System and method for determining navigation parameter

Abstract

To provide a navigation function for an autonomous vehicle using a camera.SOLUTION: A system for navigating a host vehicle may include a processing device. The processing device may be programmed to receive, from an image capturing device, at least one image representing an environment of the host vehicle, analyze the image, and identify an object in the environment of the host vehicle. The processing device may further be programmed to determine a location of the host vehicle and receive map information, which is map information associated with the determined location and includes elevation information associated with the environment of the host vehicle. Furthermore, the processing device may be programmed to determine a distance from the host vehicle to the object on the basis of the elevation information and determine a navigational action for the host vehicle on the basis of the determined distance.SELECTED DRAWING: Figure 41

Description

[Technical field]

[0001] [CROSS REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 652,029, filed April 3, 2018, and U.S. Provisional Patent Application No. 62 / 652,039, filed April 3, 2018. All of the above applications are incorporated herein by reference in their entirety. [Background technology]

[0002] The present disclosure relates generally to navigation for autonomous vehicles. [Background information]

[0003] As technology continues to advance, the goal of a fully autonomous vehicle capable of navigating roadways is in sight. An autonomous vehicle may need to consider various factors and make appropriate decisions based on those factors to safely and accurately reach a target destination. For example, an autonomous vehicle may need to process and interpret visual information (e.g., captured from a camera) and may also use information obtained from other sources (e.g., from a GPS device, speed sensors, accelerometers, suspension sensors, etc.). At the same time, to navigate to a destination, an autonomous vehicle may also need to identify a location within a particular roadway (e.g., a particular lane within a multi-lane road), navigate with other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and navigate from one road to another at appropriate intersections or interchanges. Utilizing and interpreting the vast amount of information collected by an autonomous vehicle as the vehicle navigates to its destination poses many design challenges. The sheer amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that an autonomous vehicle may need to analyze, access, and / or store poses challenges that may actually limit or even adversely affect autonomous navigation. Furthermore, if an autonomous vehicle relies on traditional mapping techniques to navigate, the sheer amount of data required to store and update maps poses a formidable challenge. Summary of the Invention

[0004] Embodiments consistent with the present disclosure provide systems and methods for navigation of an autonomous vehicle. The disclosed embodiments may provide navigation functions for an autonomous vehicle using cameras. For example, consistent with the disclosed embodiments, the disclosed systems may include one, two, or more cameras that monitor the vehicle's environment. The disclosed systems may provide a navigation response, for example, based on an analysis of images captured by one or more of the cameras.

[0005] Consistent with disclosed embodiments, a system for navigating a host vehicle is provided. The system may include at least one processing device. The at least one processing device may be programmed to receive at least one image representing an environment of the host vehicle from an image capture device. The at least one processing device may be further programmed to analyze the at least one image to identify objects within the environment of the host vehicle. The at least one processing device may be further programmed to determine a location of the host vehicle. The at least one processing device may be further programmed to receive map information associated with the determined location of the host vehicle, the map information including altitude information associated with the environment of the host vehicle. The at least one processing device may be further programmed to determine a distance from the host vehicle to the object based at least on the altitude information. The at least one processing device may be further programmed to determine a navigation operation for the host vehicle based on the determined distance.

[0006] Consistent with disclosed embodiments, a method for navigating a host vehicle is provided. The method may include receiving at least one image representative of an environment of the host vehicle from an image capture device. The method may further include analyzing the at least one image to identify objects within the environment of the host vehicle. The method may further include determining a location of the host vehicle. The method may further include receiving map information associated with the determined location of the host vehicle, the map information including altitude information associated with the environment of the host vehicle. The method may further include determining a distance from the host vehicle to the object based at least on the altitude information. The method may further include determining a navigation operation for the host vehicle based on the determined distance.

[0007] Consistent with disclosed embodiments, a system for navigating a host vehicle is provided. The system may include at least one processing device. The at least one processing device may be programmed to receive at least one image representing an environment of the host vehicle from an image capture device. The at least one processing device may be further programmed to analyze the at least one image to identify objects within the environment of the host vehicle. The at least one processing device may be further programmed to determine a location of the host vehicle. The at least one processing device may be further programmed to receive map information associated with the determined location of the host vehicle, the map information including lane width information associated with roads within the environment of the host vehicle. The at least one processing device may be further programmed to determine a distance from the host vehicle to the object based at least on the lane width information. The at least one processing device may be further programmed to determine a navigation operation for the host vehicle based on the determined distance.

[0008] Consistent with disclosed embodiments, a method for navigating a host vehicle is provided. The method may include receiving at least one image representative of an environment of the host vehicle from an image capture device. The method may further include analyzing the at least one image to identify objects within the environment of the host vehicle. The method may further include determining a location of the host vehicle. The method may further include receiving map information associated with the determined location of the host vehicle, the map information including lane width information associated with roads within the environment of the host vehicle. The method may further include determining a distance from the host vehicle to the object based on at least the lane width information. The method may further include determining a navigation operation for the host vehicle based on the determined distance.

[0009] Consistent with disclosed embodiments, a system for navigating a host vehicle is provided. The system may include at least one processing device. The at least one processing device may be programmed to receive at least one image representative of an environment of the host vehicle from an image capture device. The at least one processing device may be further programmed to analyze at least one of the plurality of images to identify a first object in the environment of the vehicle, the first object and a road on which the first object is located being at least partially obscured by a second object in the environment of the vehicle. The at least one processing device may be further programmed to determine scale change information for the first object based on at least two of the plurality of images. The at least one processing device may be further programmed to determine a lane position of the first object relative to a lane of a road on which the first object is located based on the determined scale change information for the first object. The at least one processing device may be further programmed to determine a navigation operation for the host vehicle based on the determined lane position of the first object.

[0010] Consistent with disclosed embodiments, a method for navigating a host vehicle is provided. The method may include receiving a plurality of images representing an environment of the host vehicle from an image capture device. The method may further include analyzing at least one of the plurality of images to identify a first object in the environment of the vehicle, the first object and a road on which the first object is located being at least partially obscured by a second object in the environment of the vehicle. The method may further include determining scale change information for the first object based on at least two of the plurality of images. The method may further include determining a lane position of the first object relative to a lane of a road on which the first object is located based on the determined scale change information for the first object. The method may further include determining a navigation operation for the host vehicle based on the determined lane position of the first object.

[0011] Consistent with disclosed embodiments, a system for navigating a host vehicle is provided. The system may include at least one processing device. The at least one processing device may be programmed to receive a plurality of images representing an environment of the host vehicle from an image capture device. The at least one processing device may be further programmed to analyze at least one of the plurality of images to identify a target vehicle within the environment of the host vehicle. The at least one processing device may be further programmed to receive map information associated with the environment of the host vehicle. The at least one processing device may be further programmed to determine a trajectory of the target vehicle over a period of time based on the analysis of the plurality of images. The at least one processing device may be further programmed to determine a position of the target vehicle relative to roads in the environment of the host vehicle based on the determined trajectory of the target vehicle and the map information. The at least one processing device may be further programmed to determine a navigation operation for the host vehicle based on the determined position of the target vehicle.

[0012] Consistent with disclosed embodiments, a method for navigating a host vehicle is provided. The method may include receiving a plurality of images representative of an environment of the host vehicle from an image capture device. The method may further include analyzing at least one of the plurality of images to identify a target vehicle within the environment of the host vehicle. The method may further include receiving map information associated with the environment of the host vehicle. The method may further include determining a trajectory of the target vehicle within a period of time based on the analysis of the plurality of images. The method may further include determining a position of the target vehicle relative to roads within the environment of the host vehicle based on the determined trajectory of the target vehicle and the map information. The method may further include determining a navigation operation for the host vehicle based on the determined position of the target vehicle.

[0013] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that, when executed by at least one processing device, perform any of the methods described herein.

[0014] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the scope of the appended claims. [Brief description of the drawings]

[0015] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments.

[0016] [Figure 1] FIG. 1 is a schematic diagram of an exemplary system consistent with disclosed embodiments.

[0017] [Figure 2A] FIG. 1 is a schematic side view of an exemplary vehicle including a system consistent with disclosed embodiments.

[0018] [Figure 2B] FIG. 2B is a schematic plan view of the vehicle and system shown in FIG. 2A consistent with disclosed embodiments.

[0019] [Figure 2C] FIG. 13 is a schematic plan view of another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0020] [Figure 2D] FIG. 13 is a schematic plan view of yet another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0021] [Figure 2E] FIG. 13 is a schematic plan view of yet another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0022] [Figure 2F] FIG. 1 is a schematic diagram of an example vehicle control system consistent with disclosed embodiments.

[0023] [Figure 3A] FIG. 1 is a schematic diagram of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with disclosed embodiments.

[0024] [Figure 3B] 1A-1C are diagrams of example camera mounts configured to be positioned behind a rearview mirror and opposite a vehicle windshield consistent with disclosed embodiments.

[0025] [Figure 3C] 3C is a view of the camera mount shown in FIG. 3B from a different perspective consistent with disclosed embodiments.

[0026] [Figure 3D] 1A-1C are diagrams of example camera mounts configured to be positioned behind a rearview mirror and opposite a vehicle windshield consistent with disclosed embodiments.

[0027] [Figure 4] FIG. 13 is an example block diagram of a memory configured to store instructions for performing one or more operations consistent with disclosed embodiments.

[0028] [Figure 5A] 1 is a flowchart illustrating an example process for making one or more navigational responses based on monocular image analysis consistent with disclosed embodiments.

[0029] [Figure 5B] 1 is a flowchart illustrating an example process for detecting one or more vehicles and / or pedestrians in a set of images consistent with disclosed embodiments.

[0030] [Figure 5C] 1 is a flowchart illustrating an example process for detecting road markings and / or lane shape information in a set of images consistent with disclosed embodiments.

[0031] [Figure 5D] 1 is a flowchart illustrating an example process for detecting traffic lights in a set of images consistent with disclosed embodiments.

[0032] [Figure 5E] 1 is a flowchart illustrating an example process for making one or more navigational responses based on a vehicle route consistent with disclosed embodiments.

[0033] [Figure 5F] 1 is a flowchart illustrating an example process for determining whether a leading vehicle is changing lanes consistent with disclosed embodiments.

[0034] [Figure 6] 1 is a flowchart illustrating an example process for performing one or more navigational responses based on stereo image analysis consistent with disclosed embodiments.

[0035] [Figure 7] 11 is a flowchart illustrating an example process for making one or more navigational responses based on analysis of three sets of images consistent with disclosed embodiments.

[0036] [Figure 8] 1 illustrates a sparse map for providing navigation for an autonomous vehicle consistent with disclosed embodiments.

[0037] [Figure 9A] 1 illustrates a polynomial representation of a portion of a road segment consistent with disclosed embodiments.

[0038] [Figure 9B] 1 illustrates a curve in three-dimensional space representing a target trajectory of a vehicle for a particular road segment contained in a sparse map consistent with disclosed embodiments.

[0039] [Figure 10] 1 illustrates example landmarks that may be included in a sparse map consistent with disclosed embodiments.

[0040] [Figure 11A] 1 illustrates a polynomial representation of a trajectory consistent with disclosed embodiments.

[0041] [Figure 11B] 1 illustrates a target trajectory along a multi-lane road consistent with disclosed embodiments. [Figure 11C] 1 illustrates a target trajectory along a multi-lane road consistent with disclosed embodiments.

[0042] [Figure 11D] 1 illustrates an example road signature profile consistent with disclosed embodiments.

[0043] [Figure 12] FIG. 1 is a schematic diagram of a system that uses crowdsourced data received from multiple vehicles for navigation of an autonomous vehicle consistent with disclosed embodiments.

[0044] [Figure 13] 1 illustrates an example autonomous vehicle road navigation model represented by a number of 3D splines consistent with disclosed embodiments.

[0045] [Figure 14] 1 illustrates an overview of a map generated from combining location information from multiple drives consistent with disclosed embodiments.

[0046] [Figure 15]13 shows an example of longitudinal alignment of two runs using exemplary markers as landmarks consistent with disclosed embodiments.

[0047] [Figure 16] 13 shows an example of longitudinal alignment of a number of runs using exemplary signs as landmarks consistent with disclosed embodiments.

[0048] [Figure 17] FIG. 1 is a schematic diagram of a system for generating driving data using a camera, a vehicle, and a server consistent with disclosed embodiments.

[0049] [Figure 18] FIG. 1 is a schematic diagram of a system for crowdsourcing a sparse map consistent with disclosed embodiments.

[0050] [Figure 19] 1 is a flowchart illustrating an example process for generating a sparse map for navigation of an autonomous vehicle along road segments consistent with disclosed embodiments.

[0051] [Figure 20] FIG. 1 illustrates a block diagram of a server consistent with disclosed embodiments.

[0052] [Figure 21] FIG. 1 illustrates a block diagram of a memory consistent with disclosed embodiments.

[0053] [Figure 22] 1 illustrates a process for clustering vehicle trajectories associated with a vehicle consistent with disclosed embodiments.

[0054] [Figure 23] 1 illustrates a vehicle navigation system that may be used for autonomous navigation consistent with disclosed embodiments.

[0055] [Figure 24] FIG. 1 illustrates a block diagram of a memory consistent with disclosed embodiments.

[0056] [Figure 25A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0057] [Figure 25B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0058] [Figure 26] 1 shows a flowchart illustrating an example process for navigating a host vehicle consistent with disclosed embodiments.

[0059] [Figure 27A] 1 illustrates two example splines in three-dimensional coordinates consistent with disclosed embodiments.

[0060] [Figure 27B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0061] [Figure 28A] 1 illustrates two example splines in three-dimensional coordinates consistent with disclosed embodiments.

[0062] [Figure 28B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0063] [Figure 29A] 1 illustrates an example spline in two-dimensional coordinates consistent with disclosed embodiments.

[0064] [Figure 29B] 1 illustrates an example spline in three-dimensional coordinates consistent with disclosed embodiments.

[0065] [Diagram 30] 1 illustrates an example spline projected onto two-dimensional coordinates consistent with disclosed embodiments.

[0066] [Diagram 31] 1 shows the results of a Delaunay triangulation consistent with disclosed embodiments.

[0067] [Diagram 32] 13 illustrates a related triangle projected onto an image based on a camera localization consistent with disclosed embodiments.

[0068] [Diagram 33] 1 shows a flowchart illustrating an example process for navigating a host vehicle consistent with disclosed embodiments.

[0069] [Figure 34A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0070] [Figure 34B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0071] [Figure 35A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0072] [Figure 35B] 13 illustrates exemplary received images at t1 and t2 consistent with disclosed embodiments.

[0073] [Figure 36A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0074] [Figure 36B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0075] [Figure 37] 1 shows a flowchart illustrating an example process for navigating a host vehicle consistent with disclosed embodiments.

[0076] [Figure 38A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0077] [Figure 38B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0078] [Figure 38C] FIG. 13 shows a diagram illustrating the relationship between the position (x) and width (w) of a target vehicle in a received image consistent with disclosed embodiments.

[0079] [Figure 39A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0080] [Figure 39B] 1 illustrates an exemplary received image consistent with a disclosed embodiment.

[0081] [Figure 40A] 1 illustrates an example position of a host vehicle relative to objects on a roadway consistent with disclosed embodiments.

[0082] [Figure 40B] 13 illustrates an example received image at t1 consistent with disclosed embodiments.

[0083] [Figure 40C] 13 illustrates an exemplary received image at t2 consistent with disclosed embodiments.

[0084] [Diagram 41] 1 shows a flowchart illustrating an example process for navigating a host vehicle consistent with disclosed embodiments.

[0085] [Diagram 42] 1 illustrates an example driving scenario in which a distance to a detected target vehicle may be determined. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0086] In the following detailed description, reference is made to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. Although several exemplary embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the components shown in the drawings, and the exemplary methods described herein may be modified by substituting, rearranging, removing, or adding steps to the disclosed methods. Thus, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0087] Overview of Autonomous Vehicles

[0088] As used in this disclosure, the term "autonomous vehicle" refers to a vehicle capable of implementing at least one navigational change without driver input. A "navigational change" refers to a change in one or more of the vehicle's steering, braking, or acceleration. To be autonomous, a vehicle need not be fully automatic (e.g., completely operating without a driver or driver input). Rather, autonomous vehicles include those that can operate under driver control during certain periods and without driver control during other periods. Autonomous vehicles may also include vehicles that may only control some aspects of vehicle navigation, such as steering (e.g., keeping the vehicle on a course between the vehicle's lane constraints), but leave other aspects (e.g., braking) to the driver. In some cases, an autonomous vehicle may handle some or all aspects of the vehicle's braking, speed control, and / or steering.

[0089] Human drivers typically rely on visual cues and observations to control the vehicle, and thus traffic infrastructure is formed with lane markings, traffic signs, and traffic lights all designed to provide visual information to the driver. Taking these design characteristics of traffic infrastructure into account, an autonomous vehicle may include a camera and a processing unit that analyzes visual information captured from the vehicle's environment. The visual information may include, for example, traffic infrastructure components observable by the driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Additionally, an autonomous vehicle may also use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, the vehicle may use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information related to the environment while the vehicle is traveling, and the vehicle (like other vehicles) may use the information to locate itself on the model.

[0090] In some embodiments of the present disclosure, an autonomous vehicle may use information obtained while navigating (e.g., from cameras, GPS devices, accelerometers, speed sensors, suspension sensors, etc.). In other embodiments, an autonomous vehicle may use information obtained from past navigation by the vehicle (or by other vehicles) while navigating. In yet other embodiments, an autonomous vehicle may use a combination of information obtained while navigating and information obtained from past navigation. The following section provides an overview of a system consistent with disclosed embodiments, followed by an overview of a forward-looking imaging system and methods consistent with the system. Subsequent sections disclose systems and methods for building, using, and updating sparse maps for autonomous vehicle navigation.

[0091] System Overview

[0092] FIG. 1 is a block diagram representation of a system 100 consistent with exemplary disclosed embodiments. System 100 may include various components depending on the requirements of a particular implementation. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. Processing unit 110 may include one or more processing devices. In some embodiments, processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements of a particular application. In some embodiments, image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 may also include a data interface 128 that communicatively connects processing device 110 to image acquisition device 120. For example, data interface 128 may include any one or more wired and / or wireless links for transmitting image data acquired by image acquisition device 120 to processing unit 110.

[0093] Wireless transceiver 172 may include one or more devices configured to send and receive transmissions over an air interface to one or more networks (e.g., cellular, Internet, etc.) using radio frequencies, infrared frequencies, magnetic fields, or electric fields. Wireless transceiver 172 may transmit and / or receive data using any known standard (e.g., Wi-Fi, Bluetooth, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications from the host vehicle to one or more remotely located servers. Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to facilitate adjustment of the host vehicle's navigation in light of or together with the target vehicles in the host vehicle's environment), or broadcast transmissions to unspecified recipients in the vicinity of the transmitting vehicle.

[0094] Both application processor 180 and image processor 190 may include various types of processing devices. For example, either or both of application processor 180 and image processor 190 may include a microprocessor, a preprocessor (e.g., an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for executing applications and image processing and analysis. In some embodiments, application processor 180 and / or image processor 190 may include any type of single or multi-core processor, mobile device microcontroller, central processing unit, etc. A variety of processing devices may be used, including, for example, processors available from manufacturers such as Intel®, AMD®, or GPUs available from manufacturers such as NVIDIA®, ATI®, etc., and may include a variety of architectures (e.g., x86 processor, ARM®, etc.).

[0095] In some embodiments, the application processor 180 and / or the image processor 190 may include any of the EyeQ series of processor chips available from Mobileye. Each of these processor designs includes multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors and may also include video output capabilities. In one example, the EyeQ2 uses 90 nm-micron technology operating at 332 MHz. The EyeQ2 architecture consists of two floating-point, hyper-threaded 32-bit RISC CPUs (MIPS32 34K cores), five Vision-Computing-Engines (VCEs), three Vector-Microcode Processors (VMPs), a Denali-64-bit mobile DDR controller, a 128-bit internal Sonics interconnect, a 16-bit dual video input and 18-bit video output controller, a 16-channel DMA, and several peripherals. The MIPS34K CPU manages the 5 VCEs, 3 VMPs and DMA, the second MIPS34K CPU, and the multi-channel DMA and other peripherals. The 5 VCEs, 3 VMPs and MIPS34K CPU can perform intensive visual calculations required by multi-function bundle applications. In another example, the EyeQ3, which is a third generation processor and is more than six times more powerful than the EyeQ2, can be used in the disclosed embodiments. In another example, the EyeQ4 and / or EyeQ5 can be used in the disclosed embodiments. Of course, any new or future EyeQ processing device may be used with the disclosed embodiments.

[0096] Any of the processing devices disclosed herein may be configured to perform a particular function. Configuring a processing device, such as any of the described EyeQ processors or other controllers or microprocessors, to perform a particular function may include programming computer-executable instructions and making those instructions available to the processing device for execution during operation of the processing device. In some embodiments, configuring a processing device may include directly programming the processing device with architectural instructions. For example, processing devices, such as field programmable gate arrays (FPGAs) and application specific integrated circuits (ASICs), may be configured using, for example, one or more hardware description languages ​​(HDLs).

[0097] In other embodiments, configuring the processing device may include storing executable instructions in a memory accessible to the processing device during operation. For example, the processing device may access the memory to retrieve and execute the stored instructions during operation. In any event, a processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system that controls multiple hardware-based components of a host vehicle.

[0098] 1 shows two separate processing devices included in processing unit 110, more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to 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. Additionally, in some embodiments, system 100 may include one or more processing units 110 that do not include other components, such as image acquisition unit 120.

[0099] The processing unit 110 may include various types of devices. For example, the processing unit 110 may include various devices such as a controller, an image preprocessor, a central processing unit (CPU), a graphics processing unit (GPU), support circuits, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image preprocessor may include a video processor that captures, digitizes, and processes images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may include any number of microcontrollers or microprocessors. The support circuits may be any number of circuits commonly known in the art, including cache, power supplies, clocks, and input-output circuits. The memory may store software that, when executed by the processor, controls the operation of the system. The memory may include databases and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage devices, tape storage, removable storage, and other types of storage devices. In one example, the memory may be separate from the processing unit 110. In another example, the memory may be integrated into the processing unit 110.

[0100] Each memory 140, 150 may contain software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. These memory units may include various databases and image processing software, as well as trained systems, such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read only memory (ROM), flash memory, disk drives, optical storage, tape storage, removable storage, 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.

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

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

[0103] User interface 170 may include any device suitable for providing information to or receiving input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices including, for example, a touch screen, a microphone, a keyboard, a pointer device, a track wheel, a camera, 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, selecting on-screen menu options using buttons, pointer or eye tracking capabilities, or through any other suitable technique for communicating information to system 100.

[0104] User interface 170 may comprise one or more processing devices configured to provide and receive information to and from a user, e.g., process information for use by 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 in response to keyboard entries or menu selections, etc. In some embodiments, user interface 170 may include a display, a speaker, a haptic device, and / or any other device for providing output information to a user.

[0105] Map database 160 may include any type of database for storing map data useful to system 100. In some embodiments, map database 160 may include data related to the locations in a reference coordinate system of various items, including roads, water features, geographic features, businesses, points of interest, restaurants, gas stations, and the like. Map database 160 may store not only the locations of such items, but also descriptors related to those items, including, for example, names associated with any of the stored features. In some embodiments, map database 160 may be physically located with other components of system 100. Alternatively or in addition, map database 160 or portions thereof may be located remotely relative to other components of system 100 (e.g., processing unit 110). In such embodiments, information from map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, map database 160 may store sparse data models including polynomial representations composed of specific road features (e.g., lane markings) or target trajectories relative to the host vehicle. Systems and methods for generating such maps are discussed below with reference to FIGS.

[0106] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from an environment. Additionally, any number of image capture devices may be used to obtain images for input to the image processor. In some embodiments, only a single image capture device may be included, while other embodiments may include two, three, or even four or more image capture devices. Image capture devices 122, 124, and 126 are further described below with reference to Figures 2B-2E.

[0107] System 100 or various components thereof may be incorporated into a variety of different platforms. In some embodiments, system 100 may be included in vehicle 200, as shown in FIG. 2A. For example, vehicle 200 may include processing unit 110 and any of the other components of system 100, as described above in connection with FIG. 1. In some embodiments, vehicle 200 may include only a single image capture device (e.g., a camera), while in other embodiments, multiple image capture devices may be used, for example, as discussed in connection with FIGS. 2B-2E. As shown in FIG. 2A, for example, any of image capture devices 122 and 124 of vehicle 200 may be part of an ADAS (Advanced Driver Assistance System) imaging set.

[0108] The image capture device included in vehicle 200 as part of image acquisition unit 120 may be located in any suitable location. In some embodiments, as shown in Figures 2A-2E and 3A-3C, image capture device 122 may be located near the rearview mirror. This location may provide a line of sight similar to that of the driver of vehicle 200 and may be helpful in determining what the driver can and cannot see. Image capture device 122 may be located in any location near the rearview mirror, although locating image capture device 122 on the driver's side of the mirror may be more helpful in capturing images representative of the driver's field of view and / or line of sight.

[0109] Other locations for the image capture devices of the image acquisition unit 120 may be used. For example, the image capture device 124 may be located on or in the bumper of the 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 an image capture device located on the bumper may be different from the line of sight of the driver, and thus the image capture device on the bumper and the driver do not always see the same object. The image capture devices (e.g., image capture devices 122, 124, and 126) may be located in other locations. For example, the image capture devices may be mounted on or in one or both of the side mirrors of the vehicle 200, on the roof of the vehicle 200, on the hood of the vehicle 200, on the trunk of the vehicle 200, on the side of the vehicle 200, mounted behind any of the windows of the vehicle 200, or mounted in front of any of the windows of the vehicle 200, on or near a light exterior at the front and / or rear of the vehicle 200, etc.

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

[0111] As previously discussed, the wireless transceiver 172 may transmit and / or receive data over one or more networks (e.g., a cellular network, the Internet, etc.). For example, the wireless transceiver 172 may upload data collected by the system 100 to one or more servers and download data from one or more servers. Through the wireless transceiver 172, the system 100 may receive periodic or on-demand updates to data stored in, for example, the map database 160, the memory 140, and / or the memory 150. Similarly, the wireless transceiver 172 may upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, a vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

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

[0113] In some embodiments, system 100 may upload data according to a "high" privacy level, where under a set setting system 100 may transmit data (e.g., location information associated with a route, captured images, etc.) without detailed information about a particular vehicle and / or driver / owner. For example, when uploading data according to a "high" privacy setting, system 100 may not include the vehicle identification number (VIN) or the name of the vehicle's driver or owner, and instead transmit data, e.g., captured images associated with a route and / or limited location information.

[0114] Other privacy levels are contemplated. For example, the system 100 may transmit data to the server according to a "medium" privacy level, which may include additional information not included under a "high" privacy level, such as the make and / or model of the vehicle, and / or vehicle type (e.g., car, SUV, truck, etc.). In some embodiments, the system 100 may upload data according to a "low" privacy level. Under a "low" privacy level setting, the system 100 may upload data and include sufficient information to uniquely identify a particular vehicle, owner / driver, and / or some or all of the route traveled by the vehicle. Such "low" privacy level data may include, for example, one or more of the VIN, driver / owner name, starting point of the vehicle prior to departure, intended destination of the vehicle, make and / or model of the vehicle, type of vehicle, etc.

[0115] FIG 2A is a schematic side view of an exemplary vehicle imaging system consistent with disclosed embodiments. FIG 2B is a schematic top view illustration of the embodiment shown in FIG 2A. As shown in FIG 2B, the disclosed embodiments may include a vehicle 200 including a system 100 on its body having a first image capture device 122 disposed near a rearview mirror of the vehicle 200 and / or near a driver, a second image capture device 124 disposed on or in a bumper area of ​​the vehicle 200 (e.g., one of the bumper areas 210), and a processing unit 110.

[0116] As shown in Figure 2C, both image capture devices 122 and 124 may be located near the rearview mirror and / or near the driver of vehicle 200. Additionally, while two image capture devices 122 and 124 are shown in Figures 2B and 2C, it should be understood that other embodiments may include more than two image capture devices. For example, in the embodiment shown in Figures 2D and 2E, first, second and third image capture devices 122, 124 and 126 are included in system 100 of vehicle 200.

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

[0118] It should be understood that the disclosed embodiments are not limited to vehicles and may be applied in other contexts. It should also be understood that the disclosed embodiments are not limited to a particular type of vehicle 200 and may be applicable to any type of vehicle, including cars, trucks, trailers, and other types of vehicles.

[0119] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024 WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280×960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included to provide a desired focal length and field of view for the image capture device, for example. In some embodiments, the image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, the image capture device 122 may be configured to capture an image having a desired field of view (FOV) 202, as shown in FIG. 2D. For example, image capture device 122 may be configured to have a standard FOV, including, for example, a 46 degree FOV, a 50 degree FOV, a 52 degree FOV, or a larger FOV, for example, within a range of 40 degrees to 56 degrees. Alternatively, image capture device 122 may be configured to have a narrow FOV, for example, a 28 degree FOV or a 36 degree FOV, within a range of 23 to 40 degrees. Additionally, image capture device 122 may be configured to have a wide FOV, for example, within a range of 100 to 180 degrees. In some embodiments, image capture device 122 may include a wide angle bumper camera or a camera with an FOV up to 180 degrees. In some embodiments, image capture device 122 may be a 7.2M pixel image capture device with an aspect ratio of about 2:1 (e.g., HxV=3800×1900 pixels) with a horizontal FOV of about 100 degrees. Such an image capture device may be used in place of the three image capture device configuration. Due to significant lens distortion, the vertical FOV of such an image capture device may be significantly less than 50 degrees in implementations where the image capture device uses a radially symmetric lens. For example, such a lens may not be radially symmetric to allow a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

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

[0121] The first image capture device 122 may have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate may refer to the rate at which the image sensor can acquire image data associated with each pixel included in a particular scan line.

[0122] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors including, for example, CCD sensors or CMOS sensors. In one embodiment, a CMOS image sensor may be used with a rolling shutter, where each pixel in a row is read one at a time, and the scanning of the rows proceeds row by row until the entire image frame has been captured. In some embodiments, the rows may be captured sequentially from top to bottom for the frame.

[0123] 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 camera and may have a resolution of greater than 5M pixels, 7M pixels, 10M pixels, or more.

[0124] The use of a rolling shutter may result in pixels in different rows being exposed and captured at different times, which may cause skew and other image artifacts in the captured image frame. On the other hand, for an image capture device 122 configured to operate with a global shutter or a synchronous shutter, all pixels may be exposed for the same amount of time during a common exposure time. As a result, image data in a frame collected from a system using a global shutter represents a snapshot of the entire FOV (e.g., FOV 202) at a particular time. In contrast, when applying a rolling shutter, each row in a frame is exposed and data is captured at a different time. Thus, moving objects may exhibit distortion in an image capture device with a rolling shutter. This phenomenon is explained in more detail below.

[0125] The second image capture device 124 and the third image capture device 126 may be any type of image capture device. Like the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Like 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 (e.g., FOVs 204 and 206) that is the same as or narrower than the FOV (e.g., FOV 202 associated with the image capture device 122). For example, the image capture devices 124 and 126 may have an FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees or less.

[0126] The image capture devices 124 and 126 may acquire a plurality of second and third images related to a scene associated with the 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. The image capture devices 124 and 126 may have second and third scan rates associated with acquiring each of the image scan lines in the second and third series.

[0127] Each image capture device 122, 124, and 126 may be positioned at any suitable location and orientation with respect to vehicle 200. The relative placement of image capture devices 122, 124, and 126 may be selected to aid in combining information obtained from the image capture devices with each other. For example, in some embodiments, the FOV associated with image capture device 124 (e.g., FOV 204) may partially or completely overlap with the FOV associated with image capture device 122 (e.g., FOV 202) and the FOV associated with image capture device 126 (e.g., FOV 206).

[0128] The image capture devices 122, 124, and 126 may be positioned on the vehicle 200 at any suitable relative height. In one example, there may be a height difference between the image capture devices 122, 124, and 126, which may provide sufficient disparity information to enable stereo analysis. For example, as shown in FIG. 2A, the two image capture devices 122 and 124 have different heights. There may also be a lateral misalignment difference between the image capture devices 122, 124, and 126, e.g., to provide additional disparity information for stereo analysis by the processing unit 110. As shown in FIGS. 2C and 2D, the difference in lateral misalignment may be d xIn some embodiments, a forward or rear offset (e.g., range offset) may exist between image capture devices 122, 124, and 126. For example, image capture device 122 may be positioned 0.5 to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of offset may allow one of the image capture devices to cover a possible blind spot of the other image capture device.

[0129] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor associated with image capture device 122 may be higher, lower, or the same as the resolution of the image sensors associated with image capture devices 124 and 126. In some embodiments, the image sensors associated with image capture device 122 and / or image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0130] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame before moving on to capture pixel data associated with the next image frame) may be controllable. The frame rate associated with image capture device 122 may be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame rates associated with image capture devices 122, 124, and 126 may depend on various factors that may affect the timing of the frame rate. For example, one or more of image capture devices 122, 124, and 126 may include a selectable pixel delay time before or after acquiring image data associated with one or more pixels of an image sensor in image capture devices 122, 124, and / or 126. In general, image data corresponding to each pixel may be acquired according to a clock rate for the device (e.g., one clock cycle per pixel). Additionally, in embodiments including a rolling shutter, one or more of image capture devices 122, 124, and 126 may include a selectable horizontal blanking period that occurs before and after acquiring image data associated with a row of pixels of an image sensor in image capture devices 122, 124, and / or 126. Additionally, one or more of image capture devices 122, 124, and / or 126 may include a selectable vertical blanking period that occurs before and after acquiring image data associated with an image frame of image capture devices 122, 124, and 126.

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

[0132] The timing of frame rates at image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, assuming similar line scan rates for both devices, if one device includes an image sensor with a resolution of 640×480 and the other device includes an image sensor with a resolution of 1280×960, more time will be required to acquire a frame of image data from the sensor with the higher resolution.

[0133] Another factor that may affect the timing of image data acquisition in image capture devices 122, 124, and 126 is the maximum line scan rate. For example, acquisition of a row of image data from an image sensor included in image capture devices 122, 124, and 126 requires a certain minimum amount of time. Assuming no pixel delay time is added, this minimum amount of time to acquire one row of image data is related to the maximum line scan rate for the particular device. A device that exhibits a higher maximum line scan rate may provide a higher frame rate than a device having a lower maximum line scan rate. In some embodiments, one or more of image capture devices 124 and 126 may have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 may be 1.25 times, 1.5 times, 1.75 times, 2 times, or more, greater than the maximum line scan rate of image capture device 122.

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

[0135] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric; that is, they may 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 may include any desired area relative to the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to capture image data from an environment in front of vehicle 200, behind vehicle 200, to the side of vehicle 200, or a combination thereof.

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

[0137] According to some embodiments, the FOV of one or more of image capture devices 122, 124, and 126 may have a wide angle. For example, it may be advantageous to have an FOV of 140 degrees, especially for image capture devices 122, 124, and 126 that may be used to capture images of areas in the vicinity of vehicle 200. For example, image capture device 122 may be used to capture images of areas on the right or left side of vehicle 200, and in such embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0138] 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.

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

[0140] System 100 may be configured such that the field of view of image capture device 122 at least partially or completely overlaps the field of view of image capture device 124 and / or image capture device 126. In some embodiments, system 100 may be configured such that the fields of view of image capture devices 124 and 126 are contained within (e.g., narrower than) the field of view of image capture device 122 and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs or may have partially overlapping portions in their FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 may be aligned such that the center of narrow FOV image capture device 124 and / or 126 may be located in the bottom half of the field of view of wide FOV device 122.

[0141] 2F is a schematic diagram of an example vehicle control system consistent with disclosed embodiments. As shown in FIG. 2F, vehicle 200 may include a throttling system 220, a braking system 230, and a steering system 240. System 100 may provide inputs (e.g., control signals) to one or more of throttling system 220, braking system 230, and steering system 240 via one or more data links (e.g., any one or more wired and / or wireless links for transmitting data). For example, based on analysis of images acquired by image capture devices 122, 124, and / or 126, system 100 may provide control signals to one or more of throttling system 220, braking system 230, and steering system 240 to navigate vehicle 200 (e.g., by accelerating, turning, changing lanes, etc.). Additionally, system 100 may receive inputs from one or more of throttling system 220, braking system 230, and steering system 240 indicative of operating conditions of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.). Further details are provided below in connection with FIGS. 4-7.

[0142] As shown in FIG. 3A , the vehicle 200 may include a user interface 170 for interacting with a driver or passenger of the vehicle 200. For example, the user interface 170 applied to the vehicle may include a touch screen 320, a knob 330, a button 340, and a microphone 350. The driver or passenger of the vehicle 200 may interact with the system 100 using a handle (e.g., located on or near the steering column of the vehicle 200, including a turn signal handle), a button (e.g., located on the steering wheel of the vehicle 200), and the like. In some embodiments, the microphone 350 may be located 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 include one or more speakers 360 (e.g., speakers of the vehicle's audio system). For example, the system 100 may provide various notifications (e.g., alerts) via the speaker 360.

[0143] 3B-3D are diagrams of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and facing a vehicle windshield, consistent with disclosed embodiments. As shown in FIG. 3B, 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 with the vehicle windshield and may include a film and / or anti-reflective material configuration. For example, the glare shield 380 may be positioned to align the shield against the vehicle windshield with a matching tilt. In some embodiments, each of the image capture devices 122, 124, and 126 may be positioned behind the glare shield 380, for example, as illustrated in FIG. 3D. The disclosed embodiments are not limited to any particular configuration of image capture devices 122, 124, and 126, camera mount 370, and glare shield 380. Figure 3C is a view of camera mount 370 shown in Figure 3B from the front.

[0144] As will be appreciated by those skilled in the art having access to this disclosure, numerous variations and / or modifications may be made to the disclosed embodiments above. For example, not all components are essential to the operation of system 100. Furthermore, any component may be located in any suitable portion of system 100, and the components may be reconfigured in various configurations while still providing the functionality of the disclosed embodiments. Thus, the above configurations are examples, and regardless of the configuration described above, system 100 can provide a wide range of functionality, such as analyzing the surroundings of vehicle 200 and navigating vehicle 200 in response to the analysis.

[0145] As discussed in further detail below and consistent with various disclosed embodiments, system 100 may provide various features related to autonomous driving and / or driver assistance technologies. For example, system 100 may analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in vehicle 200. System 100 may collect data for analysis from, for example, image capture unit 120, location sensor 130, and other sensors. Additionally, system 100 may analyze the collected data to determine whether vehicle 200 should perform a particular action, and then automatically perform the determined action without human intervention. For example, when vehicle 200 navigates without human intervention, system 100 may automatically control braking, acceleration, and / or steering of vehicle 200 (e.g., by sending control signals to one or more of throttling system 220, braking system 230, and steering system 240). Additionally, system 100 may analyze the collected data and issue warnings and / or alerts to vehicle occupants based on the analysis of the collected data. Further details regarding various embodiments provided by system 100 are provided below.

[0146] Forward-looking multi-imaging system

[0147] As described above, the system 100 may provide a driver assistance function using a multi-camera system. The multi-camera system may use one or more cameras facing in the direction of travel 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, the system 100 may use a two-camera imaging system, where a first camera and a second camera (e.g., image capture devices 122 and 124) may be located in front of and / or on the side of the vehicle (e.g., vehicle 200). The first camera may have a field of view that is wider, narrower, or overlaps with the field of view of the second camera. Furthermore, the first camera may be connected to a first image processor that performs monocular image analysis of the image provided by the first camera, and the second camera may be connected to a second image processor that performs monocular image analysis of the image provided by the second camera. The outputs (e.g., processed information) of the first and second image processors may be combined. In some embodiments, the second image processor may receive images from both the first and second cameras to perform stereo analysis. In another embodiment, the system 100 may use a three camera imaging system with each camera having a different field of view. Such a system may therefore make decisions based on information derived from objects located at various distances both in front of and to the side of the vehicle. References to monocular image analysis may refer to instances 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 instances where image analysis is performed based on two or more images captured with one or more variations of image capture parameters. For example, captured images suitable for performing stereo image analysis may include images captured from two or more different positions, from various fields of view, with different focal lengths, with disparity information, etc.

[0148] For example, in one embodiment, system 100 may implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 may provide a narrow field of view (e.g., 34 degrees or other value selected from a range such as about 20 to 45 degrees), image capture device 124 may provide a wide field of view (e.g., 150 degrees or other value selected from a range of about 100 to about 180 degrees), and image capture device 126 may provide an intermediate field of view (e.g., 46 degrees or other value selected from a range of about 35 to about 60 degrees). In some embodiments, image capture device 126 may operate as a main or primary camera. Image capture devices 122, 124, and 126 may be positioned behind rearview mirror 310 and positioned substantially side-by-side (e.g., 6 cm apart). Additionally, in some embodiments, as described above, one or more of the image capture devices 122, 124, and 126 may be mounted behind a glare shield 380 that fits flush against the windshield of the vehicle 200. Such a shield may operate to minimize the effect of any reflections from the interior of the vehicle on the image capture devices 122, 124, and 126.

[0149] In another embodiment, as described above in connection with Figures 3B and 3C, the wide field of view camera (e.g., image capture device 124 in the above example) may be mounted lower than the narrow and main field of view cameras (e.g., image devices 122 and 126 in the above example). This configuration may provide a free line of sight from the wide field of view camera. To reduce reflections, the camera may be mounted near the windshield of vehicle 200 and may include a polarizer on the camera to attenuate reflected light.

[0150] A three-camera system may provide certain performance characteristics. For example, some embodiments may include the ability to verify detection of an object by one camera based on detection results from another camera. In the three-camera configuration described above, processing unit 110 may include three processing devices (e.g., three EyeQ series of processor chips as described above), e.g., each processing device specialized to process images captured by one or more of image capture devices 122, 124, and 126.

[0151] In a three-camera system, the first processing device may receive images from both the main camera and the narrow FOV camera and may perform vision processing of the narrow FOV camera to detect, for example, other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. Additionally, the first processing device may calculate pixel disparity between the images from the main camera and the narrow camera to generate a 3D reconstruction of the environment of the vehicle 200. The first processing device may then combine the 3D reconstruction with 3D map data or with 3D information calculated based on information from another camera.

[0152] 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 pixel disparity between the sequence of images to generate a 3D reconstruction of the scene (e.g., structure from motion). The second processing device may transmit to the first processing device the structure from motion based 3D reconstruction of the object that is combined with the stereo 3D images.

[0153] The third processing device may receive images from the wide FOV camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device may further execute additional processing instructions to analyze the images and identify objects moving within the images, such as vehicles changing lanes, pedestrians, etc.

[0154] In some embodiments, streams of image-based information may be captured and processed independently, providing an opportunity for providing system redundancy. Such redundancy may include, for example, using a first image capture device and processed images from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0155] In some embodiments, system 100 may use two image capture devices (e.g., image capture devices 122 and 124) in providing navigation assistance to vehicle 200, and may use a third image capture device (e.g., image capture device 126) to provide redundancy and verify analysis of data received from the other two image capture devices. For example, in such a configuration, image capture devices 122 and 124 may provide images for stereo analysis by system 100 to navigate vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of information obtained based on images captured from image capture devices 122 and / or image capture device 124. That is, image capture device 126 (and corresponding processing device) may be viewed as providing a redundant subsystem to provide a check on the analysis derived from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Further, in some embodiments, redundancy and validation of the received data may be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers external to the vehicle, etc.).

[0156] Those skilled in the art will recognize that the above camera configurations, camera placements, number of cameras, camera locations, etc. are merely examples. These components and others described for the overall system may be assembled and used in a variety of different configurations without departing from the scope of the disclosed embodiments. Further details regarding the use of multi-camera systems to provide driver assistance and / or autonomous vehicle functionality are provided below.

[0157] 4 is an example functional block diagram of memory 140 and / or 150, which may be stored / programmed with instructions for performing one or more operations not inconsistent with the disclosed embodiments. Although reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0158] 4, memory 140 may store monocular image analysis module 402, stereo image analysis module 404, velocity and acceleration module 406, and navigation response module 408. The disclosed embodiments are not limited to a particular configuration of memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of modules 402, 404, 406, and 408 included in memory 140. Those skilled in the art will appreciate that references in the following description to processing unit 110 may refer to application processor 180 and image processor 190 individually or collectively. Thus, any steps of the following processes may be performed by one or more processing devices.

[0159] In one embodiment, the monocular image analysis module 402 may store instructions (e.g., computer vision software) that, when executed by the processing unit 110, perform monocular image analysis of a set of images acquired by one of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform the monocular image analysis. As described below in connection with FIGS. 5A-5D, the monocular image analysis module 402 may include instructions for detecting a set of features in the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazards, and any other features associated with the vehicle's environment. Based on the analysis, the system 100 (e.g., via the processing unit 110) may cause one or more navigational responses in the vehicle 200, such as turning, changing lanes, and changing acceleration, as discussed below in connection with the navigation response module 408.

[0160] In one embodiment, the stereo image analysis module 404 may store instructions (e.g., computer vision software) that, when executed by the processing unit 110, performs stereo image analysis on a first and second set of images captured by a combination of image capture devices selected from any of the image capture devices 122, 124, and 126. In some embodiments, the processing unit 110 may combine information from the first and second sets of images with additional sensory information (e.g., information from radar) to perform stereo image analysis. For example, the stereo image analysis module 404 may include instructions to perform stereo image analysis based on a first set of images captured by the image capture device 124 and a second set of images captured by the image capture device 126. As described below in connection with FIG. 6, the stereo image analysis module 404 may include instructions to detect a set of features in the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and hazards. Based on the analysis, processing unit 110 may cause one or more navigational responses in vehicle 200, such as turning, changing lanes, and changing acceleration, as discussed below in connection with navigational response module 408. Additionally, in some embodiments, stereo image analysis module 404 may implement techniques associated with trained systems (e.g., neural networks or deep neural networks) or untrained systems, e.g., systems that may be configured to use computer vision algorithms to detect and / or classify objects in an environment in which sensory information has been captured and processed. In one embodiment, stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0161] In one embodiment, the speed and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in the vehicle 200 configured to alter 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 execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, speed and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians or road objects, position information of the vehicle 200 relative to lane markings of the road, etc. Additionally, the processing unit 110 may calculate the target speed for the vehicle 200 based on sensory input (e.g., information from radar) and input from other systems of the vehicle 200, such as the throttling 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 send electronic signals to the throttling system 220, braking system 230, and / or steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration, for example, by physically applying the brakes or easing off the accelerator of the vehicle 200.

[0162] 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 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 of the vehicle 200, etc. Additionally, in some embodiments, the navigation response may be based (partially or fully) on map data, a predetermined position of the vehicle 200, and / or a relative speed or relative acceleration between the vehicle 200 and one or more objects detected from execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may determine a desired navigation response based on sensory input (e.g., information from a radar) and inputs from other systems of the vehicle 200, such as the throttling system 220, the braking system 230, and the steering system 240 of the vehicle 200. Based on the desired navigational response, processing unit 110 may send electronic signals to throttling system 220, braking system 230, and steering system 240 of vehicle 200 to trigger the desired navigational response, for example, by turning the steering wheel of vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, processing unit 110 may use the output of navigational response module 408 (e.g., the desired navigational response) as an input to the execution of velocity and acceleration module 406 to calculate a change in velocity of vehicle 200.

[0163] Additionally, any of the modules 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.

[0164] 5A is a flow chart illustrating an example process 500A for making one or more navigation responses based on monocular image analysis, consistent with disclosed embodiments. In 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 (e.g., image capture device 122 having a field of view 202) included in the image acquisition unit 120 may capture a plurality of images of an area in front of the vehicle 200 (or, for example, to the side or rear of the vehicle) and transmit them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). The processing unit 110 may execute the monocular image analysis module 402 in step 520 to perform analysis of the plurality of images, as described in further detail below in connection with FIGS. 5B-5D. By performing the analysis, processing unit 110 may detect a set of features in a set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, and traffic lights.

[0165] In stage 520, processing unit 110 may execute monocular image analysis module 402 to detect various road obstacles, such as truck tire parts, fallen road signs, loose cargo, and small animals. Road obstacles may vary in structure, shape, size, and color, making such obstacles more difficult to detect. In some embodiments, processing unit 110 may execute monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road obstacles. For example, processing unit 110 may estimate camera motion between successive image frames and calculate pixel disparity between frames to build a 3D map of the road. Processing unit 110 may then use the 3D map to detect the road surface and obstacles present on the road surface.

[0166] In step 530, processing unit 110 may execute navigation response module 408 to perform one or more navigation responses in vehicle 200 based on the analysis performed in step 520 and the techniques described above in connection with FIG. 4. The navigation responses may include, for example, a turn, a lane change, and a change in acceleration. In some embodiments, processing unit 110 may perform one or more navigation responses using data derived from execution of speed and acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof. For example, processing unit 110 may cause vehicle 200 to turn one lane across and then accelerate, for example, by transmitting control signals sequentially to steering system 240 and throttling system 220 of vehicle 200. Alternatively, processing unit 110 may cause vehicle 200 to brake and change lanes at the same time, for example, by transmitting control signals simultaneously to braking system 230 and steering system 240 of vehicle 200.

[0167] FIG. 5B is a flow chart illustrating an example process 500B for detecting one or more vehicles and / or pedestrians in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500B. In step 540, processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 may scan one or more images and compare the images to one or more predefined patterns to identify possible locations in each image that may contain an object of interest (e.g., a vehicle, a pedestrian, or a portion thereof). The predefined patterns may be designed in a manner to achieve a high rate of "false hits" and a low rate of "misses." For example, processing unit 110 may use a low threshold similarity with the predefined patterns to identify candidate objects as possible vehicles or pedestrians. Doing so may enable processing unit 110 to reduce the probability of missing (e.g., not identifying) a candidate object representing a vehicle or pedestrian.

[0168] At stage 542, processing unit 110 may filter the set of candidate objects to eliminate certain candidates (e.g., irrelevant or less relevant objects) based on classification criteria. Such criteria may be derived from various characteristics associated with object types stored in a database (e.g., a database stored in memory 140). The characteristics may include the object's shape, dimensions, texture, location (e.g., relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to reject false candidates from the set of candidate objects.

[0169] At stage 544, processing unit 110 may analyze multiple frames of images to determine whether objects in the set of candidate objects represent vehicles and / or pedestrians. For example, processing unit 110 may track detected candidate objects across successive frames and accumulate per-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 per-frame position data of the objects to predicted positions.

[0170] In 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 a series of time-based observations, estimation techniques using, for example, a Kalman filter or linear quadratic estimation (LQE), and / or available modeling data for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). A Kalman filter may be based on a measurement of the scale of the object, where the measurement of scale is proportional to the time to impact (e.g., the length of time it takes vehicle 200 to reach the object). Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing in the set of captured images and derive information (e.g., position, velocity, size) associated with the vehicles and pedestrians. Based on the identification and derived information, the processing unit 110 may perform one or more navigation responses in the vehicle 200, as described in connection with FIG. 5A above.

[0171] In step 548, processing unit 110 may perform optical flow analysis of one or more images to reduce the probability of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing motion patterns, distinct from road surface motion, for vehicle 200 in one or more images associated with other vehicles and pedestrians. Processing unit 110 may calculate the motion of candidate objects by observing 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 to a mathematical model for calculating the motion of candidate objects. Thus, optical flow analysis may provide another way to detect vehicles and pedestrians near vehicle 200. Processing unit 110 may perform optical flow analysis in a combination of steps 540-546 to provide redundancy for detecting vehicles and pedestrians and improve the reliability of system 100.

[0172] FIG. 5C is a flow chart illustrating an example process 500C for detecting road markings and / or lane shape information in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500C. In step 550, processing unit 110 may detect a set of objects by scanning one or more images. To detect lane markings, lane shape information, and other relevant road marking segments, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., slight potholes, small rocks, etc.). In step 552, processing unit 110 may group together segments detected in step 550 that belong to the same road marking or lane marking. Based on the grouping, processing unit 110 may develop a model, e.g., a mathematical model, to represent the detected segments.

[0173] At stage 554, processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, processing unit 110 may create a projection of the detected segment from the image plane onto a real-world plane. The projection may be characterized using a third-order polynomial with coefficients corresponding to physical properties, such as the position, slope, curvature, and curvature function of the detected road. In generating the projection, processing unit 110 may take into account variations in the road surface, as well as pitch and roll rates associated with vehicle 200. Additionally, processing unit 110 may model the elevation of the road by analyzing position and motion cues present on the road surface. Additionally, processing unit 110 may estimate pitch and roll rates associated with vehicle 200 by tracking a set of feature points in one or more images.

[0174] In stage 556, processing unit 110 may perform a multi-frame analysis, for example, by tracking the detected segments across successive image frames and accumulating frame-by-frame data associated with the detected segments. As processing unit 110 performs the multi-frame analysis, the set of measurements constructed in stage 554 may become more reliable and be associated with an increasingly higher confidence level. Thus, by performing stages 550, 552, 554, and 556, processing unit 110 may identify road markings appearing in the set of captured images and derive lane shape information. Based on the identification and derived information, processing unit 110 may perform one or more navigation responses in vehicle 200, as described in connection with FIG. 5A above.

[0175] At stage 558, processing unit 110 may consider additional sources of information to further develop a safety model for vehicle 200 in the context of its surroundings. Processing unit 110 may use the safety model to define a context in which system 100 may perform autonomous control of vehicle 200 in a safe manner. To develop the safety model, in some embodiments, processing unit 110 may consider the positions and movements of other vehicles, detected road edges and boundaries, and / or road geometry descriptions of general roads extracted from map data (e.g., data from map database 160). By considering additional sources of information, processing unit 110 may provide redundancy for detecting road markings and lane geometry and increase the reliability of system 100.

[0176] FIG. 5D is a flow chart illustrating an example process 500D for detecting traffic lights in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500D. At stage 560, processing unit 110 may scan the set of images and may identify objects appearing at locations in the images that are likely to contain traffic lights. For example, processing unit 110 may filter the identified objects to exclude those objects that are unlikely to correspond to traffic lights and build a set of candidate objects. Filtering may be based on various characteristics associated with traffic lights, such as shape, size, texture, location (e.g., relative to vehicle 200), etc. Such characteristics may be based on multiple examples of traffic lights and traffic control signals and may be stored in a database. In some embodiments, processing unit 110 may perform a multi-frame analysis on the set of candidate objects reflecting possible traffic lights. For example, processing unit 110 may track candidate objects across successive image frames, estimate the real-world locations of the candidate objects, and remove those objects that are moving (which are unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects to identify the relative locations of detected colors that appear within potential traffic lights.

[0177] In stage 562, processing unit 110 may analyze the geometry of the junction. The analysis may be based on any combination of (i) the number of lanes detected on either side of vehicle 200, (ii) markings (e.g., arrow marks) detected on the road, and (iii) a description of the junction extracted from map data (such as data from map database 160). Processing unit 110 may perform the analysis using information derived from execution of monocular analysis module 402. Furthermore, processing unit 110 may determine a correspondence between the traffic lights detected in stage 560 and lanes appearing near vehicle 200.

[0178] As vehicle 200 approaches a junction, in step 564, processing unit 110 may update a confidence level associated with the analyzed junction geometry and the detected traffic lights. For example, the number of traffic lights estimated to appear at the junction compared to the number actually appearing at the junction may affect the confidence level. Thus, based on the 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 traffic lights appearing in the set of captured images and analyze the junction geometry information. Based on the identification and analysis, processing unit 110 may perform one or more navigation responses in vehicle 200, as described in connection with FIG. 5A above.

[0179] 5E is a flowchart illustrating an example process 500E for making one or more navigation responses in vehicle 200 based on a vehicle path, consistent with disclosed embodiments. In step 570, processing unit 110 may construct an initial vehicle path associated with vehicle 200. The vehicle path may be represented using a set of points represented in coordinates (x,z), where the distance d between any two points in the set of points is expressed as i may range from 1 to 5 meters. In one embodiment, processing unit 110 may construct an initial vehicle path using two polynomials, e.g., left and right road polynomials. Processing unit 110 may calculate the geometric midpoint between the two polynomials and offset each point in the resulting vehicle path by a predetermined offset, if any (e.g., a smart lane offset) (an offset of zero may correspond to driving in the center of the lane). The 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 in the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0180] In step 572, the processing unit 110 may update the vehicle path constructed in step 570. The processing unit 110 may update the vehicle path by calculating the distance d k is the distance d i The vehicle path constructed in step 570 may be reconstructed using a higher resolution so that the distance d k may be in the range of 0.1 to 0.3 meters. Processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may yield a cumulative distance vector S that corresponds to the total length of the vehicle path (i.e., based on a set of points representing the vehicle path).

[0181] In step 574, the processing unit 110 calculates ((x l ,z l ) may be determined. The processing unit 110 may extract the look-ahead points from the cumulative distance vector S, and the look-ahead points may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance, which may have a lower limit in the range of 10 to 20 meters, may be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, if the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until the lower limit is reached). Conversely, the look-ahead time, which may range from 0.5 to 1.5 seconds, may be proportional to the gain of one or more control loops associated with making a navigation response in the vehicle 200, such as a heading error tracking control loop. For example, the gain of the heading error tracking control loop may depend on the bandwidth of the yaw rate loop, the steering actuator loop, and the lateral motion state of the vehicle. Thus, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0182] In step 576, processing unit 110 may determine a heading error and a yaw rate command based on the look ahead point determined in step 574. Processing unit 110 may calculate the arctangent of the look ahead point, e.g., arctan(xl / z l The processing unit 110 may determine the heading error by calculating the heading error ratio (L) (the heading error ratio). The processing unit 110 may determine the yaw rate command as the heading error times the high-level control gain. If the look ahead distance is not at a lower limit, the high-level control gain may be equal to (2 / look ahead time). Otherwise, the high-level control gain may be equal to (2×vehicle 200 speed / look ahead distance).

[0183] 5F is a flow chart illustrating an example process 500F for determining whether a leading vehicle is changing lanes, consistent with disclosed embodiments. In step 580, processing unit 110 may determine navigation information associated with a leading vehicle (e.g., a vehicle traveling ahead of vehicle 200). For example, processing unit 110 may determine the position, velocity (e.g., direction and speed), and / or acceleration of the leading vehicle using techniques described in connection with FIGs. 5A and 5B above. Processing unit 110 may determine one or more road polynomials, lookahead points (associated with vehicle 200), and / or a snail trail (e.g., a set of points describing a path taken by a leading vehicle) using techniques described in connection with FIG. 5E above.

[0184] In step 582, processing unit 110 may analyze the navigation information determined in step 580. In one embodiment, processing unit 110 may calculate the distance (e.g., along the trajectory) between the snail trail and the road polynomial. If the variance of this distance along the trajectory exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters for straight roads, 0.3 to 0.4 meters for moderately curvy roads, and 0.5 to 0.6 meters for roads with sharp curves), processing unit 110 may determine that the leading vehicle is likely to change lanes. If multiple vehicles are detected traveling ahead of vehicle 200, processing unit 110 may compare the snail trails associated with each vehicle. Based on the comparison, processing unit 110 may determine that a vehicle whose snail trail does not match the snail trails of other vehicles is likely to change lanes. Processing unit 110 may further compare the curvature of the snail trail (associated with the leading vehicle) to an expected curvature of the road segment on which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., from data from map database 160), from road polynomials, from snail trails of other vehicles, from prior knowledge about the road, etc. If the difference between the curvature of the snail trail and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely to change lanes.

[0185] In another embodiment, processing unit 110 may compare the leading vehicle's instantaneous position to a look-ahead point (associated with vehicle 200) over a particular period of time (e.g., 0.5 to 1.5 seconds). If the distance between the leading vehicle's instantaneous position and the look-ahead point changes during the particular period of time, processing unit 110 may determine that the leading vehicle is about to change lanes if the cumulative sum of the changes exceeds a predefined threshold (e.g., 0.3 to 0.4 meters for straight roads, 0.7 to 0.8 meters for moderately curvy roads, and 1.3 to 1.7 meters for roads with sharp curves). In another embodiment, processing unit 110 may analyze the geometry of the snail trail by comparing the lateral distance traveled along the trajectory with the expected snail trail curvature. The expected radius of curvature is calculated (δ z 2 +δ x 2 ) / 2 / (δ x ), where δ x represents the lateral distance traveled, and δ z represents the longitudinal distance traveled. If the difference between the lateral distance traveled and the expected curvature exceeds a predefined threshold (e.g., 500 to 700 meters), processing unit 110 may determine that the leading vehicle is likely to change lanes. In another embodiment, processing unit 110 may analyze the position of the leading vehicle. If the position of the leading vehicle causes the road polynomial (e.g., the leading vehicle is overlaid on top of the road polynomial) to be obscured, processing unit 110 may determine that the leading vehicle is likely to change lanes. If the leading vehicle is in a position such that another vehicle is detected ahead of the leading vehicle and the snail trails of the two vehicles are not parallel, processing unit 110 may determine that the (closer) leading vehicle is likely to change lanes.

[0186] In step 584, processing unit 110 may determine whether leading vehicle 200 is changing lanes based on the analysis performed in step 582. For example, processing unit 110 may make a determination based on a weighted average of the individual analyses performed in step 582. Under such a scheme, for example, a determination by processing unit 110 that the leading vehicle is likely to change lanes based on a particular type of analysis may be assigned a value of "1" (with a "0" representing a determination that the leading vehicle is not likely to change lanes). Different analyses performed in step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0187] 6 is a flow chart illustrating an example process 600 for making one or more navigation responses based on stereo image analysis, consistent with disclosed embodiments. In step 610, the processing unit 110 may receive a first and a second plurality of images via the data interface 128. For example, a camera included in the image acquisition unit 120 (e.g., image capture devices 122 and 124 having fields of view 202 and 204) may capture a first and a second plurality of images of an 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 and the second plurality of images via two or more data interfaces. The disclosed embodiments are not limited to a particular data interface configuration or protocol.

[0188] In step 620, processing unit 110 may execute stereo image analysis module 404 to perform stereo image analysis of the first and second plurality of images to create a 3D map of the road ahead of the vehicle and detect features in the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. The stereo image analysis may be performed in a manner similar to the steps described in connection with FIGS. 5A-5D above. For example, processing unit 110 may execute stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road markings, traffic lights, road obstacles, etc.) in the first and second plurality of images, remove a subset of the candidate objects based on various criteria, and perform a multi-frame analysis to construct measurements and determine confidence levels for the remaining candidate objects. In performing the above steps, processing unit 110 may consider information from both the first and second plurality of images, rather than information from only one set of images. For example, processing unit 110 may analyze differences in pixel-level data (or other subsets of data from the two streams of captured images) for a candidate object that appears in both the first and second multiple images. As another example, processing unit 110 may estimate a position and / or velocity of a candidate object (e.g., relative to vehicle 200) by observing that the object appears in one of the multiple images but not in the other, or in conjunction with other differences that may exist for objects that appear in the two image streams. For example, the position, velocity, and / or acceleration relative to vehicle 200 may be determined based on trajectories, positions, motion characteristics, etc. of features associated with the object that appears in one or both of the image streams.

[0189] In step 630, processing unit 110 may execute navigation response module 408 to perform one or more navigational responses in vehicle 200 based on the analysis performed in step 620 and techniques such as those described above in connection with FIG. 4. The navigational responses may include, for example, turning, changing lanes, changing acceleration, changing speed, braking, etc. In some embodiments, processing unit 110 may perform one or more navigational responses using data derived from execution of speed and acceleration module 406. Additionally, multiple navigational responses may occur simultaneously, sequentially, or any combination thereof.

[0190] 7 is a flow chart illustrating an example process 700 for making one or more navigation responses based on an analysis of three sets of images, consistent with disclosed embodiments. In step 710, the processing unit 110 may receive the first, second, and third plurality of images via the data interface 128. For example, the cameras included in the image acquisition unit 120 (e.g., image capture devices 122, 124, and 126 having fields of view 202, 204, and 206) may capture the first, second, and third plurality of images of the area 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, second, and 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 communicating data to the processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0191] In step 720, processing unit 110 may analyze the first, second, and third plurality of images to detect features in the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstructions. The analysis may be performed in a manner similar to the steps described in connection with FIGS. 5A-5D and 6 above. For example, processing unit 110 may perform monocular image analysis (e.g., via execution of monocular image analysis module 402, based on the steps described in connection with FIGS. 5A-5D above) on each of the first, second, and third plurality of images. Alternatively, processing unit 110 may perform stereo image analysis (e.g., via execution of stereo image analysis module 404, based on the steps described in connection with FIG. 6 above) on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images. Processed information corresponding to the analysis of the first, second, and / or third plurality of images may be combined. In some embodiments, processing unit 110 may perform a combination of monocular and stereo image analysis. For example, processing unit 110 may perform monocular image analysis (e.g., via execution of monocular image analysis module 402) on the first plurality of images and stereo image analysis (e.g., via execution of stereo image analysis module 404) on the second and third plurality of images. The configuration of image capture devices 122, 124, and 126 (including their respective positions and fields of view 202, 204, and 206) may affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a particular configuration of image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0192] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed in stages 710 and 720. Such tests may provide an indicator of the overall performance of system 100 for a particular configuration of image capture devices 122, 124, and 126. For example, processing unit 110 may determine the rate of "false hits" (e.g., when system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses."

[0193] At step 730, processing unit 110 may perform one or more navigation responses in vehicle 200 based on information derived from two of the first, second, and third pluralities of images. The selection of two of the first, second, and third pluralities of images may depend on various factors, such as the number, type, and size of objects detected in each of the plural images. Processing unit 110 may make the selection based on image quality and resolution, the effective field of view reflected in the images, the number of frames captured, and 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 appearing in each such frame, etc.).

[0194] In some embodiments, processing unit 110 may select information derived from two of the first, second, and third plurality of images by determining the extent to which information derived from one image source is consistent with information derived from the other image source. For example, processing unit 110 may combine processed information derived from each of image capture devices 122, 124, and 126 (whether from monocular analysis, stereo analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.) that match across the images captured from each of image capture devices 122, 124, and 126. Processing unit 110 may filter out information that is inconsistent across the captured images (e.g., vehicles changing lanes, lane models showing vehicles too close to vehicle 200, etc.). Thus, processing unit 110 may select information derived from two of the first, second and third pluralities of images based on the determination of consistent and inconsistent information.

[0195] The navigational responses may include, for example, turning, changing lanes, changing acceleration, etc. Processing unit 110 may perform one or more navigational responses based on the analysis performed in step 720 and techniques such as those described above in connection with FIG. 4. Processing unit 110 may perform one or more navigational responses using data derived from execution of velocity and acceleration module 406. In some embodiments, processing unit 110 may perform one or more navigational responses based on a relative position, relative velocity, and / or relative acceleration between an object detected in any of the first, second, and third images and vehicle 200. The multiple navigational responses may occur simultaneously, sequentially, or any combination thereof.

[0196] Sparse Road Models for Autonomous Vehicle Navigation

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

[0198] Sparse Maps for Autonomous Vehicle Navigation

[0199] In some embodiments, the disclosed systems and methods may generate a sparse map for navigation of an autonomous vehicle. For example, the sparse map may provide sufficient information for navigation without requiring excessive data storage or data transfer rates. As discussed in more detail below, a vehicle (which may be an autonomous vehicle) may use the sparse map to navigate one or more roads. For example, in some embodiments, the sparse map may include data related to roads and potential landmarks along the roads that may be sufficient for vehicle navigation but also present a small data footprint. For example, the sparse data map described in more detail below may require significantly less storage space and data transfer bandwidth compared to digital mapping that includes detailed map information, e.g., image data collected along the roads.

[0200] For example, rather than storing detailed representations of road segments, the sparse data map may store three-dimensional polynomial representations of preferred vehicle paths along roads. These paths may require little data storage space. Additionally, in the described sparse data map, landmarks may be identified and included in the sparse map road model to aid in navigation. These landmarks may be located at any suitable interval to enable vehicle navigation, although in some cases, such landmarks need not be identified and included in the model at high density and short intervals. Rather, in some cases, navigation may be possible 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 discussed in more detail in other sections, the sparse map may be generated based on data collected or measured by a vehicle equipped with various sensors and devices, e.g., image capture devices, global positioning system sensors, motion sensors, etc., as the vehicle travels along a roadway. In some cases, the sparse map may be generated based on data collected during multiple drives of one or more vehicles along a particular roadway. Generating a sparse map using multiple drives of one or more vehicles may be referred to as "crowdsourcing" the sparse map.

[0201] Consistent with disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed systems and methods may provide the sparse map to generate a road navigation model for the autonomous vehicle and navigate the autonomous vehicle along a road segment using the sparse map and / or the generated road navigation model. A sparse map consistent with this disclosure may include one or more three-dimensional contours that may represent a predetermined trajectory that the autonomous vehicle may traverse as it travels along an associated road segment.

[0202] A sparse map consistent with the present disclosure may include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and any other road-related features useful for navigating a vehicle. A sparse map 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 detailed representations of roads, such as data detailing road edges, road curvatures, images associated with road segments, or other physical features associated with road segments, disclosed embodiments of the sparse map may require relatively small storage space (and relatively small bandwidth, if portions of the sparse map are transferred to the vehicle), yet still provide sufficient for navigation of an autonomous vehicle. The small data footprint of the disclosed sparse maps, discussed in more detail below, may be achieved in some embodiments by storing representations of road-related elements that require only a small amount of data, yet still enable autonomous navigation.

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

[0204] In addition to the polynomial representation of the stored trajectories along the road segments, the disclosed sparse maps may include small data objects that may represent road features. In some embodiments, the small data objects may include digital signatures, which are derived from digital images (or digital signals) acquired from sensors (e.g., cameras or other sensors, such as suspension sensors) mounted on vehicles traveling along the road segments. The digital signatures may have a reduced size relative to the signals acquired by the sensors. In some embodiments, the digital signatures may be created to be compatible with a classification function configured to detect and identify road features from signals acquired by the sensors, for example, during subsequent driving. In some embodiments, the digital signatures may be created such that they have as small a footprint as possible while still maintaining the ability for road features to be correlated or matched with the stored signatures based on images of the road features captured by a camera-mounted vehicle traveling along the same road segment at a later time (or digital signals generated by the sensors, if the stored signature is not based on images and / or includes other data).

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

[0206] As discussed in more detail below, road features (e.g., landmarks along a road segment) may be stored as small data objects that may represent the road features in a relative few bytes, while at the same time providing sufficient information to recognize and use the features for such navigation. In one example, road signs may be identified as recognized landmarks on which vehicle navigation may be based. Representations of road signs may be stored in a sparse map, including, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign) and a few bytes of data indicating the location (e.g., coordinates) of the landmark. Navigating based on such a lightweight data representation of landmarks (e.g., using a representation sufficient to search, recognize, and navigate based on the landmarks) may provide a desired level of navigation functionality associated with a sparse map without significantly increasing the data overhead associated with the sparse map. This lean representation of landmarks (and other road features) may take advantage of sensors and processors included on-board such vehicles that are configured to detect, identify, and / or classify specific road features.

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

[0208] Generating a Sparse Map

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

[0210] 8 illustrates a sparse map 800 that one or more vehicles, e.g., vehicle 200 (which may be an autonomous vehicle), may access to provide navigation for the autonomous vehicle. Sparse map 800 may be stored in a memory, e.g., memory 140 or 150. Such a memory device may include any type of non-transitory storage device or computer-readable medium. For example, in some embodiments, memory 140 or 150 may include a hard drive, a compact disk, a flash memory, a magnetic-based memory device, an optical-based memory device, or the like. In some embodiments, sparse map 800 may be stored in a database (e.g., map database 160), which may be stored in memory 140 or 150 or another type of storage device.

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

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

[0213] Further, in such an embodiment, the sparse map 800 may be accessible to multiple vehicles passing through various road segments (e.g., tens, hundreds, thousands, or millions of vehicles). It is also noted that the sparse map 800 may include multiple sub-maps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, hundreds, or more sub-maps that may be used in navigating the vehicle. Such sub-maps may be referred to as local maps, and a vehicle traveling along a roadway may access any number of local maps that are relevant to the location where the vehicle is traveling. The local map portion of the sparse map 800 may be stored using a Global Navigation Satellite System (GNSS) key as an index to a database of the sparse map 800. Thus, in the present system, calculations of steering angles for navigating the host vehicle may be performed without reliance on the GNSS position of the host vehicle, road features, or landmarks, while such GNSS information may be used for lookup of the relevant local map.

[0214] In general, the sparse map 800 may be generated based on data collected from one or more vehicles as they travel along a roadway. For example, a trajectory of one or more vehicles traveling along the roadway may be recorded using sensors (e.g., cameras, speedometers, GPS, accelerometers, etc.) on one or more vehicles, and a polynomial representation of a preferred trajectory for the vehicle to make subsequent movements along the roadway may be determined based on the collected trajectories traveled by the one or more vehicles. Similarly, data collected by one or more vehicles may help identify possible landmarks along a particular roadway. Data collected from passing vehicles may be used to identify road profile information, such as, for example, road width profile, road roughness profile, traffic line spacing profile, road conditions, etc. Using the collected information, the sparse map 800 may be generated and provided (e.g., to local storage or via on-the-fly data transmission) for use in navigating one or more autonomous vehicles. However, in some embodiments, the generation of the map may not end upon the initial generation of the map. As discussed in more detail below, sparse map 800 may be continuously or periodically updated based on data collected from vehicles as those vehicles continue to pass through the roadways included in sparse map 800.

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

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

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

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

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

[0220] The landmarks 820 may be identified and stored in the sparse map 800 at any suitable interval. 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 used. For example, the landmarks identified (or recognized) in the sparse map 800 may be spaced apart by 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers. In some cases, the identified landmarks may be spaced even further apart than 2 kilometers.

[0221] Between landmarks, and thus during the determination 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 ego-motion and estimate its position relative to the target trajectory. Because errors may accumulate during navigation with dead reckoning, position determination over time relative to the target trajectory may become less and less accurate. The vehicle may use landmarks (their known positions) present in the sparse map 800 to remove dead reckoning-induced errors in position determination. In this manner, the identified landmarks included in the sparse map 800 may serve as navigation anchors from which the vehicle's exact position relative to the target trajectory may be determined. The identified landmarks do not need to be available to the autonomous vehicle at all times, since a certain amount of error may be acceptable at appropriate location locations. Rather, appropriate navigation may still be possible based on landmark spacing of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or longer, as discussed above. In some embodiments, a density of one identified landmark per km of road may be sufficient to maintain longitudinal positioning accuracy within 1 m. Therefore, not all possible landmarks that appear along a road segment need to be stored in the sparse map 800.

[0222] Additionally, in some embodiments, lane markings may be used to locate the vehicle in the landmark spacing. By using lane markings in the landmark spacing, accumulation during navigation due to dead reckoning may be minimized.

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

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

[0225] In the example shown in FIG. 9A, the left side 910 of the lane 900 is represented by two groups of third order polynomials. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. The two groups are substantially parallel to each other while following their respective side of the roadway. The polynomial segments 911, 912, 913, 914, 915, and 916 have a length of about 100 meters and overlap consecutively adjacent segments by about 50 meters. However, as mentioned above, polynomials of different lengths and different amounts of overlap may be used. For example, the polynomials may have a length of 500 m, 1 km, or more, and the amount of overlap may vary from 0 to 50 m, 50 to 100 m, or more than 100 m. 9A is shown as representing polynomials expanded in 2D space (e.g., on the surface of a piece of paper), it should be understood that these polynomials may represent curves that extend into three dimensions (e.g., including an elevation component) to represent elevation changes within a road segment in addition to XY curvature. In the example shown in FIG. 9A, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922, and 923, and a second group having polynomial segments 924, 925, and 926.

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

[0227] With regard to the data footprint of the polynomial curves stored in the sparse map 800, in some embodiments, each third order polynomial may be represented by four parameters, each requiring 4 bytes of data. A suitable representation may be obtained with a third order polynomial requiring approximately 192 bytes of data for every 100 meters. This may equate to approximately 200 kB per hour of data usage / transfer requirements for a host vehicle traveling at approximately 100 km per hour.

[0228] The sparse map 800 may describe the lane network using a combination of geometric descriptors and metadata. As described above, the geometry may be described by polynomials or splines. The metadata may describe the number of lanes, special characteristics (e.g., carpool lanes), and other possible sparse labels. The total footprint of such indicators may be negligible.

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

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

[0231] FIG. 10 illustrates examples of types of landmarks that may be represented in the sparse map 800. Landmarks may include any visible and identifiable object along a road segment. Landmarks may be selected such that they are constant and do not change much with respect to their location and / or content. The landmarks included in the sparse map 800 may be useful in determining the location of the vehicle 200 with respect to a target trajectory as the vehicle traverses a particular road segment. Examples of landmarks may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside structures (e.g., lamp posts, reflectors, etc.), and any other suitable categories. In some embodiments, lane markings on the road may be included as landmarks in the sparse map 800.

[0232] Examples of landmarks shown in FIG. 10 include traffic signs, directional signs, roadside structures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), yield signs (e.g., yield sign 1005), route number signs (e.g., route number sign 1010), traffic light signs (e.g., traffic light signs 1015), stop signs (e.g., stop sign 1020). Directional signs may include signs including one or more arrows indicating one or more directions to different locations. For example, directional signs may include highway signs 1025 with arrows to guide vehicles to different roads or locations, and exit signs 1030 with arrows to guide vehicles off the road, etc. Thus, at least one of the plurality of landmarks may include a road sign.

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

[0234] Landmarks may include roadside fixtures. Roadside fixtures may be objects that are not signs and may not be traffic or directional related. For example, roadside fixtures may include lamp posts (e.g., lamp posts 1035), utility poles, traffic light poles, etc.

[0235] The landmarks may include beacons that may be specially designed for use in an autonomous vehicle navigation system. For example, such beacons may include standalone structures that are placed at predetermined intervals to aid in navigating the host vehicle. Such beacons may include visual / graphical information (e.g., icons, emblems, bar codes, etc.) that are added to existing road signs that may be identified or recognized by vehicles traveling along a road segment. Such beacons may 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, the identity of the landmark and / or the location of the landmark that may be used by the host vehicle in determining its position along the target trajectory.

[0236] In some embodiments, landmarks included in sparse map 800 may be represented by data objects of a predefined size. The data representing the landmarks may include any suitable parameters for identifying a particular landmark. For example, in some embodiments, landmarks stored in sparse map 800 may include parameters such as, for example, the physical size of the landmark (e.g., supporting estimation of distance to the landmark based on a known size / scale), distance to previous landmark, lateral offset, height, type code (e.g., type of landmark - what type of directional sign, traffic sign, etc.), GPS coordinates (e.g., supporting global localization), and any other suitable parameters. Each parameter may be associated with a data size. For example, the size of the landmark may be stored using 8 bytes of data. The distance to the previous landmark, lateral offset, and height may be specified using 12 bytes of data. A type code associated with a landmark such as a directional sign or traffic sign may require approximately 2 bytes of data. For a generic sign, an image signature that allows identification of the generic sign may be stored using 50 bytes of data storage. The GPS location of the landmark may be associated with 16 bytes of data storage. These data sizes for each parameter are merely examples and other data sizes may be used.

[0237] Representing landmarks in this manner in the sparse map 800 may present a lean solution for efficiently representing landmarks in a database. In some embodiments, signs may be referred to as semantic signs and non-semantic signs. Semantic signs may include any classification of signs with a standard meaning (e.g., speed limit signs, warning signs, directional signs, etc.). Non-semantic signs may include any signs that are not associated with a standard meaning (e.g., general advertising signs that identify a place of business, etc.). For example, each semantic sign may be represented with 38 bytes of data (e.g., 8 bytes for size, 12 bytes for distance to previous landmark, lateral offset and height, 2 bytes for type code, and 16 bytes for GPS coordinates). The sparse map 800 may represent the type of landmark using a tag system. In some cases, each traffic or directional sign may be associated with a unique tag, which may be stored in the database as part of the landmark's identity. For example, the database may include about 1000 different tags to represent various traffic signs and about 10,000 different tags to represent directional signs. Of course, any suitable number of tags may be used, and additional tags may be created as needed. In some embodiments, a generic sign may be represented using less than about 100 bytes (e.g., about 86 bytes, including 8 bytes for size, 12 bytes for distance to previous landmark, lateral offset and height, 50 bytes for image signature, and 16 bytes for GPS coordinates).

[0238] Thus, for semantic road signs that do not require image signatures, the data density impact on the sparse map 800 may be about 760 bytes per kilometer (e.g., 20 landmarks per km x 38 bytes per landmark = 760 bytes), even if the landmark density is relatively high at about 1 per 50 m. Even considering generic signs that include an image signature component, the data density impact is about 1.72 kB per km (e.g., 20 landmarks per km x 86 bytes per landmark = 1720 bytes). For semantic road signs, this corresponds to about 76 kB of data usage per hour for a vehicle traveling at 100 km / h. For generic signs, this corresponds to about 170 kB per hour for a vehicle traveling at 100 km / h.

[0239] In some embodiments, a generally rectangular object, e.g., a rectangular landmark, may be represented in the sparse map 800 with 100 bytes or less of data. The representation of a generally rectangular object (e.g., a generic landmark 1040) in the sparse map 800 may include a simplified image signature (e.g., a simplified image signature 1045) associated with the generally rectangular object. This simplified image signature may be used, for example, to contribute to identifying the generic landmark as a recognized landmark. Such a simplified image signature (e.g., image information derived from real image data representing the object) may avoid the need to store a real image of the object or to compare image analysis performed on the real image to recognize the landmark.

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

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

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

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

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

[0245] In the example shown in FIG. 11A, a first reconstructed trajectory 1101 may be determined based on data received from a first vehicle traversing the road segment 1100 in a first time period (e.g., day 1), a second reconstructed trajectory 1102 may be obtained from a second vehicle traversing the road segment 1100 in a second time period (e.g., day 2), and a third reconstructed trajectory 1103 may be obtained from a third vehicle traversing the road segment 1100 in a third time period (e.g., day 3). Each of the trajectories 1101, 1102, and 1103 may be represented by a polynomial, such as a three-dimensional polynomial. Note that in some embodiments, any of the reconstructed trajectories may be assembled on a vehicle traversing the road segment 1100.

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

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

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

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

[0250] In some embodiments, the sparse map 800 may include a road signature profile. Such a road signature profile may be associated with any identifiable / measurable variation in at least one parameter associated with a road. For example, in some cases, such a profile may be associated with variations in road surface information, such as variations in surface roughness of a particular road segment, variations in road width across a particular road segment, variations in distance between painted dotted lines along a particular road segment, variations in road curvature along a particular road segment, etc. FIG. 11D illustrates an example of a road signature profile 1160. While the profile 1160 may represent any of the parameters listed above, in another example, the profile 1160 may represent a measurement of road surface roughness, such as obtained by monitoring one or more sensors that provide an output indicative of an amount of suspension deviation as the vehicle travels along a particular road segment.

[0251] Alternatively or simultaneously, the profile 1160 may represent road width variations determined based on image data acquired via a camera mounted on a vehicle traveling a particular road segment. Such a profile may be useful, for example, in determining a particular position of an autonomous vehicle relative to a particular target trajectory. That is, when traversing a road segment, the autonomous vehicle may measure a profile associated with one or more parameters associated with the road segment. If the measured profile can be correlated / matched with a predefined profile plotting parameter variations versus position along the road segment, the measured predefined profile may be used (e.g., by overlaying corresponding portions of the measured predefined profile) to determine a current position along the road segment, and thus, relative to the target trajectory of the road segment.

[0252] 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 parameters related to driving. For example, in some embodiments, different trajectories may be generated based on preferences and / or profiles of different users. Sparse map 800 including such different trajectories may be provided to different autonomous vehicles of different users. For example, some users may prioritize avoiding toll roads, while other users may prioritize taking 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 prioritize driving in the fast lane, while other users may prioritize always keeping their position in the center lane.

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

[0254] Other different parameters related to driving may be used as criteria to generate and provide different sparse maps for different autonomous vehicles. For example, when an autonomous vehicle is traveling at high speed, turns may be tight. Trajectories associated with specific lanes, rather than roads, may be included in the sparse map 800 so that the autonomous vehicle may stay within a specific lane as it follows a specific trajectory. If an image captured by a camera mounted on the autonomous vehicle indicates that the vehicle has drifted outside the lane (e.g., crossed a lane marking), an action may be triggered within the vehicle to return the vehicle to the designated lane according to the specific trajectory.

[0255] Crowdsourcing Sparse Maps

[0256] In some embodiments, the disclosed systems and methods may generate a sparse map for navigation of an autonomous vehicle. For example, the disclosed systems and methods may use crowdsourced data for generation of a sparse map that one or more autonomous vehicles may use to navigate along a system of roads. "Crowdsourcing" as used herein means that data is received from various vehicles (e.g., autonomous vehicles) traveling a road segment at different times, and such data is used to generate and / or update a road model. The model may then be transmitted to vehicles traveling later along the road segment or to other vehicles to aid in the navigation of the autonomous vehicle. The road model may include multiple target trajectories that represent preferred trajectories that the autonomous vehicles should follow as they traverse the road segment. The target trajectories may be the same as reconstructed actual trajectories collected from vehicles traversing the road segment that may be transmitted from the vehicles to a server. In some embodiments, the target trajectories may differ from actual trajectories previously taken by one or more vehicles as they traverse the road segment. The target trajectories may be generated based on the actual trajectories (e.g., through averaging or any other suitable operation).

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

[0258] In addition to trajectory information, other information that may be used in constructing 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 the locations of the landmarks. The landmarks may be used by the autonomous vehicle's navigation system to determine and / or adjust the vehicle's position along the target trajectory.

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

[0260] In some embodiments, the egomotion of the camera (and therefore the vehicle body) may be estimated based on optical flow analysis of the captured images. Optical flow analysis of a sequence of images identifies pixel motion from the sequence of images and determines the movement of the vehicle based on the identified motion. The egomotion may be integrated along road segments over time to reconstruct a trajectory associated with the road segments traversed by the vehicle.

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

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

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

[0264] Although the reconstructed trajectory modeling method may involve the accumulation of errors, which may include noise components, due to the integration of egomotion over long periods of time, such errors are insignificant because the generated models may provide sufficient accuracy for navigation over local scales. Furthermore, it is possible to counteract the integrated errors by using external information sources, such as satellite images or geodetic surveys. For example, the disclosed system and method may use a GNSS receiver to counteract the accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed system and method may enable steering applications that do not depend heavily on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed system may use GNSS signals only for database indexing purposes.

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

[0266] As explained above, a 3D road model can be built by detecting short range segments and combining them together. The combining can be enabled by calculating a six-stage ego-motion model using video and / or images captured by a camera, data from inertial sensors reflecting vehicle motion, and the host vehicle's speed signal. The accumulated error can be small enough for some local distance ranges, such as about 100 meters. All this can be completed in a single drive over a particular road segment.

[0267] In some embodiments, multiple runs may be used to average the resulting model and further improve its accuracy. The same vehicle may drive the same route multiple times, or multiple vehicles may send the model data they collect to a central server. In either case, a matching procedure may be performed to identify overlapping models and enable averaging to generate a target trajectory. The constructed model (e.g., including the target trajectory) may be used for steering once it meets the bunching criteria. Further subsequent runs may be used for further model improvement and to adapt to changes in infrastructure.

[0268] Sharing of driving experience (e.g., sensory data) between multiple automobiles becomes feasible when they are connected to a central server. Each vehicle client may store a partial copy of a universal road model that may be relevant to its current location. A bidirectional update procedure between the vehicle and the server may be performed by the vehicle and the server. The small footprint concept described above enables the disclosed system and method to perform bidirectional updates using extremely low bandwidth.

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

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

[0271] In some embodiments, multiple autonomous vehicles traveling a road segment may communicate with a server. The vehicles (or clients) may generate curves in any coordinate frame that represent their maneuvers (e.g., through egomotion synthesis). The vehicles may detect and locate landmarks in the same frame. The vehicles may upload the curves and landmarks to the server. The server may collect data from the vehicles over multiple maneuvers and generate an integrated road model. For example, as discussed below with respect to FIG. 19, the server may generate a sparse map with an integrated road model using the uploaded curves and landmarks.

[0272] The server may provide the model to a client (e.g., a vehicle). For example, the server may provide a sparse map to one or more vehicles. The server may update the model continuously or periodically as it receives new data from the vehicles. For example, the server may process the new data to evaluate whether the data contains information that should trigger an update or creation of new data on the server. The server may provide the updated model or updates to the vehicles to provide navigation for the autonomous vehicle.

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

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

[0275] In some embodiments, a remote server may collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a common road segment). The server may match curves with landmarks and create an average road model based on the collected trajectories from multiple vehicles. The server may calculate a graph of roads and the most probable path at each node or connection of road segments. For example, the remote server may align the trajectories and generate a crowdsourced sparse map from the collected trajectories.

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

[0277] In some embodiments, the server may identify changes to the model, e.g., construction, detours, new signs, removal of signs, etc., based on the data received from the vehicle. The server may update the model continuously, periodically, or immediately upon receiving new data from the vehicle. The server may provide updates to the model or provide an updated model to the vehicle to provide autonomous navigation. For example, as discussed further below, the server may use crowdsourced data to remove "ghost" landmarks detected by the vehicle.

[0278] In some embodiments, the server may analyze the driver's interference during autonomous driving. The server may analyze data received from the vehicle at the time and location when the interference occurred and / or data received prior to the time when the interference occurred. The server may identify specific pieces of data that are caused by or closely related to the interference, such as data indicating temporary lane closures, data indicating pedestrians 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.

[0279] FIG. 12 is a schematic diagram of a system that uses crowdsourcing to generate a sparse map (and serves and navigates using the crowdsourced sparse map). FIG. 12 shows a road segment 1200 that includes one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 may travel on the road segment 1200 at the same time or at different times (although shown in FIG. 12 as appearing on the road segment 1200 at the same time). At least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. To simplify the example, it is assumed that all of the vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

[0280] Each vehicle may be similar to a vehicle (e.g., vehicle 200) disclosed in other embodiments and may include components or devices included or associated with a vehicle disclosed in other embodiments. Each vehicle may include an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle may communicate with a remote server 1230 via one or more networks (e.g., via a cellular network and / or the Internet, etc.) through a wireless communication path 1235 as shown by the dotted line. Each vehicle may transmit data to and receive data from the server 1230. For example, the server 1230 may collect data from multiple vehicles traveling the road segment 1200 at different times and process the collected data to generate a road navigation model of the autonomous vehicle or updates to the model. The server 1230 may transmit the road navigation model of the autonomous vehicle or updates to the model to the vehicles that transmitted data to the server 1230. Server 1230 may transmit the autonomous vehicle's road navigation model, or updates to the model, to other vehicles that subsequently travel road segment 1200.

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

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

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

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

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

[0286] In the road navigation model of the autonomous vehicle, the geometry of the road features or target trajectories may be encoded with curves in three-dimensional space. In one embodiment, the curves may be three-dimensional splines including one or more connected three-dimensional polynomials. Those skilled in the art will appreciate that the splines may be a numerical function piecewise defined by a series of polynomials to fit the data. The splines for fitting the three-dimensional road geometry data may include linear splines (first order), quadratic splines (second order), three-dimensional 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) the data points of the three-dimensional road geometry data. In some embodiments, the road navigation model of the autonomous vehicle may include three-dimensional splines corresponding to the target trajectories along a common road segment (e.g., road segment 1200) or lanes of road segment 1200.

[0287] As described above, the road navigation model of the autonomous vehicle included in the sparse map may include other information, such as an identification of at least one landmark along the road segment 1200. The landmark may be visible within the field of view of a camera (e.g., camera 122) mounted on each of the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the camera 122 may capture an image of the landmark. A processor (e.g., processor 180, 190 or processing unit 110) provided on the vehicle 1205 may process the image of the landmark to extract identification information regarding the landmark. The identification information of the landmark may be stored in the sparse map 800 rather than the actual image of the landmark. The identification information of the landmark may require significantly less storage space than the actual image. Other sensors or systems (e.g., a GPS system) may provide specific identification information of the landmark (e.g., the location of the landmark). The landmarks may include at least one of a traffic sign, an arrow mark, a lane marking, a dashed lane marking, a traffic light, a stop line, a directional sign (e.g., a freeway exit sign with an arrow indicating a direction, a freeway sign with an arrow indicating a different direction or location), a landmark beacon, or a light pole. A landmark beacon refers to a device (e.g., an RFID device) installed along a road segment that transmits or reflects a signal to a receiver installed in a vehicle, such that if the vehicle passes by the device, the beacon received by the vehicle and the location of the device (e.g., as determined from the device's GPS location) may be used as a landmark to be included in the autonomous vehicle's road navigation model and / or sparse map 800.

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

[0289] The landmark identification information may include the size of the landmark. A processor provided in the vehicle (e.g., 1205) may estimate the physical size of the landmark based on an analysis of the image. The server 1230 may receive multiple estimates of the physical size of the same landmark from different drives of different vehicles. The server 1230 may average the different estimates to obtain a physical size for the landmark and store the size of the landmark in the road model. The estimate of the physical size 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 a scale magnification based on the position of the landmark as it appears 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 in the image from the landmark to the extended focus at time t1, and D is the change in distance to the landmark in the image from t1 to t2. dt represents (t2-t1). For example, the distance to a landmark may be estimated by Z=V×dt×R / D, where V is the speed of the vehicle, R is the distance in the image between the landmark and the extended focus, dt is the time interval, and D is the image displacement of the landmark along the epipolar line. Other formulas equivalent to the above formula can be used to estimate the distance to a landmark, for example, Z=V×ω / Δω, where V is the speed of the vehicle, ω is the image length (such as the width of the object), and Δω is the change in the image length per unit time.

[0290] If the physical size of the landmark is known, the distance to the landmark may be determined based on the following formula: 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 the landmark leaves the image. From the above formula, the change in distance Z is ΔZ=f×W×Δω / ω 2+f×ΔW / ω, where ΔW decays to zero through averaging and Δω is the number of pixels that represents the bounding box precision of the image. An estimate of the landmark's physical size can be calculated on the server side by averaging multiple observations. The resulting error in distance estimation can be very small. There are two sources of error that can occur when using the above formula, namely ΔW and Δω. Their contribution to the distance error is: ΔZ=f×W×Δω / ω 2 +f×ΔW / ω, however ΔW has decayed to zero due to averaging, and therefore ΔZ is determined by Δω (e.g., bounding box inaccuracies in the image).

[0291] For a landmark of unknown size, the distance to the landmark may be estimated by tracking feature points at the landmark across a sequence of frames. For example, a particular feature that appears on a speed limit sign may be tracked across two or more image frames. Based on those tracked features, a distribution of distances for each feature point may be generated. A distance estimate may be extracted from the distribution of distances. For example, the most frequent distance that appears in the distribution of distances may be used as the distance estimate. As another example, the mean of the distribution of distances may be used as the distance estimate.

[0292] FIG. 13 illustrates an exemplary road navigation model for an autonomous vehicle represented by a number of three-dimensional splines 1301, 1302, and 1303. The curves 1301, 1302, and 1303 illustrated in FIG. 13 are for illustrative purposes only. Each spline may include one or more three-dimensional polynomials connecting a number of data points 1310. Each polynomial may be a first order polynomial, a second order polynomial, a third order polynomial, or any suitable combination of polynomials having different dimensions. Each data point 1310 may be associated with navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to a landmark (e.g., size, location, and identification information of the landmark) and / or a road signature profile (e.g., road geometry, road roughness profile, road curvature profile, road width profile). In some embodiments, some data points 1310 may be associated with data related to landmarks and others may be associated with data related to road signature profiles.

[0293] FIG. 14 shows raw location data 1410 (e.g., GPS data) received from five separate maneuvers. One maneuver may be distinct from another if distinct vehicles passed at the same time, the same vehicle at distinct times, or distinct vehicles at distinct times. To account for errors in the location data 1410 and different positions of vehicles in the same lane (e.g., one vehicle may drive closer to the left side of the lane than another vehicle), the server 1230 may generate a map overview 1420 that uses one or more statistical techniques to determine whether variations in the raw location data 1410 represent actual differences or statistical errors. Each route in the overview 1420 may be traced back to the corresponding raw data 1410 that formed the route. For example, the route between A and B in the overview 1420 corresponds to raw data 1410 from drives 2, 3, 4, and 5, but not from maneuver 1. While the outline 1420 may not be detailed enough to be used to navigate a vehicle (e.g., because it combines maneuvers from multiple lanes on the same road, unlike the splines discussed above), it does provide useful topological information and can be used to define intersections.

[0294] FIG. 15 illustrates an example in which further detail may be generated for a sparse map within a segment of a map overview (e.g., segment A to B within overview 1420). As illustrated in FIG. 15, data (e.g., ego-motion data and road marking data, etc.) may be presented according to a position S (or S1 or S2) along a maneuver. Server 1230 may identify landmarks for the sparse map by identifying unique matches between landmarks 1501, 1503, and 1505 of maneuver 1510 and landmarks 1507 and 1509 of maneuver 1520. Such a matching algorithm may result in the identification of landmarks 1511, 1513, and 1515. However, one skilled in the art will recognize that other matching algorithms may be used. For example, stochastic optimization may be used instead of or in combination with unique matching. Server 1230 may align the maneuvers longitudinally to align the matched landmarks. For example, the server 1230 may select one run (eg, run 1520) as the reference run and then shift and / or stretch other runs (eg, run 1510) for alignment.

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

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

[0297] In some embodiments, system 1700 may remove redundancy in driving segment 1705. For example, if a landmark appears in multiple images from camera 1701, system 1700 may remove redundant data such that driving segment 1705 includes only one copy of the landmark's location and any metadata associated therewith. As a further example, if a lane marking appears in multiple images from camera 1701, system 1700 may remove redundant data such that driving segment 1705 includes only one copy of the location of any metadata and any metadata associated with the lane marking.

[0298] System 1700 also includes a server (e.g., server 1230). Server 1230 may receive multiple driving segments 1705 from the vehicles and recombine them into a single driving 1707. Such a configuration may allow the server to store data related to the entire driving while also reducing bandwidth requirements for moving data between the vehicles and the server.

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

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

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

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

[0303] Process 1900 may include receiving (step 1905) a number of images captured as one or more vehicles pass through the road segment. Server 1230 may receive the images from a camera included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 may receive removed image data that has had redundancy removed by a processor of vehicle 1205, as described above with respect to FIG.

[0304] The process 1900 may further include identifying at least one line representation of a road surface feature extending along the road segment based on the multiple images (step 1910). Each line representation may represent a path along the road segment that substantially corresponds to a road surface feature. For example, the server 1230 may analyze the environmental images received from the camera 122 to identify road edges or lane markings and determine a trajectory of travel along the road segment 1200 associated with the road edges or lane markings. In some embodiments, the trajectory (or line representation) may include a spline, a polynomial representation, or a curve. The server 1230 may determine a trajectory of travel of the vehicle 1205 based on the egomotion (e.g., 3D translational and / or 3D rotational movement) of the camera received in step 1905.

[0305] The process 1900 may include identifying a number of landmarks associated with the road segment based on the number of images (step 1910). For example, the server 1230 may analyze the environmental images received from the camera 122 to identify one or more landmarks, e.g., road signs along the road segment 1200. The server 1230 may identify the landmarks using analysis of the number of images captured as one or more vehicles pass through the road segment. To enable crowdsourcing, the analysis may include rules for accepting and rejecting potential landmarks associated with the road segment. For example, the analysis may include accepting a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0306] Process 1900 may include other operations or steps performed by server 1230. As discussed in more detail below, for example, the navigation information may include a target trajectory for a vehicle traveling along a road segment, and process 1900 may include clustering, by server 1230, vehicle trajectories associated with a plurality of vehicles traveling on the road segment, and determining a target trajectory based on the clustered vehicle trajectories. Clustering the vehicle trajectories may include clustering, by server 1230, a plurality of trajectories associated with the vehicles traveling on the road segment into a plurality of clusters based on at least one of an absolute heading of the vehicle or a lane designation of the vehicle. Generating the target trajectory may include averaging, by server 1230, the clustered trajectories. As a further example, process 1900 may include aligning the data received in step 1905. As discussed above, other operations or steps performed by server 1230 may be included in process 1900.

[0307] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates rather than global coordinates. For autonomous driving, some systems may present data in world coordinates. For example, longitude and latitude coordinates on the 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. To locate the vehicle on the map, it would be natural to use an on-board GPS device 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 path can then be represented in the body reference frame and steering commands can be calculated or generated.

[0308] The disclosed system and method may enable navigation (e.g., steering control) of an autonomous vehicle using a low-footprint model that may be collected by the autonomous vehicle itself without utilizing expensive survey equipment. To support autonomous navigation (e.g., steering applications), the road model may include a sparse map with the road geometry, its lane configuration, and landmarks that may be used to determine the location or position of the vehicle along a trajectory included in the model. As described above, the generation of the sparse map may be performed by a remote server that communicates with and receives data from the vehicles traveling on the road. The data may include sensory data, a reconstructed trajectory based on the sensory data, and / or a recommended trajectory that may represent a modified reconstructed trajectory. As discussed below, the server may send the model back to the vehicle or other vehicles that subsequently travel on the road to aid in autonomous navigation.

[0309] FIG. 20 shows a block diagram of the server 1230. The server 1230 may include a communication unit 2005, which may include both hardware components (e.g., communication control circuits, switches, and antennas) and software components (e.g., communication protocols, computer code). For example, the communication unit 2005 may include at least one network interface. The server 1230 may communicate with the vehicles 1205, 1210, 1215, 1220, and 1225 through the communication unit 2005. For example, the server 1230 may receive navigation information transmitted from the vehicles 1205, 1210, 1215, 1220, and 1225 through the communication unit 2005. The server 1230 may provide the road navigation model of the autonomous vehicle to one or more autonomous vehicles through the communication unit 2005.

[0310] The server 1230 may include at least one non-transitory storage medium 2010, such as a hard drive, compact disc, tape, etc. The storage device 1410 may be configured to store data, such as navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225, and / or a road navigation model for the autonomous vehicle generated by the server 1230 based on the navigation information. The storage device 2010 may be configured to store any other information, such as a sparse map (e.g., sparse map 800 described above with respect to FIG. 8).

[0311] 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 memory 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 for the sparse map 800), a road navigation model of the autonomous vehicle, and / or navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225.

[0312] The server 1230 may include at least one processing device 2020 configured to execute computer codes or instructions stored in the memory 2015 to perform various functions. For example, the processing device 2020 may analyze navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225 and generate a road navigation model for the autonomous vehicle based on the analysis. The processing device 2020 may control the communication unit 1405 to provide the road navigation model for the autonomous vehicle to one or more autonomous vehicles (e.g., one or more of the vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicle that subsequently travels the road segment 1200). The processing device 2020 may be similar to or different from the processors 180, 190, or the processing unit 110.

[0313] 21 shows a block diagram of a memory 2015 that may store computer code or instructions for performing one or more operations to generate a road navigation model for use in navigating an autonomous vehicle. As shown in FIG. 21, the memory 2015 may store one or more modules for performing operations to process navigation information of the vehicle. For example, the memory 2015 may include a model generation module 2105 and a model provisioning module 2110. The processor 2020 may execute instructions stored in any of the modules 2105 and 2110 included in the memory 2015.

[0314] 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 the vehicles 1205, 1210, 1215, 1220, and 1225. For example, in generating the autonomous vehicle road navigation model, the processor 2020 may cluster vehicle trajectories along the common road segment 1200 into different clusters. The processor 2020 may determine a target trajectory along the common road segment 1200 based on the clustered vehicle trajectories for each of the different clusters. Such operations may include determining a 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.

[0315] The road model and / or sparse map may store trajectories associated with road segments. These trajectories may be referred to as target trajectories that are provided to an 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 sparse map may be continuously updated (e.g., averaged) with new trajectories received from other vehicles.

[0316] A vehicle traveling along a road segment may collect data by various sensors. The data may include landmarks, road signature profiles, vehicle motion (e.g., accelerometer data, speed data), vehicle position (e.g., GPS data), and may either reconstruct the actual trajectory itself or transmit the data to a server that reconstructs the actual trajectory for the vehicle. In some embodiments, the vehicle may transmit data related to the trajectory (e.g., curves in any reference frame), data of landmarks, and lane designations along the traveled path to the server 1230. In multiple drives, different vehicles traveling along the same road segment may have different trajectories. The server 1230 may identify the path or trajectory associated with each lane from the trajectories received from the vehicles through a clustering process.

[0317] 22 illustrates a process for clustering vehicle trajectories associated with the 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 trajectories determined from the clustering process may be included in the road navigation model or sparse map 800 for the autonomous vehicle. In some embodiments, the vehicles 1205, 1210, 1215, 1220, and 1225 traveling along the road segment 1200 may transmit the trajectories 2200 to the server 1230. In some embodiments, the server 1230 may generate the trajectories based on landmark, road geometry, and vehicle motion information received from the vehicles 1205, 1210, 1215, 1220, and 1225. To generate a road navigation model for the autonomous vehicle, the server 1230 may cluster the vehicle trajectory 1600 into multiple clusters 2205, 2210, 2215, 2220, 2225, and 2230, as shown in FIG. 22.

[0318] Clustering may be performed using various criteria. In some embodiments, all maneuvers in a cluster may be similar with respect to absolute direction along the road segment 1200. The absolute direction may be obtained from GPS signals received by the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the absolute direction may be obtained using dead reckoning. As one skilled in the art will appreciate, dead reckoning may be used to determine the current position and therefore the heading of the vehicles 1205, 1210, 1215, 1220, and 1225 by using previously determined positions, estimated speeds, etc. Trajectories clustered by absolute direction may be useful for identifying paths along a roadway.

[0319] In some embodiments, all maneuvers in a cluster may be similar with respect to lane designation along the maneuvers on road segment 1200 (e.g., in the same lane before and after a junction). Trajectories clustered by lane designation may be useful for identifying lanes along a roadway. In some embodiments, both criteria (e.g., absolute direction and lane designation) may be used for clustering.

[0320] In each cluster 2205, 2210, 2215, 2220, 2225, and 2230, the trajectories may be averaged to obtain a target trajectory associated with the particular cluster. For example, trajectories from multiple drives associated with the same lane cluster may be averaged. The averaged trajectory may be the target trajectory associated with the particular lane. To average a cluster of trajectories, the server 1230 may select a reference frame for any trajectory C0. For all other trajectories (C1,...Cn), the server 1230 may find a rigid transformation that maps C to C0, where i=1, 2,...n, where n is a positive integer and corresponds to the total number of trajectories included in the cluster. The server 1230 may calculate intermediate curves or trajectories in the C0 reference frame.

[0321] In some embodiments, landmarks may define matching arc lengths between different maneuvers and can be used for trajectory alignment with lanes. In some embodiments, lane markings before and after junctions can be used for trajectory alignment with lanes.

[0322] To assemble lanes from the trajectory, server 1230 may select a frame of reference for any lane. Server 1230 may map overlapping lanes to the selected frame of reference. Server 1230 may continue mapping until all lanes are in the same frame of reference. Lanes adjacent to each other may be aligned as if they were the same lane and may later be shifted laterally.

[0323] Landmarks recognized along a road segment may be mapped to a common reference frame, first at the lane level and then at the junction level. For example, the same landmark may be recognized multiple times by multiple vehicles in multiple maneuvers. Data regarding the same landmark received in different maneuvers may be slightly different. Such data may be averaged and mapped to the same reference frame, e.g., the C0 reference frame. Additionally or alternatively, the variance of data of the same landmark received in multiple maneuvers may be calculated.

[0324] In some embodiments, each lane of road segment 120 may be associated with a target trajectory and certain landmarks. The target trajectory or multiple such target trajectories may be included in the road navigation model of the autonomous vehicle and may be used later by other autonomous vehicles traveling along the same road segment 1200. Landmarks identified by the vehicle 1205, 1210, 1215, 1220, and 1225 while the vehicle is traveling along the road segment 1200 may be recorded in association with the target trajectory. The target trajectory and landmark data may be updated continuously or periodically with new data received from other vehicles during subsequent drives.

[0325] To localize the autonomous vehicle, the disclosed system and method may use an extended Kalman filter. The vehicle's location may be determined based on 3D position data, and / or 3D orientation data, prediction of the vehicle's future location beyond its current location by integrating ego-motion. The vehicle's localization may be modified or adjusted by image observations of landmarks. For example, if the vehicle detects a landmark in an image captured by a camera, the landmark may be compared to known landmarks stored in the road model or sparse map 800. The known landmark may have a known position (e.g., GPS data) along the target trajectory stored in the road model and / or sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark may be estimated. The vehicle's location along the target trajectory may be adjusted based on the distance to the landmark (stored in the road model or sparse map 800) and the known location of the landmark. The landmark's location / location data (e.g., median value from multiple drives) stored in the road model and / or sparse map 800 may be assumed to be accurate.

[0326] In some embodiments, the disclosed system may form a closed loop subsystem, where an estimate of the vehicle's 6 degrees of freedom position (e.g., 3D position data, as well as 3D orientation data) may be used to navigate (e.g., steer the wheels) the autonomous vehicle to reach a desired point (e.g., stored 1.3 seconds ahead). The measured data from the steering and actual navigation may then be used to estimate the 6 degrees of freedom position.

[0327] In some embodiments, poles along the road, such as lampposts and power or cable poles, may be used as landmarks to locate the vehicle. Other landmarks, such as traffic signs, traffic lights, arrows on the road, stop lines, and static features or signatures of objects along the road segments may also be used as landmarks to locate the vehicle. When poles are used to identify the location, the x observation of the pole (i.e., the viewing angle from the vehicle) may be used rather than the y observation (i.e., the distance to the pole) since the bottom of the pole may be occluded and they may not be at the road plane.

[0328] FIG. 23 illustrates a navigation system for a vehicle that may be used for autonomous navigation using a crowdsourced sparse map. By way of example, the vehicle is illustrated as vehicle 1205. The vehicle illustrated in FIG. 23 may be, for example, vehicles 1210, 1215, 1220, and 1225, as well as any other vehicle disclosed herein, including vehicle 200 illustrated in other embodiments. As illustrated in FIG. 12, the vehicle 1205 may communicate with a server 1230. The vehicle 1205 may include an image capture device 122 (e.g., camera 122). The vehicle 1205 may include a navigation system 2300 configured to provide navigation guidance to the vehicle 1205 for traveling a road (e.g., road segment 1200). The vehicle 1205 may include other sensors, for example, a speed sensor 2320 and an accelerometer 2325. The speed sensor 2320 may be configured to detect the speed of the vehicle 1205. The accelerometer 2325 may be configured to detect acceleration or deceleration of the vehicle 1205. The vehicle 1205 shown in Figure 23 may be an autonomous vehicle and the navigation system 2300 may be used to provide navigation guidance for the autonomous driving. Alternatively, the vehicle 1205 may be a non-autonomous, human-controlled vehicle and the navigation system 2300 may also be used to provide navigation guidance.

[0329] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 over the communication path 1235. The navigation system 2300 may also include a GPS unit 2310 configured to receive and process GPS signals. The navigation system 2300 may further include at least one processor 2315 configured to process data, such as GPS signals, map data from the sparse map 800 (which may be stored in a storage device onboard the vehicle 1205 and / or received from the server 1230), road geometry detected by the road profile sensor 2330, images captured by the camera 122, and / or a road navigation model of the autonomous vehicle received from the server 1230. The road profile sensor 2330 may include different types of devices for measuring different types of road profiles, such as road roughness, road width, road elevation, road curvature, etc. For example, the road profile sensor 2330 may include a device that measures the suspension movement of the vehicle 2305 to derive a road roughness profile. In some embodiments, the road profile sensor 2330 may include a radar sensor that measures the distance from the vehicle 1205 to the road edge (e.g., the road edge boundary) and thereby measures the width of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the elevation above and below the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the road curvature. For example, a camera (camera 122 or another camera) may be used to capture an image of the road indicative of the road curvature. The vehicle 1205 may use such an image to detect the road curvature.

[0330] The at least one processor 2315 may be programmed to receive at least one environmental image associated with the vehicle 1205 from the camera 122. The at least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with the vehicle 1205. The navigation information may include a trajectory associated with the travel of the vehicle 1205 along the road segment 1200. The at least one processor 2315 may determine the trajectory based on a motion, e.g., a three-dimensional translational and three-dimensional rotational motion, of the camera 122 (and thus the vehicle). In some embodiments, the at least one processor 2315 may determine a translational and rotational motion of the camera 122 based on an analysis of a plurality of images acquired by the camera 122. In some embodiments, the navigation information may include lane designation information (e.g., which lane the vehicle 1205 will travel along the road segment 1200). Navigation information transmitted from vehicle 1205 to server 1230 may be used by server 1230 to generate and / or update a road navigation model for the autonomous vehicle and may be sent back from server 1230 to vehicle 1205 to provide autonomous navigation guidance to vehicle 1205.

[0331] The at least one processor 2315 may be programmed to transmit navigation information from the vehicle 1205 to the server 1230. In some embodiments, the navigation information may be transmitted to the server 1230 along with road information. The road location information may include at least one of a GPS signal received by the GPS unit 2310, landmark information, road geometry, lane information, and the like. The at least one processor 2315 may receive an autonomous vehicle road navigation model or a portion of the model from the server 1230. The autonomous vehicle road navigation model received from the server 1230 may include at least one update based on the navigation information transmitted from the vehicle 1205 to the server 1230. The portion of the model transmitted from the server 1230 to the vehicle 1205 may include an updated portion of the model. The at least one processor 2315 may perform at least one navigation maneuver by the vehicle 1205 (e.g., steering, such as turning, braking, accelerating, passing another vehicle, etc.) based on the received autonomous vehicle road navigation model or the updated portion of the model.

[0332] The at least one processor 2315 may be configured to communicate with various sensors and vehicle components included in the vehicle 1205, including the communication unit 1705, the GPS unit 2315, the camera 122, the speed sensor 2320, the accelerometer 2325, and the road profile sensor 2330. The at least one processor 2315 may collect information or data from the various sensors and vehicle components and transmit the information or data to the server 1230 through the communication unit 2305. Alternatively or in addition, the various sensors or components of the vehicle 1205 may be in communication with the server 1230 and transmit data or information collected by the sensors or components to the server 1230.

[0333] In some embodiments, the vehicles 1205, 1210, 1215, 1220, and 1225 may communicate with each other and share navigation information with each other, such that at least one of the vehicles 1205, 1210, 1215, 1220, and 1225 may generate an autonomous vehicle road navigation model using crowdsourcing, for example, based on information shared by the other vehicles. In some embodiments, the vehicles 1205, 1210, 1215, 1220, and 1225 may share navigation information with each other, and each vehicle may update its own autonomous vehicle road navigation model provided to the vehicle. In some embodiments, at least one of the vehicles 1205, 1210, 1215, 1220, and 1225 (e.g., vehicle 1205) may function as a hub vehicle. At least one processor 2315 of the hub vehicle (e.g., vehicle 1205) may perform some or all of the functions performed by the server 1230. For example, the at least one processor 2315 of the hub vehicle may communicate with and receive navigation information from other vehicles. The at least one processor 2315 of the hub vehicle may generate a road navigation model for the autonomous vehicle or update the model based on shared information received from the other vehicles. The at least one processor 2315 of the hub vehicle may transmit the road navigation model for the autonomous vehicle or updates to the model to the other vehicles to provide autonomous navigation guidance.

[0334] Using mapping altitude to determine navigation parameters

[0335] In many aspects of autonomous or semi-autonomous navigation, it may be useful to determine distances to objects in the host vehicle's environment. In some cases, the distance determination may be performed based on one or more outputs from a LIDAR or RADAR system. Alternatively or additionally, the distance determination may be performed based on analysis of images acquired from one or more image capture devices. However, in some cases, analysis of the acquired images may present certain challenges. For example, distance measurements based on image analysis may be more difficult if objects in the host vehicle's environment have different altitudes relative to the host vehicle. For example, in analysis of collected images, a target vehicle at an altitude higher than the altitude of the host vehicle may appear to be farther away from the host vehicle than it actually is. To address this issue, the distance determination based on image analysis may take into account the difference in altitude between the detected object and the host vehicle. This provides for improved accuracy of relative distance determination. Such altitude information may be determined in a variety of ways. However, in some embodiments, the altitude information may be stored for road segments (e.g., included in the sparse map described above). This mapping altitude information may be used to determine the distance from the host vehicle (particularly from the device that captured the image or images being analyzed) to target objects detected in the images. This technique for considering altitude in distance measurements based on captured images is described in more detail below.

[0336] FIG. 24 illustrates a block diagram of a memory consistent with disclosed embodiments. In some embodiments, memory 140 or 150 may include map information 2401, altitude information 2403, object identification module 2405, location module 2407, distance module 2409, and navigation module 2411. The disclosed embodiments are not limited to any particular configuration of memory 140 or 150. Furthermore, a processor (e.g., application processor 180, image processor 190, and / or processing unit 110) may execute instructions stored in any of modules 2405, 2407, 2409, and 2411 included in memory 140 or 150. Furthermore, although various modules (discussed above and below) are described for performing functions related to disclosed embodiments, these modules may not be logically separate and may instead be included or integrated (in any combination) in an integrated navigation system configured to analyze acquired images and determine a next navigation state based on features of the host vehicle environment detected by analysis of these images.

[0337] In one embodiment, the object identification module 2405 may store instructions that, when executed by the processor, enable the processor to perform image analysis of the image set and identify objects within the image set. In one embodiment, the object identification module 2405 may include a monocular image analysis module 402 and / or a stereo image analysis module 404. As described above, the monocular image analysis module 402 may include instructions for detecting a set of features within the image set, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazards, and any other features associated with the vehicle's environment. Also as described above, the stereo image analysis module 404 may include instructions for detecting a set of features within the first and second image sets, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazards, and any other features associated with the vehicle's environment. The object identification module 2405 may include instructions for identifying a type of object based on the features, such as a vehicle, a pedestrian, an object in a roadway, a manhole cover, a traffic light, a traffic sign, etc. Additionally, as part of the image analysis process, each identified object of a particular type may be assigned a bounding box that is associated with the edge boundary of the object in the associated image.

[0338] In one embodiment, the localization module 2407 may store instructions that, when executed by the processor, enable the processor to determine a location of the host vehicle. In one embodiment, the processor may determine the location of the host vehicle based on the output of at least one sensor of the host vehicle, such as a GPS device, a speed sensor, and / or an accelerometer. In one embodiment, the processor may determine the location of the host vehicle based on a localization on a sparse map road model (described above). A sparse map consistent with this disclosure may include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and any other road-related features useful for navigating a vehicle. Using the recognized landmarks identified in one or more acquired images, along with one or more target trajectories included in the sparse map, the processor may determine the location of the host vehicle relative to the target trajectories in the map. Such location information may inform the host vehicle of certain features associated with the host vehicle's environment relative to the host vehicle's determined location. For example, if the sparse map stores the locations of potholes along a road segment, locating the host vehicle relative to a particular target trajectory may determine that there is a pothole 114 meters ahead of the host vehicle along the current target trajectory. Similarly, if the sparse map stores road elevation information (e.g., every 10 cm, 1 m, 2 m, 5 m, 10 m, 50 m, 100 m, etc.), the processor may determine that the elevation of a road segment 128 m ahead of a current specific position of the host vehicle relative to a particular target trajectory is 27 m higher than the elevation of the road segment at the current specific position of the host vehicle. After locating the host vehicle, as described above, the processor may estimate its position relative to the target trajectory (e.g., between recognized landmark identifications) based on sensor outputs indicative of the ego-motion of the host vehicle between recognized landmarks.

[0339] In one embodiment, map information 2401 (including, for example, the sparse map described above) may store features associated with a particular road segment. The features may include detected lane markings, road signs, highway exit ramps, traffic lights, road infrastructure, road width information, guard rails, trees, buildings, lamp posts, and any other features related to the vehicle's environment. In one embodiment, map information 2401 may further include altitude information 2403. The altitude information 2403 may include the height of the road segment at a particular location (e.g., 10 meters, 20 meters, 30 meters, etc.) or may include the slope (e.g., 10 degrees or 11 degrees, etc.). In one embodiment, the altitude information 2403 may include the height relative to an origin (e.g., sea level, or a particular origin associated with a particular road segment). In one embodiment, the altitude information 2403 may be stored as a formula (e.g., formula (2)), each corresponding to a road segment. In one embodiment, the altitude information 2403 may be stored in a table with each altitude information entry corresponding to a particular location along a road segment. Such altitude information may be stored in the sparse map at any suitable interval (e.g., every 10 cm, 1 m, 2 m, 5 m, 10 m, 50 m, 100 m, etc.). In one embodiment, referring again to FIG. 13, a number of 3D splines 1301, 1302, and 1303 may be stored with altitude information for lanes at a number of data points 1310. The processor may obtain the altitude information from the sparse map in any suitable manner appropriate for a particular altitude storage protocol (e.g., retrieving the altitude information from a table, determining the altitude from a stored profile or function / formula, determining the altitude from a z-axis projection of a 3D spline used to represent the target trajectory, etc.).

[0340] In one embodiment, the distance module 2409 may store instructions configured to, when executed by the processor, determine a distance from the host vehicle to an identified object. The distance may be determined based on measurements from image analysis, such as scaling and / or optical flow methods. In some cases, a distance determination based on image analysis may be redundant to or used to validate one or more distance determinations based on the output of a LIDAR or RADAR system. The determined distance from the host vehicle to an object identified in one or more images may depend on the altitude of the identified object relative to the host vehicle. For example, if the target vehicle has a higher altitude than the host vehicle, the determined distance may be greater than the actual distance without considering the altitude. To determine the appropriate navigation operation for the host vehicle, accurate distance values ​​for detected objects should be available.

[0341] Consistent with disclosed embodiments, the processor may determine the distance from the host vehicle to the identified object based on the altitude information 2403. Figures 25A and 25B are schematic diagrams illustrating a situation where a target vehicle 2503 is located on a road segment at a higher altitude than the host vehicle 2501. For example, it may be assumed that the host vehicle 2501 may be on the ground plane and the target vehicle 2503 is located on a plane that is higher than the ground plane. The height Y, which is the height from the ground plane to the plane on which the target vehicle 2503 is located, may be expressed using the following equation:

number

[0342] where y denotes the vertical displacement in image space of the bottom of the target vehicle 2503, f denotes the focal length of the image capture device, and Z denotes the distance from the host vehicle to the target vehicle.

[0343] Furthermore, based on the road model, the height Y can be determined from the following equation:

number

[0344] where a represents a predetermined constant and H represents the height of the image capture device relative to the ground plane. In one embodiment, the constant a can be stored in the map information, the sparse map, and / or the cubic spline. In some cases, the constant a may be a local approximation of the spline. In one embodiment, equation (2) may include more complex functions (e.g., Y=function(Z)).

[0345] In some cases, the processor may use equations (1) and (2) to determine distance Z, which is the distance from the host vehicle 2501 to the target vehicle 2503. For example, the near area may be approximated as a plane. The vanishing line of the plane (horizon) may be determined from the vanishing point of the near part of the road. Alternatively, the local road plane may be determined by any suitable image analysis technique. The bottom of the vehicle in the image relative to the "horizon" may define a space line relative to the bottom of the vehicle, i.e., Y=-yZ / f. This results in the following equation:

number

[0346] In one embodiment, the navigation module 2411 may store software instructions executable by the processor to determine a desired navigation action based on the determined distance. In one embodiment, the navigation module 2411 includes a navigation response module 408. The determined distance from the host vehicle to the identified object (e.g., target vehicle) may be important, for example, for generating an appropriate navigation response of the autonomous vehicle. Based on the determined distance, a navigation action may be determined toward achieving one or more navigation goals of the autonomous vehicle (e.g., drive from point A to point B, do not hit a pedestrian, keep at least one meter away from the pedestrian, keep at least ten meters away from the pedestrian if the speed exceeds 30 kph (or the like), keep at least a safe distance from the leading vehicle, brake to avoid approaching within a safe distance, and many other navigation goals). The processor may achieve these goals depending at least on an accurate distance determination between the host vehicle and the detected object. For example, as the host vehicle approaches a detected pedestrian, a braking system may be triggered to stop the host vehicle at a safe distance from the pedestrian. In one embodiment, the processor may compare the determined distance to a predetermined threshold. If the determined distance exceeds the predetermined threshold (e.g., a safe distance to the preceding vehicle, which may correspond to the sum of the distance the host vehicle can travel at maximum acceleration for a reaction time associated with the host vehicle, the distance range the host vehicle can stop at its maximum braking level, the distance range the target vehicle can stop at its maximum braking level, and optionally a predetermined minimum proximity buffer to maintain to the target vehicle after stopping), the processor may allow the host vehicle to maintain its current speed, course, acceleration, etc. However, if the determined distance is equal to or lower than the predetermined threshold, the processor may cause the host vehicle to brake, turn, etc. In some embodiments, the navigation response may be determined based on a combination of the determined distance value and the relative speed and acceleration.

[0347] 26 is a flowchart of navigating a host vehicle consistent with disclosed embodiments. In step 2601, a processor may receive at least one image from an image capture device that represents the host vehicle's environment. The image may be raw or processed data sent over a network or communication path from image capture devices 122, 124, and / or 126. The data may include any suitable image format.

[0348] In step 2603, the processor may analyze at least one image to identify objects in the host vehicle's environment. The image 2500 shows the host vehicle's environment, which includes a number of different objects. The processor may analyze the image 2500 to identify objects in the image. The processor may access the object identification module 2405 to utilize any suitable image analysis technique. Examples of such techniques include object recognition, image segmentation, feature extraction, optical character recognition (OCR), object-based image analysis, shape region techniques, edge detection techniques, pixel-based detection, and the like. In addition, the processor may further use classification algorithms to distinguish different objects in the image. In one embodiment, the processor may use appropriately trained machine learning algorithms and models to perform object identification. The algorithms may include linear regression, logistic regression, linear discriminant analysis, classification and regression trees, naive Bayes, k-nearest neighbors, learning vector quantization, support vector machines, bagging and random forests, and / or boosting and adaboost, and the like. In some embodiments, the processor, upon execution of the object identification module 2405, may identify objects within the image based at least on visual characteristics of the objects (e.g., size, shape, texture, character, color, etc.).

[0349] In step 2605, the processor may determine a location of the host vehicle. In one embodiment, the processor may determine the location based on analysis of the image. Further, the processor may determine the location of the host vehicle as a specific location of the host vehicle along a cubic spline representing a target trajectory of the host vehicle along a road segment, as described above. Further, consistent with disclosed embodiments, the prediction of the host vehicle's location along the predefined cubic spline may be based on observed locations of at least one recognized landmark. Consistent with disclosed embodiments, the processor may predict the host vehicle's location based on localization on the sparse map road model. In one embodiment, as described above, the host vehicle's location may be determined based on the output of at least one sensor of the host vehicle, such as a GPS device, a speed sensor, and / or an accelerometer. For example, location information from a GPS receiver may contribute to determining the host vehicle's location.

[0350] In stage 2607, the processor may receive map information associated with the determined location of the host vehicle. This map information may include altitude information associated with the environment of the host vehicle. Based on the determined location (e.g., GPS output, or a previous location fix against a sparse map), the processor may obtain map information for a particular location or a particular road segment. The obtained map information may include altitude information for the road segment on which the host vehicle is traveling. The altitude information may be stored in the map, for example, in any manner described above.

[0351] In step 2609, the processor may determine a distance from the host vehicle to the object based on at least the altitude information. According to disclosed embodiments, the processor may utilize the above equations to determine the distance to an object identified in one or more images. For example, based on the altitude information from a stored map, the processor may calculate the relative distance to the target object using equation (2).

[0352] In stage 2611, the processor may determine a navigation action for the host vehicle based on the determined distance. In one embodiment, the processor may access the navigation module 2411 to determine the navigation action. The navigation action may include any of the navigation actions described above that may depend on the determined distance to the identified target object.

[0353] In some cases, as described above, the determined navigation action may include one or more navigation actions developed in response to a goal that the host vehicle maintains at least a safe distance from other vehicles. For example, if the determined distance, taking into account the altitude difference between the host vehicle and the identified target vehicle, is equal to or less than the safe distance, or if the host vehicle is in proximity to a safe distance buffer, the navigation processor may determine a navigation action for the host vehicle aimed at at least achieving or maintaining a safe distance from the identified target vehicle. For example, in some cases, the safe distance may be the sum of the host vehicle's current stopping distance based on the host vehicle's current speed and its current maximum braking performance, an acceleration distance corresponding to the distance the host vehicle will travel at its current maximum acceleration performance during the reaction time associated with the host vehicle, and a stopping distance until the target vehicle reduces its current speed to zero due to the target vehicle's maximum braking performance. The navigation action may be determined based on one or more of the formulas described above in connection with the Responsibility Sensitive Safety (RSS) model.

[0354] In some embodiments, the processor may implement the determined navigation operation if the host vehicle's maximum braking capability, the host vehicle's current speed, the host vehicle's maximum acceleration capability, and / or the reaction time associated with the host vehicle allow the host vehicle to stop within a stopping distance between the host vehicle and the target vehicle that is less than the determined next-state distance (i.e., the distance between the host vehicle and the target vehicle as a result of performing the determined navigation operation). In some cases, the implementation of the determined navigation operation may further take into account the target vehicle's stopping distance, which is based on its determined speed and maximum braking capability. If the host vehicle processor determines that the next-state distance is sufficient to stop between the preceding visible target vehicle and the host vehicle without colliding or causing a collision that is the host vehicle's responsibility, and further assuming that the preceding visible target vehicle may suddenly come to a complete stop at any time, then the host vehicle processor may execute the navigation operation as planned. On the other hand, if the distance is insufficient to stop the host vehicle without colliding or causing a collision that is the host vehicle's responsibility, then the determined navigation operation may not be executed.

[0355] Navigation Parameter Determination Using Mapped Lane Widths

[0356] Similar to the above-described embodiment in which elevation information may be stored in the sparse map for a particular road segment, lane widths measured for the road segment may also be stored in the sparse map. For example, lane width determination may be performed along the road segment as the vehicle passes through the road segment. These lane width measurements may be refined and then integrated into the above-described sparse map by crowdsourcing. For example, the lane width information may be stored as a table for the length of the road segment, as a function or formula defining the width along the length with respect to one or more 3D splines that indicate target trajectories for lanes to travel along the road segment, or in any other suitable form. As described in more detail below, the mapped lane width information may be useful for determining distances between a host vehicle and one or more target objects identified on the road segment. The determined distances may be useful, for example, for validating measurements from a LIDAR system, a RADAR system, or for determining one or more navigation actions for the host vehicle.

[0357] As discussed above, in one embodiment, the processor may receive one or more captured images representative of the host vehicle's surroundings. In one embodiment, as discussed above, the object identification module 2405 may store instructions that, when executed by the processor, enable the processor to perform image analysis of the set of images and identify objects within the set of images. The processor may identify objects within the images, landmarks associated with a road segment (e.g., road signs). The objects may be identified with any of the techniques disclosed above. For example, object recognition, image segmentation, feature extraction, optical character recognition (OCR), object-based image analysis, shape region techniques, edge detection techniques, pixel-based detection, etc. may all be used alone or in combination.

[0358] In one embodiment, as described above, the processor may determine the location of the host vehicle. As described above, the location may be determined by a variety of techniques, including GPS location, recognized landmark location along the target trajectory of the sparse map, combinations thereof, and the like. For example, referring to FIG. 27A, the techniques described above may be used to determine a specific location of the host vehicle 2701 along a spline representing a target trajectory associated with a lane of a road segment along which the host vehicle 2701 is traveling using landmarks 2705.

[0359] In one embodiment, as described above, the distance module 2409 may store instructions that, when executed by the processor, enable the processor to determine the distance from the host vehicle to an identified object. For example, referring to FIG. 27A, a host vehicle 2701, a target vehicle 2703, a landmark 2705, and two splines S1 and S2 are shown in a three-dimensional space relative to (X,Y,Z) coordinates. The splines S1 and S2 may represent the boundaries of a lane associated with a road segment along which the host vehicle 2701 is traveling. The distance determination between the host vehicle 2701 and the target vehicle 2703 may be based on the output of a LIDAR or RADAR system. The distance between the host vehicle 2701 and the target vehicle 2703 may further be determined by image analysis, for example, using scaling of the object between a series of images. The distance determination may take into account altitude differences, as described in the section above. Distance determination may further be based on the tracking trajectory of the target vehicle 2703, comparing the observed tracking trajectory with mapping information (such as a spline representing the driving lane) to determine where the target vehicle is located along the target trajectory. The distance between the host vehicle 2701 and the target vehicle 2703 may be determined as the shortest straight line distance between the host vehicle and the target vehicle. In other cases, the distance between the host vehicle 2701 and the target vehicle 2703 may be determined as the distance of a curved three-dimensional path between the host vehicle and the target vehicle (e.g., along the spline between the lane edge splines S1 and S2, representing the target trajectory traveled by the host vehicle).

[0360] The processor may further determine a distance from the host vehicle to the identified object based on the mapped lane width information. For example, the map information in the sparse map described above may include lane width information associated with the road segment on which the host vehicle travels. As described above, the sparse map may store the lane width information in any suitable format (e.g., a relationship table, periodic values ​​along the road segment length, a three-dimensional spline from which the lane width can be determined, such as between splines S1 and S2 shown in Figures 27A and 27B). For example, the lane width between splines S1 and S2 at a length distance associated with the target vehicle 2703 may be represented as the difference between the x-coordinate projection at point y2 associated with spline S2 and the x-coordinate projection at point y1 associated with spline S1.

[0361] Referring to FIG. 28A, there is shown a host vehicle 2801, a target vehicle 2803, a landmark 2805, and two splines S1 and S2. The splines S1 and S2 may represent lane boundaries associated with the road segments along which the host and target vehicles travel. As shown, there is a width W between the splines S1 and S2. In some embodiments, the width W may be constant or approximately constant between the two splines representing the detected lane boundaries. FIG. 28B shows the splines S1 and S2 projected onto an (x,y) two-dimensional coordinate system (e.g., in image space). Based on known lane width information (e.g., W=3.8 meters), the distance Z from the host vehicle 2801 to the target vehicle 2803 may be determined by the following formula:

number

[0362] where f denotes the focal length of the image capture device and w denotes the width of the lane in image space. For example, w may be 125 pixels and f may be 1400 pixels. If the lane width W in physical space is known to be 3.8 meters (e.g., based on a stored sparse map), then Z may be calculated to be 42.56 meters.

[0363] FIG. 29A shows another image with splines s1, s2, and s3 in a (x,y) two-dimensional coordinate system. FIG. 29B shows an image of splines S1, S2, and S3 in three-dimensional coordinates. In one embodiment, the server may receive the captured image 2900 and use the image to construct an image 2910 by mapping the (x,y) two-dimensional coordinates to a (X,Y,Z) three-dimensional coordinate system. For example, to construct the image 2910, the server may detect a target vehicle 2903 and determine the (x,y) value of the bottom of the target vehicle 2903. In some embodiments, applying a mapping function, the server may calculate the (X,Y,Z) value of the point (x,y). Thus, a three-dimensional spline may be constructed based on the two-dimensional image.

[0364] In one embodiment, using all the constructed splines, the server may generate a road surface model. For example, using the image 2910, the server may generate a road surface model, which may be used as a segment of the map. For example, to generate the road surface model, the server may select points on the splines S1, S2, and S3 at a predefined interval (e.g., 1 meter interval). Furthermore, as shown in FIG. 29B, the server may apply Delaunay triangulation. FIG. 30 shows an example spline projected to a 2D coordinate. FIG. 31 shows the result of the Delaunay triangulation. As shown, points outside the road edge 3101 are filtered out. Furthermore, a region 3103 is added as a fixed width margin outside the road edge. These (X,Y,Z) 3D coordinates may be constructed by the server from the (x,y) 2D coordinates as described above. From the 3D values, the server may obtain information about the road 3101 and the area near the road (e.g., area 3103).

[0365] In some embodiments, the server may map coordinates (e.g., position and rotation information) using one or more 3D splines from the map to map (x,y) two-dimensional coordinates to an (X,Y,Z) three-dimensional coordinate system. For example, the server may project a 3D spline representing lane boundaries into the image. For every 3D point (e.g., spaced apart) along the spline, the server may calculate a 2D image projection using known information (e.g., focal length, principal point, lens distortion, etc.) about the camera or cameras that captured the image. Instead of determining RGB values, the server may determine and store (X,Y,Z) values ​​of the projected points. Thus, the server may determine (X,Y,Z) values ​​for every (x,y) two-dimensional coordinate along the projected spline in the image. When the server detects a contact point of the vehicle with the road (e.g., detected in the image data), the server may look at points y1 and y2 on nearby splines s1 and s2 and determine the distance to the vehicle as the (weighted) average of y1 and y2. Such an approach can be effective when a vehicle is equipped with multiple surround cameras.

[0366] Figure 32 shows the associated triangle projected onto the image based on the camera localization. When the server applies the Delaunay triangulation function, it assigns an (X,Y,Z) 3D value to a point in the image if it falls within the triangle based on the triangle.

[0367] In one embodiment, a processor of the host vehicle may receive the surface model. As described above, the processor may use the techniques described above to determine the location of the host vehicle and its position in a three-dimensional coordinate system. For example, such location determination may be based on location relative to identified landmarks and / or based on determined ego-motion of the host vehicle relative to an identified object (e.g., a target vehicle) between the landmarks. The processor may use the road surface model to determine the distance from the host vehicle to the identified object. For example, when a target vehicle 2903 is detected, the contact point (x,y) with the road is a spatial line. The 3D point of intersection of that line with the road surface provides the distance Z from the host vehicle to the target vehicle.

[0368] As discussed above, the processor may determine a navigation action based at least on the determined distance, for example, if the determined distance from the host vehicle to the target vehicle is less than the current stopping distance, the processor may determine to brake, etc.

[0369] 33 is a flow chart illustrating an example process for navigating a host vehicle consistent with disclosed embodiments. In step 3301, a processor may receive at least one image from an image capture device that represents the host vehicle's environment. The image may be raw or processed data sent from image capture devices 122, 124, and / or 126 over a network or communication path. The data may include data described in some image format.

[0370] In stage 3303, the processor may analyze at least one image to identify objects in the host vehicle's environment. Image 2800 shows the host vehicle's environment, which includes a number of different objects. The processor may analyze image 2800 to identify objects in the image. As described above, the processor may access object identification module 2705 to utilize any suitable image analysis technique. In addition, the processor may further use classification algorithms to distinguish different objects in the image. In one embodiment, the processor may use appropriately trained machine learning algorithms and models to perform object identification.

[0371] In stage 3305, the processor may determine a location of the host vehicle. In one embodiment, as described above, the processor may determine the location of the host vehicle based on a prediction of the host vehicle's location along a predefined cubic spline that represents a target trajectory of the host vehicle along the road segment. For example, referring to FIG. 27A, the processor may determine the location of the host vehicle based on the identified landmarks 2705. Further, consistent with disclosed embodiments, the prediction of the host vehicle's location along the predefined cubic spline may be based on the observed location of at least one recognized landmark. In one embodiment, as described above, the location of the host vehicle may be determined based on the output of at least one sensor of the host vehicle, such as a GPS device, a speed sensor, and / or an accelerometer.

[0372] In step 3307, the processor may access map information associated with the determined location of the host vehicle. This map information includes lane width information associated with roads in the host vehicle's environment. In one embodiment, the processor may receive a sparse map associated with a particular segment along which the host vehicle is traveling. The processor may then determine the location of the host vehicle relative to the trajectory in the map, as described above. Once the trajectory is determined, the processor may determine a future path for the host vehicle based on the determined particular location of the host vehicle along the cubic spline that represents the target trajectory. Additionally, the processor may receive lane width information at all points (or at least equally spaced points) along the road segment ahead of the host vehicle. The lane width information may be stored in the sparse map in any suitable format. Example formats are described above. In some embodiments, the lane width information may include left and right values ​​relative to the target trajectory spline at predetermined longitudinal distance values ​​along the spline, and / or any other storage format.

[0373] In step 3309, the processor may determine a distance from the host vehicle to the object based on at least the lane width information. For example, as described above, the processor may average the y values ​​when the spline is projected into two-dimensional coordinates (e.g., Z=(y1+y2) / 2). In another example, using equation (4), the processor may determine the distance from the host vehicle to the object. Alternatively, the distance may be determined based on the output of at least one sensor of the host vehicle, such as a LIDAR system, a RADAR system, a GPS device, a speed sensor, and / or an accelerometer. In one embodiment, validation of the distance determined based on the output of another sensor of the host vehicle may utilize an image analysis based method of determining the distance from the host vehicle to the object based at least on the lane width information.

[0374] In stage 3311, the processor may determine a navigation action for the host vehicle based on the determined distance. For example, as described above, a navigation action may be determined to maintain or achieve a safe distance (e.g., with respect to the RSS model, as described above) to one or more detected vehicles.

[0375] Lane position determination for partially invisible target vehicles

[0376] In some cases, a target vehicle may be represented in its entirety in an image captured by an image capture device associated with the host vehicle. In such cases, distance determination to the target vehicle may be based on an observed line or location in the image where the target vehicle contacts the road surface. In other cases, however, one or more target vehicles may not be represented in their entirety in the captured image. For example, one or more target vehicles may be partially obscured from the captured image(s), such that the intersection of the target vehicle with the road surface is not observable. In such cases, other techniques may be used to estimate position information for one or more detected target vehicles and determine the distance between the host vehicle and the detected target vehicles. Alternatively or additionally, the estimated position information for the detected target vehicles, optionally in combination with stored map information (e.g., from the sparse map described above), may be used to determine the lane of travel in which the detected target vehicles are traveling, the expected direction of travel of the target vehicles, etc.

[0377] As discussed above, in one embodiment, a processor for image processing may receive one or more captured images representative of the environment surrounding the host vehicle. In one embodiment, as discussed above, the processor may perform image analysis on the set of images to identify objects in the set of images. The processor may identify objects in the images, landmarks associated with a road segment (e.g., road signs). Objects may be identified by any of the techniques disclosed above, such as object recognition, image segmentation, feature extraction, optical character recognition (OCR), object-based image analysis, shape region techniques, edge detection techniques, pixel-based detection, etc.

[0378] In one embodiment, based on the analysis, the processor may identify a first object (e.g., a target vehicle) in the environment. The first object and the road on which the first object is located are partially obscured by a second object (e.g., an obstruction, a road sign, etc.). Figure 34A illustrates an example situation in which the target vehicle may be at least partially obscured in an image captured from the host vehicle 3401. Figure 34A illustrates the position of the host vehicle 3401 relative to other objects, such as the target vehicle 3403 and an obstruction 3405.

[0379] FIG. 34B illustrates an example image that may be captured by a camera associated with the host vehicle 3401. In the image illustrated in FIG. 34B, the target vehicle 3403 may be detected in the image. However, an occlusion 3405 is depicted that obscures portions of the image of the target vehicle 3403. For example, the bottom of the target vehicle 3403 is obscured by the occlusion 3405. Nevertheless, the relevant lane in which the target vehicle is traveling (or the path the target vehicle is traveling and is expected to travel) may be determined, for example, by tracking the movement of the target vehicle 3403 over time (e.g., represented by two or more captured images) and comparing it to mapping information (e.g., the sparse map described above) to estimate the lane or path the target vehicle 3403 is traveling.

[0380] More specifically, based on two or more captured images, the processor may determine the lane position and / or the target vehicle position relative to stored map information. For example, based on a sparse map that stores trajectories for drivable lanes along a road segment (which may include multiple intersecting road portions), the processor may determine that the target vehicle 3403 is located on a lane associated with the target trajectory L1. That is, using the above-mentioned localization techniques, the processor may determine the position of the host vehicle 3401. The image coordinates of the target vehicle 3403 may be mapped by the line V1. As described above, the image coordinates can be converted to map coordinates. Based on the map coordinates and the intersection of the line V1 and the lane L1, the processor may determine the position of the target vehicle 3403.

[0381] Alternatively or additionally, the host vehicle may capture two or more images of the target vehicle 3403 and observe how the representation of the target vehicle changes in the captured images. For example, as the host vehicle 3401 and the target vehicle 3403 approach a junction, the captured images including the target vehicle 3403 may show that the target vehicle 3403 occupies a larger proportion of the captured image as the distance between the host vehicle 3401 and the target vehicle 3403 decreases. Based on the change in the image representation size of the target vehicle 3403 (or based on any other observable image feature associated with the relative movement between the host vehicle 3401 and the target vehicle 3403), the processor may estimate the driving lane of the target vehicle 3403. For example, the processor may access a stored sparse map and determine a driving lane that may be on the other side of the occlusion 3405 observed in the captured image depicted in FIG. 34B. In the illustrated example, the processor may determine that there is one lane of travel on the other side of the occlusion 3405, and that the lane is associated with the target trajectory L1. The processor may examine observed movement characteristics associated with the target vehicle 3403 and determine whether the movement characteristics match the target vehicle's movement along the target trajectory L1. If there is a match, the navigation processor of the host vehicle 3401 may infer that the target vehicle 3403 is traveling along path L1 in the lane on the other side of the occlusion 3405. With this information, the host vehicle processor may infer the future path of the target vehicle. This inference may include, for example, inferring how the target vehicle may interact with the host vehicle or they may merge at an upcoming lane merge. In some cases, the host vehicle may slow down to let the target vehicle go ahead at an upcoming lane merge, even if the target vehicle is partially invisible. In some cases, the host vehicle may accelerate to stay ahead of the target vehicle at the lane merge. The host vehicle determines the distance to the target vehicle based on the sparse map information, and the image coordinates of the target vehicle 3403 may be mapped by the line V1.

[0382] While the illustrated example includes only one lane of travel, the lane estimation and difference determination techniques may also be used when multiple lanes are not visible from the field of view of the host vehicle's image capture device. For example, if two, three, or more lanes are not visible due to occlusion 3405, the same techniques of comparing the observed movement characteristics of the target vehicle in two or more captured images with the lane / trajectory information stored in the sparse map can enable the host vehicle processor to estimate which of the non-visible lanes the target vehicle will be traveling in. From this information, the future path of the target vehicle can be determined.

[0383] FIG. 35A shows an example where multiple lanes are not visible. FIG. 35B shows image coordinates of target vehicle 3503 at t1 and t2 mapped by lines V1 and V2, respectively. The host vehicle 3501 is approaching an intersection with a two-lane road 3507. The processor may determine whether the identified target vehicle 3503 is in lane L1 or lane L2. This determination may be important for proper navigation operation deployment. For example, if the target vehicle is determined to be in the lane associated with trajectory L1, there may be insufficient space for the host vehicle to make a left turn into the lane associated with trajectory L1. On the other hand, if the host vehicle processor determines that the target vehicle 3503 is traveling in the lane associated with trajectory L2, using estimation techniques based on the observed motion characteristics of the vehicle 3503 and stored map data, the processor may conclude that there is enough space for the host vehicle 3501 to make a left turn into the lane associated with trajectory L1 without interfering with the detected target vehicle. In one embodiment, based on the distance from the host vehicle to the target vehicle and the position of the target vehicle from the image, the processor can determine or estimate the speed of the target vehicle. For example, based on lines V1 and V2, the processor can determine the distance traveled by the target vehicle 3503 for a known time interval t2-t1. Thus, the speed of the target vehicle can be determined.

[0384] 35B, when the host vehicle 3501 approaches the intersection between times t1 and t2, the distance from the host vehicle 3501 to the target vehicle 3503 decreases and the size of the target vehicle 3503 in the image 3510 also increases. In one embodiment, the processor may use the formula below to determine the distance Z1 from the host vehicle 3501 to the target vehicle 3503 at t1 and the distance Z2 from the host vehicle 3501 to the target vehicle 3503 at t2:

number

number

[0385] where w1 may indicate the size of the target vehicle 3503 in the image 3510 at t1, w2 may indicate the size of the target vehicle 3503 in the image 3510 at t2, and dZ may indicate the distance traveled by the host vehicle 3501 between t1 and t2, which may be detected by the processor using the image analysis techniques described above. The dZ value may be determined by information from a speed sensor (e.g., a speedometer). Based on the calculated Z1 and Z2, the processor may determine the lane position of the target vehicle 3503.

[0386] FIG. 36A shows another example of a multi-lane road where both the host vehicle 3601 and the target vehicle 3603 are approaching a lane merging point. FIG. 36B shows the image coordinates of the target vehicle 3603 at times t1 to t2, mapped by V1 and V2, respectively. As shown in FIG. 36A, a curved lane 3609 merges with the road 3607. The processor may approximate the curved lane 3609 as a straight line 3613 to simplify the calculations. The processor may use the equations below to determine the distance Z1 from the host vehicle 3601 to the target vehicle 3603 at t1 and the distance Z2 from the host vehicle 3601 to the target vehicle 3603 at t2:

number

number

[0387] where dZ may indicate the distance traveled by the host vehicle 3601 between t1 and t2, a may indicate the angle between the line 3613 and the road 3607, w1 may indicate the size of the target vehicle 3603 in the image 3610 at t1, and w2 may indicate the size of the target vehicle 3603 in the image 3610 at t2. In one embodiment, for simplicity, the processor may virtually rotate the image capture device (e.g., camera) to make the optical axis perpendicular to the lanes L1 and L2. This allows the movement of the target vehicle 3603 to be ignored. Furthermore, based on the calculated Z1 and Z2, the processor may determine the lane position of the target vehicle 3603 by estimation based on comparison with stored map data (e.g., determining which lane trajectory best matches the observed movement characteristics of the target vehicle).

[0388] In one embodiment, the processor may determine scale change information for the identified object. The scale change information may include size change information of the identified object in the image. For example, in image 3510, the processor may determine whether the size of the target vehicle 3503 (or an identifiable portion or part of the target vehicle) in the image is larger at t2 than at t1. The scale change information may further include position change information of the identified object in the image. For example, in image 3510, the processor may detect a right-to-left movement of the target vehicle 2503 in the image from time t1 to t2. The size of the object in the image may be expressed in pixels. In one embodiment, the time interval may be determined based on the timestamp of the image. In one embodiment, the scale change information includes configuration information regarding the lane configuration of the road. Based on the image analysis, the processor may determine the lane configuration of the road. The configuration may include lane characteristics (e.g., straight lane, roundabout, two-meter wide lane, right turn ahead, etc.).

[0389] In one embodiment, as described above, the processor may determine a desired navigation action based on the determined lane location of the identified object. For example, if the target vehicle 3503 is determined to be located in lane L2 of FIG. 35A, the processor may have the host vehicle 3501 turn left and safely enter L1. If the target vehicle 3503 is determined to be located in lane L1, the processor may have the host vehicle 3501 slow down and wait to turn left. In another example, if the target vehicle 3603 is located in lane L1 of FIG. 36A, the processor may slow down the host vehicle 3601 to avoid colliding with the target vehicle 3603. Further, as described above, the processor may determine a navigation action based on the determined lane location of the target vehicle and the RSS safe distance.

[0390] 37 is a flowchart of navigating a host vehicle consistent with disclosed embodiments. In step 3701, a processor may receive at least one image from an image capture device that represents the host vehicle's environment. The image may be raw or processed data sent from image capture devices 122, 124, and / or 126 over a network or communication path. The data may include data described in some image format.

[0391] In step 3703, the processor may analyze at least one of the plurality of images to identify a first object in the host vehicle's environment. A second object in the vehicle's environment at least partially obscures the first object and the road on which the first object is located. As described above, the images 3410, 3510, 3610 may depict the host vehicle's environment. As described above, the processor may analyze the images and identify objects in the images using image analysis techniques including, for example, object recognition, image segmentation, feature extraction, optical character recognition (OCR), object-based image analysis, shape region techniques, edge detection techniques, pixel-based detection, and the like. For example, based on the analysis, the processor may identify the first target vehicle 3503 as obscured by an occlusion 3505 image 3510.

[0392] In stage 3705, the processor may determine scale change information for the first object based on at least two of the multiple images. For example, the processor may compare images 3510, which include images of the target vehicle 3503 at both t1 and t2, and determine a size change of the target vehicle 3503 in the images.

[0393] In stage 3707, based on the determined scale change information for the first object, the processor may determine a lane position of the first object relative to the lanes of the road in which the first object is located. As described above, based on Z1 and Z2, the processor may determine a lane position of the target vehicle.

[0394] In step 3709, the processor may determine a navigation action for the host vehicle based on the determined lane location of the first object. As described above, for example, if the target vehicle 3503 is determined to be located in lane L2 of FIG. 35A, the processor may have the host vehicle 3501 turn left and safely enter L1. If the target vehicle 3503 is determined to be located in lane L1, the processor may have the host vehicle 3501 slow down and wait until it makes a left turn.

[0395] Determining road position of target vehicle based on tracking trajectory

[0396] As mentioned above, the target vehicle may be partially obscured in the acquired image. In such a case, a comparison with stored sparse map information may be used to determine the distance to the detected target vehicle. Alternatively or in addition, as mentioned above, the movement characteristics of the detected target vehicle (observed by image analysis) may be compared to the sparse map information to estimate the lane in which the target vehicle is traveling, the expected direction of travel of the target vehicle, etc.

[0397] As discussed above, in one embodiment, a processor for image processing may receive one or more captured images showing the surrounding environment of the host vehicle. In one embodiment, as discussed above, the processor may perform image analysis on the set of images to identify objects in the set of images. The processor may identify objects in the images, landmarks associated with a road segment (e.g., road signs). Objects may be identified by any of the techniques disclosed above, such as object recognition, image segmentation, feature extraction, optical character recognition (OCR), object-based image analysis, shape region techniques, edge detection techniques, pixel-based detection, etc.

[0398] In one embodiment, based on the analysis, the processor may identify a first object (e.g., a target vehicle) in the environment. The first object and the road on which the first object is located are partially obscured by a second object (e.g., an obstruction, a road sign, a roundabout, etc.). FIG. 38A illustrates a position of the host vehicle 3801 relative to the objects on the road segment. The processor of the host vehicle 3801 may detect the target vehicle 3803 and the roundabout 3805 by analysis of one or more captured images. Based on the determined position relative to the host vehicle, the processor associated with the host vehicle may receive map information associated with the host vehicle's environment, as described above. For example, a sparse map associated with the road segment on which the host vehicle 3801 is traveling may be provided to the host vehicle 3801.

[0399] FIG. 38A shows the positions of the target vehicle 3803 and the host vehicle 3801 relative to the roundabout 3805 at times t1, t2, and t3. From the positions of the captured images of the target vehicle 3803 and / or based on other movement characteristics associated with the target vehicle (e.g., object zoom between captured images, etc.), the processor may determine a trajectory for the target vehicle 3803 (e.g., the tracking trajectory traveled by the target vehicle from time t1 to time t3). The target vehicle 3803 entering the roundabout may turn right. The initial turning angle may be approximately 90 degrees to the right (relative to the original driving direction at times t1 and t2). Furthermore, as the target vehicle travels around the roundabout, it continues to turn left until it exits the roundabout. FIG. 38B shows an exemplary composite image representing two different images received by the processor of the host vehicle 3801 from the image capture device at time t2 and later at time t3. The images are combined to show the progress of a target vehicle 3803 from time t2 to time t3. The target vehicle 3803 is partially obscured by an obstruction 3805.

[0400] As described above, based on the images captured between t1 and r3, the processor may track changes in the size (or width (w)) of the target vehicle 3803 in the images. The processor may also track the driving direction of the target vehicle. From this information, a driving path may be determined for the target vehicle, even if it is partially invisible. By comparing the determined driving path with the lane trajectories stored in the sparse map, it may be determined which of the stored lane trajectories match the driving path of the target vehicle determined from the image analysis. By identifying the driving lane in this way, the host vehicle navigation processor may be able to determine the expected driving path of the target vehicle at a future time and determine a navigation operation for the host vehicle with respect to the determined driving lane for the detected target vehicle.

[0401] FIG. 38C is a diagram illustrating the relationship between the position (x) and width (w) of the target vehicle 3803 in the image. As shown, an inflection point may occur where the target vehicle 3803 enters the roundabout. Based on the inflection point, the processor may select the image captured at the time the inflection point occurred. Based on the image analysis described above, the processor may determine the distance Z from the host vehicle 3801 to the target vehicle 3808. Based on the determined distance Z and the image width (w), the processor may calculate the actual vehicle width W using the formula described above. Once both the width (w) and the actual width W in the image are determined, the processor may calculate the distance Z from the host vehicle 3801 to the target vehicle 3803 at any point where the image width (w) was determined in the image analysis. The above method for determining the distance from the host vehicle to the target vehicle may be applied to any target vehicle trajectory where an inflection point occurs in the diagram illustrating the relationship between image width (w) and image position (x).

[0402] FIG. 39A illustrates the location of the host vehicle 3901 relative to the target vehicle 3903, the roundabout 3905, and the obstruction 3907 in one example. FIG. 39B illustrates one image received by the processor of the host vehicle 3901 from the image capture device. In one embodiment, the processor may determine the lane location of the target vehicle 3903, i.e., whether the target vehicle 3903 is in the inside lane (T1), the outside lane (T2), etc. Based on the stored sparse map information, the processor may generate a tangent line from the host vehicle's current location to the known center location of the lane divider between lanes T1 and T2, as shown in FIG. 39A. Using this tangent line to analyze the captured image shown in FIG. 39B, the processor may determine the lane location of the target vehicle 3903. For example, if the target vehicle 3903 is to the left of the tangent line in the image, the processor may determine that the target vehicle 3903 is in the outside lane (T2). If the target vehicle 3903 is to the right of the tangent in the image, the processor may determine that the target vehicle 3903 is in the inside lane (T1). The above-described method for determining the lane position of a target vehicle may be applied to any multi-lane curve or roundabout.

[0403] FIG. 40A illustrates another example where a host vehicle 4001 approaching a target vehicle 4003 is partially obscured by an obscurant 4007. FIG. 40B illustrates an example image received by a processor from an image capture device associated with the host vehicle. Consistent with disclosed embodiments, the processor may receive an image 4010 captured by an image capture device of the host vehicle 4001. As shown in image 4010, the bottom of the target vehicle 4003 is obscured by an obscurant 4007. Based on an analysis of the captured image, the processor may determine that the target vehicle 4003 is located along a line V1 relative to the host vehicle, even though the exact location along the line V1 is unknown. To determine the actual location of the target vehicle 4003, the processor may assume a distance (e.g., Z1 or Z2) from the host vehicle 4001 to the target vehicle 4003. The processor may monitor the observed movement characteristics of the target vehicle 4003 between two or more captured images as described above, and determine an observed trajectory of the target vehicle for each hypothetical distance (e.g., Z1 or Z2), each of which may be associated with a different observed trajectory of the target vehicle. The processor may compare the observed trajectory for the target vehicle to stored map information indicating the available lanes and associated trajectories on the other side of the occlusion 4007. From this comparison, the processor may determine which of the hypothetical trajectories is most likely (e.g., which best matches the actual lane and trajectory values ​​represented in the stored map). In some cases, the processor may rank each hypothetical trajectory according to a confidence (or other value) that the particular hypothetical trajectory for the target vehicle matches the actual trajectory of the target vehicle (e.g., which observed trajectory best matches an available or associated mapping trajectory).

[0404] In one example, as shown in FIG. 40A, when the actual position of the target vehicle is T1, the path Z1 to Z1' of the target vehicle is parallel to the lane L1. In other words, if the vehicle 4003 is assumed to be at a distance Z1 from the host vehicle, and the host vehicle observes the movement characteristics of the vehicle 4003 between two or more captured images, the processor of the host vehicle may determine that the image representation of the target vehicle has changed in accordance with the target vehicle moving along the path L1 represented in the stored map. On the other hand, if the processor assumes that the target vehicle is a distance Z2 away from the host vehicle (e.g., the target vehicle position 4005), the observed changes in the image representation of the target vehicle will result in a trajectory that is different from path L1 or path L2. For example, the observed trajectory based on the Z2 starting distance may extend from Z2 to Z2'. This path will not be parallel to either path L1 or L2. As a result, the host vehicle's processor may determine that the target vehicle is not at distance Z2 because the observed trajectory based on the distance Z2 assumption does not match any of the valid trajectories stored in the map. However, because the observed trajectory associated with distance Z1 matches a valid trajectory stored in the map, the processor may determine that the target vehicle is at distance Z1 from the host vehicle and travels along path L1.

[0405] Based on this analysis, path L1 may be considered as the most likely candidate for the actual trajectory of the partially invisible vehicle 4003. The map data may also include stored "likely path" information accumulated from crowdsourcing for the road segment or similar road segments. In this case, the vehicle may be in the process of lane change maneuver if the initial trajectory determination is inaccurate and the correct path is from Z2 to Z2'. At some point, the vehicle will be on L1, and then by repeating the above process, it is determined that the target vehicle is currently traveling along path L1. This may represent a comprehensive solution to the above situation. For example, if the target vehicle in FIG. 38A is tracked and various distances are assumed, only one of the assumptions will follow the map data exactly. Machine learning methods may be used to estimate the likelihood of a particular path. Referring again to FIG. 40A, the RSS framework shows that the ego-vehicle is safe for any position of the target vehicle along V1. However, the CRSS framework (eg, the buffer distance is greater than the minimum safe distance to ensure that no collision occurs for which the host vehicle is responsible) can assume the most likely location.

[0406] Generally, the processor may monitor observed movement characteristics of the target vehicle 4003 between two or more captured images as described above and determine one or more estimated trajectories of the target vehicle. By comparing the observed target trajectory to stored map information indicating available lanes on the other side of the obstruction 4007 and their associated trajectories, the processor may determine which available lanes the target vehicle is traversing. For example, the processor may determine that the observed movement (e.g., zooming, etc.) of the target vehicle 4003 is consistent with trajectory L1 but not with trajectory L2.

[0407] As described above, the processor may determine the distance from the host vehicle 4001 to the target vehicle 4003 from the following formula:

number

[0408] wher...

Claims

1. 1. A system for navigating a host vehicle, the system comprising: at least one processing device having circuitry and memory; The memory, when executed by the circuit, causes the at least one processing device to: receiving at least one image captured by an image capture device, the image being indicative of an environment of the host vehicle; analyzing the at least one image to identify objects within the environment of the host vehicle; determining a position of the host vehicle based on a predicted position of the host vehicle along a predetermined cubic spline representing a target trajectory of the host vehicle along a road segment, the predicted position of the host vehicle along the predetermined cubic spline being based on an observed position of at least one recognized landmark; receiving map information associated with the determined location of the host vehicle, the map information including lane width information associated with roads in the environment of the host vehicle; determining a distance from the host vehicle to the object based at least on the lane width information; determining a navigation operation for the host vehicle based on the determined distance; have the command to system.

2. The system of claim 1 , wherein the lane width information comprises a lane width profile along the length of the road.

3. The system of claim 1 , wherein the lane width information includes a lane width change signature.

4. The system of claim 1 , wherein the lane width information includes a distance relative to a reference point of the road.

5. The system of claim 1 , wherein the determination of the distance from the host vehicle to the object is further based on an analysis of the at least one image.

6. The system of claim 1 , wherein the determination of the distance from the host vehicle to the object is further based on the position of the host vehicle.

7. The system of claim 1 , wherein the determination of the location of the host vehicle is based on an output of at least one sensor of the host vehicle.

8. The system of claim 7 , wherein the at least one sensor includes a GPS device, a speed sensor, or an accelerometer.

9. The system of claim 1 , wherein the determination of the distance from the host vehicle to the object is further based on an output of at least one sensor of the host vehicle.

10. The system of claim 9 , wherein the at least one sensor includes a GPS device, a speed sensor, or an accelerometer.

11. The system of claim 1 , wherein the navigation action includes causing at least one adjustment of a navigation actuator of the host vehicle to be performed.

12. The system of claim 11 , wherein the navigation actuator comprises at least one of a steering mechanism, a brake, and an accelerator of the host vehicle.

13. The system of claim 1 , wherein the object comprises a target vehicle.

14. The system of claim 1 , wherein the observed location of the at least one recognized landmark is determined based on an analysis of the at least one image.

15. 2. The system of claim 1, wherein the predicted position of the host vehicle along the predetermined cubic spline is determined by localizing the host vehicle relative to the target trajectory based on a stored position of the at least one recognized landmark relative to the target trajectory.

16. 1. A method of navigating a host vehicle, comprising: receiving at least one image captured by an image capture device, the image being indicative of an environment of the host vehicle; analyzing the at least one image to identify objects within the environment of the host vehicle; determining a position of the host vehicle based on a predicted position of the host vehicle along a predetermined cubic spline representing a target trajectory of the host vehicle along a road segment, the predicted position of the host vehicle along the predetermined cubic spline being based on an observed position of at least one recognized landmark; receiving map information associated with the determined location of the host vehicle, the map information including lane width information associated with roads in the environment of the host vehicle; determining a distance from the host vehicle to the object based at least on the lane width information; determining a navigation operation for the host vehicle based on the determined distance; Equipped with method.

17. The method of claim 16 , wherein the lane width information comprises a lane width profile along the length of the road.

18. The method of claim 16 , wherein the lane width information includes a lane width change signature.

19. The method of claim 16 , wherein the lane width information includes a distance relative to a reference point of the road.

20. The method of claim 16 , wherein determining the distance from the host vehicle to the object is further based on an analysis of the at least one image.

21. The method of claim 16 , wherein determining the distance from the host vehicle to the object is further based on the position of the host vehicle.

22. The method of claim 16 , wherein the observed location of the at least one recognized landmark is determined based on an analysis of the at least one image.

23. 17. The method of claim 16, wherein the predicted position of the host vehicle along the predetermined cubic spline is determined by localizing the host vehicle relative to the target trajectory based on a stored position of the at least one recognized landmark relative to the target trajectory.

24. 1. A program that causes at least one processor to execute a method for navigating a host vehicle, the method comprising: receiving at least one image captured by an image capture device, the image being indicative of an environment of the host vehicle; analyzing the at least one image to identify objects within the environment of the host vehicle; determining a position of the host vehicle based on a predicted position of the host vehicle along a predetermined cubic spline representing a target trajectory of the host vehicle along a road segment, the predicted position of the host vehicle along the predetermined cubic spline being based on an observed position of at least one recognized landmark; receiving map information associated with the determined location of the host vehicle, the map information including lane width information associated with roads in the environment of the host vehicle; determining a distance from the host vehicle to the object based at least on the lane width information; determining a navigation operation for the host vehicle based on the determined distance; Equipped with program.

Images