System and method for navigating host vehicle

Abstract

In one implementation, a method is provided that includes receiving at least one image captured by a camera of a host vehicle from an environment of the host vehicle; analyzing the at least one image to identify a region of interest; selecting a portion of the at least one image based on the region of interest; receiving map information associated with the environment of the host vehicle; providing the portion of the at least one image and the map information to a trained system; and receiving an output provided by the trained system. The output includes an identifier of an object in the environment of the host vehicle and positioning information of the object relative to the map information. The method further includes causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning information of the object.

Description

BACKGROUND OF THE INVENTION

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority of U.S. Provisional Application No. 63 / 618,503, filed on Jan. 8, 2024, and No. 63 / 678,210, filed on Aug. 1, 2024. The foregoing applications are hereby incorporated by reference in their entirety.

[0003] Background Information

[0004] As technology continues to advance, the goal of fully autonomous vehicles that can navigate on roads is approaching. Autonomous vehicles may need to consider multiple factors and make appropriate decisions based on those factors to safely and accurately reach the intended destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured from cameras), and may also use information obtained from other sources (e.g., from GPS devices, speed sensors, accelerometers, suspension sensors, etc.). At the same time, to navigate to a destination, autonomous vehicles may also need to identify their position within a particular road (e.g., a particular lane in a multi-lane road), navigate side-by-side with other vehicles, avoid obstacles and pedestrians, obey traffic signals and signs, and travel from one road to another at appropriate intersections or junctions. Utilizing and interpreting the large amount of information collected by an autonomous vehicle as the vehicle travels to its destination presents numerous design challenges. The sheer volume of data that an autonomous vehicle may need to analyze, access, and / or store (e.g., captured image data, map data, GPS data, sensor data, etc.) presents challenges that can actually limit or even adversely affect autonomous navigation. Additionally, if an autonomous vehicle relies on traditional mapping techniques for navigation, the sheer amount of data required to store and update maps presents a daunting challenge. BRIEF DESCRIPTION OF THE DRAWINGS

[0005] The drawings incorporated in and constituting a part of this disclosure illustrate various disclosed embodiments. In the drawings:

[0006] Figure 1 is a schematic representation of an exemplary system consistent with the disclosed embodiments.

[0007] Figure 2A is a schematic side view representation of an exemplary vehicle including a system consistent with the disclosed embodiments.

[0008] Figure 2B is consistent with the disclosed embodiments Figure 2A is a schematic top view representation of the vehicle and system shown in

[0009] Figure 2CSchematic top view representation of another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0010] Figure 2D Schematic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0011] Figure 2E Schematic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0012] Figure 2F Schematic representation of an exemplary vehicle control system consistent with the disclosed embodiments.

[0013] Figure 3A Schematic representation of the interior of a vehicle consistent with the disclosed embodiments, including a rearview mirror and a user interface for a vehicle imaging system.

[0014] Figure 3B 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.

[0015] Figure 3C From different perspectives, consistent with the disclosed embodiments Figure 3B Illustration of the camera mount shown in

[0016] Figure 3D 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.

[0017] Figure 4 Exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0018] Figure 5A Flowchart showing an exemplary process for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments.

[0019] Figure 5B Flowchart showing an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments.

[0020] Figure 5C Flowchart showing an exemplary process for detecting road markings and / or lane geometry feature information in a set of images consistent with the disclosed embodiments.

[0021] Figure 5DA flowchart showing an illustrative process for detecting traffic lights in a set of images consistent with the disclosed embodiments.

[0022] Figure 5E A flowchart showing an illustrative process for causing one or more navigation responses based on a vehicle path consistent with the disclosed embodiments.

[0023] Fig. 5F A flowchart showing an illustrative process for determining whether a vehicle ahead is changing lanes consistent with the disclosed embodiments.

[0024] Figure 6 A flowchart showing an illustrative process for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments.

[0025] Figure 7 A flowchart showing an illustrative process for causing one or more navigation responses based on the analysis of three sets of images consistent with the disclosed embodiments.

[0026] Figure 8 Shows a sparse map for providing autonomous vehicle navigation consistent with the disclosed embodiments.

[0027] Fig.9A Shows a polynomial representation of a portion of a road segment consistent with the disclosed embodiments.

[0028] Fig. 9B Shows a curve representing a target trajectory of a vehicle for a road segment in three-dimensional space, the curve being included in a sparse map consistent with the disclosed embodiments.

[0029] Fig.10 Shows exemplary landmarks that may be included in a sparse map consistent with the disclosed embodiments.

[0030] Fig.11A Shows a polynomial representation of a trajectory consistent with the disclosed embodiments.

[0031] Fig. 11B and Fig. 11C Shows a target trajectory along a multi-lane road consistent with the disclosed embodiments.

[0032] Fig.11D Shows an exemplary road characteristic curve consistent with the disclosed embodiments.

[0033] Fig.12 A schematic illustration of a system for autonomous vehicle navigation using crowdsourced data received from multiple vehicles consistent with the disclosed embodiments.

[0034] Fig.13An exemplary autonomous vehicle road navigation model represented by a plurality of three-dimensional splines consistent with the disclosed embodiments is presented.

[0035] Fig.14 A map skeleton generated from combined positioning information from multiple drives consistent with the disclosed embodiments is shown.

[0036] Fig.15 An example of a longitudinal alignment of two drives with exemplary signs as landmarks is shown consistent with the disclosed embodiments.

[0037] Fig.16 An example of longitudinal alignment of multiple drives with exemplary signs as landmarks is shown consistent with the disclosed embodiments.

[0038] Fig.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.

[0039] Fig.18 is a schematic illustration of a system for crowdsourcing sparse maps consistent with the disclosed embodiments.

[0040] Fig.19 A flow chart illustrating an illustrative process for generating a sparse map for autonomous vehicle navigation along a road segment consistent with the disclosed embodiments.

[0041] Fig. 20 A block diagram of a server consistent with the disclosed embodiments is shown.

[0042] Fig.21 A block diagram of a memory consistent with the disclosed embodiments is shown.

[0043] Fig. 22 A process for clustering vehicle trajectories associated with vehicles consistent with the disclosed embodiments is presented.

[0044] Fig.23 A navigation system for a vehicle consistent with the disclosed embodiments is presented that can be used for autonomous navigation.

[0045] Fig.24A , Fig. 24B , Fig.24C and Fig.24D Exemplary lane markings that may be detected consistent with the disclosed embodiments are shown.

[0046] Fig.24E Exemplary mapped lane markings consistent with the disclosed embodiments are shown.

[0047] Fig.24FIllustrates an exemplary anomaly associated with detecting lane markings consistent with the disclosed embodiments.

[0048] Fig.25A Illustrates an exemplary image of a vehicle's surrounding environment for navigation based on mapped lane markings consistent with the disclosed embodiments.

[0049] Fig.25B Shows the lateral positioning correction of a vehicle based on mapped lane markings in a road navigation model consistent with the disclosed embodiments.

[0050] Fig.25C and Fig.25D Provides a conceptual representation of a positioning technique for positioning a host vehicle along a target trajectory using mapped features included in a sparse map.

[0051] Fig.26A Is a flowchart illustrating an exemplary process for mapping lane markings for use in autonomous vehicle navigation consistent with the disclosed embodiments.

[0052] Fig.26B Is a flowchart illustrating an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings consistent with the disclosed embodiments.

[0053] Fig. 27 Is a flowchart illustrating an exemplary process for navigating a host vehicle consistent with the disclosed embodiments.

[0054] Fig.28 Illustrates an exemplary image of a vehicle's surrounding environment captured by a camera of a host vehicle consistent with the disclosed embodiments.

[0055] Fig.29 Is an exemplary functional block diagram of a trained system consistent with the disclosed embodiments. SUMMARY OF THE INVENTION

[0056] Embodiments consistent with the present disclosure provide systems and methods for navigating a host vehicle.

[0057] In one embodiment, a system for navigating a host vehicle is disclosed. The system can include at least one processor that includes circuitry and a memory, where the memory includes instructions that, when executed by the circuitry, cause the at least one processor to: receive at least one image captured by a camera of the host vehicle from the environment of the host vehicle, analyze the at least one image to identify a region of interest in the environment of the host vehicle, select a portion of the at least one image based on the region of interest, and receive map information associated with the environment of the host vehicle. The map information can include one or more identifiers of the route of the host vehicle. The instructions can further cause the at least one processor to provide the portion of the at least one image and the map information to a trained system. The trained system can be configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information. The instructions can further cause the at least one processor to receive an output provided by the trained system. The output can include an identifier of an object in the environment of the host vehicle and location information of the object relative to the map information. Additionally, the instructions can further cause the at least one processor to cause the host vehicle to initiate at least one navigation action based on the identifier of the object and the location information of the object.

[0058] In one embodiment, a method for navigating a host vehicle includes: receiving at least one image captured by a camera of the host vehicle from the environment of the host vehicle; analyzing the at least one image to identify a region of interest in the environment of the host vehicle; selecting a portion of the at least one image based on the region of interest; receiving map information associated with the environment of the host vehicle, where the map information includes one or more identifiers of the route of the host vehicle; providing the portion of the at least one image and the map information to a trained system, where the trained system is configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information; receiving an output provided by the trained system, where the output includes an identifier of an object in the environment of the host vehicle and location information of the object relative to the map information; and causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the location information of the object.

[0059] In one embodiment, a non-transitory computer-readable medium stores program instructions executable by at least one processor to perform a method. The method includes receiving at least one image captured by a camera of a host vehicle from an environment of the host vehicle; analyzing the at least one image to identify a region of interest in the environment of the host vehicle; selecting a portion of the at least one image based on the region of interest; receiving map information associated with the environment of the host vehicle, wherein the map information includes one or more identifiers of a route of the host vehicle; providing the portion of the at least one image and the map information to a trained system, wherein the trained system is configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information; receiving an output provided by the trained system, wherein the output includes an identifier of an object in the environment of the host vehicle and positioning information of the object relative to the map information; and causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning information of the object.

[0060] In one embodiment, a non-transitory computer-readable medium may store program instructions executable by at least one processor to perform a method. The method may include: receiving at least one image captured by a camera of a host vehicle from an environment of the host vehicle, analyzing the at least one image to identify a region of interest in the environment of the host vehicle, selecting a portion of the at least one image based on the region of interest, and receiving map information associated with the environment of the host vehicle. The map information may include one or more identifiers of a route of the host vehicle. The method may further include providing the portion of the at least one image and the map information to a trained system. The trained system may be configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information. The method may further include receiving an output provided by the trained system. The output may include an identifier of an object in the environment of the host vehicle and positioning information of the object relative to the map information. The method may further include causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning of the object.

[0061] In one embodiment, a non-transitory computer-readable medium may store program instructions executable by at least one processor to perform a method. The method may include: receiving at least one image captured by a camera of a host vehicle from the environment of the host vehicle, and receiving map information associated with the environment of the host vehicle. The map information may include one or more identifiers of a route of the host vehicle. The method may further include providing the at least one image and the map information to a trained system. The trained system may be configured to generate one or more detections using a language model architecture based on an analysis of the at least one image and the map information. The method may further include receiving an output provided by the trained system. The received output may include an identifier of an object in the environment of the host vehicle and positioning information of the object relative to the map information. The method may further include causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning of the object.

[0062] The foregoing general description and the following detailed description are merely illustrative and explanatory and do not limit the claims. Detailed Description

[0063] The following detailed description refers to the accompanying drawings. Whenever possible, the same reference numbers are used in the drawings and the following description to refer to the same or like parts. Although several illustrative embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, components shown in the drawings may be replaced, added, or modified, and the illustrative methods described herein may be modified by replacing, reordering, removing, or adding steps. Accordingly, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0064] Autonomous Vehicle (AV) Overview

[0065] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle capable of achieving at least one navigation change without driver input. "Navigation change" refers to a change in one or more of the steering, braking, or acceleration of a vehicle. To be autonomous, a vehicle does not need to be fully automatic (e.g., full operation without a driver or without driver input). Instead, an autonomous vehicle includes a vehicle that may be operated under driver control during some time periods and without driver control during other time periods. An autonomous vehicle may also include a vehicle that controls only some aspects of vehicle navigation (such as steering (e.g., to maintain a vehicle route between vehicle lane constraints)), but leaves other aspects to the driver (such as braking). In some cases, an autonomous vehicle may handle some or all aspects of vehicle braking, speed control, and / or steering.

[0066] Since human drivers typically rely on visual cues and observations to control a vehicle, traffic infrastructure has accordingly been established, where lane markings, traffic signs, and traffic lights are all designed to provide visual information to the driver. Given these design features of the traffic infrastructure, an autonomous vehicle can include a camera and a processing unit that analyzes visual information captured from the vehicle's environment. The visual information can include, for example, components of the traffic infrastructure observable by a driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, an autonomous vehicle can also use stored information, such as information providing a model of the vehicle's environment when providing navigation. For example, the vehicle can use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.) and / or other map data to provide information related to its environment when the vehicle is in motion, and the vehicle (and other vehicles) can use this information to position itself on the model.

[0067] In some embodiments of the present disclosure, an autonomous vehicle can use information obtained during navigation (e.g., from a camera, GPS device, accelerometer, speed sensor, suspension sensor, etc.). In other embodiments, an autonomous vehicle can use information obtained from past navigation by the vehicle (or by other vehicles) during navigation. In still other embodiments, an autonomous vehicle can use a combination of information obtained during navigation and information obtained from past navigation. The following sections provide an overview of the system consistent with the disclosed embodiments, followed by an overview of the forward imaging system and method consistent with the system. The following sections disclose systems and methods for constructing, using, and updating a sparse map for autonomous vehicle navigation.

[0068] System Overview

[0069] Figure 1FIG. 0 is a block diagram representation of a system 100 consistent with an exemplary disclosed embodiment. Depending on the requirements of a particular implementation, system 100 may include various components. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. The processing unit 110 may include one or more processing devices. In some embodiments, the processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, depending on the requirements of a particular application, the image acquisition unit 120 may include any number of image acquisition devices and components. In some embodiments, the image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 may also include a data interface 128 that communicatively couples the processing unit 110 to the image acquisition unit 120. For example, the data interface 128 may include any one or more wired and / or wireless links for transmitting image data acquired by the image acquisition unit 120 to the processing unit 110.

[0070] The wireless transceiver 172 may include one or more devices configured to exchange transmissions with one or more networks (e.g., cellular networks, the Internet, etc.) over an air interface using radio frequency, infrared frequency, magnetic field, or electric field. The wireless transceiver 172 may use any known standard to transmit and / or receive data (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 (one-way or two-way) communications between the host vehicle and one or more target vehicles in the environment of the host vehicle (e.g., to facilitate coordination of navigation of the host vehicle in view of or in conjunction with target vehicles in the environment of the host vehicle), or even broadcast transmissions to unspecified recipients in the vicinity of the transmitting vehicle.

[0071] Both the application processor 180 and the image processor 190 may include various types of processing devices. For example, either or both of the application processor 180 and the image processor 190 may include a microprocessor, a pre-processor (such as an image pre-processor), a graphics processing unit (GPU), a central processing unit (CPU), support circuitry, a digital signal processor, an integrated circuit, a memory, or any other type of device suitable for running application programs 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 purchased from manufacturers such as etc., or GPUs purchased from manufacturers such as etc., and may include various architectures (e.g., x86 processors, etc.).

[0072] In some embodiments, the application processor 180 and / or the image processor 190 may include any one of the processor chips of the EyeQ series purchased from . Each of these processor designs includes multiple processing units with local memory and instruction sets. Such processors may include a video input for receiving image data from multiple image sensors and may also include video output capabilities. In one example, uses 90nm micron technology operating at 332Mhz. The architecture consists of two floating-point hyper-threaded 32-bit RISC CPUs ( cores), five vision computing engines (VCEs), three vector microcode processors Denali 64-bit mobile DDR controller, 128-bit internal Sonics interconnect, dual 16-bit video input and 18-bit video output controllers, 16-channel DMA, and several peripheral devices. The MIPS34K CPU manages five VCEs, three VMPs TM and DMA, a second MIPS34K CPU, and multi-channel DMA, and other peripheral devices. The five VCEs, three and the MIPS34K CPU can perform the intensive vision calculations required for multifunctional bundled applications. In another example, (which is a third-generation processor and has six times the performance of ) can be used in the disclosed embodiments. In other examples, and / or can be used in the disclosed embodiments. Of course, any newer or future EyeQ processing device can also be used with the disclosed embodiments.

[0073] Any processing device disclosed herein may be configured to perform certain functions. Configuring a processing device, such as any of the described EyeQ processors or other controllers or microprocessors, to perform certain functions may include programming computer-executable instructions and making those instructions available for execution by the processing device during operation of the processing device. In some embodiments, configuring the processing device may include directly programming the processing device using architectural instructions. For example, a processing device such as a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), etc. may be configured using, for example, one or more hardware description languages (HDLs).

[0074] In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible by the processing device during operation. For example, the processing device may access the memory during operation to obtain and execute the stored instructions. In either case, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a hardware-based system that controls multiple hardware-based components of the host vehicle.

[0075] Although Figure 1 FIG. depicts two separate processing devices included in processing unit 110, more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to 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. Further, in some embodiments, system 100 may include one or more processing units 110 without including other components, such as image acquisition unit 120.

[0076] Processing unit 110 may include various types of devices. For example, 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 circuitry, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image preprocessor may include a video processor for capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuitry may be 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 case, the memory may be separate from processing unit 110. In another case, the memory may be integrated into processing unit 110.

[0077] Each memory 140, 150 may include software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. For example, these memory units may include various databases and image processing software, as well as trained systems such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage devices, tape storage devices, removable storage devices, and / or any other type of storage device. In some embodiments, memory units 140, 150 may be separate from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

[0078] Position sensor 130 may include any type of device adapted to determine the location associated with at least one component of system 100. In some embodiments, position sensor 130 may include a GPS receiver. Such a receiver may determine the user location and rate by processing signals broadcast by Global Positioning System satellites. The location information from position sensor 130 may be used by application processor 180 and / or image processor 190.

[0079] In some embodiments, system 100 may include components such as speed sensors (e.g., tachometers, speedometers) for measuring the speed of vehicle 200 and / or accelerometers (single-axis or multi-axis) for measuring the acceleration of vehicle 200.

[0080] User interface 170 may include any device adapted to provide information to or receive input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including for example touchscreens, microphones, keyboards, pointer devices, rollers, cameras, knobs, buttons, etc. Using such input devices, a user may be able to provide information input or commands to system 100 by typing instructions or information, providing voice commands, (using buttons, pointers or eye tracking capabilities) selecting menu options on a screen, or via any other suitable technology for transmitting information to system 100.

[0081] The user interface 170 may be equipped with one or more processing devices configured to provide information to and receive information from a user and 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 touchscreen, responding to keyboard inputs or menu selections, and the like. 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 the user.

[0082] The map database 160 may include any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 may include data related to the locations of various items in a reference coordinate system, the various items including roads, water features, geographic features, businesses, 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 related to those items, the descriptors including, for example, names associated with any of the stored features. In some embodiments, the map database 160 may be physically located together with other components of the system 100. Alternatively or additionally, the map database 160 or a portion thereof may be located remotely relative to other components of the system 100 (e.g., the processing unit 110). In such embodiments, information from the map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, the map database 160 may store a sparse data model, including polynomial representations of certain road features (e.g., lane markings) or target trajectories for the host vehicle. Systems and methods for generating such maps will be discussed below with reference to Figures 8 to 19 systems and methods for generating such maps.

[0083] The image capture devices 122, 124, and 126 may each include any type of device adapted to capture at least one image from the environment. Additionally, any number of image capture devices may be used to acquire images for input to an image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four or more image capture devices. The image capture devices 122, 124, and 126 will be further described below with reference to FIG. 2B to FIG. 2E systems and methods for generating such maps.

[0084] 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 on a vehicle 200, as Figure 2A shown. For example, the vehicle 200 may be equipped with the processing unit 110 and any other components of the system 100, as described above with respect to Figure 1As described. Although in some embodiments, vehicle 200 may be equipped with only a single image capture device (e.g., a camera), in other embodiments, such as in the embodiments discussed in conjunction with FIG. 2B to FIG. 2E multiple image capture devices may be used. For example, as Figure 2A shown, either of image capture devices 122 and 124 of vehicle 200 may be part of an ADAS (Advanced Driver Assistance System) imaging set.

[0085] The image capture device included on vehicle 200 as part of image acquisition unit 120 may be positioned at any suitable location. In some embodiments, as FIG. 2A to FIG. 2E and FIG. 3A to FIG. 3C shown, image capture device 122 may be located in the vicinity of the rearview mirror. This location may provide a line of sight similar to that of the driver of vehicle 200, which may assist in determining what is visible and not visible to the driver. Image capture device 122 may be positioned at any location near the rearview mirror, but placing image capture device 122 on the driver side of the mirror may further assist in obtaining an image representative of the driver's field of view and / or line of sight.

[0086] Other locations for the image capture device of image acquisition unit 120 may also be used. For example, image capture device 124 may be located on or in the bumper of vehicle 200. Such a location may be particularly suitable for an image capture device with a wide field of view. The line of sight of the image capture device located on the bumper may be different from that of the driver, and thus the bumper image capture device and the driver may not always see the same objects. The image capture devices (e.g., image capture devices 122, 124, and 126) may also be located in other locations. For example, the image capture device may be located on or in one or both of the side 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 of the windows of vehicle 200, positioned behind or in front of it, and mounted in or near the lighting pattern in the front and / or rear of vehicle 200, etc.

[0087] 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, or integrated with or separated from the engine control unit (ECU) of the vehicle. Vehicle 200 may also be equipped with a position sensor 130 such as a GPS receiver, and may also include a map database 160 as well as memory units 140 and 150.

[0088] As discussed previously, the wireless transceiver 172 can receive data via one or more networks (e.g., cellular networks, 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 the one or more servers. Via the wireless transceiver 172, the system 100 can receive, for example, periodic or on-demand updates to data stored in the map database 160, the memory 140, and / or the memory 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, vehicle control systems, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0089] The system 100 can upload data to a server (e.g., to the cloud) based on privacy level settings. For example, the system 100 can implement privacy level settings to regulate or limit the types of data (including metadata) sent to a 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, set by factory default, or initialized by data received by the wireless transceiver 172.

[0090] In some embodiments, the system 100 can upload data according to a "high" privacy level, and under the set settings, the system 100 can transmit data (e.g., location information related to a 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 instead can transmit data such as captured images and / or restricted location information related to a route.

[0091] Other privacy levels are conceivable. For example, the system 100 can transmit data to a server according to a "medium" privacy level and include additional information not included under the "high" privacy level, such as the make and / or model of the vehicle and / or the type of vehicle (e.g., passenger vehicle, sport utility vehicle, truck, etc.). In some embodiments, the system 100 can upload data according to a "low" privacy level. Under the "low" privacy level setting, the system 100 can upload data and include information sufficient to uniquely identify a particular vehicle, owner / driver, and / or part or all of the route traveled by the vehicle. Such "low" privacy level data can include, for example, one or more of the VIN, driver / owner name, starting point of the vehicle before departure, expected destination of the vehicle, make and / or model of the vehicle, type of vehicle, etc.

[0092] Figure 2ASchematic side view representation of an exemplary vehicle imaging system consistent with the disclosed embodiments. Figure 2B For Figure 2A Schematic top view illustration of the embodiment shown. As Figure 2B Shown, the disclosed embodiments may include a vehicle 200 that includes in its body a system 100 having a first image capture device 122 positioned in a vicinity of the rearview mirror and / or near a driver of the vehicle 200, a second image capture device 124 positioned on or in a bumper region of the vehicle 200 (e.g., one of the bumper regions 210), and a processing unit 110.

[0093] As Figure 2C Shown, both image capture devices 122 and 124 may be positioned in a vicinity of the rearview mirror and / or near a driver of the vehicle 200. Additionally, although Figure 2B and Figure 2C two image capture devices 122 and 124 are shown, it should be understood that other embodiments may include more than two image capture devices. For example, in Figure 2D and Figure 2E the embodiment shown, first, second, and third image capture devices 122, 124, and 126 are included in the system 100 of the vehicle 200.

[0094] As Figure 2D Shown, the image capture device 122 may be positioned in a vicinity of the rearview mirror and / or near a driver of the vehicle 200, and the image capture devices 124 and 126 may be positioned on or in a bumper region of the vehicle 200 (e.g., one of the bumper regions 210). And as Figure 2E Shown, the image capture devices 122, 124, and 126 may be positioned in a vicinity of the rearview mirror and / or near a driver's seat of the vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices may be positioned in any suitable location within and / or on the vehicle 200.

[0095] It should be understood that the disclosed embodiments are not limited to vehicles and may be applied to other scenarios. It should also be understood that the disclosed embodiments are not limited to a particular type of vehicle 200 and may be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0096] The first image capture device 122 can include any suitable type of image capture device. The image capture device 122 can include an optical axis. In one case, the image capture device 122 can include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capture device 122 can provide a resolution of 1280x960 pixels and can include a rolling shutter. The image capture device 122 can include various optical elements. In some embodiments, one or more lenses can be included, such as to provide a desired focal length and field of view for the image capture device. In some embodiments, the image capture device 122 can be associated with a 6mm lens or a 12mm lens. In some embodiments, the image capture device 122 can be configured to capture an image with a desired field of view (FOV) 202, as Figure 2D shown. For example, the image capture device 122 can be configured to have a regular 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 greater. 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 an FOV of up to 180 degrees. In some embodiments, the image capture device 122 can be a 7.2M pixel image capture device with an aspect ratio of about 2:1 (e.g., HxV = 3800x1900 pixels) and a horizontal FOV of about 100 degrees. Such an image capture device can be used to replace a three-image capture device configuration. Due to significant lens distortion, in implementations 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 as well as a horizontal FOV of 100 degrees.

[0097] The first image capture device 122 can acquire a plurality of first images with respect to 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 include a plurality of pixels.

[0098] The first image capture device 122 can have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate can refer to the rate at which the image sensor can acquire image data associated with each pixel included in a particular scan line.

[0099] For example, image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, including 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 scanning of the row is performed on a row-by-row basis until the entire image frame has been captured. In some embodiments, the rows may be captured sequentially from the top to the bottom of the frame.

[0100] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) may constitute a high-resolution imager and may have a resolution greater than 5M pixels, 7M pixels, 10M pixels, or greater.

[0101] The use of a rolling shutter may cause pixels in different rows to be exposed and captured at different times, which may result in skewing 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 synchronous shutter, all pixels may be exposed for the same amount of time and during a common exposure period. Thus, 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 the data is captured at different times. Thus, moving objects may appear distorted in an image capture device having a rolling shutter. This phenomenon will be described in more detail below.

[0102] The second image capture device 124 and the third image capture device 126 may be any type of image capture device. Similar to the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor having a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image capture devices 124 and 126 may provide a FOV (such as FOV 204 and 206) that is the same as or narrower than the FOV (such as FOV 202) associated with the image capture device 122. For example, the image capture devices 124 and 126 may have a FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0103] Image capture devices 124 and 126 may acquire a plurality of second and third images with respect to a scene associated with vehicle 200. Each of the plurality of second and third images may be acquired as a 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 acquisition of each of the image scan lines included in the second and third series.

[0104] Each of the image capture devices 122, 124, and 126 may be positioned at any suitable location and orientation relative to vehicle 200. The relative positioning of the image capture devices 122, 124, and 126 may be selected to assist in fusing together the 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 fully overlap with the FOV associated with image capture device 122 (such as FOV 202) and the FOV associated with image capture device 126 (such as FOV 206).

[0105] Image capture devices 122, 124, and 126 may be located at any suitable relative height on vehicle 200. In one case, there may be a height difference between image capture devices 122, 124, and 126, which may provide sufficient parallax information to enable stereoscopic analysis. For example, as Figure 2A shown, two image capture devices 122 and 124 are at different heights. For example, there may also be a lateral displacement difference between image capture devices 122, 124, and 126, thereby giving additional parallax information for stereoscopic analysis by processing unit 110. The difference in lateral displacement may be represented by d x as shown in Figure 2C and Figure 2D shown. In some embodiments, there may be a forward or backward displacement (e.g., range displacement) between image capture devices 122, 124, and 126. For example, image capture device 122 may be located 0.5 meters to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of displacement may enable one of the image capture devices to cover potential blind spots of the other image capture devices.

[0106] The image capture device 122 can have any suitable resolution capabilities (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor associated with the image capture device 122 can be higher, lower, or the same as the resolution of the image sensors associated with the image capture devices 124 and 126. In some embodiments, the image sensors associated with the image capture device 122 and / or the image capture devices 124 and 126 can have a resolution of 640x480, 1024x768, 1280x960, or any other suitable resolution.

[0107] The frame rate (e.g., the rate at which the 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 the image capture device 122 can be higher, lower, or the same as the frame rates associated with the image capture devices 124 and 126. The frame rates associated with the image capture devices 122, 124, and 126 can depend on a variety of factors that can affect the timing of the frame rate. For example, one or more of the image capture devices 122, 124, and 126 can include an optional pixel delay period applied before or after the acquisition of image data associated with one or more pixels of the image sensor in the image capture devices 122, 124, and / or 126. Generally, image data corresponding to each pixel can be acquired according to the clock rate of the device (e.g., one pixel per clock cycle). Additionally, in embodiments that include a rolling shutter, one or more of the image capture devices 122, 124, and 126 can include an optional horizontal blanking period applied before or after the acquisition of image data associated with a row of pixels of the image sensor in the image capture devices 122, 124, and / or 126. Further, one or more of the image capture devices 122, 124, and / or 126 can include an optional vertical blanking period applied before or after the acquisition of image data associated with the image frames of the image capture devices 122, 124, and 126.

[0108] These timing controls can achieve synchronization of the frame rates associated with the image capture devices 122, 124, and 126, even when the line scan rates of each image capture device are different. Additionally, as will be discussed in more detail below, these factors such as the optional timing controls (e.g., image sensor resolution, maximum line scan rate, etc.) can achieve synchronization of image capture from the region where the FOV of the image capture device 122 overlaps with one or more FOVs of the image capture devices 124 and 126, even when the field of view of the image capture device 122 is different from the FOVs of the image capture devices 124 and 126.

[0109] The frame rate timing in image capture devices 122, 124, and 126 can depend on the resolution of the associated image sensor. For example, assuming a similar line scan rate for two devices, if one device includes an image sensor with a resolution of 640x480 and another device includes an image sensor with a resolution of 1280x960, it will take more time to acquire one frame of image data from the sensor with the higher resolution.

[0110] 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, it takes some minimum amount of time to acquire one line of image data from the image sensors included in image capture devices 122, 124, and 126. Assuming no pixel delay cycles are added, this minimum amount of time for the acquisition of one line of image data will be related to the maximum line scan rate for a particular device. A device with a higher maximum line scan rate has the potential to provide a higher frame rate than a device with a lower maximum line scan rate. 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 device 124 and / or 126 can be 1.25 times, 1.5 times, 1.75 times, or 2 times or more than the maximum line scan rate of image capture device 122.

[0111] In another embodiment, image capture devices 122, 124, and 126 can have the same maximum line scan rate, but image capture device 122 can be operated at a scan rate that is less than or equal to its maximum scan rate. The system can be configured such that one or more of image capture devices 124 and 126 operate at a line scan rate that is equal to the line scan rate of image capture device 122. In other cases, the system can be configured such that the line scan rate of image capture device 124 and / or image capture device 126 can be 1.25 times, 1.5 times, 1.75 times, or 2 times or more than the line scan rate of image capture device 122.

[0112] In some embodiments, image capture devices 122, 124, and 126 can be asymmetric. That is, they can include cameras with different fields of view (FOV) and focal lengths. For example, the fields of view of image capture devices 122, 124, and 126 can include any desired regions with respect to the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 can 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.

[0113] Further, the focal length associated with each of the image capture devices 122, 124, and / or 126 may be selectable (e.g., by including an appropriate lens, etc.) such that each device acquires an image of an object at a desired distance range relative to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 may acquire images of close-up objects within a few meters of the vehicle. The image capture devices 122, 124, and 126 may also be configured to acquire images of objects at a greater range from the vehicle (e.g., 25 m, 50 m, 100 m, 150 m, or further). Further, the focal lengths of the image capture devices 122, 124, and 126 may be selected such that one image capture device (e.g., the image capture device 122) may acquire an image of an object relatively close to the vehicle (e.g., within 10 m or within 20 m), while other image capture devices (e.g., the image capture devices 124 and 126) may acquire images of objects further from the vehicle 200 (e.g., greater than 20 m, 50 m, 100 m, 150 m, etc.).

[0114] According to some embodiments, the FOV of one or more of the image capture devices 122, 124, and 126 may be wide-angle. For example, an FOV of 140 degrees may be advantageous, particularly for the image capture devices 122, 124, and 126 that may be used to capture images of areas in the vicinity of the vehicle 200. For example, the image capture device 122 may be used to capture images of areas to the right or left of the vehicle 200, and in such embodiments, it may be desirable for the image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0115] The field of view associated with each of the image capture devices 122, 124, and 126 may depend on the respective focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0116] The image capture devices 122, 124, and 126 may be configured to have any suitable field of view. In one particular example, the image capture device 122 may have a horizontal FOV of 46 degrees, the image capture device 124 may have a horizontal FOV of 23 degrees, and the image capture device 126 may have a horizontal FOV between 23 degrees and 46 degrees. In another case, the image capture device 122 may have a horizontal FOV of 52 degrees, the image capture device 124 may have a horizontal FOV of 26 degrees, and the image capture device 126 may have a horizontal FOV between 26 degrees and 52 degrees. In some embodiments, the ratio of the FOV of the image capture device 122 to the FOV of the image capture device 124 and / or the image capture device 126 may vary from 1.5 to 2.0. In other embodiments, the ratio may vary between 1.25 and 2.25.

[0117] System 100 can be configured such that the field of view of image capture device 122 at least partially or completely overlaps with the field of view of image capture 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 the field of view of image capture device 122 (e.g., are narrower than the field of view) and share a common center with the field of view. 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 centers 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 image capture device 122.

[0118] Figure 2F Schematic representation of an exemplary vehicle control system consistent with the disclosed embodiments. As Figure 2F indicated, vehicle 200 can include a throttle system 220, a brake system 230, and a steering system 240. System 100 can provide an input (e.g., a control signal) to one or more of throttle system 220, brake system 230, and steering system 240 via one or more data links (e.g., any wired and / or wireless link or link for transmitting data). For example, based on the analysis of images acquired by image capture devices 122, 124, and / or 126, System 100 can provide a control signal to one or more of throttle system 220, brake system 230, and steering system 240 to navigate vehicle 200 (e.g., by causing acceleration, turning, lane changes, etc.). Further, System 100 can receive an input indicating the operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.) from one or more of throttle system 220, brake system 230, and steering system 24. Further details are provided below in connection with Figures 4 to 7 Provide further details.

[0119] As Figure 3AAs shown, vehicle 200 may also include a user interface 170 for interacting with the driver or passenger of vehicle 200. For example, the 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 passenger of vehicle 200 may also use a handle (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), etc. to interact with system 100. In some embodiments, the microphone 350 may be positioned adjacent to the rearview mirror 310. Similarly, in some embodiments, the image capture device 122 may be located near the rearview mirror 310. In some embodiments, the user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, system 100 may provide various notifications (e.g., alerts) via the speakers 360.

[0120] FIG. 3B to FIG. 3D FIG. is an illustration of an exemplary camera mount 370 consistent with the disclosed embodiments, the camera mount being configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and against a vehicle windshield. As Figure 3B shown, the camera mount 370 may include image capture devices 122, 124, and 126. The image capture devices 124 and 126 may be positioned behind a glare shield 380, which may be flush against the vehicle windshield and include a composition of film and / or anti-reflective material. For example, the glare shield 380 may be positioned such that the shield is aligned against the vehicle windshield with a matching slope. In some embodiments, each of the image capture devices 122, 124, and 126 may be positioned behind the glare shield 380, as depicted, for example, Figure 3D therein. The disclosed embodiments are not limited to any particular configuration of the image capture devices 122, 124, and 126, the camera mount 370, and the glare shield 380. Figure 3C FIG. is of the camera mount 370 shown from a front perspective Figure 3B as shown.

[0121] As will be understood by those skilled in the art who benefit from this disclosure, various changes and / or modifications may be made to the foregoing disclosed embodiments. For example, not all components are necessary for the operation of system 100. Further, any component may be located in any suitable part of system 100, and these components may be rearranged into various configurations while providing the functions of the disclosed embodiments. Accordingly, the foregoing configurations are exemplary, and regardless of the configurations discussed above, system 100 may provide a wide range of functions to analyze the surrounding environment of vehicle 200 and navigate vehicle 200 in response to that analysis.

[0122] As discussed further below and consistent with the various disclosed embodiments, system 100 may provide various features related to autonomous driving and / or driver assistance technologies. For example, system 100 may analyze image data, location data (e.g., GPS positioning information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 may collect data for analysis from, for example, image acquisition unit 120, location sensor 130, and other sensors. Further, system 100 may analyze the collected data to determine whether vehicle 200 should take a particular action and then automatically take the determined action without human intervention. For example, when vehicle 200 is navigating without human intervention, system 100 may automatically control the braking, acceleration, and / or steering of vehicle 200 (e.g., by sending control signals to one or more of throttle system 220, braking system 230, and steering system 240). Further, system 100 may analyze the collected data and issue warnings and / or alerts to vehicle occupants based on the analysis of the collected data. Additional details regarding the various embodiments provided by system 100 are provided below.

[0123] Forward multiple imaging system

[0124] As discussed above, system 100 may provide driving assistance functions using a multi-camera system. The multi-camera system may use one or more cameras facing the forward direction of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side of the vehicle or the rear of the vehicle. In one embodiment, for example, system 100 may use a dual-camera imaging system, where a first camera and a second camera (e.g., image capture devices 122 and 124) may be positioned at the front and / or side of a vehicle (e.g., vehicle 200). The first camera may have a field of view that is greater than, less than, or partially overlapping with the field of view of the second camera. Additionally, the first camera may be connected to a first image processor to perform monocular image analysis on the images provided by the first camera, and the second camera may be connected to a second image processor to perform monocular image analysis on the images provided by the second camera. The outputs (e.g., processed information) of the first image processor and the second image processor may be combined. In some embodiments, the second image processor may receive images from both the first camera and the second camera for stereo analysis. In another embodiment, system 100 may use a triple-camera imaging system, where each of the cameras has a different field of view. Thus, such a system may make decisions based on information derived from objects at varying distances from both the front and side of the vehicle. Reference to monocular image analysis may refer to a situation where image analysis is performed based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may refer to a situation 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 stereo image analysis may include: images captured from two or more different positions, images captured from different fields of view, images captured using different focal lengths, and images with parallax information, etc.

[0125] For example, in one embodiment, system 100 may implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees, or other values selected within a range of approximately 20 degrees to 45 degrees, etc.), image capture device 124 may provide a wide field of view (e.g., 150 degrees or other values selected within 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 other values selected within a range of approximately 35 degrees to approximately 60 degrees). In some embodiments, image capture device 126 may act as the primary or main camera. Image capture devices 122, 124, and 126 may be positioned behind rearview mirror 310 and positioned substantially side by side (e.g., spaced 6 cm apart). Further, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 may be mounted behind glare shield 380 flush with the windshield of vehicle 200. Such shielding may serve to minimize the effect of any reflections from inside the sedan on image capture devices 122, 124, and 126.

[0126] In another embodiment, as discussed above in connection with Figure 3B and Figure 3C the wide field of view camera (e.g., image capture device 124 in the example above) may 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 example above). This configuration may provide a clear line of sight from the wide field of view camera. To reduce reflections, the camera may be mounted close to the windshield of vehicle 200 and may include a polarizer on the camera to attenuate the reflected light.

[0127] The three-camera system may provide certain performance characteristics. For example, some embodiments may include the ability to verify the detection of an object by one camera based on the detection results from another camera. In the three-camera configuration discussed above, processing unit 110 may include, for example, three processing devices (e.g., three processor chips of the EyeQ series, as discussed above), where each processing device is dedicated to processing the images captured by one or more of image capture devices 122, 124, and 126.

[0128] In the three-camera system, the first processing device may receive images from both the main camera and the narrow field of view camera and perform visual processing on the narrow FOV camera to, for example, detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Further, the first processing device may calculate the pixel disparity between the images from the main camera and the narrow camera and create a 3D reconstruction of the environment of vehicle 200. The first processing device may then combine the 3D reconstruction with 3D map data or with 3D information calculated based on information from another camera.

[0129] The second processing device may receive images from the main camera and perform vision processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the second processing device may calculate the camera displacement and, based on the displacement, calculate the pixel disparity between successive images and create a 3D reconstruction of the scene (e.g., structure from motion). The second processing device may send the structure from the motion-based 3D reconstruction to the first processing device for combination with the stereo 3D image.

[0130] 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.

[0131] In some embodiments, enabling the image-based information streams to be captured and processed independently can provide opportunities for providing redundancy in the system. Such redundancy may include, for example, using the first image capture device and the images processed from that device to verify and / or supplement the information obtained by capturing and processing the image information from at least a second image capture device.

[0132] 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 verify the analysis of the data received from the other two image capture devices. For example, in such a configuration, image capture devices 122 and 124 may provide images for stereo analysis by system 100 for navigating vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of the information obtained based on the images captured by image capture device 122 and / or image capture device 124. That is, image capture device 126 (and the corresponding processing device) may be considered to provide a redundant subsystem for providing an examination of the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Additionally, in some embodiments, the redundancy and verification of the received data may be supplemented based on the information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers external to the vehicle, etc.).

[0133] Those skilled in the art will recognize that the above camera configurations, camera placements, number of cameras, camera positioning, etc. are merely examples. These components and other components described relative 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 provided below.

[0134] Figure 4 An illustrative functional block diagram of memories 140 and / or 150 that can be stored / programmed with instructions for performing one or more operations consistent with the disclosed embodiments. Although the following refers to memory 140, those skilled in the art will recognize that the instructions can be stored in memory 140 and / or 150.

[0135] As Figure 4 shown, memory 140 can store a monocular image analysis module 402, a stereo image analysis module 404, a speed and acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of memory 140. Further, application processor 180 and / or image processor 190 can execute instructions stored in any of modules 402, 404, 406, and 408 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following discussion can refer to application processor 180 and image processor 190 individually or jointly. Accordingly, the steps of any of the following processes can be performed by one or more processing devices.

[0136] In one embodiment, the monocular image analysis module 402 can store instructions (such as computer vision software) that, when executed by processing unit 110, perform monocular image analysis on a set of images acquired by one of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 can combine information from a set of images with additional sensing information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. As described below in connection with FIG. 5A to FIG. 5D what follows, the monocular image analysis module 402 can include instructions for detecting a set of features (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) within the set of images. Based on this analysis, system 100 (e.g., via processing unit 110) can cause one or more navigation responses in vehicle 200, such as turning, lane changing, changing acceleration, etc., as discussed below in connection with navigation response module 408.

[0137] In one embodiment, the stereoscopic image analysis module 404 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform stereoscopic image analysis on a first set of images and a second set of images acquired by a combination of image capture devices selected from among image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first set of images and the second set of images with additional sensing information (e.g., information from radar) for stereoscopic image analysis. For example, the stereoscopic image analysis module 404 may include instructions for performing stereoscopic 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 connection with Figure 6 the stereoscopic image analysis module 404 may include instructions for detecting a set of features (such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, etc.) within the first set of images and the second set of images. Based on this analysis, the processing unit 110 may cause one or more navigation responses in vehicle 200, such as turning, lane changes, changes in acceleration, etc., as discussed below in connection with the navigation response module 408. Additionally, in some embodiments, the stereoscopic image analysis module 404 may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system (such as a system that may be configured to use computer vision algorithms to detect and / or label objects in an environment from which sensing information is captured and processed). In one embodiment, the stereoscopic image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0138] 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, the one or more computing and electromechanical devices being configured to cause a change 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 the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, a target position, speed and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, position information of the vehicle 200 relative to the lane markings of the road, and so on. In addition, the processing unit 110 may calculate a target speed for the vehicle 200 based on sensing inputs (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle system 220, the braking system 230, and / or the steering system 240 of the vehicle 200. Based on the calculated target speed, the processing unit 110 may transmit an electronic signal to the throttle system 220, the braking system 230, and / or the steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration by, for example, physically depressing the brakes or relaxing the accelerator of the vehicle 200.

[0139] In one embodiment, the navigation response module 408 may store software executable by the processing unit 110 to determine a desired navigation response based on data 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 speed information associated with nearby vehicles, pedestrians, and road objects, target position information for the vehicle 200, and so on. Additionally, in some embodiments, the navigation response may be (partially or fully) based on map data, a pre-determined position of the vehicle 200, and / or the relative speed or relative acceleration between the vehicle 200 and one or more objects detected from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine a desired navigation response based on sensing inputs (e.g., information from radar) and inputs from other systems of the vehicle 200, such as the throttle system 220, the braking system 230, and the steering system 240 of the vehicle 200. Based on the desired navigation response, the processing unit 110 may transmit an electronic signal to the throttle 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 rotation at a pre-determined angle. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as an input to the execution of the speed and acceleration module 406 for calculating a change in the speed of the vehicle 200.

[0140] In addition, any module disclosed herein (e.g., modules 402, 404, and 406) may implement techniques associated with a trained system, such as a neural network or a deep neural network, or an untrained system.

[0141] Figure 5A FIG. 500A is a flowchart of an exemplary process for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via a data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera included in the image acquisition unit 120 (such as the image capture device 122 having a field of view 202) may capture a plurality of images of an area in front of the vehicle 200 (or, for example, 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.). The processing unit 110 may execute the monocular image analysis module 402 at step 520 to analyze the plurality of images, as described in further detail below in connection with FIG. 5B to FIG. 5D In the further details. By performing this analysis, the processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0142] The processing unit 110 may also execute the monocular image analysis module 402 at step 520 to detect various road hazards, such as, for example, parts of a truck tire, a fallen road sign, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of such hazards more challenging. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on the plurality of images to detect road hazards. For example, the processing unit 110 may estimate the camera motion between consecutive image frames and calculate the pixel disparity between the frames to construct a 3D map of the road. The processing unit 110 may then use the 3D map to detect the road surface and hazards present above the road surface.

[0143] At step 530, the processing unit 110 may execute the navigation response module 408 based on the analysis performed at step 520 and as described above in connection with Figure 4The described techniques are used to cause one or more navigation responses in vehicle 200. Navigation responses can include, for example, turning, lane changes, changes in acceleration, and the like. In some embodiments, processing unit 110 can use data derived from the execution of speed and acceleration module 406 to cause one or more navigation responses. Additionally, multiple navigation responses can occur simultaneously, sequentially, or any combination thereof. For example, processing unit 110 can cause vehicle 200 to change out of a lane and then accelerate by, for example, sequentially transmitting control signals to steering system 240 and throttle system 220 of vehicle 200. Alternatively, processing unit 110 can cause vehicle 200 to brake while changing lanes by, for example, simultaneously transmitting control signals to braking system 230 and steering system 240 of vehicle 200.

[0144] Figure 5B A flowchart illustrating 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 can execute monocular image analysis module 402 to implement process 500B. At step 540, processing unit 110 can determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 can scan one or more images, compare the images to one or more pre - determined patterns, and identify possible locations within each image that may contain an object of interest (e.g., a vehicle, a pedestrian, or a part thereof). The pre - determined patterns can be designed in a way that achieves a high "false hit" rate and a low "miss" rate. For example, processing unit 110 can use a low threshold of similarity to a pre - determined pattern to identify candidate objects as possible vehicles or pedestrians. Doing so can allow processing unit 110 to reduce the probability of missing (e.g., not identifying) candidate objects representing vehicles or pedestrians.

[0145] At step 542, processing unit 110 can filter a set of candidate objects based on classification criteria to exclude specific candidates (e.g., irrelevant or less relevant objects). Such criteria can be derived from various attributes associated with object types stored in a database (e.g., a database stored in memory 140). Attributes can include object shape, size, texture, location (e.g., relative to vehicle 200), and the like. Thus, processing unit 110 can use one or more sets of criteria to reject false candidates from a set of candidate objects.

[0146] At step 544, processing unit 110 may analyze multiple image frames to determine whether an object in a 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.). Additionally, processing unit 110 may estimate parameters for the detected objects and compare the frame-by-frame position data of the objects to predicted positions.

[0147] At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects. In some embodiments, processing unit 110 may construct the measurements based on estimation techniques using a series of time-based observations such as a Kalman filter or linear quadratic estimation (LQE) and / or based on available modeling data for different object types (e.g., sedan, truck, pedestrian, bicycle, road sign, etc.). The Kalman filter may be based on measurements of the scale of an object, where the scale measurement is proportional to the time to collision (e.g., the amount of time for vehicle 200 to reach the object). Thus, by performing steps 540 to 546, processing unit 110 may identify vehicles and pedestrians present within a set of captured images and derive information associated with the vehicles and pedestrians (e.g., position, speed, 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 connection with Figure 5A that described.

[0148] At step 548, processing unit 110 may perform optical flow analysis on one or more images to reduce the probability of detecting "false positives" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing the motion patterns relative to vehicle 200 in one or more images associated with other vehicles and pedestrians, and the motion patterns are different from the road surface motion. Processing unit 110 may calculate the motion of candidate objects by observing the different positions of the objects across multiple image frames captured at different times. Processing unit 110 may use the position and time values as inputs into a mathematical model to calculate the motion of the candidate objects. Thus, optical flow analysis may provide an alternative method for detecting vehicles and pedestrians near vehicle 200. Processing unit 110 may perform optical flow analysis in conjunction with steps 540 to 546 to provide redundancy for detecting vehicles and pedestrians and increase the reliability of system 100.

[0149] Figure 5CFlowchart of an exemplary process 500C for detecting road markings and / or lane geometry feature information in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500C. At step 550, the processing unit 110 may detect a set of objects by scanning one or more images. To detect segments of lane markings, lane geometry feature information, and other relevant road markings, the processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., small potholes, small rocks, etc.). At step 552, the processing unit 110 may group together the segments detected in step 550 that belong to the same road marking or lane marking. Based on this grouping, the processing unit 110 may develop a model representing the detected segments, such as a mathematical model.

[0150] At step 554, the processing unit 110 may construct a set of measurements associated with the detected segments. In some embodiments, the processing unit 110 may create a projection of the detected segments from the image plane to the real-world plane. A cubic polynomial with coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivative of the detected road may be used to characterize the projection. When generating the projection, the processing unit 110 may consider changes in the road surface as well as the pitch rate and roll rate associated with the vehicle 200. In addition, the processing unit 110 may model the road elevation by analyzing the position and motion cues present on the road surface. Further, the processing unit 110 may estimate the pitch rate and roll rate associated with the vehicle 200 by tracking a set of feature points in one or more images.

[0151] At step 556, the processing unit 110 may perform multi-frame analysis by, for example, tracking the detected segments across consecutive image frames and accumulating frame-by-frame data associated with the detected segments. When the processing unit 110 performs multi-frame analysis, the set of measurements constructed at step 554 may become more reliable and associated with an increasingly high confidence level. Thus, by performing steps 550, 552, 554, and 556, the processing unit 110 may identify road markings present within a set of captured images and derive lane geometry feature information. Based on this identification and the derived information, the processing unit 110 may cause one or more navigation responses in the vehicle 200, as described above in connection with Figure 5A as described.

[0152] At step 558, the processing unit 110 may consider additional information sources to further develop a safety model for the vehicle 200 in the context of its surrounding environment. The processing unit 110 may use the safety model to define scenarios in which the system 100 can perform autonomous control of the vehicle 200 in a safe manner. To develop the safety model, in some embodiments, the processing unit 110 may consider the positions and movements of other vehicles, detected road edges and obstacles, and / or general road shape descriptions extracted from map data (such as data from the map database 160). By considering additional information sources, the processing unit 110 may provide redundancy for detecting road markings and lane geometric features and increase the reliability of the system 100.

[0153] Figure 5D A flowchart illustrating an exemplary process 500D for detecting traffic lights in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500D. At step 560, the processing unit 110 may scan the set of images and identify objects that appear in the images at locations that may contain traffic lights. For example, the processing unit 110 may filter the identified objects to build a set of candidate objects, excluding those objects that are less likely to correspond to traffic lights. The filtering may be done based on various attributes associated with traffic lights, such as shape, size, texture, location (e.g., relative to the vehicle 200), etc. Such attributes may be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, the processing unit 110 may perform multi-frame analysis on a set of candidate objects that reflect possible traffic lights. For example, the processing unit 110 may track candidate objects across consecutive image frames, estimate the real-world positions of the candidate objects, and filter out those objects that are moving (which are less likely to be traffic lights). In some embodiments, the processing unit 110 may perform color analysis on the candidate objects and identify the relative positions of the detected colors that appear inside the possible traffic lights.

[0154] At step 562, the processing unit 110 may analyze the geometric features of the intersection. The analysis may be based on any combination of the following: (i) the number of lanes detected on either side of the vehicle 200, (ii) the markings detected on the road (such as arrow markings), and (iii) a description of the intersection extracted from map data (such as data from the map database 160). The processing unit 110 may use the information derived from the execution of the monocular analysis module 402 to perform the analysis. In addition, the processing unit 110 may determine the correspondence between the traffic lights detected at step 560 and the lanes that appear near the vehicle 200.

[0155] When vehicle 200 approaches an intersection, at step 564, processing unit 110 may update the confidence level associated with the analyzed intersection geometric features and detected traffic lights. For example, the estimated number of traffic lights present at the intersection may affect the confidence level compared to the actual number present at the intersection. Thus, based on this confidence level, processing unit 110 may delegate control to the driver of vehicle 200 to improve safety conditions. By performing steps 560, 562, and 564, processing unit 110 may identify the traffic lights present within the set of captured images and analyze the intersection geometric feature information. Based on this identification and analysis, processing unit 110 may cause one or more navigation responses in vehicle 200, as described above in conjunction with Figure 5A as described.

[0156] Figure 5E FIG. is a flowchart of an exemplary process 500E for causing 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 using a set of points expressed in coordinates (x, z), and the distance d between two points in the set of points i may fall within the range of 1 meter to 5 meters. In one embodiment, processing unit 110 may use two polynomials (such as a left road polynomial and a right road polynomial) to construct the initial vehicle path. Processing unit 110 may calculate the geometric midpoint between the two polynomials and, if any, offset each point included in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset) (a zero offset may correspond to driving in the middle of the lane). This offset may be in a direction perpendicular to the segment between any two points in the vehicle path. In another embodiment, processing unit 110 may use one polynomial and an estimated lane width to offset each point of the vehicle path by half of the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0157] At step 572, processing unit 110 may update the vehicle path constructed at step 570. Processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution such that the distance d between two points in the set of points representing the vehicle path k is less than the distance d described above i . For example, the distance d k may fall within the range of 0.1 meter to 0.3 meter. Processing unit 110 may use a parabolic spline algorithm to reconstruct the vehicle path, which may produce 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).

[0158] At step 574, the processing unit 110 may determine a look-ahead point (expressed in coordinates as (x l , z l )) based on the updated vehicle path constructed at step 572. The processing unit 110 may extract the look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance (which may have a lower limit in the range from 10 meters to 20 meters) may be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, as the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower limit). The look-ahead time (which may be in the range from 0.5 seconds to 1.5 seconds) may be inversely proportional to the gain of one or more control loops (such as the heading error tracking control loop) associated with causing a navigation response in the vehicle 200. For example, the gain of the heading error tracking control loop may depend on the bandwidths of the yaw rate loop, the steering actuator loop, the car lateral dynamics, etc. Thus, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0159] At step 576, the processing unit 110 may determine a heading error and a yaw rate command based on the look-ahead point determined at step 574. The processing unit 110 may determine the heading error by calculating the arctangent of the look-ahead point, e.g., arctan(x l / z l ). The processing unit 110 may determine the yaw rate command as the product of the heading error and a 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 * speed of the vehicle 200 / look-ahead distance).

[0160] Fig. 5F A flowchart showing an exemplary process 500F for determining whether a vehicle ahead is changing lanes consistent with the disclosed embodiments. At step 580, the processing unit 110 may determine navigation information associated with a vehicle ahead (e.g., a vehicle traveling in front of the vehicle 200). For example, the processing unit 110 may use the techniques described above in connection with Figure 5A and Figure 5B to determine the position, rate (e.g., direction and speed), and / or acceleration of the vehicle ahead. The processing unit 110 may also use the techniques described above in connection with Figure 5E to determine one or more road polynomials, look-ahead points (associated with the vehicle 200), and / or a snail trajectory (e.g., a set of points describing the path taken by the vehicle ahead).

[0161] At step 582, the processing unit 110 may analyze the navigation information determined at step 580. In one embodiment, the processing unit 110 may calculate the distance between the snail trajectory and the road polynomial (e.g., along the trajectory). If the variance of this distance along the trajectory exceeds a pre-determined threshold (e.g., 0.1 m to 0.2 m on a straight road, 0.3 m to 0.4 m on a moderately curved road, and 0.5 m to 0.6 m on a road with sharp curves), then the processing unit 110 may determine that the vehicle ahead may be changing lanes. In a case where multiple vehicles are detected traveling in front of the vehicle 200, the processing unit 110 may compare the snail trajectories associated with each vehicle. Based on this comparison, the processing unit 110 may determine that a vehicle whose snail trajectory does not match the snail trajectories of other vehicles may be changing lanes. The processing unit 110 may additionally compare the curvature of the snail trajectory (associated with the vehicle ahead) with the expected curvature of the road segment on which the vehicle ahead is traveling. The expected curvature may be extracted from map data (e.g., data from the map database 160), from the road polynomial, from the snail trajectories of other vehicles, from prior knowledge about the road, etc. If the difference between the curvature of the snail trajectory and the expected curvature of the road segment exceeds a pre-determined threshold, then the processing unit 110 may determine that the vehicle ahead may be changing lanes.

[0162] In another embodiment, the processing unit 110 may compare the instantaneous position of the vehicle ahead with a look-ahead point (associated with the vehicle 200) within a specific time period (e.g., 0.5 seconds to 1.5 seconds). If the distance between the instantaneous position of the vehicle ahead and the look-ahead point changes within the specific time period, and the cumulative sum of the changes exceeds a pre-determined threshold (e.g., 0.3 m to 0.4 m on a straight road, 0.7 m to 0.8 m on a moderately curved road, and 1.3 m to 1.7 m on a road with sharp curves), the processing unit 110 may determine that the vehicle ahead may be changing lanes. In another embodiment, the processing unit 110 may analyze the geometric characteristics of the trajectory by comparing the lateral distance traveled along the snail trajectory with the expected curvature of the snail trajectory. The expected radius of curvature can be determined according to the following calculation: (δ z 2 +δ x 2 ) / 2 / (δ x ) where δ x represents the lateral distance traveled, and δ zRepresents the longitudinal distance traveled. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 meters to 700 meters), the processing unit 110 may determine that the vehicle ahead may be changing lanes. In another embodiment, the processing unit 110 may analyze the position of the vehicle ahead. If the position of the vehicle ahead occludes the road polynomial (e.g., the vehicle ahead is positioned on top of the road polynomial), the processing unit 110 may determine that the vehicle ahead may be changing lanes. In the case where the position of the vehicle ahead is such that another vehicle is detected in front of the vehicle ahead and the snail trajectories of the two vehicles are not parallel, the processing unit 110 may determine that the (closer) vehicle ahead may be changing lanes.

[0163] At step 584, the processing unit 110 may determine whether the vehicle ahead 200 is changing lanes based on the analysis performed at step 582. For example, the processing unit 110 may make the determination based on a weighted average of the respective analyses performed at step 582. In such a scenario, for example, a determination that the vehicle ahead may be changing lanes made by the processing unit 110 based on a particular type of analysis may be assigned the value "1" (and "0" to indicate a determination that the vehicle ahead is less likely 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.

[0164] Figure 6 Flowchart of an exemplary process 600 for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments. At step 610, the processing unit 110 may receive a first plurality of images and a second plurality of images via the data interface 128. For example, cameras included in the image acquisition unit 120 (such as image capture devices 122 and 124 having fields of view 202 and 204) may capture a first plurality of images and a second plurality of images of the area in front of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first plurality of images and the second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0165] At step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis of the first plurality of images and the second plurality of images to create a 3D map of the road in the front of the vehicle and detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. Stereo image analysis can be performed in a manner similar to that described above in connection with FIG. 5A to FIG. 5Din the manner of the steps described. For example, the processing unit 110 may execute the stereoscopic image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) within the first plurality of images and the second plurality of images, filter out a subgroup of candidate objects based on the respective objects, and perform multi-frame analysis, construct measurement results, and determine confidence levels for the remaining candidate objects. When performing the steps above, the processing unit 110 may consider information from both the first plurality of images and the second plurality of images, rather than information from only one set of images. For example, the processing unit 110 may analyze the differences in pixel-level data (or other subgroups of data from among the two streams of captured images) of candidate objects that appear in both the first plurality of images and the second plurality of images. As another example, the processing unit 110 may estimate the position and / or rate (e.g., relative to vehicle 200) of a candidate object by observing that the candidate object appears in one of the plurality of images but not the other or other differences that may exist relative to an object that would have appeared if both image streams were present. For example, the position, rate, and / or acceleration relative to vehicle 200 may be determined based on the trajectories, positions, movement characteristics, etc. of features associated with objects that appear in one or both of the image streams.

[0166] At step 630, the processing unit 110 may execute the navigation response module 408 to cause one or more navigation responses in vehicle 200 based on the analysis performed at step 620 and the techniques described above in connection with Figure 4 the techniques described. The navigation responses may include, for example, turning, lane changes, changes in acceleration, changes in rate, braking, etc. In some embodiments, the processing unit 110 may use data derived from the execution of the speed and acceleration module 406 to cause one or more navigation responses. Additionally, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0167] Figure 7Flowchart of an exemplary process 700 for causing one or more navigation responses based on an analysis of three sets of images, consistent with the disclosed embodiments. At step 710, the processing unit 110 may receive a first plurality of images, a second plurality of images, and a third plurality of images via the data interface 128. For example, cameras included in the image acquisition unit 120 (such as image capture devices 122, 124, and 126 having fields of view 202, 204, and 206) may capture a first plurality of images, a second plurality of images, and a third plurality of images of regions in front of and / or to the sides of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first plurality of images, the second plurality of images, and the third plurality of images via three or more data interfaces. For example, each of the image capture devices 122, 124, 126 may have an associated data interface for transmitting data to the processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0168] At step 720, the processing unit 110 may analyze the first plurality of images, the second plurality of images, and the 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. The analysis can be performed in a manner similar to the steps described above in connection with FIG. 5A to FIG. 5D and Figure 6 . For example, the processing unit 110 may perform monocular image analysis on each of the first plurality of images, the second plurality of images, and the third plurality of images (e.g., via the execution of the monocular image analysis module 402 and based on the steps described above in connection with FIG. 5A to FIG. 5D . Alternatively, the processing unit 110 may perform stereo image analysis on the first plurality of images and the second plurality of images, the second plurality of images and the third plurality of images, and / or the first plurality of images and the third plurality of images (e.g., via the execution of the stereo image analysis module 404 and based on the steps described above in connection with Figure 6(the steps described). Processed information corresponding to the analysis of the first plurality of images, the second plurality of images, and / or the third plurality of images can be combined. In some embodiments, the processing unit 110 can perform a combination of monocular image analysis and stereo image analysis. For example, the processing unit 110 can perform monocular image analysis on the first plurality of images (e.g., via the execution of the monocular image analysis module 402), and perform new stereo image analysis on the second plurality of images and the third plurality of images (e.g., via the execution of the stereo image analysis module 404). The configurations of the image capture devices 122, 124, and 126 - including their respective positions and fields of view 202, 204, and 206 - can affect the type of analysis performed on the first plurality of images, the second plurality of images, and the third plurality of images. The disclosed embodiments are not limited to a specific configuration of the image capture devices 122, 124, and 126, or the type of analysis performed on the first plurality of images, the second plurality of images, and the third plurality of images.

[0169] In some embodiments, the processing unit 110 can test the system 100 based on the images acquired and analyzed at steps 710 and 720. Such tests can provide an indicator of the overall performance of the system 100 for a specific configuration of the image capture devices 122, 124, and 126. For example, the processing unit 110 can determine the proportion of "false positives" (e.g., situations where the system 100 incorrectly determines the presence of a vehicle or a pedestrian) and "misses".

[0170] At step 730, the processing unit 110 can cause one or more navigation responses in the vehicle 200 based on information derived from two of the first plurality of images, the second plurality of images, and the third plurality of images. The selection of two of the first plurality of images, the second plurality of images, and the third plurality of images can depend on various factors, such as, for example, the number, type, and size of the objects detected in each of the plurality of images. The processing unit 110 can also be 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 object appears, the proportion of the object in each such frame, etc.), and so on.

[0171] In some embodiments, the processing unit 110 may select information derived from two of the first plurality of images, the second plurality of images, and the third plurality of images by determining the degree to which information derived from one image source is consistent with information derived from other image sources. For example, the processing unit 110 may combine the processed information derived from each of the image capture devices 122, 124, and 126 (whether by monocular analysis, stereoscopic analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, detected vehicles and their positioning and / or path, detected traffic lights, etc.) that are consistent across the images captured from each of the image capture devices 122, 124, and 126. The processing unit 110 may also exclude information that is inconsistent across the captured images (e.g., a vehicle changing lanes, a lane model indicating a vehicle too close to vehicle 200, etc.). Thus, the processing unit 110 may select information derived from two of the first plurality of images, the second plurality of images, and the third plurality of images based on the determination of consistent and inconsistent information.

[0172] The navigation response may include, for example, turning, lane changing, a change in acceleration, etc. The processing unit 110 may cause one or more navigation responses based on the analysis performed at step 720 and the techniques described above in connection with Figure 4 The processing unit 110 may also use data derived from the execution of 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 speed, and / or relative acceleration between vehicle 200 and an object detected within any of the first plurality of images, the second plurality of images, and the third plurality of images. The plurality of navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0173] Sparse road models for autonomous vehicle navigation

[0174] In some embodiments, the disclosed systems and methods may use a sparse map for autonomous vehicle navigation. Specifically, the sparse map may be used for autonomous vehicle navigation along a road segment. For example, the sparse map may provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed further below, an autonomous vehicle may use the sparse map to navigate one or more roads based on one or more stored trajectories.

[0175] Sparse maps for autonomous vehicle navigation

[0176] In some embodiments, the disclosed systems and methods can generate a sparse map 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 further below, a vehicle (which can be an autonomous vehicle) can use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map can include data related to roads and potential landmarks along the roads that is sufficient for vehicle navigation, but the data also exhibits a small data footprint. For example, compared to a digital map that includes detailed map information such as image data collected along a road, the sparse data map described in detail below may require significantly less storage space and data transfer bandwidth.

[0177] For example, instead of storing a detailed representation of a road segment, the sparse data map can store a three-dimensional polynomial representation of a preferred vehicle path along the road. These paths may require little data storage space. Further, 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, it is not necessary to identify and include such landmarks in the model at a high density and short spacing. Instead, in some cases, it is possible to navigate based on landmarks spaced at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart. As will be discussed in more detail in other sections, the 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 a road. In some cases, the sparse map can be generated based on data collected during multiple drives of one or more vehicles along a particular road. Generating a sparse map using multiple drives of one or more vehicles can be referred to as "crowdsourcing" the sparse map.

[0178] Consistent with the disclosed embodiments, an autonomous vehicle system can use a sparse map for navigation. For example, the disclosed systems and methods can distribute 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 an autonomous vehicle along a road segment. A sparse map consistent with this disclosure can include one or more three-dimensional profiles that can represent a predetermined trajectory that an autonomous vehicle can travel along as it moves along an associated road segment.

[0179] Sparse maps consistent with the present disclosure may also include data representing one or more road features. Such road features may include identified landmarks, road characteristic curves, and any other road-related features useful in navigating a vehicle. Sparse maps consistent with the present disclosure may enable autonomous navigation of a vehicle based on a relatively small amount of data included in the sparse map. For example, rather than including a detailed representation of a road, such as road edges, road curvature, images associated with road segments, or data detailing other physical characteristics associated with road segments, the disclosed embodiments of the sparse map may require relatively little storage space (and relatively little bandwidth when portions of the sparse map are transferred to a vehicle), but may still adequately provide for autonomous vehicle navigation. The small data footprint of the disclosed sparse maps, discussed further in detail below, may be achieved in some embodiments by storing representations of road-related elements that require little data but still enable autonomous navigation.

[0180] For example, the disclosed sparse map may store polynomial representations 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, rather than storing (or having to transmit) details about the physical properties of a road to enable navigation along the road, with the disclosed sparse map, a vehicle may navigate along a particular road segment without, in some cases, having to interpret the physical aspects of the road, but rather by aligning its travel path with a trajectory (e.g., a polynomial spline) along the particular road segment. In this manner, a vehicle may be navigated primarily based on stored trajectories (e.g., polynomial splines), which may require significantly less storage space compared to stored methods involving road images, road parameters, road layouts, etc.

[0181] In addition to the stored polynomial representations of trajectories along road segments, the disclosed sparse map may also include small data objects that may represent road features. In some embodiments, the small data objects may include digital characteristics that are derived from digital images (or digital signals) obtained from sensors (e.g., cameras or other sensors, such as suspension sensors) mounted on a vehicle traveling along a road segment. The digital characteristics may have a reduced size relative to the signals acquired by the sensors. In some embodiments, the digital characteristics may be created to be compatible with a classifier function that is configured to detect and identify road features from signals acquired by the sensors, for example, during subsequent driving. In some embodiments, the digital characteristics may be created such that they have the smallest possible footprint while maintaining the ability to correlate or match road features with the stored characteristics based on an image of the road feature (or if the stored characteristics are not based on images and / or include other data, based on digital signals generated by the sensors) captured by a camera mounted on a vehicle traveling along the same road segment at a subsequent time.

[0182] In some embodiments, the size of the data object can be further associated with the uniqueness of the road feature. For example, for road features detectable by a camera mounted on a vehicle, and when a camera system mounted on the vehicle is coupled to a classifier capable of classifying the image data corresponding to the road feature as being associated with a particular type of road feature (e.g., a road sign), and when such road signs are locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), this can be sufficient for storing data indicating the type and location of the road feature.

[0183] 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 the road feature in relatively few bytes, while providing sufficient information for identifying such features and using such features for navigation. In one example, a road sign can be identified as a recognized landmark on which vehicle navigation can be based. The representation of the road sign can be stored in a sparse map to include, for example, a few bytes of data indicating the type of the landmark (e.g., a stop sign) and a few bytes of data indicating the location of the landmark (e.g., coordinates). Navigation based on such a data-only representation of the landmark (e.g., using a representation sufficient for localization, identification, and navigation based on the landmark) can provide the desired level of navigation functionality associated with the sparse map without significantly increasing the data overhead associated with the sparse map. This compact representation of landmarks (and other road features) can utilize sensors and processors mounted on such vehicles that are configured to detect, identify, and / or classify specific road features.

[0184] When, for example, a sign or even a particular type of sign is locally unique in a given area (e.g., when there are no other signs and no other signs of the same type), the sparse map can use data indicating a class of landmarks (signs or a particular type of sign), and during navigation (e.g., autonomous navigation), when a camera mounted on an autonomous vehicle captures an image of an area including the sign (or a particular type of sign), the processor can process the image, detect the sign (if it is indeed present in the image), classify the image as a sign (or a particular type of sign), and associate the location of the image with the location of the sign as stored in the sparse map.

[0185] The sparse map may include any suitable representation of objects identified along a road segment. In some cases, the objects may be referred to as semantic objects or non-semantic objects. Semantic objects may include, for example, objects associated with a pre-determined type classification. Such type classification may be useful in reducing the amount of data required to describe the semantic objects identified in the environment, which is beneficial both during the acquisition phase (e.g., reducing the cost associated with the bandwidth usage for transmitting driving information from multiple acquisition vehicles to the server) and during the navigation phase (e.g., the reduction of map data may accelerate the transmission of map tiles from the server to the navigation vehicle and may also reduce the cost associated with the bandwidth usage of such transmission). The semantic object classification types may be assigned to any type of object or feature expected to be encountered along the road.

[0186] Semantic objects may be further divided into two or more logical groupings. For example, in some cases, the types of semantic objects in one grouping may be associated with a pre-determined dimension. Such semantic objects may include specific speed limit signs, yield signs, merge signs, stop signs, traffic lights, direction arrows on the road, manhole covers, or any other type of object that may be associated with a standardized size. One benefit provided by such semantic objects is that little data may be required to represent / fully define the object. For example, if the standardized size of the speed limit sign is known, the acquisition vehicle may only need to identify (through analysis of the captured image) the presence of the speed limit sign (the identified type) along with an indication of the location of the detected speed limit sign (e.g., the 2D location in the captured image of the center of the sign or a certain corner of the sign (or, alternatively, the 3D location in real-world coordinates)) to provide sufficient information for map generation on the server side. In the case of transmitting the 2D image location to the server, the location associated with the captured image of the detected sign may also be transmitted, so that the server can determine the real-world location of the sign (e.g., by using the structure-from-motion technique from multiple captured images from one or more acquisition vehicles). Even in the case of limited information (only a few bytes may be required to define each detected object), the server can build a map including a complete representation of the speed limit sign based on the type classification (indicating a speed limit sign) received from one or more acquisition vehicles along with the location information for the detected sign.

[0187] Semantic objects may also include other recognized object or feature types not associated with specific standardized characteristics. Such objects or features may include potholes, tar seams, light poles, non-standard signs, curbs, trees, branches, or any other type of recognized object type having one or more variable characteristics (e.g., variable size). In such cases, in addition to transmitting an indication of the detected object or feature type (e.g., pothole, pole, etc.) and location information for the detected object or feature to the server, the acquisition vehicle may also transmit an indication of the size of the object or feature. The size may be expressed in 2D image dimensions (e.g., using a bounding box or one or more size values) or real-world dimensions (determined by structure-from-motion calculations, based on lidar or radar system outputs, based on trained neural network outputs, etc.).

[0188] Non-semantic objects or features may include any detectable object or feature that falls outside of a recognized class or type, but that may still provide valuable information in map generation. In some cases, such non-semantic features may include detected corners of buildings or corners of detected windows of buildings, a unique rock or object near a road, concrete splashes in a road shoulder, or any other detectable object or feature. When such an object or feature is detected, one or more acquisition vehicles may transmit the localization of one or more points (2D image points or 3D real-world points) associated with the detected object / feature to the map generation server. Additionally, a compressed or simplified image segment (e.g., an image hash) may be generated for the region of the captured image that includes the detected object or feature. The image hash may be calculated based on a pre-determined image processing algorithm and may form an effective characteristic for the detected non-semantic object or feature. Such a characteristic may be useful for navigation relative to a sparse map that includes non-semantic features or objects, as vehicles driving along the road may apply an algorithm similar to the one used to generate the image hash in order to confirm / verify the presence of the captured image of the mapped non-semantic feature or object. Using this technique, non-semantic features may be added to the richness of the sparse map (e.g., to enhance its usefulness in navigation) without adding significant data overhead.

[0189] As noted, target trajectories may be stored in the sparse map. These target trajectories (e.g., 3D splines) may represent preferred or recommended paths for each available lane of a road, each valid approach through an intersection, for lane changes and exits, etc. In addition to target trajectories, other road features may also be detected, acquired, and incorporated into the sparse map in the form of representative splines. Such features may include, for example, road edges, lane markings, curbs, guardrails, or any other object or feature that extends along a road or road segment.

[0190] Generating sparse maps

[0191] In some embodiments, a sparse map may include at least one line representation of road surface features extending along a road segment and a plurality of landmarks associated with the road segment. In certain aspects, the sparse map may be generated via "crowdsourcing", such as by image analysis of a plurality of images acquired when one or more vehicles drive over the road segment.

[0192] Figure 8 Shown is a sparse map 800 that one or more vehicles (e.g., vehicle 200, which may be an autonomous vehicle) may access to provide autonomous vehicle navigation. The sparse map 800 may be stored in a memory (such as memory 140 or 150). Such memory devices may include any type of non-transitory storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 may include a hard disk drive, an optical disc, flash memory, a magnetic-based memory device, an optical-based memory device, etc. In some embodiments, the sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150 or other types of storage devices.

[0193] In some embodiments, the sparse map 800 may be stored on a storage device or non-transitory computer-readable medium configured to be loaded on vehicle 200 (e.g., a storage device included in a navigation system loaded on vehicle 200). A processor provided on vehicle 200 (e.g., processing unit 110) may access the sparse map 800 stored in the storage device or computer-readable medium configured to be loaded on vehicle 200 to generate navigation instructions for guiding the autonomous vehicle 200 as the vehicle drives over the 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 provided on a remote server in communication with vehicle 200 or a device associated with vehicle 200. A processor provided on vehicle 200 (e.g., processing unit 110) may receive data included in the sparse map 800 from the remote server and may execute the data for guiding the autonomous driving of vehicle 200. In such embodiments, the remote server may store all or only a portion of the sparse map 800. Accordingly, a storage device or computer-readable medium configured to be loaded on vehicle 200 and / or on one or more additional vehicles may store the remaining portion of the sparse map 800.

[0195] In addition, in such embodiments, the sparse map 800 may be made accessible to multiple vehicles (e.g., dozens, hundreds, thousands, or millions of vehicles, etc.) traversing various road segments. It should also be noted that the sparse map 800 may include multiple sub-maps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, millions, or more sub-maps (e.g., map tiles) that can be used to navigate vehicles. Such sub-maps may be referred to as local maps or map tiles, and a vehicle traveling along a road may access any number of local maps related to the location where the vehicle is traveling. The local map segments of the sparse map 800 may be stored together with a Global Navigation Satellite System (GNSS) key as an index to the database of the sparse map 800. Thus, while the calculation of the steering angle for navigating the host vehicle in this system may be performed without relying on the host vehicle's GNSS position, road features, or landmarks, such GNSS information may be used for retrieving the relevant local maps.

[0196] Generally speaking, the sparse map 800 may be generated based on data (e.g., driving information) collected from one or more vehicles while traveling along a road. For example, using sensors (e.g., cameras, speedometers, GPS, accelerometers, etc.) mounted on one or more vehicles, the trajectories of one or more vehicles traveling along a road may be recorded, and a polynomial representation of the preferred trajectory for a vehicle for a subsequent journey along the road may be determined based on the collected trajectories of the one or more vehicles traveling. Similarly, data collected by one or more vehicles may help identify potential landmarks along a particular road. Data collected from passing vehicles may also be used to identify road profile information, such as road width curves, road roughness curves, traffic line spacing curves, road conditions, etc. Using the information collected, the sparse map 800 may be generated and distributed (e.g., for local storage or via on-the-fly data transfer) 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 may be continuously or periodically updated based on data collected from vehicles as those vehicles continue to traverse the roads included in the sparse map 800.

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

[0198] In a specific example, the collection vehicles can drive through a specific road segment. Each collection vehicle captures images of their respective environments. Images can be collected at any suitable frame capture rate (e.g., 9Hz, etc.). The image analysis processor mounted on each collection vehicle analyzes the captured images to detect the presence of semantic and / or non-semantic features / objects. At a high level, the collection vehicle transmits an indication of the detection of semantic and / or non-semantic objects / features along with the location associated with those objects / features to the mapping server. More specifically, a type indicator, a size indicator, etc. can be transmitted together with the location information. The location information can include any suitable information for enabling the mapping server to aggregate the detected objects / features into a sparse map useful for navigation. In some cases, the location information may include one or more 2D image locations (e.g., X-Y pixel location) in the captured image where the semantic or non-semantic feature / object is detected. Such image locations can correspond to the center, corners, etc. of the feature / object. In this scenario, to help the mapping server reconstruct the driving information and align the driving information from multiple collection vehicles, each collection vehicle can also provide the location (e.g., GPS location) where each image is captured to the server.

[0199] In other cases, the collection vehicle may provide one or more 3D real-world points associated with the detected object / feature to the server. Such 3D points may be relative to a pre-determined origin (such as the origin of the driving segment) and may be determined by any suitable technique. In some cases, structure-from-motion techniques may be used to determine the 3D real-world position of the detected object / feature. For example, a particular object such as a particular speed limit sign may be detected in two or more captured images. Using information such as the known ego-motion (speed, trajectory, GPS position, etc.) of the collection vehicle between the captured images, along with the observed changes (changes in X-Y pixel location, size, etc.) of the speed limit sign in the captured images, the real-world position of one or more points associated with the speed limit sign may be determined and transmitted to the mapping server. Such methods are optional as they require more computation on parts of the collection vehicle system. The sparse map of the disclosed embodiments may enable autonomous navigation of the vehicle using a relatively small amount of stored data. In some embodiments, the sparse map 800 may have a data density of less than 2MB per kilometer of road, less than 1MB per kilometer of road, less than 500 kB per kilometer of road, or less than 100 kB per kilometer of road (e.g., including data representing target trajectories, landmarks, and any other stored road features). In some embodiments, the data density of the sparse map 800 may be less than 10 kB per kilometer of road or even less than 2 kB per kilometer of road (e.g., 1.6 kB per kilometer), or not exceeding 10 kB per kilometer of road, or not exceeding 20 kB per kilometer of road. In some embodiments, most (if not all) roads in the United States may be autonomously navigated using a sparse map with a total of 4GB or less of data. These data density values may represent an average over the entire sparse map 800, on a local map within the sparse map 800, and / or on a particular road segment within the sparse map 800.

[0200] As noted, the sparse map 800 may include a representation of multiple target trajectories 810 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 previously traversed and reconstructed trajectories of a vehicle 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 expected driving path along the road in a first direction, and a second target trajectory may be stored to represent an expected driving path along the road in another direction (e.g., opposite the first direction). Additional target trajectories may be stored relative to a particular road segment. For example, on a multi-lane road, one or more target trajectories representing the expected driving paths of a vehicle in one or more lanes associated with the multi-lane road may be stored. In some embodiments, each lane of a multi-lane road may be associated with its own target trajectory. In other embodiments, there may be fewer stored target trajectories than there are lanes present on a multi-lane road. In such cases, a vehicle navigating on a multi-lane road may use any stored target trajectory to guide its navigation by considering the lane offset from the lane for which the target trajectory is stored (e.g., if a vehicle is traveling in the leftmost lane of a three-lane highway and a target trajectory is stored only for the middle lane of the highway, when generating navigation instructions, the vehicle may use the target trajectory of the middle lane for navigation by considering the lane offset between the middle lane and the leftmost lane).

[0201] In some embodiments, a target trajectory may represent an ideal path that a vehicle should take when driving. The target trajectory may be located, for example, at approximately the center of a driving lane. In other cases, the target trajectory may be located at other positions relative to the road segment. For example, the target trajectory may generally coincide with the center of the road, the edge of the road, or the edge of a lane, etc. In such cases, navigation based on the target trajectory may include determining an offset to maintain relative to the position of the target trajectory. Additionally, in some embodiments, the determined offset to maintain relative to the position of the target trajectory may vary based on the type of vehicle (e.g., a passenger vehicle including two axles may have an offset along at least a portion of the target trajectory that is different from that of a truck including more than two axles).

[0202] The sparse map 800 may also include data related to multiple pre-determined landmarks 820 associated with a particular road segment, local map, etc. As discussed in more detail below, these landmarks may be used for the navigation of an autonomous vehicle. For example, in some embodiments, a landmark may be used to determine the current position of a vehicle relative to a stored target trajectory. Using this position information, the autonomous vehicle may be able to adjust its heading direction to match the direction of the target trajectory at the determined position.

[0203] Multiple landmarks 820 can be identified and stored in the sparse map 800 at any suitable spacing. In some embodiments, the landmarks may be stored at a relatively high density (e.g., every few meters or more). However, in some embodiments, significantly larger landmark spacing values may be employed. For example, in the sparse map 800, the identified (or recognized) landmarks may be spaced apart by 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers. In certain cases, the identified landmarks may be located at distances even more than 2 kilometers apart.

[0204] Between the landmarks, and thus between the determinations of the vehicle's position relative to the target trajectory, the vehicle may navigate based on dead reckoning, where the vehicle uses sensors to determine its self-motion and estimate its position relative to the target trajectory. Since errors may accumulate during navigation by dead reckoning, over time, the determination of the position relative to the target trajectory may become increasingly inaccurate. The vehicle may use the landmarks (and their known positions) that appear in the sparse map 800 to remove the dead reckoning-induced errors in the position determination. In this way, the identified landmarks included in the sparse map 800 may act as navigation anchors from which the accurate position of the vehicle relative to the target trajectory can be determined. Since a certain amount of error in position localization is acceptable, the identified landmarks do not need to always be available to the autonomous vehicle. Instead, suitable navigation may even be based on landmark spacings of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or more as indicated above. In some embodiments, a density of 1 identified landmark per 1 km of road may be sufficient to maintain the longitudinal position determination accuracy within 1 m. Therefore, not every potential landmark that appears along a road segment needs to be stored in the sparse map 800.

[0205] In addition, in some embodiments, lane markings may be used for the localization of the vehicle during landmark spacing. By using lane markings during landmark spacing, the accumulation of errors during navigation by dead reckoning can be minimized.

[0206] In addition to the target trajectory and the identified landmarks, the sparse map 800 may also include information related to various other road features. For example, Fig.9A shows a representation of a curve along a specific road segment that can be stored in the sparse map 800. In some embodiments, a single lane of a road can be modeled by a three-dimensional polynomial description of the left and right sides of the road. Such polynomials representing the left and right sides of a single lane are shown in Fig.9A Regardless of how many lanes the road may have, the road can be represented using polynomials in a manner similar to that shown in Fig.9A For example, the left and right sides of a multi-lane road can be represented by polynomials similar to those shown in Fig.9Arepresented by polynomials such as those shown, and including intermediate lane markings on a multi-lane road (e.g., short dash-dot markings indicating lane boundaries, solid yellow lines indicating boundaries between lanes traveling in different directions, etc.) can also be represented using polynomials such as Fig.9A those shown.

[0207] As Fig.9A shown, lane 900 can be represented using polynomials (e.g., polynomials of first order, second order, third order, or any suitable order). For illustrative purposes, lane 900 is shown as a two-dimensional lane and the polynomials are shown as two-dimensional polynomials. As Fig.9A depicted, lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial can be used to represent the positioning of each side of a road or lane boundary. For example, each of the left side 910 and the right side 920 can be represented by a plurality of polynomials of any suitable length. In some cases, the polynomials can have a length of approximately 100 m, but other lengths greater than or less than 100 m can also be used. Additionally, the polynomials can overlap each other to facilitate seamless transitions when navigating based on subsequently encountered polynomials as the host vehicle travels along the road. For example, each of the left side 910 and the right side 920 can be represented by a plurality of third-order polynomials that are divided into segments of approximately 100-meter length (an example of a first predetermined range) and overlap each other by approximately 50 meters. The polynomials representing the left side 910 and the right side 920 may or may not have the same order. For example, in some embodiments, some polynomials can be second-order polynomials, some can be third-order polynomials, and some can be fourth-order polynomials.

[0208] In Fig.9A the example shown, the left side 910 of lane 900 is represented by two grouped third-order polynomials. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. Although the two groups are generally parallel to each other, they follow the positioning of the corresponding side of the road. The polynomial segments 911, 912, 913, 914, 915, and 916 have a length of approximately 100 meters and overlap the adjacent segments in the series by approximately 50 meters. However, as previously noted, polynomials of different lengths and different amounts of overlap can also be used. For example, the polynomials can have lengths of 500 m, 1 km, or longer, and the amount of overlap can vary from 0 m to 50 m, 50 m to 100 m, or greater than 100 m. Additionally, although Fig.9A shown as representing polynomials extending in a 2D space (e.g., on the surface of a piece of paper), it should be understood that these polynomials can represent curves extending in three dimensions (e.g., including a height component) to represent elevation changes of road segments in addition to X-Y curvature. In Fig.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.

[0209] Returning to the target trajectory of the sparse map 800, Fig. 9B a three-dimensional polynomial representing the target trajectory of a vehicle traveling along a specific road segment is shown. The target trajectory represents not only the X-Y path that the host vehicle should travel along the specific road segment, but also the elevation change that the host vehicle will experience as it travels along that road segment. Thus, each target trajectory in the sparse map 800 can be represented by one or more three-dimensional polynomials, such as Fig. 9B the three-dimensional polynomial 950 shown. The sparse map 800 can include a plurality of trajectories (e.g., millions or billions or more to represent the trajectories of vehicles along various road segments of roads throughout the world). In some embodiments, each target trajectory can correspond to a spline connecting three-dimensional polynomial segments.

[0210] 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, and each parameter requires four bytes of data. A suitable representation can be obtained with a cubic polynomial, which requires approximately 192 bytes of data per 100 m. For a host vehicle traveling at approximately 100 km / hr, this can be interpreted as a data usage / transmission requirement of approximately 200 kB per hour.

[0211] The sparse map 800 can use a combination of geometric feature descriptors and metadata to describe the lane network. The geometric features can be described by polynomials or splines as described above. The metadata can describe the number of lanes, special features (such as carpool lanes), and possibly other sparse labels. The total footprint of such indicators may be negligible.

[0212] Accordingly, a sparse map according to an embodiment of the present disclosure can include at least one line representation of a road surface feature extending along a road segment, each line representation representing a path along a road segment that substantially corresponds to the road surface feature. In some embodiments, as discussed above, the at least one line representation of the road surface feature can include a spline, a polynomial representation, or a curve. Additionally, in some embodiments, the road surface feature can include at least one of a road edge or a lane marking. Further, as discussed below regarding "crowdsourcing", the road surface feature can be identified by image analysis of a plurality of images acquired when one or more vehicles drive over the road segment.

[0213] As previously indicated, the sparse map 800 may include a plurality of pre - determined landmarks associated with road segments. Each landmark in the sparse map 800 can be represented and identified using less data than would be required to store the actual image. Instead of storing the actual image of the landmark and relying on, for example, image recognition analysis based on the captured image and the stored image, the data representing the landmark can still include sufficient information to describe or identify the landmark along the road. Storing data that describes the characteristics of the landmark rather than the actual image of the landmark can reduce the size of the sparse map 800.

[0214] Fig.10 An example of the types of landmarks that can be represented in the sparse map 800 is shown. A landmark can include any visible and recognizable object along a road segment. Landmarks can be selected such that they are fixed and do not change frequently with respect to their location and / or content. When a vehicle drives past a particular road segment, the landmarks included in the sparse map 800 can be useful in determining the vehicle 200's position relative to a target trajectory. Examples of landmarks can include traffic signs, direction signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., streetlight poles, reflectors, etc.), and any other suitable categories. In some embodiments, lane markings on the road can also be included as landmarks in the sparse map 800.

[0215] Fig.10 Examples of the landmarks shown include traffic signs, direction signs, roadside fixtures, and general signs. Traffic signs can 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), stop signs (e.g., stop sign 1020). Direction signs can include signs that include one or more arrows indicating one or more directions to different places. For example, a direction sign can include a highway sign 1025 having arrows for guiding a vehicle to different roads or places, an exit sign 1030 having an arrow for guiding a vehicle off the road, etc. Accordingly, at least one of the plurality of landmarks can include a road sign.

[0216] General signs can be unrelated to traffic. For example, general signs can include billboards for advertising or welcome signs adjacent to the boundary between two countries, states, counties, cities, or towns. Fig.10 A general sign 1040 (“Joe's Restaurant”) is shown. Although the general sign 1040 can have a rectangular shape, as Fig.10 shown, the general sign 1040 can have other shapes, such as square, circular, triangular, etc.

[0217] Landmarks may also include roadside fixtures. Roadside fixtures may be objects that are not signs and may not be related to traffic or direction. For example, roadside fixtures may include streetlight poles (e.g., streetlight pole 1035), utility poles, traffic light poles, etc.

[0218] Landmarks may also include beacons specifically designed for autonomous vehicle navigation systems. For example, such beacons may include free-standing structures placed at predetermined intervals to assist in navigating the host vehicle. Such beacons may also include visual / graphic information added to existing road signs (e.g., icons, symbols, barcodes, etc.) that can be recognized or identified by vehicles traveling along a road segment. Such beacons may also include electronic components. In such embodiments, electronic beacons (e.g., RFID tags, etc.) may be used to transmit non-visual information to the host vehicle. Such information may include, for example, landmark identification and / or landmark location information that the host vehicle can use to determine its position along a target trajectory.

[0219] In some embodiments, landmarks included in the sparse map 800 may be represented by data objects of a predetermined size. The data representing a landmark may include any suitable parameters for identifying a particular landmark. For example, in some embodiments, landmarks stored in the sparse map 800 may include parameters such as the physical size of the landmark (e.g., to support estimation of the distance to the landmark based on a known size / scale), the distance to a previous landmark, a lateral offset, a height, a type code (e.g., landmark type - what type of direction sign, traffic sign, etc.), GPS coordinates (e.g., to support global positioning), and any other suitable parameters. Each parameter may be associated with a data size. For example, 8 bytes of data may be used to store the landmark size. The distance to a previous landmark, the lateral offset, and the height may be specified using 12 bytes of data. The type code associated with a landmark such as a direction sign or traffic sign may require approximately 2 bytes of data. For a general sign, 50 bytes of data storage may be used to store image characteristics that can identify the general sign. The landmark GPS position may be associated with 16 bytes of data storage. These data sizes for each parameter are merely examples, and other data sizes may also be used. Representing landmarks in the sparse map 800 in this manner may provide a lean solution for efficiently representing landmarks in a database. In some embodiments, an object may be referred to as a standard semantic object or a non-standard semantic object. A standard semantic object may include any kind of object for which there is a standardized set of characteristics (e.g., speed limit signs, warning signs, direction signs, traffic lights, etc. having known dimensions or other characteristics). A non-standard semantic object may include any object not associated with a standardized set of characteristics (e.g., general advertising signs, signs identifying commercial establishments, potholes, trees, etc., which may have variable dimensions). Each non-standard semantic object may be represented using 38 bytes of data (e.g., 8 bytes of data for size, 12 bytes for the distance to a previous landmark, lateral offset, and height, 2 bytes for the type code, and 16 bytes for the position coordinates). Standard semantic objects may be represented using even less data, since the mapping server may not require size information to fully represent the objects in the sparse map.

[0220] The sparse map 800 can use a tagging system to represent landmark types. In some cases, each traffic sign or direction sign can be associated with its own tag, which is stored in a database as part of the landmark identification. For example, the database can include nearly 1000 different tags to represent various traffic signs and nearly about 10000 different tags to represent direction signs. Of course, any suitable number of tags can be used, and additional tags can be created as needed. In some embodiments, a generic sign can be represented using less than about 100 bytes (e.g., about 86 bytes, including 8 bytes for size; 12 bytes for distance to a previous landmark, lateral offset, and height; 50 bytes for image characteristics; and 16 bytes for GPS coordinates).

[0221] Thus, for semantic road signs that do not require image characteristics, even at a relatively high landmark density of about 1 per 50m, the data density impact on the sparse map 800 can be close to 760 bytes per kilometer (e.g., 20 landmarks per km x 38 bytes per landmark = 760 bytes). Even for generic signs that include image characteristic components, the data density impact is about 1.72 kB per km (e.g., 20 landmarks per km x 86 bytes per landmark = 1,720 bytes). For semantic road signs, this corresponds to a data usage of about 76 kB per hour for a vehicle traveling at 100 km / hr. For generic signs, this corresponds to about 170 kB per hour for a vehicle traveling at 100 km / hr. It should be noted that in some environments (e.g., urban environments), the density of detected objects available for inclusion in the sparse map can be much higher (possibly more than one per meter). 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 generic sign 1040) in the sparse map 800 can include compressed image characteristics or an image hash associated with the generally rectangular object (e.g., the compressed image characteristics 1045). The compressed image characteristics / image hash can be determined using any suitable image hashing algorithm and can be used, for example, to help identify a generic sign as a recognized landmark. Such compressed image characteristics (e.g., image information derived from the actual image data representing the object) can avoid the need to store the actual image of the object or the need for comparative image analysis of the actual image to identify the landmark.

[0222] Reference Fig.10, the sparse map 800 may include or store compressed image features 1045 associated with the general sign 1040, rather than the actual image of the general sign 1040. For example, after an image capture device (e.g., image capture devices 122, 124, or 126) captures an image of the general sign 1040, a processor (e.g., image processor 190 or any other processor that can process images loaded on the host vehicle or located remotely relative to the host vehicle) may perform image analysis to extract / create compressed image features 1045, which include unique features or patterns associated with the general sign 1040. In one embodiment, the compressed image features 1045 may include shapes, color patterns, brightness patterns, or any other features that can be extracted from the image of the general sign 1040 to describe the general sign 1040.

[0223] For example, in Fig.10 , the circles, triangles, and stars shown in the compressed image features 1045 may represent regions of different colors. The patterns represented by the circles, triangles, and stars may be stored in the sparse map 800, e.g., stored within 50 bytes designated to include image features. It is noted that the circles, triangles, and stars do not necessarily mean that such shapes are stored as part of the image features. Instead, these shapes conceptually represent distinguishable regions with discernible color differences, text regions, graphic shapes, or other variations of features that can be associated with a general sign. Such compressed image features can be used to identify landmarks in the form of general signs. For example, the compressed image features can be used to perform same and different analyses based on a comparison of the stored compressed image features with, e.g., image data captured using a camera mounted on an autonomous vehicle.

[0224] Accordingly, multiple landmarks can be identified through image analysis of multiple images obtained when one or more vehicles drive through a road segment. As explained below regarding "crowdsourcing", in some embodiments, the image analysis for identifying multiple landmarks may include accepting potential landmarks when the ratio of images in which a landmark appears to images in which it does not appear exceeds a threshold. Additionally, in some embodiments, the image analysis for identifying multiple landmarks may include rejecting potential landmarks when the ratio of images in which a landmark does not appear to images in which it appears exceeds a threshold.

[0225] Returning to the target trajectory that the host vehicle can use to navigate a particular road segment, Fig.11AShows polynomial representation trajectories captured during the process of establishing or maintaining a sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 can be determined based on two or more previously driven and reconstructed trajectories of the vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be an aggregation of two or more previously driven and reconstructed trajectories of the vehicle along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 can be an average of two or more previously driven and reconstructed trajectories of the vehicle along the same road segment. Other mathematical operations can also be used to construct the target trajectory along the road path based on the reconstructed trajectories collected from vehicles driving along the road segment.

[0226] As Fig.11A shown, the road segment 1100 can be traveled by multiple vehicles 200 at different times. Each vehicle 200 can collect data related to the path traveled 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, as well as other potential sources. Such data can be used to reconstruct the trajectory of the vehicle traveling along the road segment, and based on these reconstructed trajectories, the target trajectory (or target trajectories) can be determined for a particular road segment. Such a target trajectory can represent the preferred path of the host vehicle when the vehicle travels along the road segment (e.g., guided by an autonomous navigation system).

[0227] In Fig.11A the example shown, the first reconstructed trajectory 1101 can be determined based on data received from the first vehicle that traveled the road segment 1100 during the first time period (e.g., day 1), the second reconstructed trajectory 1102 can be obtained from the second vehicle that traveled the road segment 1100 during the second time period (e.g., day 2), and the third reconstructed trajectory 1103 can be obtained from the third vehicle that traveled the road segment 1100 during the third time period (e.g., day 3). Each of the trajectories 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 of the reconstructed trajectories can be assembled and loaded on the vehicle that traveled the road segment 1100.

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

[0229] At the mapping server, the server can receive the actual trajectories for a road segment from multiple collection vehicles that have traversed the specific road segment. To generate a target trajectory for each valid path (e.g., each lane, each driving direction, each path through an intersection, etc.) along the road segment, the received actual trajectories can be aligned. The alignment process can include using the detected objects / features identified along the road segment and the collected locations of those detected objects / features to relate the actual, collected trajectories to each other. Once aligned, an average or "best fit" target trajectory for each available lane can be determined based on the aggregated, related / aligned actual trajectories, etc.

[0230] Fig. 11B and Fig. 11C further illustrates the concept of a target trajectory associated with a road segment existing within the geographical region 1111. As Fig. 11BAs shown, the first road segment 1120 within the geographical region 1111 may include a multi-lane road that includes two lanes 1122 designated for vehicles to travel in a first direction and two additional lanes 1124 designated for vehicles to travel in a second direction opposite to the first direction. The lanes 1122 and the lanes 1124 may be separated by a double yellow line 1123. The geographical region 1111 may also include a branch road segment 1130 that intersects the road segment 1120. The road segment 1130 may include a two-lane road, with each lane designated for a different direction of travel. The geographical region 1111 may also include other road features, such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0231] As Fig. 11C shown, the sparse map 800 may include a local map 1140 that includes a road model for assisting the autonomous navigation of vehicles within the geographical region 1111. For example, the local map 1140 may include target trajectories for one or more lanes associated with the road segments 1120 and / or 1130 within the geographical region 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that an autonomous vehicle may access or rely on when driving through the lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that an autonomous vehicle may access or rely on when driving through the lane 1124. Further, the local map 1140 may include target trajectories 1145 and / or 1146 that an autonomous vehicle may access or rely on when driving through the road segment 1130. The target trajectory 1147 represents the preferred path that an autonomous vehicle should follow when transitioning from the lane 1120 (and specifically, relative to the target trajectory 1141 associated with the rightmost lane of the lane 1120) to the road segment 1130 (and specifically, relative to the target trajectory 1145 associated with the first side of the road segment 1130). Similarly, the target trajectory 1148 represents the preferred path that an autonomous vehicle should follow when transitioning from the road segment 1130 (and specifically, relative to the target trajectory 1146) to a portion of the road segment 1124 (and specifically, as shown, relative to the target trajectory 1143 associated with the left lane in the lane 1124).

[0232] The sparse map 800 may also include representations of other road-related features associated with the geographical area 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in the geographical area 1111. Such landmarks may include a first landmark 1150 associated with a stop line 1132, a second landmark 1152 associated with a stop sign 1134, a third landmark 1154 associated with a speed limit sign, and a fourth landmark 1156 associated with a hazard sign 1138. Such landmarks can be used, for example, to assist an autonomous vehicle in determining its current position relative to any of the shown target trajectories, such that the vehicle can adjust its heading to match the direction of the target trajectory at the determined location.

[0233] In some embodiments, the sparse map 800 may also include road characteristic curves. Such road characteristic curves may be associated with any distinguishable / measurable change in at least one parameter associated with the road. For example, in some cases, such curves may be associated with changes in road surface information, such as changes in the surface roughness of a particular road segment, changes in the road width above a particular road segment, changes in the distance between short dash-dotted lines drawn along a particular road segment, changes in the road curvature along a particular road segment, etc. Fig.11D An example of a road characteristic curve 1160 is shown. While the curve 1160 may represent any of the parameters mentioned above or other parameters, in one example, the curve 1160 may represent a measure of road surface roughness, as obtained, for example, by monitoring one or more sensors that provide an output indicative of the amount of suspension displacement of a vehicle as it travels along a particular road segment.

[0234] Alternatively or concurrently, the curve 1160 may represent a change in road width, as determined based on image data obtained via a camera mounted on a vehicle traveling along a particular road segment. For example, such a curve can be used to determine the specific location of an autonomous vehicle relative to a particular target trajectory. That is, as the autonomous vehicle travels along a road segment, it can measure a curve associated with one or more parameters associated with that road segment. If the measured curve can be correlated / matched with a pre-determined curve depicting the parameter change relative to the position along the road segment, the measured curve and the pre-determined curve can be used (e.g., by overlaying corresponding sections of the measured curve and the pre-determined curve) to determine the current position along the road segment and, thus, the current position relative to the target trajectory for the road segment.

[0235] In some embodiments, the sparse map 800 may include different trajectories based on different characteristics associated with the user of the autonomous vehicle, environmental conditions, and / or other driving-related parameters. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or profiles. The sparse map 800 including such different trajectories 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 the presence of 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 the fast-moving lanes, while other users may prefer to always stay in the position in the central lane.

[0236] Different trajectories may be generated based on different environmental conditions (such as day and night, snow, rain, fog, etc.) and included in the sparse map 800. The sparse map 800 generated based on such different environmental conditions may be provided to autonomous vehicles traveling in different environmental conditions. In some embodiments, a camera disposed on the autonomous vehicle may detect the environmental conditions and provide such information back to the server that generates and provides the sparse map. For example, the server may generate or update the already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. When the autonomous vehicle is traveling along the road, the update of the sparse map 800 based on the environmental conditions may be performed dynamically.

[0237] Other different driving-related parameters may also be used as a basis for generating different sparse maps and providing them to different autonomous vehicles. For example, when an autonomous vehicle is traveling at a high speed, the turns may be tighter. Trajectories associated with a specific lane rather than the road may be included in the sparse map 800 such that the autonomous vehicle may stay within a specific lane when the vehicle follows a specific trajectory. When an image captured by a camera mounted on the autonomous vehicle indicates that the vehicle has deviated from the lane (e.g., crossed the lane marking), an action may be triggered inside the vehicle to bring the vehicle back to the designated lane according to the specific trajectory.

[0238] Crowdsourcing sparse maps

[0239] The disclosed sparse maps can be effectively (and passively) generated through the power of crowdsourcing. For example, any private or commercial vehicle equipped with a camera (e.g., a simple low-resolution camera commonly included as an OEM device on today's vehicles) and a suitable image analysis processor can be used as a collection vehicle. No special equipment (e.g., high-resolution imaging and / or positioning systems) is required. Due to the disclosed crowdsourcing technology, the generated sparse maps can be extremely accurate and can include extremely fine location information (achieving a navigation error limit of 10 cm or less) without the need for any specialized imaging or sensing equipment as input to the map generation process. Crowdsourcing also enables faster (and cheaper) updates to the generated maps, as new driving information is continuously available to the map-drawing server system from any road that a private or commercial vehicle minimally equipped to also act as a collection vehicle drives on. No designated vehicles equipped with high-resolution imaging and mapping sensors are required. Thus, the costs associated with establishing such specialized vehicles can be avoided. Further, updates to the currently disclosed sparse maps can be much faster than systems that rely on dedicated, specialized mapping vehicles (which are typically limited in number far below the number of private or commercial vehicles already available for the disclosed collection techniques due to their cost and specialized equipment).

[0240] The disclosed sparse maps generated through crowdsourcing can be extremely accurate because they can be generated based on many inputs from multiple (tens, hundreds, millions, etc.) collection vehicles that have collected driving information along a particular road segment. For example, each collection vehicle driving along a particular road segment can record its actual trajectory and can determine position information relative to detected objects / features along the road segment. This information is passed from the multiple collection vehicles to the server. The actual trajectories are aggregated to generate a refined target trajectory for each valid driving path along the road segment. Additionally, the position information collected from multiple collection vehicles for each detected object / feature (semantic or non-semantic) along the road segment can also be aggregated. Thus, the mapped position of each detected object / feature can constitute an average of hundreds, thousands, or millions of individually determined positions for each detected object / feature. Such techniques can produce extremely accurate mapped positions for detected objects / features.

[0241] In some embodiments, the disclosed systems and methods may generate a sparse map for autonomous vehicle navigation. For example, the disclosed systems and methods may use crowdsourced data for generating the sparse map, which may be used by one or more autonomous vehicles 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 such data is used to generate and / or update a road model, including sparse map tiles. The model or any of its sparse map tiles may then be transmitted to vehicles traveling along the road segment at a later time or other vehicles for assisting autonomous vehicle navigation. The road model may include a plurality of target trajectories representing preferred trajectories that an autonomous vehicle should follow when traversing the road segment. The target trajectories may be the same as the reconstructed actual trajectories collected from vehicles traversing the road segment, which may be transmitted from the vehicles to a server. In some embodiments, the target trajectories may be different from the actual trajectories taken by one or more vehicles previously when traversing the road segment. The target trajectories may be generated based on the actual trajectories (e.g., by averaging or any other suitable operation).

[0242] Vehicle trajectory data that a vehicle may upload to a server may correspond to or may correspond to a recommended trajectory for the vehicle, which may be based on or related to the vehicle's actual reconstructed trajectory but may be different 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.

[0243] In addition to trajectory information, other information that may be used in establishing the sparse data map 800 may include information related to potential landmark candidates. For example, through crowdsourcing of information, the disclosed systems and methods may identify potential landmarks in the environment and refine landmark locations. Landmarks may be used by the navigation system of an autonomous vehicle to determine and / or adjust the vehicle's position along a target trajectory.

[0244] The reconstructed trajectory that a vehicle may generate while the vehicle is traveling along a road may be obtained by any suitable method. In some embodiments, the reconstructed trajectory may be developed by stitching together segments of the vehicle's motion using, for example, ego-motion estimation (e.g., three-dimensional translation and three-dimensional rotation of a camera and thus the vehicle's body). The rotation and translation estimation may be determined based on an analysis of images captured by one or more image capture devices together with information from other sensors or devices (such as inertial sensors and speed sensors). For example, the inertial sensor may include an accelerometer or other suitable sensors configured to measure changes in the translation and / or rotation of the vehicle's body. The vehicle may include a speed sensor that measures the speed of the vehicle.

[0245] In some embodiments, the self-motion of the camera (and thus the vehicle body) can be estimated based on an optical flow analysis of the captured images. The optical flow analysis of the image sequence identifies the movement of pixels from the image sequence and determines the movement of the vehicle based on the identified movement. The self-motion can be integrated over time and along a road segment to reconstruct the trajectory associated with the road segment that the vehicle has followed.

[0246] Data (e.g., reconstructed trajectories) collected by multiple vehicles during multiple drives along a road segment at different times can be used to construct a road model (e.g., including target trajectories, etc.) included in the sparse data map 800. The data collected by multiple vehicles during multiple drives along a road segment at different times can also be averaged to improve the accuracy of the model. In some embodiments, data regarding road geometric features and / or landmarks can be received from multiple vehicles traveling through a common road segment at different times. Such data received from different vehicles can be combined to generate and / or update a road model.

[0247] The geometric features of the reconstructed trajectory (and also the 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 from the analysis of a video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a localization located a few meters in front of the current position of the vehicle is identified in each frame or image. This localization is the position that the vehicle is expected to travel to within a predetermined time period. This operation can be repeated frame by frame, and at the same time the vehicle can calculate the self-motion (rotation and translation) of the camera. At each frame or image, a short-range model for the desired path is generated by the vehicle in the 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. Then the three-dimensional model of the road can be fitted by a spline, which can include or connect polynomials of one or more appropriate orders.

[0248] To derive the short-range road model for each frame, one or more detection modules can be used. For example, a bottom-up lane detection module can be used. The bottom-up lane detection module can be useful when lane markings are drawn on the road. This module can look for edges in the image and assemble them together to form lane markings. A second module can be used in conjunction with the bottom-up lane detection module. The second module is an end-to-end deep neural network that can be trained to predict the correct short-range path 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.

[0249] Although the reconstructed trajectory modeling method may introduce the accumulation of errors due to the integration of self-motion over a long time period, which may include noise components, such errors may be insignificant because the generated model can provide sufficient accuracy for navigation at the local scale. In addition, the integrated errors may be eliminated by using external information sources such as satellite images or geodetic results. For example, the disclosed systems and methods may use a GNSS receiver to eliminate the accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed systems and methods can implement steering applications that are weakly dependent on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be restricted. For example, in some embodiments, the disclosed system may use GNSS signals only for database indexing purposes.

[0250] In some embodiments, the distance scale (e.g., local scale) associated with the autonomous vehicle navigation steering application can be approximately 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances can be used because the geometric road model is mainly used for two purposes: planning the front trajectory and positioning 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 (or any other time, such as 1.5 seconds, 1.7 seconds, 2 seconds, etc.) ahead, the planning task may use a model within a typical range of 40 meters ahead (or any other suitable distance ahead, such as 20 meters, 30 meters, 50 meters). According to a method called "tail alignment" described in more detail in another section, the positioning task uses the road model within a typical range of 60 meters behind the sedan (or any other suitable distance, such as 50 meters, 100 meters, 150 meters, etc.). The disclosed systems and methods can generate a geometric model with sufficient accuracy within a specific range (such as 100 meters) such that the planned trajectory will not deviate from the lane center by more than, for example, 30 cm.

[0251] As explained above, the three-dimensional road model can be constructed by detecting short-range road segments and stitching them together. The stitching can be achieved by calculating a six-degree-of-freedom self-motion model using the video and / or images captured by the camera, the data from the inertial sensors reflecting the motion of the vehicle, and the host vehicle speed signal. The accumulated errors may be small enough at certain local range scales (such as approximately 100 meters). All of this can be done during a single drive on a specific road segment.

[0252] In some embodiments, multiple drives can be used to average the resulting models and further to improve their accuracy. The same car may drive the same route multiple times, or multiple cars may send the model data they collect to a central server. In either case, a matching process can be performed to identify overlapping models and achieve averaging in order to generate a target trajectory. Once the convergence criteria are met, the constructed model (e.g., including the target trajectory) can be used for steering. Subsequent drives can be used for further model improvement and to adapt to infrastructure changes.

[0253] If multiple cars are connected to a central server, it becomes feasible to share driving experiences (such as sensed data) among the multiple cars. Each vehicle client can store a partial copy of a general road model, which may be relevant to its current location. A two-way 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 systems and methods to perform two-way updates using a very small bandwidth.

[0254] 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 including 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 a previous landmark, the lateral position of the landmark (e.g., the position of the landmark relative to the driving lane), the GPS coordinates of the landmark, the type of the landmark, the identification of the text on the landmark, etc. For example, a vehicle can analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

[0255] A vehicle may determine a distance from the vehicle to a landmark or a location associated with the landmark (e.g., any semantic or non-semantic object or feature along a road segment) based on an analysis of one or more images. In some embodiments, the distance may be determined based on an analysis of an image of the landmark using suitable image analysis methods such as a scaling method and / or an optical flow method. As previously indicated, the location of the object / feature may include the 2D image location of one or more points associated with the object / feature (e.g., the X-Y pixel location in one or more captured images), or may include the 3D real-world location of one or more points (e.g., determined by techniques such as structure from motion / optical flow, lidar or radar information, etc.). In some embodiments, the disclosed systems and methods may be configured to determine the type or classification of potential landmarks. In the case where a vehicle determines that a certain potential landmark corresponds to a predetermined type or classification stored in the sparse map, it may be sufficient for the vehicle to transmit an indication of the type or classification of the landmark along with the localization of the landmark to the server. The server may store such indications. At a later time, during navigation, the navigating vehicle may capture an image including a representation of the landmark, process the image (e.g., using a classifier), and compare the resulting landmark in order to confirm the detection of the mapped landmark and in order to localize the navigating vehicle relative to the sparse map using the mapped landmark.

[0256] In some embodiments, multiple autonomous vehicles traveling on a road segment may communicate with a server. A vehicle (or client) may generate a curve describing its driving in any coordinate system (e.g., by integrating self-motion). The vehicle may detect landmarks and localize them in the same frame. The vehicle may upload the curve and the landmarks to the server. The server may collect data from the vehicles through multiple drives and generate a unified road model. For example, as discussed below with respect to Fig.19 what is discussed, the server may use the uploaded curves and landmarks to generate a sparse map with a unified road model.

[0257] The server may also distribute the model to the clients (e.g., vehicles). For example, the server may distribute the sparse map to one or more vehicles. When new data is received from a vehicle, the server may update the model continuously or periodically. For example, the server may process the new data to evaluate whether the data includes information that should trigger an update or creation of new data on the server. The server may distribute the updated model or the update to the vehicles for use in providing autonomous vehicle navigation.

[0258] 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, when the new data indicates that a previously identified landmark at a specific location no longer exists or has been replaced by another landmark, the server can determine that the new data should trigger an update to the model. As another example, when the new data indicates that a road segment has been closed and this is confirmed by data received from other vehicles, the server can determine that the new data should trigger an update to the model.

[0259] The server can distribute the updated model (or the updated portion of the model) to one or more vehicles traveling on a road segment associated with the update to the model. The server can also distribute the updated model to vehicles that are about to travel on that road segment or whose planned itinerary includes a road segment associated with the update to the model. For example, when an autonomous vehicle is traveling along another road segment before reaching a road segment associated with an update, the server can distribute the update or the updated model to the autonomous vehicle before it reaches that road segment.

[0260] In some embodiments, a remote server can collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a common 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 road map and the most likely path for each node or intersection of the road segment. For example, the remote server can align the trajectories to generate a crowdsourced sparse map from the collected trajectories.

[0261] The server can average landmark properties received from multiple vehicles traveling along a common road segment (such as the distance between one landmark and 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 for each client vehicle along the path. The server can average the physical dimensions of landmarks measured by multiple vehicles traveling along a common road segment and identifying the same landmark. The averaged physical dimensions can be used to support distance estimation, such as the distance from a vehicle to a landmark. The server can average the lateral position of landmarks (e.g., the position of the landmark from the lane in which the vehicle is traveling) measured by multiple vehicles traveling along a common road segment and identifying the same landmark. The averaged lateral portion can be used to support lane assignment. The server can average the GPS coordinates of landmarks measured by multiple vehicles traveling along the same road segment and identifying the same landmark. The averaged GPS coordinates of the landmark can be used to support the global localization or positioning of the landmark in the road model.

[0262] In some embodiments, the server may identify model changes based on data received from the vehicle, such as construction, detours, new signs, removal of signs, etc. The server may update the model continuously or periodically or immediately when new data is received from the vehicle. The server may distribute the updates to the model or the updated model to the vehicle for providing autonomous navigation. For example, as further discussed below, the server may use crowdsourced data to filter out "phantom" landmarks detected by the vehicle.

[0263] In some embodiments, the server may analyze driver interventions during autonomous driving. The server may analyze data received from the vehicle at the time and location when the intervention occurred and / or data received before the intervention occurred. The server may identify certain portions of the data that caused or are closely related to the intervention, such as data indicating a temporary lane closure setting, data indicating a pedestrian in the road. The server may update the model based on the identified data. For example, the server may modify one or more trajectories stored in the model.

[0264] Fig.12 Schematic illustration of a system for using crowdsourcing to generate a sparse map (and for distributing and navigating using the crowdsourced sparse map). Fig.12 A road segment 1200 including one or more lanes is shown. 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 shown as being on the road segment 1200 at the same time in Fig.12 ). At least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. For simplicity of this example, all vehicles 1205, 1210, 1215, 1220, and 1225 are assumed to be autonomous vehicles.

[0265] Each vehicle may be similar to the vehicles disclosed in other embodiments (e.g., vehicle 200), and may include components or devices included in or associated with the 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.) through a wireless communication path 1235 indicated by dashed lines. Each vehicle may transmit data to the server 1230 and receive data from the server 1230. For example, the server 1230 may collect data from multiple vehicles traveling on a road segment 1200 at different times, and may process the collected data to generate an autonomous vehicle road navigation model or an update to the model. The server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to the vehicles that transmitted data to the server 1230. The server 1230 may transmit the autonomous vehicle road navigation model or an update to the model to other vehicles traveling on the road segment 1200 at a later time.

[0266] When vehicles 1205, 1210, 1215, 1220, and 1225 are traveling on the road segment 1200, the navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 may be transmitted to the server 1230. In some embodiments, the navigation information may be associated with the common road segment 1200. The navigation information may include the trajectories associated with each of vehicles 1205, 1210, 1215, 1220, and 1225 when each vehicle is traveling on the road segment 1200. In some embodiments, the trajectories may be reconstructed based on data sensed by various sensors and devices provided on vehicle 1205. For example, the trajectories may be reconstructed based on at least one of accelerometer data, speed data, landmark data, road geometric feature or profile data, vehicle positioning data, and ego-motion data. In some embodiments, the trajectories may be reconstructed based on data from inertial sensors such as accelerometers and the rate of vehicle 1205 sensed by a speed sensor. Additionally, in some embodiments, the trajectories may be determined based on the sensed ego-motion of the camera (e.g., by a processor loaded on each of vehicles 1205, 1210, 1215, 1220, and 1225), which may indicate three-dimensional translation and / or three-dimensional rotation (or rotational motion). The ego-motion of the camera (and thus the vehicle body) may be determined from the analysis of one or more images captured by the camera.

[0267] In some embodiments, the trajectory of vehicle 1205 can be determined by a processor configured to be loaded on the vehicle 1205 and transmitted to server 1230. In other embodiments, server 1230 can receive data sensed by various sensors and devices disposed in vehicle 1205 and determine the trajectory based on the data received from vehicle 1205.

[0268] In some embodiments, the navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to server 1230 can include data regarding road surface, road geometric features, or road profile. The geometric features of road segment 1200 can include lane structure and / or landmarks. The lane structure can include the total number of lanes of road segment 1200, the type of lanes (e.g., one-way lanes, two-way lanes, driving lanes, passing lanes, etc.), the markings on the lanes, the width of the lanes, etc. In some embodiments, the navigation information can include lane assignment, e.g., which lane among multiple lanes the vehicle is traveling in. For example, the lane assignment can be associated with the numerical value “3,” which indicates that the vehicle is traveling in the third lane from the left or right. As another example, the lane assignment can be associated with the text value “center lane” indicating that the vehicle is traveling in the center lane.

[0269] Server 1230 can store the navigation information on a non-transitory computer-readable medium (such as a hard disk drive, optical disk, magnetic tape, memory, etc.). Server 1230 can generate (e.g., by a processor included in server 1230) at least a portion of an autonomous vehicle road navigation model for common road segment 1200 based on the navigation information received from multiple vehicles 1205, 1210, 1215, 1220, and 1225 and can store the model as part of a sparse map. Server 1230 can determine the trajectories associated with each lane based on the crowdsourced data (e.g., navigation information) received from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling in the lanes of the road segment at different times. Server 1230 can generate an autonomous vehicle road navigation model or a portion of the model (e.g., an updated portion) based on the multiple trajectories determined based on the crowdsourced navigation data. Server 1230 can transmit the model or the 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 vehicle traveling on the road segment at a later time for 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 an autonomous vehicle when autonomously navigating along common road segment 1200.

[0270] As explained above, an autonomous vehicle road navigation model may be included in a sparse map (e.g., the sparse map 800 depicted in Figure 8 ). The sparse map 800 may include sparse records of data related to road geometric features and / or landmarks along the road, and the sparse records may provide sufficient information for guiding the autonomous navigation of an autonomous vehicle without requiring excessive data storage. In some embodiments, the autonomous vehicle road navigation model may be stored separately from the sparse map 800 and may use map data from the sparse map 800 when the model is executed for navigation. In some embodiments, the autonomous vehicle road navigation model may use map data included in the sparse map 800 to determine a target trajectory along a road segment 1200 for guiding the autonomous navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225 or other vehicles that will travel along the road segment 1200 at a later time. For example, when the autonomous vehicle road navigation model is executed by a processor included in the navigation system of vehicle 1205, the model may cause the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a pre-determined trajectory included in the sparse map 800 to verify and / or correct the current driving route of vehicle 1205.

[0271] In the autonomous vehicle road navigation model, the geometric features of road features or target trajectories may be encoded by curves in three-dimensional space. In one embodiment, the curve may be a three-dimensional spline that includes one or more connected three-dimensional polynomials. As will be understood by those skilled in the art, a spline may be a numerical function defined piecewise by a series of polynomials used to fit data. The splines used to fit the three-dimensional geometric feature data of a road may include linear splines (first order), quadratic splines (second order), cubic splines (third order), or any other splines (other orders), or combinations thereof. The splines may include one or more three-dimensional polynomials of different orders that connect (e.g., fit) data points of the three-dimensional geometric feature data of the road. In some embodiments, the autonomous vehicle road navigation model may include three-dimensional splines corresponding to target trajectories along a common road segment (e.g., road segment 1200) or lanes of the road segment 1200.

[0272] As explained above, an autonomous vehicle road navigation model included in a sparse map may include other information, such as an identification of at least one landmark along a road segment 1200. The landmark may be visible within the field of view of cameras (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 (e.g., processor 180, 190, or processing unit 110) disposed on vehicle 1205 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. The landmark identification information may require much less storage space than the actual image. Other sensors or systems (e.g., a GPS system) may also provide certain identification information (e.g., the location of the landmark) of the landmark. The landmark may include at least one of a traffic sign, an arrow marking, a lane marking, a dashed lane marking, a traffic light, a stop line, a direction sign (e.g., a highway exit sign having an arrow indicating a direction, a highway sign having arrows pointing to different directions or places), a landmark beacon, or a street light pole. A landmark beacon refers to a device (e.g., an RFID device) installed along a road segment that transmits or reflects a signal to a receiver mounted on a vehicle such 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 GPS location of the device) may be used as a landmark to be included in the autonomous vehicle road navigation model and / or sparse map 800.

[0273] 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 measurement results obtained using sensor systems (e.g., a global positioning system, an inertia-based positioning system, a landmark beacon, 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 measurement results 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 measurement result data to server 1230, which may average the position measurement results and use the averaged position measurement results as the location of the landmark. The location of the landmark may be continuously refined by measurement results received from vehicles during subsequent drives.

[0274] The identification of a landmark may include the size of the landmark. A processor disposed in a vehicle (e.g., 1205) may estimate the physical size of the landmark based on the analysis of an image. The server 1230 may receive multiple estimates of the physical size of the same landmark from different vehicles driven differently. The server 1230 may average the different estimates to arrive at the physical size for 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 the extended scale based on 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 the distance of the landmark in the image from t1 to t2. dt represents (t2 - t1). For example, the distance to the landmark may be estimated by Z = V * dt * R / D, where V is the speed of the vehicle, R is the distance between the landmark and the extended focus in the image, dt is the time interval, and D is the image displacement amount of the landmark along the epipolar line. Other equations equivalent to the above equation, such as Z = V * ω / Δω, may be used to estimate the distance to the landmark. Here, V is the vehicle speed, ω is the image length (such as the object width), and Δω is the change in the image length per unit time.

[0275] When the physical size of the landmark is known, the distance to the landmark may also be determined based on the following equation: Z = f * W / ω, where f is the focal length, W is the size of the landmark (e.g., height or width), and ω is the number of pixels when the landmark leaves the image. According to the above equation, the change in the distance Z can be calculated using ΔZ = f * W * Δω / ω2 + f * ΔW / ω, 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 at the server side. The error of the resulting distance estimate may be very small. There are two sources of error that may occur when using the above formula, namely ΔW and Δω. Their contribution to the distance error is given by ΔZ = f * W * Δω / ω2 + f * ΔW / ω. However, ΔW decays to zero by averaging; thus ΔZ is determined by Δω (e.g., the inaccuracy of the bounding box in the image).

[0276] For a landmark of unknown size, the distance to the landmark may be estimated by tracking feature points on the landmark between consecutive frames. For example, certain features appearing on a speed limit sign may be tracked between two or more image frames. Based on these tracked features, a distance distribution for each feature point may be generated. The distance estimate may be extracted from the distance distribution. For example, the most frequently occurring distance in the distance distribution may be used as the distance estimate. As another example, the average value of the distance distribution may be used as the distance estimate.

[0277] Fig.13 An exemplary autonomous vehicle road navigation model represented by a plurality of three-dimensional splines 1301, 1302, and 1303 is shown. Fig.13 The curves 1301, 1302, and 1303 shown are for illustrative purposes only. Each spline may include one or more three-dimensional polynomials that connect a plurality of data points 1310. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or a combination of any suitable polynomials of different orders. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to landmarks (e.g., size, location, and identification information of the landmarks) and / or road characteristic curves (e.g., road geometric features, road roughness curves, road curvature curves, road width curves). In some embodiments, some data points 1310 may be associated with data related to landmarks, and other data points may be associated with data related to road characteristic curves.

[0278] Fig.14 Raw positioning data 1410 (e.g., GPS data) received from five separate drives is shown. A drive may be separated from another drive if one drive is made by a separate vehicle at the same time, by the same vehicle at a separate time, or by a separate vehicle at a separate time. To account for errors in the positioning data 1410 and to account for different positions of vehicles within the same lane (e.g., one vehicle may drive closer to the left side of the lane than another vehicle), the server 1230 may use one or more statistical techniques to generate a map skeleton 1420 to determine whether changes in the raw positioning data 1410 represent actual deviations or statistical errors. Each path within the skeleton 1420 may be linked back to the raw data 1410 that formed that path. For example, the path between A and B within the skeleton 1420 is linked to the raw data 1410 from drives 2, 3, 4, and 5 but not from drive 1. The skeleton 1420 may not be detailed enough to be used to navigate a vehicle (e.g., because, unlike the splines described above, it combines drives from multiple lanes on the same road), but may provide useful topological information and may be used to define intersections.

[0279] Fig.15 An example of generating additional details for a sparse map within a segment of the map skeleton (e.g., segment A to B within the skeleton 1420) is shown. As Fig.15As depicted, data (e.g., ego - motion data, road - sign data, etc.) can be shown as a function of the position S (or S1 or S2) along the drive. Server 1230 can identify landmarks for a sparse map by identifying unique matches between landmarks 1501, 1503, and 1505 of drive 1510 and landmarks 1507 and 1509 of drive 1520. Such matching algorithms can result in 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 or in combination with unique matching. Server 1230 can longitudinally align the drives to align the matched landmarks. For example, server 1230 can select one drive (e.g., drive 1520) as a reference drive and then transform and / or elastically stretch the other drives (e.g., drive 1510) for alignment.

[0280] Fig.16 An example of aligned landmark data for use in a sparse map is shown. In Fig.16 the example, landmark 1610 includes a road sign. Fig.16 The example further depicts data from multiple drives 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In Fig.16 the example, the data from drive 1613 consists of "ghost" landmarks, and server 1230 can identify such landmarks because none of drives 1601, 1603, 1605, 1607, 1609, and 1611 include the identification of a landmark in the vicinity of the identified landmark in drive 1613. Accordingly, server 1230 can accept potential landmarks when the ratio of images where a landmark appears to images where a landmark does not appear exceeds a threshold, and / or can reject potential landmarks when the ratio of images where a landmark does not appear to images where a landmark appears exceeds a threshold.

[0281] Fig.17 A system 1700 for generating drive data that can be used for crowdsourcing a sparse map is depicted. As Fig.17 depicted, system 1700 can include a camera 1701 and a positioning device 1703 (e.g., a GPS locator). Camera 1701 and positioning device 1703 can be mounted on a vehicle (e.g., one of vehicles 1205, 1210, 1215, 1220, and 1225). Camera 1701 can generate multiple types of data, e.g., ego - motion data, traffic - sign data, road data, etc. The camera data and positioning data can be segmented into drive segments 1705. For example, each drive segment 1705 can have camera data and positioning data from a drive of less than 1 km.

[0282] In some embodiments, system 1700 can remove redundancy in the driving segment 1705. For example, if a landmark appears in multiple images from camera 1701, system 1700 can remove the redundant data such that the driving segment 1705 contains only one copy of the location of the landmark and any metadata associated with the landmark. By way of additional example, if a lane marking appears in multiple images from camera 1701, system 1700 can remove the redundant data such that the driving segment 1705 contains only one copy of the location of the lane marking and any metadata associated with the lane marking.

[0283] System 1700 also includes a server (e.g., server 1230). Server 1230 can receive the driving segment 1705 from the vehicle and reassemble the driving segment 1705 into a single drive 1707. Such an arrangement can allow for reduced bandwidth requirements when transmitting data between the vehicle and the server, while also allowing the server to store data related to an entire drive.

[0284] Fig.18 System 1700 is further configured for crowdsourcing a sparse map Fig.17 of. As shown in Fig.17 , system 1700 includes a vehicle 1810 and a positioning device (e.g., a GPS locator), and the vehicle uses, for example, a camera (which generates, for example, ego-motion data, traffic sign data, road data, etc.) to capture driving data. As shown in Fig.17 , vehicle 1810 splits the collected data into driving segments (depicted as "DS1 1", "DS2 1", "DSN 1" in Fig.18 ). Server 1230 then receives the driving segments and reconstructs the drive from the received segments (depicted as "Drive 1" in Fig.18 ).

[0285] As further depicted in Fig.18 , 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 splits the collected data into driving segments (depicted as "DS1 2", "DS2 2", "DSN 2" in Fig.18 ). Server 1230 then receives the driving segments and reconstructs the drive from the received segments (depicted as "Drive 2" in Fig.18 ). Any number of additional vehicles can be used. For example, Fig.18 also includes "Sedan N", which captures driving data, splits it into driving segments (depicted in Fig.18Depicted as “DS1 N”, “DS2 N”, “DSN N”) and send it to server 1230 for reconstruction for driving (at Fig.18 depicted as “Driving N”).

[0286] As Fig.18 depicted, server 1230 may use the reconstructed drives (e.g., “Drive 1”, “Drive 2”, and “Drive N”) collected from multiple vehicles (e.g., “Sedan 1” (also labeled as vehicle 1810), “Sedan 2” (also labeled as vehicle 1820), and “Sedan N”) to construct a sparse map (depicted as “Map”).

[0287] Fig.19 Flowchart showing an exemplary process 1900 for generating a sparse map for autonomous vehicle navigation along a road segment. Process 1900 may be performed by one or more processing devices included in server 1230.

[0288] Process 1900 may include receiving a plurality of images acquired when one or more vehicles drive over a road segment (step 1905). Server 1230 may receive images from a camera included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, when vehicle 1205 drives along road segment 1200, camera 122 may capture one or more images of the environment around vehicle 1205. In some embodiments, server 1230 may also receive reduced image data that has been made redundant-free by a processor on vehicle 1205, as discussed above with respect to Fig.17 discussed.

[0289] 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 images received from camera 122 to identify road edges or lane markings and determine the driving trajectory along road segment 1200 associated with the road edges or lane markings. In some embodiments, the trajectory (or line representation) may include a spline, polynomial representation, or curve. Server 1230 may determine the driving trajectory of vehicle 1205 based on the camera ego-motion (e.g., three-dimensional translation and / or three-dimensional rotational motion) received in step 1905.

[0290] Process 1900 may also include identifying a plurality of landmarks associated with a road segment based on a plurality of images (step 1910). For example, server 1230 may analyze environmental images received from camera 122 to identify one or more landmarks, such as road signs along road segment 1200. Server 1230 may use the analysis of a plurality of images acquired as one or more vehicles travel along the road segment to identify the landmarks. To enable crowdsourcing, the analysis may include rules regarding accepting and rejecting potential 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 appears exceeds a threshold.

[0291] 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 the road segment, and process 1900 may include clustering, by server 1230, vehicle trajectories associated with a plurality of vehicles traveling on the road segment and determining the target trajectory based on the clustered vehicle trajectories, as discussed in further detail below. Clustering the vehicle trajectories may include clustering, by server 1230, a plurality of trajectories associated with vehicles traveling on the road segment into a plurality of clusters based on at least one of the absolute heading of the vehicle or the lane assignment of the vehicle. Generating the target trajectory may include averaging, by server 1230, the clustered trajectories. By way of additional 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.

[0292] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates instead of global coordinates. For autonomous driving, some systems may present data in world coordinates. For example, longitude and latitude coordinates on the earth's surface may be used. To use a map for steering, the host vehicle may determine its position and orientation relative to the map. It may seem natural to use an on-vehicle GPS device to locate the vehicle on the map and to find the 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 may be expressed in the body reference frame and the steering command may be calculated or generated.

[0293] The disclosed systems and methods enable autonomous vehicle navigation (e.g., steering control) with a low footprint model that can be collected by the autonomous vehicle itself without the aid of expensive survey equipment. To support autonomous navigation (e.g., steering applications), the road model can include a sparse map that has geometric features of the road, the lane structure of the road, and landmarks that can be used to determine the positioning or location of the vehicle along a trajectory included in the model. As discussed above, the generation of the sparse map can be performed by a remote server that communicates with vehicles traveling on the road and receives data from the vehicles. The data can include sensed data, trajectories reconstructed based on the sensed data, and / or recommended trajectories that can represent modified reconstructed trajectories. As discussed below, the server can transmit the model back to the vehicle or other vehicles traveling on the road later to assist with autonomous navigation.

[0294] Fig. 20 A block diagram of server 1230 is shown. Server 1230 can include a communication unit 2005 that can include both hardware components (e.g., communication control circuits, switches, and antennas) and software components (e.g., communication protocols, computer code). For example, communication unit 2005 can include at least one network interface. Server 1230 can communicate with vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. For example, server 1230 can receive navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 via communication unit 2005. Server 1230 can distribute an autonomous vehicle road navigation model to one or more autonomous vehicles via communication unit 2005.

[0295] Server 1230 can include at least one non-transitory storage medium 2010, such as a hard disk drive, optical disk, magnetic tape, etc. Storage device 1410 can be configured to store data, such as navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and / or an autonomous vehicle road navigation model generated by server 1230 based on the navigation information. Storage device 2010 can be configured to store any other information, such as a sparse map (e.g., sparse map 800 discussed above with respect to Figure 8 discussion).

[0296] In addition to or instead of the storage device 2010, the server 1230 may include a memory 2015. The memory 2015 may be similar to or different from the memories 140 or 150. The memory 2015 may be a non-transitory memory, such as a flash memory, a random access memory, etc. The memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., the processor 2020), map data (e.g., data of the sparse map 800), an autonomous vehicle road navigation model, and / or navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225.

[0297] The server 1230 may include at least one processing device 2020 configured to execute computer code or instructions stored in the memory 2015 for various functions. For example, the processing device 2020 may analyze navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225 and generate an autonomous vehicle road navigation model based on the analysis. The processing device 2020 may control the communication unit 1405 to distribute the autonomous vehicle road navigation model to one or more autonomous vehicles (e.g., one or more of the vehicles 1205, 1210, 1215, 1220, and 1225 or any vehicle traveling on the road segment 1200 at a later time). The processing device 2020 may be similar to or different from the processors 180, 190, or the processing unit 110.

[0298] Fig.21 A block diagram of the memory 2015 is shown, which may store computer code or instructions for performing one or more operations for generating a road navigation model for use in autonomous vehicle navigation. As Fig.21 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 distribution module 2110. The processor 2020 may execute instructions stored in any of the modules 2105 and 2110 included in the memory 2015.

[0299] The model generation module 2105 may store instructions that, when executed by the processor 2020, may generate at least a portion of an autonomous vehicle road navigation model for a common road segment (e.g., road segment 1200) based on navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. For example, when generating the autonomous vehicle road navigation model, the processor 2020 may cluster vehicle trajectories along the common road segment 1200 into different clusters. The processor 2020 may determine a target trajectory along the common road segment 1200 based on the clustered vehicle trajectories for each of the different clusters. Such operations may include finding the mean or average trajectory of the clustered vehicle trajectories in each cluster (e.g., by averaging data representing the clustered vehicle trajectories). In some embodiments, the target trajectory may be associated with a single lane of the common road segment 1200.

[0300] The road model and / or the sparse map may store trajectories associated with road segments. These trajectories may be referred to as target trajectories that are provided to the autonomous vehicle for autonomous navigation. The target trajectories may be received from multiple vehicles or may be generated based on actual trajectories or recommended trajectories (actual trajectories with some modifications) received from multiple vehicles. The target trajectories included in the road model or the sparse map may be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0301] Vehicles traveling on a road segment may collect data through various sensors. The data may include landmarks, road characteristic curves, vehicle motion (e.g., accelerometer data, speed data), vehicle position (e.g., GPS data), and may reconstruct the actual trajectory itself or transmit the data to a server that will reconstruct the actual trajectory for the vehicle. In some embodiments, the vehicle may transmit data related to the trajectory (e.g., a curve in any reference frame), landmark data, and lane assignment along the driving path to the server 1230. Various vehicles traveling along the same road segment under multiple drives may have different trajectories. The server 1230 may identify the routes or trajectories associated with each lane from the trajectories received from the vehicles through a clustering process.

[0302] Fig. 22Illustrates a process of clustering vehicle trajectories associated with vehicles 1205, 1210, 1215, 1220, and 1225 to determine a target trajectory for a common road segment (e.g., road segment 1200). The target trajectory or target trajectories determined from the clustering process may be included in an autonomous vehicle road navigation model or sparse map 800. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 traveling along road segment 1200 may transmit a plurality of trajectories 2200 to server 1230. In some embodiments, server 1230 may generate trajectories based on landmarks, road geometry features, and vehicle motion information received from vehicles 1205, 1210, 1215, 1220, and 1225. To generate an autonomous vehicle road navigation model, server 1230 may cluster vehicle trajectories 1600 into a plurality of clusters 2205, 2210, 2215, 2220, 2225, and 2230, as Fig. 22 shown.

[0303] Various criteria may be used for clustering. In some embodiments, all of the driving in a cluster may be similar with respect to the absolute heading along road segment 1200. The absolute heading may be obtained from GPS signals received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, dead reckoning may be used to obtain the absolute heading. As will be understood by those skilled in the art, dead reckoning may be used to determine the current position and thus the heading of vehicles 1205, 1210, 1215, 1220, and 1225 by using previously determined positions, estimated speeds, etc. Trajectories clustered by absolute heading may be useful for identifying routes along a road.

[0304] In some embodiments, all of the driving in a cluster may be similar with respect to lane assignment for driving along road segment 1200 (e.g., in the same lane before and after an intersection). Trajectories clustered by lane assignment may be useful for identifying lanes along a road. In some embodiments, two criteria (e.g., absolute heading and lane assignment) may be used for clustering.

[0305] In each of the clusters 2205, 2210, 2215, 2220, 2225, and 2230, the trajectories can be averaged to obtain a target trajectory associated with a particular cluster. For example, the trajectories from multiple drives associated with the same lane cluster can be averaged. The averaged trajectory can be the target trajectory associated with a particular lane. To average the clusters of trajectories, the server 1230 can select a reference frame of any 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 included in the cluster. The server 1230 can compute the mean curve or trajectory in the C0 reference frame.

[0306] In some embodiments, landmarks can define an arc length that matches between different drives, and this arc length can be used for aligning the trajectory with the lane. In some embodiments, the lane markings before and after an intersection can be used for aligning the trajectory with the lane.

[0307] To assemble lanes from trajectories, the server 1230 can select a reference frame of any lane. The server 1230 can map the partially overlapping lanes to the selected reference frame. The server 1230 can continue mapping until all lanes are in the same reference frame. Lanes adjacent to each other may align as if they were the same lane, and then they may shift laterally.

[0308] Landmarks identified along a road segment can first be mapped to a common reference frame at the lane level and then at the intersection level. For example, the same landmark may be identified multiple times by multiple vehicles during multiple drives. The data received about the same landmark during different drives may vary slightly. Such data can be averaged and mapped to the same reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of the data for the same landmark received during multiple drives can be computed.

[0309] In some embodiments, each lane of the road segment 120 can be associated with a target trajectory and certain landmarks. The target trajectory or multiple such target trajectories can be included in an autonomous vehicle road navigation model that can later be used by other autonomous vehicles traveling along the same road segment 1200. Landmarks identified by the vehicles 1205, 1210, 1215, 1220, and 1225 as they travel along the road segment 1200 can be recorded in association with the target trajectory. The data for the target trajectory and the landmarks can be continuously or periodically updated with new data received from other vehicles during subsequent drives.

[0310] For vehicle positioning, the disclosed systems and methods may use an Extended Kalman Filter. Vehicle positioning may be determined based on three-dimensional position data and / or three-dimensional orientation data, a prediction of the vehicle's future positioning ahead of its current positioning through integration of self-motion. Vehicle positioning may be corrected or adjusted through visual observation of landmarks. For example, when a vehicle detects a landmark within an image captured by a camera, the landmark may be compared to known landmarks stored within a road model or sparse map 800. The known landmarks may have known positions (e.g., GPS data) along a target trajectory stored within the road model and / or sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark may be estimated. The vehicle's positioning along the target trajectory may be adjusted based on the distance to the landmark and the known position of the landmark (stored within the road model or sparse map 800). The position / location data of the landmarks stored within the road model and / or sparse map 800 (e.g., the mean from multiple drives) may be assumed to be accurate.

[0311] In some embodiments, the disclosed systems may form a closed-loop subsystem where an estimate of the vehicle's six-degree-of-freedom positioning (e.g., three-dimensional position data plus three-dimensional orientation data) may be used to navigate an autonomous vehicle (e.g., steer its steering wheel) to reach a desired point (e.g., 1.3 seconds ahead in storage). Subsequently, data from the steering and actual navigation measurements may be used to estimate the six-degree-of-freedom positioning.

[0312] In some embodiments, poles along a road (such as streetlight poles and utility poles or cable poles) may be used as landmarks for vehicle positioning. Other landmarks such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or characteristics of objects along a road segment may also be used as landmarks for vehicle positioning. When using poles for positioning, the x observation of the pole (i.e., from the vehicle's viewing angle) may be used instead of the y observation (i.e., the distance to the pole) because the bottom of the pole may be occluded and sometimes they are not in the road plane.

[0313] Fig.23 A navigation system for a vehicle is shown that may be used for autonomous navigation using a crowdsourced sparse map. For illustration, the vehicle is referred to as vehicle 1205. As Fig.23 shown, the vehicle may be any of the other vehicles disclosed herein, including for example vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 shown in other embodiments. As Fig.12As shown, vehicle 1205 can communicate with server 1230. Vehicle 1205 can include an image capture device 122 (e.g., camera 122). Vehicle 1205 can include a navigation system 2300 that is configured to provide navigation guidance for vehicle 1205 to travel 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 the acceleration or deceleration of vehicle 1205. Fig.23 The illustrated vehicle 1205 can be an autonomous vehicle, and the navigation system 2300 can be used to provide navigation guidance for autonomous driving. Alternatively, vehicle 1205 can also be a non-autonomous, human-controlled vehicle, and the navigation system 2300 can still be used to provide navigation guidance.

[0314] Navigation system 2300 can include a communication unit 2305 configured to communicate with server 1230 via communication path 1235. Navigation system 2300 can also include a GPS unit 2310 configured to receive and process GPS signals. Navigation system 2300 can further include at least one processor 2315 configured to process data, such as GPS signals, map data from sparse map 800 (which can be stored on a storage device configured to be loaded on vehicle 1205 and / or received from server 1230), geometric features sensed by road profile sensor 2330, images captured by camera 122, and / or an autonomous vehicle road navigation model received from server 1230. Road profile sensor 2330 can include different types of devices for measuring different types of road profiles, such as road surface roughness, road width, road elevation, road curvature, etc. For example, road profile sensor 2330 can include a device for measuring the movement of the suspension 2305 of the vehicle to derive a road roughness curve. In some embodiments, road profile sensor 2330 can include a radar sensor to measure the distance from vehicle 1205 to the road side (e.g., an obstacle on the road side), thereby measuring the width of the road. In some embodiments, road profile sensor 2330 can include a device configured to measure the up and down elevation of the road. In some embodiments, road profile sensor 2330 can include a device configured to measure the road curvature. For example, a camera (e.g., camera 122 or another camera) can be used to capture an image of the road showing the road curvature. Vehicle 1205 can use such an image to detect the road curvature.

[0315] At least one processor 2315 can be programmed to receive at least one environmental image associated with vehicle 1205 from camera 122. The at least one processor 2315 can analyze the at least one environmental image to determine navigation information related to vehicle 1205. The navigation information can include a trajectory related to the travel of vehicle 1205 along road segment 1200. The at least one processor 2315 can determine the trajectory based on the motion of camera 122 (and thus the vehicle), such as three-dimensional translational and three-dimensional rotational motion. In some embodiments, the at least one processor 2315 can determine the translational and rotational motion of camera 122 based on the analysis of multiple images acquired by camera 122. In some embodiments, the navigation information can include lane assignment information (e.g., in which lane vehicle 1205 is traveling along road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 can be used by server 1230 to generate and / or update an autonomous vehicle road navigation model, which can be transmitted back from server 1230 to vehicle 1205 for providing autonomous navigation guidance for vehicle 1205.

[0316] The at least one processor 2315 can also be programmed to transmit the navigation information from vehicle 1205 to server 1230. In some embodiments, the navigation information can be transmitted to server 1230 together with road information. The road location information can include at least one of GPS signals received by GPS unit 2310, landmark information, road geometric features, lane information, etc. The at least one processor 2315 can receive an autonomous vehicle road navigation model or a portion of the model from server 1230. The autonomous vehicle road navigation model received from server 1230 can include at least one update based on the navigation information transmitted from vehicle 1205 to server 1230. The portion of the model transmitted from server 1230 to vehicle 1205 can include the updated portion of the model. The at least one processor 2315 can cause at least one navigation maneuver (e.g., steering such as turning, braking, accelerating, passing another vehicle, etc.) to be performed by vehicle 1205 based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0317] The at least one processor 2315 can be configured to communicate with various sensors and components included in vehicle 1205, including communication unit 2305, GPS unit 2310, camera 122, speed sensor 2320, accelerometer 2325, and road profile sensor 2330. The at least one processor 2315 can 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, the various sensors or components of vehicle 1205 can also communicate with server 1230 and transmit the data or information collected by the sensors or components to server 1230.

[0318] In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may communicate with each other and may share navigation information with each other such that at least one of vehicles 1205, 1210, 1215, 1220, and 1225 may generate an autonomous vehicle road navigation model using crowdsourcing, e.g., based on information shared by other vehicles. In some embodiments, vehicles 1205, 1210, 1215, 1220, and 1225 may share navigation information with each other and each vehicle may update its own autonomous vehicle road navigation model in the vehicle. In some embodiments, at least one of vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) may act as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) may perform some or all of the functions performed by server 1230. For example, at least one processor 2315 of the hub vehicle may communicate with other vehicles and receive navigation information from other vehicles. At least one processor 2315 of the hub vehicle may generate an autonomous vehicle road navigation model or an update to the model based on the shared information received from other vehicles. At least one processor 2315 of the hub vehicle may transmit the autonomous vehicle road navigation model or an update to the model to other vehicles for providing autonomous navigation guidance.

[0319] Navigation based on sparse maps

[0320] As previously discussed, an autonomous vehicle road navigation model including sparse map 800 may include a plurality of mapped lane markings and a plurality of mapped objects / features associated with road segments. As discussed in more detail below, these mapped lane markings, objects, and features may be used when an autonomous vehicle is navigating. For example, in some embodiments, the mapped objects and features may be used to position the host vehicle relative to the map (e.g., relative to the mapped target trajectory). The mapped lane markings may be used (e.g., as a check) to determine the lateral position and / or orientation relative to a planned or target trajectory. Using this position information, the autonomous vehicle may be able to adjust its heading direction to match the direction of the target trajectory at the determined position.

[0321] Vehicle 200 may be configured to detect lane markings in a given road segment. A road segment may include any markings on a road for guiding vehicle traffic on the road. For example, lane markings may be continuous lines or short dash lines that demarcate the edges of driving lanes. Lane markings may also include double lines, such as double continuous lines, double short dash lines, or a combination of continuous lines and short dash lines, indicating, for example, whether passing is permitted in adjacent lanes. Lane markings may also include highway entrance and exit markings indicating, for example, deceleration lanes for exit ramps, or dotted lines indicating that a lane is only turning or that a lane is ending. The markings may further indicate work areas, temporary lane changes, driving paths through intersections, medians, dedicated lanes (e.g., bicycle lanes, HOV lanes, etc.), or other miscellaneous markings (e.g., crosswalks, speed bumps, railroad crossings, stop lines, etc.).

[0322] Vehicle 200 may use cameras such as image capture devices 122 and 124 included in image acquisition unit 120 to capture images of surrounding lane markings. Vehicle 200 may analyze the images to detect point locations associated with lane markings based on features identified within one or more of the captured images. These point locations may be uploaded to a server to represent lane markings in sparse map 800. Depending on the position and field of view of the camera, lane markings may be detected simultaneously for both sides of the vehicle from a single image. In other embodiments, different cameras may be used to capture images on multiple sides of the vehicle. Instead of uploading the actual images of the lane markings, the markings may be stored in sparse map 800 as splines or a series of points, thereby reducing the size of sparse map 800 and / or the data that must be remotely uploaded by the vehicle.

[0323] FIG. 24A to FIG. 24D Illustrative point locations that may be detected by vehicle 200 to represent a particular lane marking are shown. Similar to the landmarks described above, vehicle 200 may use various image recognition algorithms or software to identify point locations within the captured images. For example, vehicle 200 may identify a series of edge points, corner points, or various other point locations associated with a particular lane marking. Fig.24A Continuous lane marking 2410 that may be detected by vehicle 200 is shown. Lane marking 2410 may represent the outer edge of the road, represented by a white continuous line. As Fig.24A shown, vehicle 200 may be configured to detect a plurality of edge location points 2411 along the lane marking. The location points 2411 may be collected to represent the lane marking at any interval sufficient to create a mapped lane marking in the sparse map. For example, the lane marking may be represented by one point per meter of detected edge, one point per five meters of detected edge, or at other suitable spacings. In some embodiments, the spacing may be determined by other factors such as, for example, points based on vehicle 200 having the highest confidence rating for the location of the detected points, rather than at a set interval. Although Fig.24Ashows edge location points on the inner edge of the lane marking 2410, but points can be collected on the outer edge of the line or along both edges. Further, although a single line is shown in Fig.24A , similar edge points can be detected for double continuous lines. For example, points 2411 can be detected along the edge of one or more of the continuous lines.

[0324] Depending on the type or shape of the lane marking, the vehicle 200 can also represent the lane marking differently. Fig. 24B Shows an exemplary dashed lane marking 2420 with short dashes that can be detected by the vehicle 200. Instead of identifying edge points as in Fig.24A , the vehicle can detect a series of corner points 2421 representing the corners of the lane short dashes to define the complete boundary of the short dashes. Although Fig. 24B shows each corner of a given short dash marking that is located, the vehicle 200 can detect or upload a subgroup of the points shown in the figure. For example, the vehicle 200 can detect the front edge or front corner of a given short dash marking, or can detect the two corner points closest to the inside of the lane. Further, not every short dash marking can be captured. For example, the vehicle 200 can capture and / or record points representing a sample of the short dash marking (e.g., every other, every third, every fifth, etc.) or points of the short dash marking at a predetermined spacing (e.g., every meter, every five meters, every 10 meters, etc.). For similar lane markings, such as markings indicating that a lane is an exit ramp, a marking indicating the end of a particular lane, or various other lane signs that may have detectable corner points, corner points can also be detected. Corner points can also be detected for lane markings consisting of a combination of double dashed lines or continuous lines and dashed lines with short dashes.

[0325] In some embodiments, the points uploaded to the server to generate the mapped lane markings can represent other points in addition to the detected edge points or corner points. Fig.24C Shows a series of points that can represent the centerline of a given lane marking. For example, the continuous lane 2410 can be represented by centerline points 2441 along the centerline 2440 of the lane marking. In some embodiments, the vehicle 200 can be configured to detect these center points using various image recognition techniques (such as convolutional neural networks (CNNs), scale-invariant feature transform (SIFT), histogram of oriented gradients (HOG) features, or other techniques). Alternatively, the vehicle 200 can detect other points, such as Fig.24A the edge points 2411 shown, and can calculate the centerline points 2441, for example, by detecting points along each edge and determining the midpoint between the edge points. Similarly, the dashed lane marking 2420 with short dashes can be represented by centerline points 2451 along the centerline 2450 of the lane marking. The centerline points can be located at the edge of the short dashes, as in Fig.24CAs shown, or at various other positions along the centerline. For example, each short dash can be represented by a single point at the geometric center of the short dash. These points can also be spaced apart along the centerline at predetermined intervals (e.g., every meter, 5 meters, 10 meters, etc.). The centerline point 2451 can be directly detected by the vehicle 200, or can be calculated based on other detected reference points (such as the corner point 2421 as Fig. 24B shown). Using techniques similar to those described above, the centerline can also be used to represent other lane marking types, such as double lines.

[0326] In some embodiments, the vehicle 200 can identify points representing other features, such as the vertex between two intersecting lane markings. Fig.24D An exemplary point representing the intersection between two lane markings 2460 and 2465 is shown. The vehicle 200 can calculate the vertex 2466 representing the intersection between two lane markings. For example, one of the lane markings 2460 or 2465 can represent a railroad crossing area or other intersection area in a road segment. Although the lane markings 2460 and 2465 are shown as intersecting perpendicularly to each other, various other configurations can be detected. For example, the lane markings 2460 and 2465 can intersect at other angles, or one or both of the lane markings can terminate at the vertex 2466. Similar techniques can also be applied to intersections between short dash dotted lines or other lane marking types. In addition to the vertex 2466, various other points 2467 can also be detected, thereby providing further information about the orientation of the lane markings 2460 and 2465.

[0327] Vehicle 200 can associate real-world coordinates with each detected point of the lane markings. For example, a positioning identifier can be generated, including the coordinates for each point, to be uploaded to a server for mapping the lane markings. The positioning identifier can further include other identification information about the point, including whether the point represents a corner point, an edge point, a center point, etc. Vehicle 200 can thus be configured to determine the real-world position of each point based on the 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 position of the lane markings. This can involve determining the positioning of the lane markings in the image relative to the detected landmarks, or determining the position of the vehicle based on the detected landmarks, and then determining the distance from the vehicle (or the vehicle's target trajectory) to the lane markings. When the landmarks are not available, the positioning of the lane marking points can be determined relative to the position of the vehicle determined based on dead reckoning. The real-world coordinates included in the positioning identifier can be represented as absolute coordinates (e.g., latitude / longitude coordinates), or can be relative to other features, such as the longitudinal position along the target trajectory and the lateral distance from the target trajectory. The positioning identifier can then be uploaded to the server for the generation of the mapped lane markings in a navigation model, such as the sparse map 800. In some embodiments, the server can construct a spline representing the lane markings of a road segment. Alternatively, vehicle 200 can generate the spline and upload it to the server for recording in the navigation model.

[0328] Fig.24E An exemplary navigation model or sparse map for a corresponding road segment including the mapped lane markings is shown. The sparse map can include a target trajectory 2475 for the vehicle to travel along the road segment. As described above, the target trajectory 2475 can represent the ideal path that the vehicle takes when traveling on the corresponding road segment, or can be located elsewhere on the road (e.g., the centerline of the road, etc.). The target trajectory 2475 can be calculated by various methods described above, for example, based on the aggregation (e.g., weighted combination) of two or more reconstructed trajectories of vehicles that have traveled the same road segment.

[0329] In some embodiments, the target trajectory may be generated equally for all vehicle types and for all road, vehicle, and / or environmental conditions. However, in other embodiments, various other factors or variables may also be considered when generating the target trajectory. Different target trajectories may be generated for different types of vehicles (e.g., passenger cars, light trucks, and full trailers). For example, a target trajectory with a relatively tighter turning radius may be generated for a small passenger car compared to a larger semi-trailer truck. In some embodiments, road, vehicle, and environmental conditions may also be considered. For example, different target trajectories may be generated for different road conditions (e.g., wet, snowy, icy, dry, etc.), vehicle conditions (e.g., tire condition or estimated tire condition, braking condition or estimated braking condition, remaining fuel amount, etc.), or environmental factors (e.g., time of day, visibility, weather, etc.). The target trajectory may also depend on one or more aspects or features of a particular road segment (e.g., speed limit, turning frequency and size, slope, etc.). In some embodiments, various user settings may also be used to determine the target trajectory, such as a set driving mode (e.g., desired driving aggressiveness, economy mode, etc.).

[0330] The sparse map may also include mapped lane markings 2470 and 2480 representing lane markings along a road segment. The mapped lane markings may be represented by a plurality of positioning identifiers 2471 and 2481. As described above, the positioning identifier may include a positioning in the real-world coordinates of points associated with the detected lane marking. Similar to the target trajectory in the model, the lane marking may also include elevation data and may be represented as a curve in three-dimensional space. For example, the curve may be a spline connecting three-dimensional polynomials of an appropriate order, and the curve may be calculated based on the positioning identifier. The mapped lane markings may also include other information or metadata about the lane markings, such as an identifier of the type of lane marking (e.g., between two lanes with the same driving direction, between two lanes with opposite driving directions, the edge of the road, etc.) and / or other characteristics of the lane marking (e.g., continuous, short dash-dotted, single line, double line, yellow, white, etc.). In some embodiments, the mapped lane markings may be continuously updated in the model using, for example, crowdsourcing techniques. The same vehicle may upload positioning identifiers during multiple instances of 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 positioning identifiers received from and stored in the vehicles by 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.

[0331] Generating the mapped lane markings in the sparse map may also include detecting and / or reducing errors based on anomalies in the image or in the actual lane markings themselves. Fig.24F An exemplary anomaly 2495 associated with detecting lane markings 2490 is shown. Anomaly 2495 may appear in an image captured by vehicle 200, for example, from an object obstructing the camera's view of the lane markings, debris on the lens, etc. In some cases, the anomaly may be due to the lane markings themselves, which may be damaged or worn, or partially covered by dirt, debris, water, snow, or other materials on the road. Anomaly 2495 may cause vehicle 200 to detect an error point 2491. The sparse map 800 may provide the correct mapped lane markings and exclude the errors. In some embodiments, vehicle 200 may detect error point 2491, for example, by detecting anomaly 2495 in the image or by identifying the error based on lane marking points detected before and after the anomaly. Based on the detected anomaly, the vehicle may ignore point 2491 or may adjust it to be consistent with other detected points. In other embodiments, the error may be corrected after the points have been uploaded, for example, by determining that the points are outside the expected threshold based on other points uploaded during the same trip or based on an aggregation of data from previous trips along the same road segment.

[0332] The mapped lane markings in the navigation model and / or sparse map may also be used for navigation by autonomous vehicles driving along the corresponding road. For example, a vehicle navigating along a target trajectory may periodically use the mapped lane markings in the sparse map to align itself with the target trajectory. As mentioned above, a vehicle may navigate between landmarks based on dead reckoning, where the vehicle uses sensors to determine its self-motion and estimate its position relative to the target trajectory. Errors may accumulate over time, and the determination of the vehicle's position relative to the target trajectory may become increasingly inaccurate. Accordingly, the vehicle may use the lane markings (and their known positioning) present in the sparse map 800 to reduce the dead reckoning-induced errors in position determination. In this way, the identified lane markings included in the sparse map 800 may act as navigation anchors from which the accurate position of the vehicle relative to the target trajectory can be determined.

[0333] Fig.25A An exemplary image 2500 of the vehicle's surrounding environment that can be used for navigation based on the mapped lane markings is shown. Image 2500 may be captured, for example, by vehicle 200 through image capture devices 122 and 124 included in the image acquisition unit 120. Image 2500 may include an image of at least one lane marking 2510, as Fig.25A shown. Image 2500 may also include one or more landmarks 2521, such as road signs, for navigation as described above. Fig.25ASome of the elements shown in, such as elements 2511, 2530, and 2520 (which do not appear in the captured image 2500 but are detected and / or determined by the vehicle 200), are also shown for reference.

[0334] Using the various techniques described above with respect to FIG. 24A to FIG. 24D and Fig.24F the vehicle can analyze the image 2500 to identify the lane markings 2510. Various points 2511 corresponding to the features of the lane markings in the image can be detected. For example, the points 2511 can correspond to the edges of the lane markings, the corners of the lane markings, the midpoints of the lane markings, the vertices between two intersecting lane markings, or various other features or positions. The points 2511 can be detected as positions corresponding to points stored in a navigation model received from a server. For example, if a sparse map containing points representing the centerlines of the mapped lane markings is received, the points 2511 can also be detected based on the centerlines of the lane markings 2510.

[0335] The vehicle can also determine the longitudinal position represented by the element 2520 and located along the target trajectory. The longitudinal position 2520 can be determined from the image 2500, for example, by detecting landmarks 2521 within the image 2500 and comparing the measured positions with known landmark positions stored in a road model or sparse map 800. The position of the vehicle along the target trajectory can then be determined based on the distance to the landmark and the known position of the landmark. The longitudinal position 2520 can also be determined from images other than those used to determine the positions of the lane markings. For example, the longitudinal position 2520 can be determined by detecting landmarks in images captured by other cameras within the image acquisition unit 120 that are taken simultaneously or almost simultaneously with the image 2500. In some cases, the vehicle may not be close to any landmarks or other reference points for determining the longitudinal position 2520. In such cases, the vehicle can navigate based on dead reckoning and can therefore use sensors to determine its self-motion and estimate the longitudinal position 2520 relative to the target trajectory. The vehicle can also determine the distance 2530, which represents the actual distance between the vehicle and the lane markings 2510 observed in the captured image. Camera angle, the speed of the vehicle, the width of the vehicle, or various other factors can be considered when determining the distance 2530.

[0336] Fig.25BShows the lateral positioning correction of a vehicle based on mapped lane markings in a road navigation model. As described above, vehicle 200 can use one or more images captured by vehicle 200 to determine the distance 2530 between vehicle 200 and lane marking 2510. Vehicle 200 may also have access to a road navigation model, such as sparse map 800, which may include mapped lane markings 2550 and target trajectory 2555. The mapped lane markings 2550 can be modeled using the techniques described above (e.g., using crowdsourced positioning identifiers captured by multiple vehicles). The target trajectory 2555 can also be generated using the various techniques described previously. Vehicle 200 can also determine or estimate the longitudinal position 2520 along the target trajectory 2555, as described above with respect to Fig.25A that. Vehicle 200 can then determine the expected distance 2540 based on the lateral distance between the target trajectory 2555 and the mapped lane markings 2550 corresponding to the longitudinal position 2520. The lateral positioning of vehicle 200 can be corrected or adjusted by comparing the actual distance 2530 measured using the captured images with the expected distance 2540 from the model.

[0337] Fig.25C and Fig.25D Provides illustrations associated with another example for positioning a host vehicle based on mapped landmarks / objects / features in a sparse map during navigation. Fig.25C Conceptually represents a series of images captured from a vehicle navigating along road segment 2560. In this example, road segment 2560 includes a straight section of a two-lane divided highway marked by road edges 2561 and 2562 and a center lane marking 2563. As shown, the host vehicle is navigating along lane 2564 associated with the mapped target trajectory 2565. Thus, ideally (and without influencing factors such as the presence of target vehicles or objects in the road), the host vehicle should closely follow the mapped target trajectory 2565 as it navigates along lane 2564 of road segment 2560. In practice, the host vehicle may experience drift while navigating along the mapped target trajectory 2565. For effective and safe navigation, this drift should be maintained within acceptable limits (e.g., a lateral displacement amount from the target trajectory 2565 of + / - 10 cm or any other suitable threshold). To periodically account for drift and make any required route corrections to ensure the host vehicle follows the target trajectory 2565, the disclosed navigation system may be able to use one or more mapped features / objects included in the sparse map to position the host vehicle along the target trajectory 2565 (e.g., determine the lateral and longitudinal positions of the host vehicle relative to the target trajectory 2565).

[0338] As a simple example, Fig.25CShows a speed limit sign 2566 that may appear in five different, sequentially captured images as the host vehicle travels along road segment 2560. For example, at a first time t0, sign 2566 may appear in the captured image near the horizon. As the host vehicle approaches sign 2566, in subsequent captured images at times t1, t2, t3, and t4, sign 2566 will appear at different 2D X-Y pixel locations in the captured image. For example, in the captured image space, sign 2566 will move down and to the right along curve 2567 (e.g., a curve that extends through the center of the sign in each of the five captured image frames). As the host vehicle approaches sign 2566, the sign will also appear to increase in size (i.e., it will occupy a greater number of pixels in subsequent captured images).

[0339] These changes in the image space representation of an object such as sign 2566 can be utilized to determine the local position of the host vehicle along a target trajectory. For example, as described in the present disclosure, any detectable object or feature (such as a semantic feature like sign 2566 or a detectable non-semantic feature) can be identified by one or more collection vehicles of a previously traversed road segment (e.g., road segment 2560). A mapping server can collect the collected driving information from multiple vehicles, aggregate and correlate this information, and generate a sparse map that includes, for example, a target trajectory 2565 for lane 2564 of road segment 2560. The sparse map can also store the location of sign 2566 (along with type information, etc.). During navigation (e.g., before entering road segment 2560), a map tile including the sparse map for road segment 2560 can be supplied to the host vehicle. To navigate in lane 2564 of road segment 2560, the host vehicle can follow the mapped target trajectory 2565.

[0340] The mapped representation of sign 2566 can be used by the host vehicle to position itself relative to the target trajectory. For example, a camera on the host vehicle will capture an image 2570 of the host vehicle's environment, and the captured image 2570 can include an image representation of sign 2566 having a specific size and specific X-Y image location, as Fig.25DAs shown. This size and X-Y image positioning can be used to determine the position of the host vehicle relative to the target trajectory 2565. For example, based on a sparse map including a representation of the landmark 2566, the navigation processor of the host vehicle can determine that in response to the host vehicle traveling along the target trajectory 2565, the representation of the landmark 2566 should appear in the captured image such that the center of the landmark 2566 will move along line 2567 (in image space). If the captured image (such as image 2570) shows that the center (or other reference point) is displaced from line 2567 (e.g., the expected image space trajectory), the host vehicle navigation system can determine that it is not on the target trajectory 2565 at the time of the captured image. However, based on the image, the navigation processor can determine an appropriate navigation correction to return the host vehicle to the target trajectory 2565. For example, if the analysis shows that the image positioning of the landmark 2566 is displaced a distance 2572 to the left of the expected image space positioning on line 2567 in the image, the navigation processor can cause a change in the heading of the host vehicle (e.g., change the steering angle of the wheels) to move the host vehicle leftward a distance 2573. In this way, each captured image can be used as part of a feedback loop process such that the difference between the observed image position of the landmark 2566 and the expected image trajectory 2567 can be minimized to ensure that the host vehicle continues to travel along the target trajectory 2565 with little or no deviation. Of course, the more mapped objects available, the more frequently the described positioning techniques can be employed, which can reduce or eliminate drift-induced deviations from the target trajectory 2565.

[0341] The process described above can be used to detect the lateral orientation or displacement of the host vehicle relative to the target trajectory. The positioning of the host vehicle relative to the target trajectory 2565 can also include determination of the longitudinal positioning of the target vehicle along the target trajectory. For example, the captured image 2570 includes a representation of the landmark 2566 having a specific image size (e.g., a 2D X-Y pixel region). As the mapped landmark 2566 travels through image space along line 2567 (e.g., when the size of the landmark gradually increases, as Fig.25C shown), this size can be compared to the expected image size of the mapped landmark. Based on the image size of the landmark 2566 in the image 2570 and based on the expected size progression in image space relative to the mapped target trajectory 2565, the host vehicle can determine its longitudinal position relative to the target trajectory 2565 (at the time when the image 2570 was captured). This longitudinal position, coupled with any lateral displacement relative to the target trajectory 2565 as described above, allows for the complete positioning of the host vehicle relative to the target trajectory 2565 as the host vehicle navigates along the road 2560.

[0342] Fig.25C and Fig.25DOnly one example of the disclosed localization technique using a single mapped object and a single target trajectory is provided. In other examples, there may be more target trajectories (e.g., one target trajectory for each viable lane of a multi-lane highway, urban street, complex intersection, etc.) and there may be more mappings available for localization. For example, a sparse map representing an urban environment may include many objects per meter that are available for localization.

[0343] Fig.26A A flowchart of an exemplary process 2600A for mapping lane markings for use in autonomous vehicle navigation consistent with the disclosed embodiments is shown. At step 2610, process 2600A may include receiving two or more localization 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 localization identifier may include the localization of a point associated with the detected lane marking in real-world coordinates, as described above with respect to Fig.24E what has been described. In some embodiments, the localization identifier may also contain other data, such as additional information about the road segment or lane marking. Additional data may also be received during step 2610, such as accelerometer data, speed data, landmark data, road geometry feature or profile data, vehicle localization data, ego-motion data, or various other forms of data as described above. The localization 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 obtaining at least one image representing the environment of the host vehicle from a camera associated with the host vehicle, analyzing the at least one image to detect lane markings in the environment of the host vehicle, and analyzing the at least one image to determine the position of the detected lane markings relative to the localization associated with the host vehicle. As described above, lane markings may include a variety of different marking types, and the localization identifier may correspond to a variety of points relative to the lane marking. For example, in the case where the detected lane marking is part of a short dash-dotted line marking a lane boundary, the point may correspond to the detected corner of the lane marking. In the case where the detected lane marking is part of a continuous line marking a lane boundary, the point may correspond to the detected edge of the lane marking, with various spacings as described above. In some embodiments, the point may correspond to the centerline of the detected lane marking, as Fig.24C shown, or may correspond to the vertex between two intersecting lane markings and at least two other points associated with the intersecting lane markings, as Fig.24D shown.

[0344] At step 2612, process 2600A may include associating the detected lane markings with the 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 the positioning information stored in the autonomous vehicle road navigation model. Server 1230 may determine the road segment in the model that corresponds to the real-world road segment of the detected lane markings.

[0345] At step 2614, process 2600A may include updating the autonomous vehicle road navigation model relative to the corresponding road segment based on 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 server 1230 may update the sparse map to include or adjust the mapped lane markings in the model. Server 1230 may update the model based on the various methods or processes described above with respect to Fig.24E In some embodiments, updating the autonomous vehicle road navigation model may include storing one or more indicators of the position in the real-world coordinates of the detected lane markings. The autonomous vehicle road navigation model may also include at least one target trajectory for the vehicle to travel along the corresponding road segment, as Fig.24E shown.

[0346] 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 that can 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.) over the wireless communication path 1235, as Fig.12 shown.

[0347] In some embodiments, the lane markings may be mapped using data received from a plurality of vehicles, such as through crowdsourcing techniques, as described above with respect to Fig.24EAs described. For example, process 2600A may include receiving a first communication from a first host vehicle, including a positioning identifier associated with a detected lane marking, and receiving a second communication from a second host vehicle, including an additional positioning identifier associated with the detected lane marking. For example, the second communication may be received from a following vehicle traveling on the same road segment or from the same vehicle in a subsequent journey along the same road segment. Process 2600A may further include refining the determination of at least one position associated with the detected lane marking based on the positioning identifier received in the first communication and based on the additional positioning identifier received in the second communication. This may include using the average of multiple positioning identifiers and / or filtering out "ghost" identifiers that may not reflect the real-world position of the lane marking.

[0348] Fig.26B A flowchart 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 the processing unit 110 of the 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 for the host vehicle along the road segment and positioning identifiers associated with one or more lane markings associated with the road segment. For example, vehicle 200 may receive the sparse map 800 or another road navigation model developed using process 2600A. In some embodiments, the target trajectory may be represented as a three-dimensional spline, for example, as Fig. 9B shown. As described above with respect to FIG. 24A to FIG. 24F the positioning identifier may include the positioning of points associated with the lane marking in real-world coordinates (e.g., the corner points of a dashed lane marking, the edge points of a continuous lane marking, the vertices between two intersecting lane markings and other points associated with the intersecting lane markings, the centerline associated with the lane marking, etc.).

[0349] 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 through image capture devices 122 and 124 included in the image acquisition unit 120. The image may include an image of one or more lane markings, similar to the image 2500 described above.

[0350] At step 2622, process 2600B may include determining the longitudinal position of the host vehicle along the target trajectory. As described above with respect to Fig.25A this may be based on other information in the captured image (e.g., landmarks, etc.) or by dead reckoning of the vehicle between detected landmarks.

[0351] At step 2623, process 2600B may include determining an expected lateral distance to a lane marking based on a determined longitudinal position of the host vehicle along a target trajectory and based on two or more positioning identifiers associated with at least one lane marking. For example, vehicle 200 may use sparse map 800 to determine the expected lateral distance to a lane marking. As Fig.25B shown, the longitudinal position 2520 along the target trajectory 2555 may be determined in step 2622. Using sparse map 800, vehicle 200 may determine the expected distance 2540 to the mapped lane marking 2550 corresponding to the longitudinal position 2520.

[0352] 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, as Fig.25A shown.

[0353] At step 2625, process 2600B may include determining an actual lateral distance to at least one lane marking based on the analysis of at least one image. For example, the vehicle may determine a distance 2530 representing the actual distance between the vehicle and lane marking 2510, as Fig.25A shown. Camera angle, vehicle speed, vehicle width, the position of the camera relative to the vehicle, or various other factors may be considered when determining distance 2530.

[0354] At step 2626, process 2600B may include determining an autonomous steering action for the host vehicle based on the difference between the expected lateral distance to at least one lane marking and the determined actual lateral distance to at least one lane marking. For example, as described above with respect to Fig.25B vehicle 200 may compare the actual distance 2530 with the expected distance 2540. The difference between the actual distance and the expected distance may 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 may determine an autonomous steering action or other autonomous actions based on this difference. For example, if the actual distance 2530 is less than the expected distance 2540, as Fig.25B shown, the vehicle may determine an autonomous steering action to direct the vehicle to the left away from lane marking 2510. Thus, the position of the vehicle relative to the target trajectory may be corrected. Process 2600B may be used, for example, to improve the navigation of the vehicle between landmarks.

[0355] Processes 2600A and 2600B provide only examples of techniques that may be used to navigate the host vehicle using the disclosed sparse map. In other examples, relative to Fig.25C and Fig.25DA process consistent with the described process can also be performed.

[0356] In some embodiments, the disclosed systems, methods, and non-transitory computer-readable media may use one or more AV maps. An autonomous vehicle (AV) map (or AV map) may include information for supporting and / or enabling one or more autonomous vehicle (AV) functions of a vehicle in a manner that enables the vehicle to operate in a safe manner and / or navigate in an accurate manner. AV functions supported and / or enabled by an autonomous vehicle (or semi-autonomous vehicle) may include one or more functions of autonomous control (e.g., functions determined, selected, and / or enabled based on instructions executed by at least one processor) such as steering, accelerating, and / or braking the vehicle. An AV function may be part of a driving strategy such as RSS, which is developed and implemented, for example, by Mobileye in Jerusalem, Israel. Information for operating the vehicle in a safe manner may include, but is not limited to, information related to one or more regulations applicable to the location or jurisdiction of the vehicle (e.g., right-hand traffic or left-hand traffic jurisdiction), information related to the environment in which the vehicle is located (e.g., information related to drivable paths, stop signs, traffic lights, speed limits, lane markings, landmarks, free space, virtual or physical stop lines, traffic light correlation information, etc.), and / or information related to adjusting and / or adapting the navigation of the vehicle to account for one or more objects in the vehicle's environment (e.g., other vehicles, pedestrians, objects, obstacles, occlusions, hazards, road work zones, traffic cones, etc.). The vehicle may use one or more sensors (e.g., cameras, radar, lidar) to sense objects in the vehicle's environment, as discussed herein. The AV map may act as a redundant source of information for the sensed information and, in some cases, may also supplement the sensed information (e.g., providing the location of a virtual stop line where there is no marked stop line on the road). In some embodiments, operating the vehicle in a safe manner may further include operating the vehicle to maintain a level of comfort for one or more passengers in the vehicle. The level of comfort may include one or more pre-determined criteria (e.g., related to speed, acceleration, and / or turning) selected such that the vehicle operates in a manner that meets or exceeds a specified or selected level of passenger comfort. The level of comfort may be formalized and expressed in an appropriate mathematical formula. For example, a mathematical formula that limits the degree of jerk or acceleration applied to a passenger in different directions may be used. Information for operating the vehicle in an accurate manner may include, but is not limited to, information related to a planned or specified navigation path (e.g., a trajectory, as discussed herein) or route (e.g., from a particular location such as a starting location to a destination). In some embodiments, the information included in the AV map may further include information for supporting and / or enabling one or more AV functions in an efficient manner.Information for operating a vehicle in an efficient manner may include information related to speed, acceleration, lane changes, and / or lane positioning, and / or information for driving and / or selecting a path or route based on traffic conditions (e.g., traveling a route that is farther than a shorter route experiencing the traffic conditions) and / or other factors or attributes related to a potential route (e.g., weather conditions, road conditions, or other characteristics of the route, such as traveling on a highway without traffic lights rather than a road with traffic lights). In some embodiments, the AV map may further include at least some information from a high-resolution (HD) map. In some embodiments, the AV map may be a sparse map, as described above. In some embodiments, the AV map may be crowdsourced, as discussed herein. In the present disclosure, the terms “AV map” and “sparse map” are used interchangeably.

[0357] Map-based sensing status

[0358] A primary vehicle (autonomous or semi-autonomous) vehicle may include a camera that captures images of the primary vehicle's environment, and the primary vehicle may include a navigation system that analyzes the captured images to make navigation decisions. Current navigation systems typically capture images at a high resolution and reduce their resolution so that the system can process the images faster with fewer computing resources, but thereby lose information and accuracy present in the original high-resolution images. Using low-resolution images can pose challenges when the images include representations of distant objects. Since the distant objects are far from the camera and the images are of low resolution, the navigation system typically has difficulty identifying the objects themselves and the regions of the images that include representations of the distant objects. Failure to identify the regions of the images that include representations of the distant objects can lead to the distant objects being misidentified. Alternatively, if the navigation system can locate these regions of the images, the navigation system may need to use a scaled version of the images to analyze potential objects in these regions of the images. However, even after these regions are found, aligning the relative positions of the scaled images with the position of the primary vehicle remains challenging for the navigation system. Accordingly, although the navigation system may be able to identify distant objects, the system may not be able to correctly correlate the positioning of the distant objects with the positioning of the vehicle. The disclosed embodiments include systems and methods that build on these prior arts and reduce or eliminate the foregoing disadvantages.

[0359] Fig. 27A flowchart of an exemplary process 2700 for navigating a host vehicle consistent with the disclosed embodiments is shown. Process 2700 may be performed by at least one processing device (such as the processing unit 110 included in system 100, or various other devices described herein). It should be understood that throughout the above and this entire specification, the term "processor" or "processing unit" is used as a shorthand for "at least one processor" or "at least one processing unit". In other words, a processor or processing unit may include one or more structures (e.g., circuits) that perform logical operations, whether such structures are arranged in parallel, 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 process 2700. Additionally, process 2700 is not necessarily limited to Fig. 27 the steps shown in Fig. 27 and at least some of the steps shown in may be optional, and any steps or processes of the various embodiments described throughout this disclosure may also be included in process 2700.

[0360] At step 2702, the processing unit 110 may receive at least one image captured by a camera of the host vehicle from the environment of the host vehicle. For example, cameras included in the image acquisition unit 120 of system 100 (such as the image capture devices 122, 124, or 126 having fields of view 202, 204, and 206, respectively) may capture at least one image of the area surrounding the host vehicle 200 and transmit them via a data interface 128 to the processing unit 110 through a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). In some embodiments, the camera may be a front-facing camera of the host vehicle, such as camera 122 that captures the area in front of the host vehicle 200. In some other embodiments, the processing unit 110 may receive multiple captured images from one or more cameras mounted on the host vehicle. For example, the image capture devices 122, 124, and 126 included in the image acquisition unit 120, each having fields of view 202, 204, and 206, respectively, may all send some images representing the environment of the host vehicle. Additionally, in some embodiments, the at least one captured image may include a representation of at least one object in the environment of the host vehicle. Fig.28 An illustration of an exemplary image 2800 captured by the camera 122 of the host vehicle 200 is shown, which depicts its surrounding environment. In image 2800, a representation of a road segment 2810 on which the host vehicle 200 is traveling is shown. Additionally, the image includes a representation of road markings 2815 associated with the road segment 2810, as well as various objects within the environment of the host vehicle, such as another vehicle 2830 and a tree 2850.

[0361] At step 2704, the processing unit 110 may analyze the at least one image to identify regions of interest in the environment of the host vehicle. As used herein, a region of interest (ROI) in the environment of the host vehicle refers to any area or zone that is of particular importance to the host vehicle system. The regions of interest may be determined based on factors that may require the attention of the host vehicle, such as obstacles or objects, road boundaries, or traffic signs. In the context of the host vehicle's perception system, the ROI can help focus processing power and sensors on relevant areas, thereby improving safety, efficiency, and situational awareness. In some embodiments, the regions of interest in the environment of the host vehicle may be identified based on the trajectory or route of the host vehicle. In still other embodiments, the regions of interest may be determined based on one or more outputs provided by a trained system (e.g., a trained network, such as a neural network). For example, the trained system may be configured to learn to identify one or more regions of interest in one or more images based on any one or more of the factors discussed above, and then output one or more portions of the one or more images associated with the identified one or more regions of interest. A route refers to a predefined or planned path that the host vehicle plans to follow to reach a destination, taking into account the general position and orientation of the vehicle. For example, a route may include a set of instructions provided by the host vehicle's navigation system or navigation application, and the host vehicle follows the set of instructions to travel from a first location (e.g., an origin location) to a second location (e.g., a destination location). The set of instructions may identify certain roads, locations, landmarks, etc. that collectively comprise the route, as well as the relationships (e.g., directions) between the roads, locations, landmarks, etc. along the route. A trajectory not only follows the planned route, but also further takes into account the real-time dynamics of the vehicle, such as its speed, precise location, and any necessary adjustments along the way to navigate obstacles or changes in the environment. Information about the route or trajectory of the host vehicle (i.e., details related to the expected direction of the host vehicle) can help predict where the host vehicle will be located at a future moment based on the captured images of its surrounding environment. This predictive ability can enable the identification of areas in the environment that may pose a potential threat or require the attention of the host vehicle (i.e., regions of interest). That is, the trajectory may constitute the positioning of the host vehicle along one or more roads (the one or more roads being along the route) (e.g., a three-dimensional spline representing a drivable path). In some embodiments, reference to the trajectory can contribute to a more accurate identification of the regions of interest. Accordingly, in some embodiments, route-based identification of regions of interest may not be as accurate as trajectory-based identification of regions of interest, and route-based identification may therefore use additional information to identify the regions of interest. Reference Fig.28 , providing the trajectory or route 2840 (represented as a black dashed line) of the host vehicle 200 can assist the processing unit 110 in identifying the regions of interest within the image 2800. In Fig.28 the scenario depicted, the regions of interest are located in the area in front of the host vehicle 200.

[0362] At step 2706, the processing unit 110 may select a portion of the at least one image based on the region of interest. For example, referring to Fig.28 , the processing unit 110 may select portion 2820 of image 2800 based on a region of interest that is identified as being in the region in front of the host vehicle 200. The p...

Claims

1. A system for navigating a host vehicle, the system comprising: at least one processor, including circuitry and memory, wherein the memory includes instructions that, when executed by the circuitry, cause the at least one processor to: receive at least one image captured by a camera of the host vehicle from the environment of the host vehicle; analyze the at least one image to identify a region of interest in the environment of the host vehicle; select a portion of the at least one image based on the region of interest; receive map information associated with the environment of the host vehicle, wherein the map information includes one or more identifiers of a route of the host vehicle; provide the portion of the at least one image and the map information to a trained system, wherein the trained system is configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information; receive an output provided by the trained system, wherein the output includes an identifier of an object in the environment of the host vehicle and positioning information of the object relative to the map information; and cause the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning information of the object.

2. The system according to claim 1, wherein the camera is a front-view camera of the host vehicle.

3. The system according to claim 1, wherein the at least one image includes a representation of the object.

4. The system according to claim 1, wherein the region of interest in the environment of the host vehicle is identified based on a trajectory of the host vehicle.

5. The system according to claim 1, wherein the region of interest in the environment of the host vehicle is identified based on the route of the host vehicle.

6. The system according to claim 1, wherein the region of interest in the environment of the host vehicle is identified based on the map information.

7. The system according to claim 1, wherein the one or more identifiers of the route of the host vehicle are associated with a road segment.

8. The system according to claim 1, wherein the one or more identifiers of the route of the host vehicle are associated with a lane of a road segment.

9. The system according to claim 1, wherein the one or more identifiers of the route of the host vehicle are relative to a lane center.

10. The system according to claim 1, wherein the map information includes at least one of a lane center, a road edge, a lane marking, or a drivable path.

11. The system according to claim 1, wherein the positioning information of the object includes coordinate information.

12. The system according to claim 1, wherein the positioning information of the object is relative to the route of the host vehicle.

13. The system according to claim 1, wherein the trained system is further configured to identify the object in the environment of the host vehicle.

14. The system according to claim 1, wherein the trained system is further configured to generate information indicating the positioning information of the object relative to the map information.

15. The system according to claim 1, wherein the trained system is further configured to generate a sequence of markers representing the object based on the portion of the at least one image.

16. The system according to claim 16, wherein the trained system is further configured to determine an identifier of the object in the environment of the host vehicle based on the sequence of markers.

17. The system according to claim 1, wherein the trained system includes one or more machine learning models.

18. The system according to claim 1, wherein the trained system includes one or more neural networks.

19. The system according to claim 1, wherein the identifier of the object includes the category of the object.

20. The system according to claim 19, wherein the category of the object includes a target vehicle or a pedestrian.

21. The system according to claim 1, wherein the positioning information of the object includes the coordinates of the object.

22. The system according to claim 1, wherein the object is a target vehicle.

23. The system according to claim 1, wherein the object is a pedestrian.

24. The system according to claim 1, wherein the at least one navigation action includes braking, accelerating, or steering the host vehicle.

25. The system according to claim 1, wherein the memory further includes instructions that, when executed by the circuit, cause the at least one processor to: provide the trained system with an image selected from the captured images.

26. The system according to claim 24, wherein the resolution of the selected image is lower than the resolution of the selected portion of the at least one image.

27. The system according to claim 1, wherein the identifier includes a unique identifier of the detected object.

28. The system according to claim 27, wherein the object unique identifier is used to track the object between sequences of detections.

29. The system according to claim 1, wherein the language model is configured to generate a language-based description of the scene.

30. The system according to claim 29, wherein the description includes at least one detected object, and the description includes at least one of the positioning, category, and identifier of the object.

31. A method for navigating a host vehicle, the method comprising: receiving at least one image captured by a camera of the host vehicle from the environment of the host vehicle; analyzing the at least one image to identify a region of interest in the environment of the host vehicle; selecting a portion of the at least one image based on the region of interest; receiving map information associated with the environment of the host vehicle, wherein the map information includes one or more identifiers of the route of the host vehicle; Providing the portion of the at least one image and the map information to a trained system, where the trained system is configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information; Receiving an output provided by the trained system, where the output includes identifiers of objects in the environment of the host vehicle and positioning information of the objects relative to the map information; And Causing the host vehicle to initiate at least one navigation action based on the identifiers of the objects and the positioning information of the objects.

32. The method according to claim 31, wherein the region of interest in the environment of the host vehicle is identified based on the trajectory of the host vehicle.

33. The method according to claim 31, wherein the region of interest in the environment of the host vehicle is identified based on the route of the host vehicle.

34. The method according to claim 31, wherein the region of interest in the environment of the host vehicle is identified based on the map information.

35. The method according to claim 31, the method further comprising providing an image selected from the captured images to the trained system.

36. The method according to claim 35, wherein the resolution of the selected image is lower than the resolution of the selected portion of the at least one image.

37. The method according to claim 31, wherein the language model is configured to generate a language-based description of the scene.

38. The method according to claim 37, wherein the description includes at least one detected object, and the description includes at least one of the positioning, category, and identifier of the object.

39. A non-transitory computer-readable medium storing program instructions executable by at least one processor to perform a method, the method comprising: Receiving at least one image captured by a camera of the host vehicle from the environment of the host vehicle; Analyzing the at least one image to identify a region of interest in the environment of the host vehicle; Selecting a portion of the at least one image based on the region of interest; Receiving map information associated with the environment of the host vehicle, where the map information includes one or more identifiers of the route of the host vehicle; Providing the portion of the at least one image and the map information to a trained system, where the trained system is configured to generate one or more detections using a language model architecture based on an analysis of the portion of the at least one image and the map information; Receiving an output provided by the trained system, where the output includes identifiers of objects in the environment of the host vehicle and positioning information of the objects relative to the map information; And Causing the host vehicle to initiate at least one navigation action based on the identifiers of the objects and the positioning information of the objects.

40. The non-transitory computer-readable medium according to claim 39, wherein the region of interest in the environment of the host vehicle is identified based on the trajectory of the host vehicle.

41. The non-transitory computer-readable medium according to claim 39, wherein the region of interest in the environment of the host vehicle is identified based on the route of the host vehicle.

42. The non-transitory computer-readable medium according to claim 39, wherein the region of interest in the environment of the host vehicle is identified based on the map information.

43. The non-transitory computer-readable medium according to claim 39, wherein the language model is configured to generate a language-based description of a scene.

44. A non-transitory computer-readable medium storing program instructions executable by at least one processor to perform a method, the method comprising: Receiving at least one image captured by a camera of the host vehicle from the environment of the host vehicle; Analyzing the at least one image to identify a region of interest in the environment of the host vehicle; Selecting a portion of the at least one image based on the region of interest; Receiving map information associated with the environment of the host vehicle, wherein the map information includes one or more identifiers of the route of the host vehicle; Providing the portion of the at least one image and the map information to a trained system, wherein the trained system is configured to generate one or more predictions using a language model architecture based on an analysis of the portion of the at least one image and the map information; Receiving an output provided by the trained system, wherein the output includes identifiers of objects in the environment of the host vehicle and positioning information of the objects relative to the map information; And Causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning information of the object.

45. A non-transitory computer-readable medium storing program instructions executable by at least one processor to perform a method, the method comprising: Receiving at least one image captured by a camera of the host vehicle from the environment of the host vehicle; Receiving map information associated with the environment of the host vehicle, wherein the map information includes one or more identifiers of the route of the host vehicle; Providing the at least one image and the map information to a trained system, wherein the trained system is configured to generate one or more predictions using a language model architecture based on an analysis of the at least one image and the map information; Receiving an output provided by the trained system, wherein the output includes identifiers of objects in the environment of the host vehicle and positioning information of the objects relative to the map information; And Causing the host vehicle to initiate at least one navigation action based on the identifier of the object and the positioning information of the object.

Images