and / or filtering out "ghost" identifiers that may not reflect the real-world location of the lane marking.

[0339] Figure 26B is a flow chart illustrating an exemplary process 2600B for autonomously navigating a host vehicle along a road segment using mapped lane markings. Process 2600B may be performed, for example, by processing unit 110 of autonomous vehicle 200. At step 2620, process 2600B may include receiving an autonomous vehicle road navigation model from a server-based system. In some embodiments, the autonomous vehicle road navigation model may include a target trajectory of the host vehicle along the road segment and a positioning identifier associated with one or more lane markings associated with the road segment. For example, vehicle 200 may receive sparse map 800 or another road navigation model generated using process 2600A. In some embodiments, the target trajectory may be represented as a three-dimensional spline, such as Figure 9B As shown above. Figures 24A-24F The positioning identifier may include the positioning of a point associated with a lane marking in real-world coordinates (e.g., a corner point of a dashed lane marking, an edge point of a solid lane marking, a vertex between two intersecting lane markings and other points associated with intersecting lane markings, a center line associated with a lane marking, etc.).

[0340] At step 2621, process 2600B may include receiving at least one image representing the environment of the vehicle. The image may be received from an image capture device of the vehicle, such as by image capture devices 122 and 124 included in image acquisition unit 120. The image may include an image of one or more lane markings, similar to image 2500 described above.

[0341] At step 2622, process 2600B may include determining the longitudinal position of the host vehicle along the target trajectory. Figure 25A As mentioned, this may be based on other information in the captured image (e.g., landmarks, etc.) or by dead reckoning of the vehicle between detected landmarks.

[0342] At step 2623, process 2600B may include determining an expected lateral distance to a lane marker based on the determined longitudinal position of the host vehicle along the target trajectory and based on two or more positioning identifiers associated with at least one lane marker. For example, vehicle 200 may use sparse map 800 to determine the expected lateral distance to the lane marker. Figure 25B As shown, longitudinal position 2520 along target trajectory 2555 may be determined in step 2622. Using sparse map 800, vehicle 200 may determine expected distance 2540 to mapped lane marker 2550 corresponding to longitudinal position 2520.

[0343] At step 2624, process 2600B may include analyzing at least one image to identify at least one lane marking. For example, vehicle 200 may use various image recognition techniques or algorithms to identify lane markings within the image, as described above. For example, lane marking 2510 may be detected by image analysis of image 2500, such as Figure 25A shown.

[0344] At step 2625, process 2600B may include determining an actual lateral distance to at least one lane marker based on analysis of the at least one image. For example, the vehicle may determine distance 2530 representing the actual distance between the vehicle and lane marker 2510, such as Figure 25A When determining distance 2530, the camera angle, the speed of the vehicle, the width of the vehicle, the position of the camera relative to the vehicle, or various other factors may be considered.

[0345] At step 2626, process 2600B may include determining an autonomous steering action for the host vehicle based on a difference between the expected lateral distance to the at least one lane marker and the determined actual lateral distance to the at least one lane marker. Figure 25B As described above, the vehicle 200 can compare the actual distance 2530 with the expected distance 2540. The difference between the actual distance and the expected distance can indicate the error (and its magnitude) between the actual position of the vehicle and the target trajectory that the vehicle is to follow. Accordingly, the vehicle can determine autonomous steering actions or other autonomous actions based on the difference. For example, if the actual distance 2530 is less than the expected distance 2540, as shown in FIG. Figure 25B As shown, the vehicle can determine an autonomous steering action to guide the vehicle away from lane marking 2510. As a result, the vehicle's position relative to the target trajectory can be corrected. Process 2600B can be used, for example, to improve vehicle navigation between landmarks.

[0346] Navigation based on road vector field

[0347] As described above, vehicles such as autonomous or semi-autonomous vehicles can navigate based on road navigation maps. Such maps can provide information about drivable paths, lane semantics, intersections, etc., which can allow the host vehicle to navigate road segments and build accurate predictions for the future. In some embodiments, the vehicle can navigate based on sparse maps, which, as described above, can provide sufficient information for navigation without requiring excessive data storage or data transfer rates. In some cases, positioning problems can cause sparse maps or other navigation data to be inaccurate or even unavailable. Other problems with the map can arise due to changes in road or lane markings, changes in traffic patterns, the addition of additional traffic signs, or other real-world changes that can affect navigation. In addition, there may be some areas for which no map data is available. Based on these and other potential problems with road navigation maps, it may be desirable to have alternative and / or additional methods for navigation based on sensor data.

[0348] Thus, the present disclosure may include a vehicle navigation system that analyzes an image captured by an image capture device of a host vehicle. The system may analyze one or more pixels within the captured image and generate predicted or estimated paths at various points within the image. The estimated path may include any representation of the motion that a vehicle or other agent (e.g., a pedestrian, animal, etc.) associated with that point may have. In some embodiments, the estimated path may be an estimated path for the host vehicle. Additionally or alternatively, the estimated path may be determined for other vehicles (e.g., a target vehicle captured in the image). In some embodiments, the estimated path may represent the path of a hypothetical vehicle at different points, where the hypothetical vehicle is not included in the image.

[0349] The estimated path can be represented in various forms. For example, the estimated path can include a set of points that indicate the expected positions of the vehicle or other agent at various times in the future. The estimated path can be represented as a spline that indicates the path that the vehicle is expected to follow over a period of time. In some embodiments, the estimated path can be represented as a vector at a given point that indicates the predicted motion that the vehicle at that point will have. The vector prediction can be based on features detected within the image, such as road direction arrows, curbs, road curvature, or other road topology features detected in the image. The motion vector predictions at several points in the entire image can be aggregated to form a vector array or vector field that indicates the predicted motion at their respective points. The resulting vector field can be used, for example, to predict the future paths of the host vehicle and / or other target vehicles in the host vehicle's environment. The resulting path can be used as a supplement to or replacement for sparse maps or other road navigation map data.

[0350] Figure 27 is an illustration of an example image 2700 that may be captured by a host vehicle consistent with the disclosed embodiments. For example, image 2700 may be captured from the environment of host vehicle 200 using image acquisition unit 120, as described in detail above. Image 2700 may include a road surface 2730 on which host vehicle 200 is traveling. The road may include multiple lanes of travel, as indicated by lane markings 2734 and 2736. Figure 27 In the example shown, image 2700 may include an intersection or road entry point, as shown by driveway 2732. The image may also include other vehicles, such as target vehicle 2720, which, in this example, may enter the road from driveway 2732. Image 2700 may also include directional arrow 2738, indicating that the lane associated with directional arrow 2738 is a turn-only lane. Image 2700 may include other features, such as curbs 2740 and 2742, guardrail 2744, and median 2746.

[0351] The vehicle navigation system can be configured to detect road topology features from within image 2700. As used herein, a road topology feature can include any natural or man-made feature contained within the environment of the host vehicle. Such road topology features can indicate the configuration, layout, and traffic patterns of portions of a road. A road topology feature can include any feature included in image 2700 as described above. Figure 28 is an illustration of another example image 2800 with additional example road topology features that can be detected by a host vehicle consistent with the disclosed embodiments. In some embodiments, the road topology features can include features on the road surface. For example, the road topology features can include directional arrows, such as turn arrows (e.g., Figure 27 ), merge arrows, U-turn arrows, etc. Road topology features may include other road markings, such as lane markings, HOV lane markings, bicycle lane markings, stop lines, crosswalks (e.g., Figure 28 Crosswalk 2840 as shown), or other markings on the road surface.

[0352] In some embodiments, the road topology features may include the edges of the road. For example, the image 2800 may include Figure 28 Curbs 2810 and 2820 (and / or Figure 27 Curbs 2740 and 2742 are shown. A curb can be any transition from a drivable road surface to a non-drivable road surface or object. For example, curb 2810 can be the edge of a dirt, gravel, or grass surface area to indicate the edge of the road. Curb 2820 can include an elevated structure, such as a concrete curb or barrier, which can indicate the edge of the road. Other obstacles or barriers (such as guardrail 2744) can be detected as road topology features. In some embodiments, road topology features can include the shape or curvature of the road. For example, image 2800 can include curve 2850, which can be detected by a vehicle navigation system. Other features associated with the shape of the road can include: merging lanes, exit ramps, intersections, lane splits, etc.

[0353] Any suitable means can be used to detect such road topology features. For example, a vehicle navigation system can use a computer vision algorithm to detect and / or label objects in an environment from which images are captured and processed, as described in various embodiments above. In some embodiments, road topology features can be detected at least in part based on elevation. For example, a plurality of images captured at different times can indicate the elevation of the object in the image. In image 2800, road surface 2830 can be determined to have an elevation different from curb 2820, which can be used to detect road topology features. In some embodiments, one or more road topology features can be identified based on a trained machine learning process. For example, an image set containing road topology features and labels or other identifications of these features can be input into a machine learning model as training data. The resulting trained model can be used to analyze images to identify the road topology features in the image. Various other machine learning algorithms may be used, including logistic regression, linear regression, regression, random forest, K-nearest neighbor (KNN) model, K-means model, decision tree, Cox proportional hazards regression model, naive Bayes model, support vector machine (SVM) model, gradient boosting algorithm, deep learning model, or any other form of machine learning model or algorithm.

[0354] Based on these detected features within the image, the vehicle navigation system can be configured to determine an estimated path associated with one or more points in the vehicle's environment. In some embodiments, the estimated path can be expressed as a prediction of the movement that the vehicle at that point will make. Figure 29 is an illustration of an example vector field overlaid on image 2700 consistent with the disclosed embodiments. Figure 29 As shown, the vehicle navigation system can determine a predicted motion vector 2920 at point 2910. As described above, predicted motion vector 2920 can represent the predicted motion that the vehicle at point 2910 will take. In some embodiments, predicted motion vector 2920 can represent the motion that the vehicle will take if it travels along a path that includes point 2910. Because a vehicle is larger than a single point in an image, a representative anchor point for the vehicle can be assumed (e.g., on an edge of the vehicle, at the center of the vehicle, etc.), and the motion vector can represent the motion that the vehicle will take with the anchor point at that location. For example, predicted motion vector 2920 can indicate the direction that the vehicle will travel based on the center point of the vehicle (or any other point of the vehicle) passing through point 2910. In some embodiments, the generated vector can have a predetermined length. For example, vector 2920 can represent a path along the expected path of the vehicle at point 2910, connecting point 2910 to a second point at a predetermined distance from point 2910 (e.g., 0.5 meters, 1 meter, 2 meters, 5 meters, etc.).

[0355] like Figure 29 As shown, this process can be performed for several points within image 2700 to generate a vector array (i.e., vector field) 2930. Each vector in vector field 2930 can represent the direction that a vehicle at that point (e.g., having a center point or other point at that location) is expected or predicted to travel. The resulting vector array can map the expected travel path for each point within the image. For example, Figure 29 As shown, vehicles near the driving lane 2732 can be expected to travel into the driving lane near the entrance, and vehicles on the other side of the driving lane can be expected to travel into the road. Similarly, the vector array can indicate that vehicles in the turning lane (i.e., the lane associated with the turn arrow 2738 as described above) can be expected to turn left, as indicated by the vectors in that lane. It is worth noting that the vector field can be determined without relying on lane markings (e.g., lane marking 2734). This can be advantageous because lane markings are not always present in every vehicle environment, such as in an urban environment. In addition, lane markings can be difficult to detect, for example: due to limitations of image detection technology, due to wear or damage to the lane markings, due to debris or other materials covering the lane markings (e.g., dirt, snow, water, etc.), or because objects block the lane markings from view.

[0356] In some embodiments, a vector in vector field 2930 can be determined for each pixel contained in the captured image. Thus, the resulting vector field can have a resolution equal to that of the captured image. In other embodiments, each point (e.g., point 2910) can be associated with a group of pixels. For example, point 2910 can represent a group of consecutive pixels (e.g., 2 pixels, 5 pixels, 10 pixels, 20 pixels, 50 pixels, etc.), and a predicted motion vector can be determined for each group of pixels within the image. The system can be configured to determine predicted motion vectors only for pixels associated with a road surface. For example, a trained neural network can be configured to detect road surface 2730 and can generate vectors only for pixels (or groups of pixels) associated with road surface 2730. In some embodiments, this can be inherent in the process of generating the vector field. For example, a vehicle navigation system may not generate vectors (or may generate vectors with zero magnitude) for pixels not associated with a road surface.

[0357] Vector field 2930 can be generated according to any suitable technique. In some embodiments, a trained neural network (or another form of machine learning model) can be developed to generate a vector field for an input image. The model can be trained using a training dataset that includes a set of training images that have been inspected and characterized so that each pixel (or group of pixels) is associated with a predicted motion vector. This characterization can be performed, for example, by one or more human inspectors who analyze the captured images in the training dataset and assign predicted motion vectors to the pixels of the captured images. As a result, the trained neural network model can be configured to determine a motion vector for each pixel within the input image.

[0358] The effectiveness and accuracy of a neural network can depend on the quality and quantity of the training data available within the training dataset. Therefore, advantages can be provided by employing a large training dataset (e.g., comprising hundreds, thousands, or millions of specified captured images). However, generating such a large dataset using a manual inspection process may be impractical or impossible. To address this challenge, the system can employ a series of image analysis algorithms that are designed to specifically identify a predicted motion vector for each pixel within an image. In some embodiments, this can be based on information included in a sparse map. For example, an algorithm can be implemented to interpolate between multiple drivable paths included in a sparse map to generate a corresponding vector field within a road segment. This vector field can be correlated with multiple images captured along the road segment to generate training data. Based on the resulting training dataset, a neural network model can be developed to determine vector fields for other input images.

[0359] The resulting vector field 2930 can be used to determine additional information about the host vehicle's environment. In some embodiments, a predicted path for the host vehicle or target vehicle, or a predicted path not associated with a vehicle, can be determined. Figure 30 3010, 3012, 3014, and 3020, as shown in FIG. Figure 30 Predicted paths 3010, 3012, 3014, and 3020 can be determined based at least in part on vector field 2930. For example, a starting point can be established for the predicted path, and the system can track a series of predicted motion vectors through vector field 2930 to generate the predicted path.

[0360] Predicted paths can be generated at various locations within image 2700. Predicted path 3010 can represent the predicted path of the host vehicle (e.g., the vehicle that captured the image). Thus, in embodiments where a sparse map or other navigation map is unavailable, predicted path 3010 can be used to navigate vehicle 200. In other embodiments, predicted path 3010 can be used as a redundant path. For example, predicted path 3010 can be used as a check to ensure that the information in the sparse map is accurate and up-to-date. Any discrepancies can be tracked and, in some embodiments, can be used to update the sparse map.

[0361] In some embodiments, predicted path 3010 (or predetermined paths 3012, 3014, and / or 3020) can be associated with a predetermined distance (D), as described above. In embodiments where each vector is associated with a predetermined distance, the predicted path can be determined based on the number of vectors used to generate the predicted path. For example, if each vector is 1 meter long, the length of the predicted path generated by tracking 100 vectors would be 100 meters. Predicted path 3010 can originate from a point in front of the host vehicle. In some embodiments, this can be a predetermined distance in front of the host vehicle (e.g., 2 meters, 5 meters, 6 meters, 10 meters, etc.). Predicted path 3010 can follow vectors within vector field 2930 within a predetermined distance (D) (e.g., 50 meters, 100 meters, 200 meters, etc.). In other embodiments, predicted path 3010 can extend as far as the path can be seen in image 2700.

[0362] A similar process can be used to generate predicted paths for other actors within image 2700, such as target vehicle 2720. For example, a vehicle navigation system can generate predicted path 3020, which represents the predicted path of target vehicle 2720. Predicted path 3020 can be determined in a manner similar to predicted path 3010, for example, by tracking a vector in front of target vehicle 2720. In some embodiments, the vector can be tracked for a predetermined distance, which can be the same as or different from predetermined distance D. Predicted path 3020 can originate from a point associated with target vehicle 2720 detected in the image. For example, the path can include the center point of target vehicle 2720. In some embodiments, predicted paths can be generated for multiple points associated with target vehicle 2720. For example, predicted paths can be generated for points on either side of target vehicle 2720 to generate a predicted corridor for target vehicle 2720. This corridor can be used to predict interactions between host vehicle 200 and target vehicle 2720. For example, the lateral spacing between predicted path 301 and predicted path 3020 (ie, corridors) may be analyzed to predict future spacing between vehicles, which may be used to make navigation determinations.

[0363] In some embodiments, predicted paths may be generated for other locations not associated with a vehicle. For example, predicted paths 3012 and 3014 may be generated for lanes adjacent to the lane in which the host vehicle 200 is traveling. Figure 30 As shown, predicted path 3014 may indicate that a vehicle traveling in a lane to the left of host vehicle 200 is expected to turn. In some embodiments, the predicted path may branch into multiple possible paths. For example, a vehicle traveling along predicted path 3012 may turn into driving lane 2732, or may continue straight ahead. Figure 30 As shown, based on the analysis of the vector field 2930, the predicted path 3012 can be split to display multiple paths.

[0364] As described above, vector field 2930 can be determined without considering lane markings (e.g., lane marking 2734). Thus, in areas where lane markings are detected, the lane markings can be used to adjust or calibrate the predicted path. For example, lane markings 2734 and 2736 may be detected by the vehicle navigation system, but they may not be used to generate vector field 2930. The positions of lane markings 2734 and 2736 can then be used to adjust vector field 2930 and / or predicted path 3010. For example, various points within vector field 2930 can be adjusted or stabilized to align with the centerlines of lane markings 2734 and 2736. Additional centerlines can be interpolated throughout the image to align the vectors of vector field 2930. As another example, predicted path 3010 can be offset based on detected lane markings 2734 and 2736 so that it is centered in the lane. In such embodiments, vector field 2930 and predicted path may not be adjusted based on lane markings if no lane markings are detected in the image or if the lane markings are unreliable.

[0365] While images 2700 and 2800 represent images captured from the front-facing camera of host vehicle 200, it should be understood that various other camera angles can be used to generate the vector field and the associated predicted path. For example, the process described above can be used to generate the vector field using images captured from the side, corner, or rear of the vehicle. Thus, a predicted path can be determined for lanes adjacent to the host vehicle, as well as predicted paths for vehicles traveling adjacent to host vehicle 200. In some embodiments, multiple cameras can be used to generate the vector field. For example, side or corner cameras can be used to extend the range of the primary front-facing camera. The resulting vector fields can be combined to generate a vector field for a larger area surrounding host vehicle 200.

[0366] In some embodiments, additional predictions can be determined for the target vehicle, rather than simply following the trajectory of vector field 2390. For example, the target vehicle's velocity can be used to adjust the vehicle's predicted path. Using multiple images captured at different times (e.g., consecutive images, etc.), the target vehicle's velocity can be determined. To accomplish this, changes in the vehicle's position can be tracked across two or more image frames, and based on the time elapsed between images, the velocity can be determined. In some embodiments, this can include lateral velocity, which can be the component of the vehicle's velocity that is perpendicular to the lane of travel and, therefore, perpendicular to vector field 2930. This lateral velocity can be used to determine a predicted path for the vehicle. For example, rather than following the trajectory of vector field 2930, a predicted path for the vehicle can be generated based on the measured lateral velocity, such that the vehicle also moves laterally through vector field 2930. This modified predicted path can be useful in determining the navigation maneuvers of the host vehicle. For example, the navigation system can determine that the predicted path of the host vehicle and the predicted path of the target vehicle intersect. Based on the vector field, the navigation system can determine the distance ahead of the vehicle at which the paths intersect. Thus, the host vehicle can determine whether a braking maneuver (eg, to maintain a safe following distance), an evasive maneuver, an acceleration maneuver, etc. should be performed.

[0367] Figure 31 is a flow chart illustrating an example process 3100 for navigating a host vehicle based on a vector field consistent with the disclosed embodiments. As described above, the process 3100 may be performed by at least one processing device, such as the processing unit 110. It should be understood that throughout this disclosure, the term "processor" is used as shorthand for "at least one processor." In other words, a processor may include one or more structures that perform logical operations, whether such structures are collocated, connected, or distributed. In some embodiments, a non-transitory computer-readable medium may contain instructions that, when executed by a processor, cause the processor to perform the process 3100. Furthermore, the process 3100 is not necessarily limited to Figure 31 The steps shown in FIG. 31 and any steps or processes of the various embodiments described throughout this disclosure may also be included in process 3100, including the steps described above with respect to FIG. Figures 27-30 The steps or processes described.

[0368] In step 3110, process 3100 may include receiving at least one image captured from the vehicle's environment from a camera of the vehicle. For example, image acquisition unit 120 may capture one or more images representing the environment of host vehicle 200. The captured images may correspond to, for example, the images described above with respect to FIG. Figure 27 and 28 The images described.

[0369] In step 3120, process 3100 may include analyzing at least one image to identify road topology features in the vehicle's environment, represented in the at least one image. As described above, a road topology feature may be any natural or man-made object or other feature within the host vehicle's environment. In some embodiments, a road topology feature may include a road surface, such as road surface 2730. Road topology may include other features, such as bends or curves in a road segment (e.g., curve 2850), edges of a road (e.g., curbs 2740, 2742, 2810, and / or 2820), obstacles associated with a road boundary (e.g., curb 2820), curbstones, walls, guardrails, etc. Road topology may include features such as merging lanes, exit ramps, crosswalks (e.g., crosswalk 2840), intersections, lane splits, driving lanes, or various other features of a road. In some embodiments, the elevation of one or more of the features described above, such as the elevation of the road surface or an obstacle, may be detected as a road topology feature. In some embodiments, analyzing at least one image to identify a road topology feature may include analyzing the at least one image using a trained system. For example, as described above, the trained system may include a neural network.

[0370] Step 3120 may further include analyzing at least one image to identify at least one point associated with the at least one image. For example, as described above, the at least one point may correspond to point 2910. The at least one point may be associated with at least one pixel of the at least one image, and in some embodiments, may be associated with multiple pixels of the at least one image. The at least one point may correspond to various locations within the at least one image. In some embodiments, the at least one point may be included along at least a portion of the vehicle's predicted driving path (the predicted driving path includes the at least one point). For example, the at least one point may be along the path of the host vehicle 200 or the target vehicle 2720. In some embodiments, the at least one point may not correspond to a location of the vehicle. For example, the at least one point may be selected as any point associated with the at least one image. In other embodiments, the at least one point may be determined based on a grid or other predetermined interval.

[0371] In step 3130, process 3100 may include determining an estimated path associated with the at least one point in the vehicle's environment based on the identified road topology features. The estimated path may correspond to a predicted travel path starting from a location corresponding to the at least one point in the image, such as predicted paths 3010, 3012, 3014, and 3020. In some embodiments, the estimated path may be a predicted path for the host vehicle. Thus, the location may be in front of the vehicle. In some embodiments, based on the vehicle's current or projected speed, the vehicle may be located at the location within a predetermined amount of time (e.g., 1 second, 2 seconds, 3 seconds, etc.). In some embodiments, the estimated path may correspond to a vector prediction of the vehicle's motion along the travel path in front of the vehicle. The vector prediction of the vehicle's motion along the travel path in front of the vehicle may be capable of being traversed by the vehicle within a predetermined amount of time (e.g., 1 second, 2 seconds, 3 seconds, etc.). Process 3100 may further include predicting a vehicle's direction of travel based on the estimated path. In some embodiments, the predicted path may be associated with a target vehicle, such as target vehicle 2720. Thus, process 3100 may include predicting a direction of travel of a detected target vehicle based on the estimated path.

[0372] In step 3140, process 3100 may include causing the vehicle to perform a navigation action based on the estimated path. For example, the navigation action may be maintaining the current speed, maintaining the current heading, performing a braking maneuver, performing a lateral movement (e.g., changing lanes, avoiding maneuvers, etc.), accelerating, or similar navigation actions. In some embodiments, process 3100 may also include transmitting the estimated path to a location outside the vehicle. For example, the location may include another vehicle, such as target vehicle 2720, another host vehicle (e.g., vehicles 1205-1225 described above), or other vehicles. In some embodiments, the location may be a server, such as server 1230 described above.

[0373] In some embodiments, process 3100 may further include analyzing the at least one image to identify a second point associated with the at least one image. Processing unit 110 may be configured to determine an estimated second path associated with the second point in the environment of the vehicle based on the identified road topology features. Process 3100 may include causing the vehicle to implement a second navigation action based on the estimated second path.

[0374] Figure 32is a flow chart illustrating an example process 3200 for navigating a host vehicle based on a vector field consistent with the disclosed embodiments. As described above, process 3200 may be performed by at least one processing device, such as processing unit 110. In some embodiments, a non-transitory computer-readable medium may contain instructions that, when executed by a processor, cause the processor to perform process 3200. Furthermore, process 3100 is not necessarily limited to Figure 32 The steps shown, and any steps or processes of the various embodiments described throughout this disclosure may also be included in process 3200 , including those steps or processes described above with respect to process 3100 .

[0375] In step 3210, process 3200 may include receiving at least one image captured from the vehicle's environment from a camera of the vehicle. For example, image acquisition unit 120 may capture one or more images representing the environment of host vehicle 200. The captured images may correspond to, for example, the images described above with respect to FIG. Figure 27 and 28 The images described.

[0376] In step 3220, process 3200 may include analyzing the at least one image to identify one or more road topology features in the environment of the vehicle that are represented in the at least one image. For example, as described above, road topology features may include a road surface, an elevation of a road surface, a bend or curve in a road segment, an edge of a road, an obstacle associated with a road boundary, a turn lane, a merging lane, an exit ramp, a crosswalk, an intersection, a lane split, a directional arrow, or any similar feature that can indicate a direction of travel of the vehicle.

[0377] In step 3230, process 3200 may include, for each of the plurality of segments of the at least one image, determining, based on the identified one or more road topology features, an estimated path at a location in the environment of the vehicle that corresponds to one of the plurality of segments. In some embodiments, each of the plurality of segments may correspond to a single pixel of the at least one image. In other embodiments, each of the plurality of segments may correspond to a plurality of pixels of the at least one image. For example, the segments may correspond to a plurality of contiguous pixels. In some embodiments, the estimated path may correspond to a predicted path of the vehicle. Thus, one or more estimated paths correspond to a predicted travel path ahead of the detected target vehicle, and one or more estimated paths correspond to a predicted travel path ahead of the vehicle.

[0378] At step 3240, process 3200 may include causing the vehicle to implement a navigation action based on at least one of the predicted paths associated with the plurality of segments of the at least one image. For example, the navigation action may include maintaining a current speed, maintaining a current heading, performing a braking maneuver, performing a lateral movement, accelerating, or a similar navigation action.

[0379] Semantic Lane Description

[0380] As described above, a vehicle, such as an autonomous or semi-autonomous vehicle, can use images to assist in navigation through the vehicle's environment. As described above, a vehicle navigation system can analyze images to determine context information that can assist in determining navigation actions. In some embodiments, the context information can include information about traffic lanes included in the vehicle's environment. The vehicle navigation system can be configured to characterize the current lane in which the vehicle is traveling and other surrounding lanes. For example, the system can determine the direction of travel associated with the lane, whether the lane is associated with oncoming traffic, usage restrictions associated with the lane, or other information that can be relevant to navigation action decisions. Such information can also be provided to a central server for use in generating and / or updating sparse maps or other road maps, as described in detail above.

[0381] Figure 33 is an illustration of an example image 3300 captured by a host vehicle for lane analysis consistent with the disclosed embodiments. For example, the image 3300 may be captured from the environment of the host vehicle 200 using the image acquisition unit 120 as described in detail above. The image 3300 may include representations of one or more lanes, such as lanes 3310, 3312, and 3314. As used herein, a lane may refer to a portion of a road that is designated for use by a single file of vehicles. In some cases, lanes may be separated by lane markings, such as Figure 33 Lane markings 3326 and 3322 are shown. In example image 3300, lane 3310 may represent the current lane of travel of the host vehicle. In other words, host vehicle 200 may capture image 3300 while traveling along lane 3310. Lanes 3312 and 3314 may represent additional lanes in the environment of vehicle 200, which may include lanes of travel adjacent to the host vehicle's lane of travel. Image 3300 may include other features or attributes that may provide context for characterizing lanes 3310, 3312, and / or 3314. For example, image 3300 may include a directional arrow 3320 associated with lane 3312, which may indicate that lane 3312 is a left-turn lane, as shown.

[0382] The vehicle navigation system may analyze image 3300 to characterize one or more lanes within the image. In some embodiments, the vehicle navigation system may analyze image 3300 to identify the lane of travel of the host vehicle. Figure 33 In the example shown, this may correspond to lane 3310. Various techniques may be used to identify lane 3310. In some embodiments, lane 3310 may be identified based on lane markings, such as lane markers 3324 and 3322. These lane markings may be identified based on various image analysis algorithms, such as object detection, edge detection, or other feature detection algorithms. Additional details regarding lane and lane marking detection are provided above with respect to Figures 24A-24D Detailed description is given below. In some embodiments, lanes can be detected based on other features, such as curbs 3332 and 3334. As described above, the vehicle navigation system can also be configured to detect one or more additional lanes, such as lanes 3312 and 3314. Additional lanes can be identified using similar techniques as for the host vehicle lanes.

[0383] The vehicle navigation system may also analyze image 3330 to identify attributes associated with additional lanes of travel. The attributes may include any quality or feature associated with a lane of travel that can be detected from the image. For example, the system may identify a directional arrow 3320 associated with lane 3312. Various techniques may be used to detect directional arrow 3320 (and / or other attributes of image 3300). In some embodiments, similar to lane markings 3322 and 3324 as described above, an object recognition algorithm may be used to detect the attributes. Figure 34 Additional examples of attributes that may be recognized by a vehicle navigation system are provided.

[0384] The vehicle navigation system may also be configured to determine information indicating a characterization of an additional lane of travel based on an attribute. A lane characterization may include any description or classification of a traffic lane. In some embodiments, a lane may be characterized according to a set of predetermined lane property categories. Example attributes may include lane presence, lane type, lane orientation, and / or lane direction. Lane presence may be an attribute or value indicating whether a particular lane exists. Lane presence may be represented in a variety of formats, including a numerical value (e.g., "1" indicates lane presence, "0" indicates lane absence), a text value (e.g., "present" / "absent," "yes" / "no," etc.), a numerical value, an alphanumeric value, a symbol or icon, or various other formats. As described above, the presence of a particular lane may be determined based on image analysis, wherein the presence of the particular lane may be identified based on a spatial relationship relative to the host vehicle lane (e.g., two lanes to the left, one lane to the left, one lane to the right, two lanes to the right, etc.).

[0385] The lane orientation attribute can indicate whether the traffic orientation associated with the lane is preceding (i.e., in the same direction as the host vehicle) or oncoming (i.e., in the opposite direction of the host vehicle). Similar to the lane presence value, the lane orientation can be expressed as a numerical value (e.g., 0 = preceding, 1 = oncoming, etc.), a text value (e.g., "preceding" / "oncoming", etc.), a numerical value, an alphanumeric value, a symbol or icon (e.g., an arrow, etc.), or various other formats. In some embodiments, a lane can be bidirectional, such as a center turn lane, a flexible use lane, a merging lane, etc.

[0386] The lane direction attribute may indicate a target direction associated with the lane. For example, a lane that continues straight ahead may be designated as a "straight" lane, while a turning lane may be designated as a "left turn" or "right turn" lane. Various other lane direction classifications may be used, for example, indicating that the lane is a merging lane (e.g., "merge left" or "merge right"), an exit lane, etc. In some embodiments, lane direction may be represented by a numerical value or code associated with various lane directions (e.g., 1 = right turn, 2 = left turn, 3 = right turn, etc.). In some embodiments, a lane may be associated with more than one direction. For example, a lane may allow a vehicle to continue straight ahead or to turn right (e.g., designated by a straight / right turn arrow, etc.). Thus, a lane may have a separate "straight / right turn" designation, or may have multiple designated lane directions (e.g., "straight" and "right turn").

[0387] The lane type attribute may include restrictions associated with the lane, which may specify the types or classes of vehicles permitted to travel in the lane. For example, the lane type may indicate whether the lane is a high occupancy vehicle (HOV) lane or a carpool lane, a truck-only lane, a lane that does not allow trucks, a bus-only lane, a lane with vehicle weight restrictions, a bicycle lane, an emergency vehicle-only lane, etc. The lane type may include additional classifications, such as whether the lane is associated with the shoulder (e.g., a hard shoulder), whether the lane is open or closed for travel, whether the lane is a parking lane (e.g., along a row of parking meters, etc.). In some embodiments, the lane type may be represented by a text value or string (e.g., "HOV," "Bus Only," etc.). In other embodiments, the lane type may be represented by a numerical value or code associated with each lane type (e.g., 0 = unknown, 1 = shoulder, 3 = bicycle lane, 4 = carpool, etc.).

[0388] In some embodiments, lane characterization can include a spatial relationship relative to the host vehicle's lane. For example, a lane can be characterized as a certain number of lanes (e.g., one, two, three, etc.) away from the host lane in a particular direction (e.g., left or right). Various other characterizations can also be identified, including lane surface type (e.g., dirt, gravel, asphalt, concrete, etc.), lane condition (e.g., wet, dry, damaged, etc.), lane color, lane elevation, or various other characteristics. In some embodiments, one or more of these examples can be combined with or included in another classification attribute (e.g., lane type), or can be used to identify the other lane characterizations described above.

[0389] In some embodiments, determining information indicative of lane characterization may be based at least in part on historical information. Historical information may include any information associated with a lane or road segment that was recorded prior to the image being captured. In some embodiments, the historical information may have been captured by the host vehicle (e.g., at a previous location along the road segment during the same trip, during a previous trip along the same road segment, etc.). Therefore, the historical information may be stored in a memory of the host vehicle, such as memory 140. In ot...

Claims

1. A navigation system for a vehicle, the system comprising: At least one processor programmed to: receiving at least one image captured from an environment of the vehicle from a camera of the vehicle; analyzing the at least one image to identify road topology features in the environment of the vehicle represented in the at least one image and a plurality of points associated with the at least one image; determining an estimated path associated with at least one of the plurality of points in an environment of the vehicle based on the identified road topology features, wherein determining the estimated path comprises analyzing the at least one image to determine, for each of the plurality of points, a motion vector indicating a predicted direction of travel when located at the respective point; and The vehicle is caused to perform a navigation action based on the estimated path. The navigation system of claim 1 , wherein the road topology feature comprises a road surface. The navigation system according to claim 1 , wherein the road topology feature comprises an elevation of a road surface. 4 . The navigation system of claim 1 , wherein the road topology feature comprises at least one of a bend or curve in a road segment, an edge of a road, or an obstacle associated with a road boundary. 5 . The navigation system of claim 1 , wherein the road topology feature comprises at least one of a turn lane, a merging lane, an exit ramp, a crosswalk, an intersection, or a lane split. 6 . The navigation system of claim 1 , wherein analyzing the at least one image to identify the road topology features comprises analyzing the at least one image using a trained system.

7. The navigation system of claim 6, wherein the trained system comprises a neural network.

8. The navigation system of claim 1, wherein the at least one point is associated with at least one pixel of the at least one image.

9. The navigation system of claim 1, wherein the at least one point is associated with a plurality of pixels of the at least one image. 10 . The navigation system of claim 1 , wherein the estimated path corresponds to a predicted travel path starting from a location corresponding to the at least one point in the image. The navigation system of claim 10 , wherein the location is in front of the vehicle. 12 . The navigation system of claim 10 , wherein the vehicle can be located at the location within a predetermined amount of time based on a current speed or a projected speed of the vehicle.

13. The navigation system of claim 12, wherein the predetermined amount of time is at least one second.

14. The navigation system of claim 1, wherein the estimated path corresponds to a vector prediction of the vehicle's motion along a travel path ahead of the vehicle.

15. The navigation system of claim 14, wherein the vector prediction of the vehicle's motion along the travel path ahead of the vehicle can be traversed by the vehicle within a predetermined amount of time.

16. The navigation system of claim 15, wherein the predetermined amount of time is at least one second.

17. The navigation system of claim 1, wherein the at least one processor is further programmed to transmit the estimated path to a location external to the vehicle.

18. The navigation system of claim 17, wherein the location comprises another vehicle.

19. The navigation system of claim 17, wherein the location comprises a server.

20. The navigation system of claim 1, wherein the at least one processor is further programmed to predict a direction of travel for the vehicle based on the estimated path.

21. The navigation system of claim 1, wherein the at least one processor is further programmed to predict a direction of travel of a detected target vehicle based on the estimated path.

22. The navigation system of claim 1, wherein the at least one point is selected as an arbitrary point associated with the at least one image.

23. The navigation system of claim 1, wherein the at least one point does not correspond to a location of a vehicle.

24. The navigation system of claim 1, wherein the at least one point is included along at least a portion of a predicted travel path of the vehicle that includes the at least one point.

25. The navigation system of claim 1, wherein the at least one processor is further programmed to analyze the at least one image to identify a second point associated with the at least one image.

26. The navigation system of claim 25, wherein the at least one processor is further programmed to determine an estimated second path associated with the second point in the environment of the vehicle based on the identified road topology characteristics.

27. The navigation system of claim 26, wherein the at least one processor is further programmed to cause the vehicle to implement a second navigation action based on the estimated second path.

Images