System and method for vehicle navigation

Abstract

This invention provides a system and method for autonomous vehicle navigation. [Solution] A navigation system for a host vehicle may include a processor programmed to identify at least one indicator of the host vehicle's ego-motion. The processor may also be programmed to receive from a LIDAR system a first point cloud containing a first representation of at least a portion of an object, and a second point cloud containing a second representation of at least a portion of an object. The processor may further be programmed to identify the velocity of an object based on at least one indicator of the host vehicle's ego-motion and based on a comparison between the first point cloud containing the first representation of at least a portion of an object and the second point cloud containing the second representation of at least a portion of an object.

Description

[Technical Field]

[0001] [Cross-reference of related applications] This application claims priority rights under U.S. Provisional Patent Application No. 62 / 957,000 filed on 3 January 2020 and U.S. Provisional Patent Application No. 63 / 082,619 filed on 24 September 2020. The aforementioned applications are incorporated herein by reference in their entirety.

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

[0003] As technology continues to advance, the goal of fully autonomous vehicles capable of navigating roadways is drawing closer. Autonomous vehicles may need to consider various factors, make appropriate decisions based on these factors, and reach their intended destination safely and accurately. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured by cameras), and may also use information obtained from other sources (e.g., GPS units, speed sensors, accelerometers, suspension sensors, etc.). At the same time, in order to navigate to their destination, autonomous vehicles may need to identify their position on a specific roadway (e.g., a specific lane on a multi-lane road), navigate alongside other vehicles, avoid obstacles and pedestrians, obey traffic signals and signs, and navigate from one road to another at appropriate intersections or interchanges. The use and interpretation of the vast amount of information that an autonomous vehicle collects as it travels to its destination presents many design challenges. The enormous amount of data that autonomous vehicles may need to analyze, access, and / or store (e.g., captured image data, map data, GPS data, sensor data, etc.) presents challenges that could actually limit, or even negatively impact, autonomous navigation. Furthermore, if autonomous vehicles navigate using conventional mapping technologies, the enormous amount of data required to store and update maps presents an extremely difficult challenge. [Overview of the project]

[0004] Embodiments not inconsistent with this disclosure provide systems and methods for autonomous vehicle navigation. The disclosed embodiments may use cameras to provide autonomous vehicle navigation functionality. For example, not inconsistent with the disclosed embodiments, the disclosed system may include one, two, or more cameras that monitor the vehicle environment. The disclosed system may provide navigation responses based, for example, on an analysis of images captured by one or more of these cameras.

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

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

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

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

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

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

[0011] In one embodiment, a navigation system for a host vehicle may include at least one processor programmed to receive at least one captured image from a camera in the host vehicle representing the environment of the host vehicle. The camera may be located at a first location relative to the host vehicle. The at least one processor may also be programmed to receive point cloud information from a LIDAR system in the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be located at a second location relative to the host vehicle, which may be different from the first location. The camera's field of view may at least partially overlap with the LIDAR system's field of view to provide a shared field of view area. The at least one processor may further be programmed to analyze at least one captured image and the received point cloud information to detect one or more objects in the shared field of view area. The detected one or more objects may be represented in only one of the at least one captured image or the received point cloud information. At least one processor may also be programmed to determine whether the difference in viewpoint between the first location of the camera and the second location of the LIDAR system takes into account one or more detected objects represented in only one of the at least one captured image or received point cloud information. If the difference in viewpoint does not take into account one or more detected objects represented in only one of the at least one captured image or received point cloud information, at least one processor may be programmed to perform at least one remedial action. If the difference in viewpoint does not take into account one or more detected objects represented in only one of the at least one captured image or received point cloud information, at least one processor may determine and perform at least one navigation action on the host vehicle based on one or more detected objects.

[0012] In one embodiment, a method for determining navigation behavior for a host vehicle may include receiving at least one captured image from a camera in the host vehicle that represents the environment of the host vehicle. The camera may be located at a first location relative to the host vehicle. The method may also include receiving point cloud information from a LIDAR system in the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be located at a second location relative to the host vehicle, which may be different from the first location. The camera's field of view may at least partially overlap with the LIDAR system's field of view to provide a shared field of view area. The method may further include analyzing at least one captured image and the received point cloud information to detect one or more objects in the shared field of view area. The detected one or more objects may be represented in only one of the at least one captured image or the received point cloud information. The method may also include determining whether the difference in viewpoint between the first location of the camera and the second location of the LIDAR system takes into account one or more detected objects that are represented in only one of the at least one captured image or the received point cloud information. The method may further include, if the difference in viewpoint does not take into account one or more detected objects represented in only one of the captured images or received point cloud information, then causing the host vehicle to perform at least one remediation operation. The method may also include, if the difference in viewpoint does not take into account one or more detected objects represented in only one of the captured images or received point cloud information, then determining at least one navigation operation to be performed on the host vehicle based on one or more detected objects, and causing the host vehicle to perform at least one navigation operation.

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

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

[0015] Without being inconsistent with other disclosed embodiments, a non-temporary computer-readable storage medium may store program instructions, which may be executed by at least one processing device in any of the methods described herein.

[0016] The above summary and the following detailed explanation are illustrative and illustrative only, and do not limit the scope of the claims. [Brief explanation of the drawing]

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

[0018] [Figure 1] A schematic diagram of an exemplary system that does not conflict with the disclosed embodiments.

[0019] [Figure 2A] A schematic side view of an exemplary vehicle including a system that does not conflict with the disclosed embodiments.

[0020] [Figure 2B] A schematic top view of the vehicle and system shown in FIG. 2A that does not conflict with the disclosed embodiments.

[0021] [Figure 2C] A schematic top view of another embodiment of a vehicle including a system that does not conflict with the disclosed embodiments.

[0022] [Figure 2D] A schematic top view of yet another embodiment of a vehicle including a system that does not conflict with the disclosed embodiments.

[0023] [Figure 2E] A schematic top view of yet another embodiment of a vehicle including a system that does not conflict with the disclosed embodiments.

[0024] [Figure 2F] A schematic diagram of an exemplary vehicle control system that does not conflict with the disclosed embodiments.

[0025] [Figure 3A] A schematic view of the interior of a vehicle including a rearview mirror and user interface for a vehicle imaging system that does not conflict with the disclosed embodiments.

[0026] [Figure 3B]This figure shows an example of a camera mount configured to be positioned behind the rearview mirror and in contact with the vehicle's windshield, consistent with the embodiments disclosed.

[0027] [Figure 3C] This is a view of the camera mount shown in Figure 3B from a different angle, which is consistent with the disclosed embodiment.

[0028] [Figure 3D] This figure shows an example of a camera mount configured to be positioned behind the rearview mirror and in contact with the vehicle's windshield, consistent with the embodiments disclosed.

[0029] [Figure 4] This is an exemplary block diagram of memory configured to store instructions for performing one or more operations, consistent with the embodiments disclosed.

[0030] [Figure 5A] A flowchart shows an exemplary process for generating one or more navigation responses based on monocular image analysis, consistent with the embodiments disclosed.

[0031] [Figure 5B] This flowchart illustrates an exemplary process for detecting one or more vehicles and / or one or more pedestrians included in a set of images, consistent with the embodiments disclosed.

[0032] [Figure 5C] This flowchart illustrates an exemplary process for detecting road markings and / or lane geometric structure information contained in a set of images, consistent with the embodiments disclosed.

[0033] [Figure 5D]This flowchart shows an exemplary process for detecting a traffic light included in a set of images, consistent with the embodiments disclosed.

[0034] [Figure 5E] A flowchart illustrating an exemplary process for generating one or more navigation responses based on a vehicle path, consistent with the embodiments disclosed.

[0035] [Figure 5F] This flowchart shows an exemplary process for determining whether a preceding vehicle is changing lanes, which is consistent with the embodiments disclosed.

[0036] [Figure 6] This flowchart illustrates an exemplary process for generating one or more navigation responses based on stereo image analysis, consistent with the embodiments disclosed.

[0037] [Figure 7] This flowchart illustrates an exemplary process for generating one or more navigation responses based on the analysis of three sets of images, consistent with the embodiments disclosed.

[0038] [Figure 8] This figure shows a sparse map for providing autonomous vehicle navigation, consistent with the disclosed embodiments.

[0039] [Figure 9A] This figure shows a polynomial representation of a portion of a road segment, consistent with the disclosed embodiments.

[0040] [Figure 9B] This figure shows a curve in three-dimensional space representing the target trajectory of a vehicle for a specific road segment, included in a sparse map that is consistent with the disclosed embodiments.

[0041] [Figure 10] This figure shows exemplary landmarks that may be included in a sparse map that are consistent with the disclosed embodiments.

[0042] [Figure 11A] This figure shows a polynomial representation of the trajectory that is consistent with the disclosed embodiments.

[0043] [Figure 11B] This figure shows a target trajectory along a multi-lane road, consistent with the disclosed embodiments. [Figure 11C] This figure shows a target trajectory along a multi-lane road, consistent with the disclosed embodiments.

[0044] [Figure 11D] This figure shows an exemplary road signature profile that is consistent with the disclosed embodiments.

[0045] [Figure 12] This is a schematic diagram of a system that uses crowdsourced data received from multiple vehicles for autonomous vehicle navigation, consistent with the disclosed embodiments.

[0046] [Figure 13] This figure shows an exemplary road navigation model for an autonomous vehicle, represented by multiple three-dimensional splines, which is consistent with the disclosed embodiments.

[0047] [Figure 14] This figure shows the framework of a map generated by combining location information from multiple drives, which is consistent with the disclosed embodiments.

[0048] [Figure 15] This figure shows an example of a landmark, exemplary sign, and two drives aligned longitudinally, consistent with the disclosed embodiments.

[0049] [Figure 16] This figure shows an example of a landmark sign and multiple drives aligned longitudinally, consistent with the disclosed embodiments.

[0050] [Figure 17] This is a schematic diagram of a system for generating drive data using a camera, vehicle, and server, consistent with the embodiments disclosed.

[0051] [Figure 18] This is a schematic diagram of a system for crowdsourcing sparse maps, consistent with the disclosed embodiments.

[0052] [Figure 19] This flowchart illustrates an exemplary process for generating a sparse map for autonomous vehicle navigation along a road segment, consistent with the disclosed embodiments.

[0053] [Figure 20] This figure shows a block diagram of a server that is consistent with the disclosed embodiment.

[0054] [Figure 21] This figure shows a memory block diagram that is consistent with the disclosed embodiment.

[0055] [Figure 22] This figure shows a process for clustering vehicle trajectories associated with a vehicle, consistent with the disclosed embodiments.

[0056] [Figure 23] This figure shows a vehicle navigation system that can be used for automatic navigation, consistent with the disclosed embodiments.

[0057] [Figure 24A] This figure shows exemplary detectable lane markings, consistent with the disclosed embodiments. [Figure 24B] This figure shows exemplary detectable lane markings, consistent with the disclosed embodiments. [Figure 24C] This figure shows exemplary detectable lane markings, consistent with the disclosed embodiments. [Figure 24D] This figure shows exemplary detectable lane markings, consistent with the disclosed embodiments.

[0058] [Figure 24E] This figure shows an exemplary mapped lane marking, consistent with the disclosed embodiments.

[0059] [Figure 24F] This figure shows an exemplary anomaly related to lane marking detection, which is consistent with the embodiments disclosed.

[0060] [Figure 25A] This figure shows an exemplary image of the vehicle's surrounding environment for navigation based on mapped lane markings, consistent with the embodiments disclosed.

[0061] [Figure 25B] This figure shows a correction for vehicle lateral positioning based on mapped lane markings in a road navigation model, consistent with the embodiments disclosed.

[0062] [Figure 25C] This provides a conceptual representation of a localization method for locating a host vehicle along a target trajectory using mapped features contained in a sparse map. [Figure 25D] This provides a conceptual representation of a localization method for locating a host vehicle along a target trajectory using mapped features contained in a sparse map.

[0063] [Figure 26A]This flowchart shows an exemplary process for mapping lane markings for use in autonomous vehicle navigation, consistent with the embodiments disclosed.

[0064] [Figure 26B] This flowchart illustrates an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings, consistent with the embodiments disclosed.

[0065] [Figure 27] An exemplary system for determining the velocity of an object is shown, consistent with the embodiments disclosed.

[0066] [Figure 28] An exemplary server consistent with the disclosed embodiments is shown.

[0067] [Figure 29] An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0068] [Figure 30A] The following shows exemplary objects in the field of view related to a navigation system that are consistent with the disclosed embodiments.

[0069] [Figure 30B] The following shows exemplary objects in the field of view related to a navigation system that are consistent with the disclosed embodiments.

[0070] [Figure 31] This flowchart shows an exemplary process for determining the velocity of an object that is consistent with the disclosed embodiments.

[0071] [Figure 32] An exemplary system for determining navigation behavior for a host vehicle that is consistent with the disclosed embodiments is shown.

[0072] [Figure 33] An exemplary server consistent with the disclosed embodiments is shown.

[0073] [Figure 34] An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0074] [Figure 35A] An exemplary road segment consistent with the disclosed embodiments is shown.

[0075] [Figure 35B] An exemplary sparse map relating to an exemplary road segment, consistent with the disclosed embodiments, is shown.

[0076] [Figure 35C] An exemplary road segment consistent with the disclosed embodiments is shown.

[0077] [Figure 36] A flowchart illustrating exemplary processes for determining navigation behavior for a host vehicle that is consistent with the disclosed embodiments.

[0078] [Figure 37] An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0079] [Figure 38] This flowchart shows exemplary processes for identifying navigation behavior for a host vehicle that is consistent with the disclosed embodiments.

[0080] [Figure 39A] Exemplary point cloud information and images that are consistent with the disclosed embodiments are shown. [Figure 39B] Exemplary point cloud information and images that are consistent with the disclosed embodiments are shown.

[0081] [Figure 40]An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0082] [Figure 41] This flowchart shows exemplary processes for identifying navigation behavior for a host vehicle that is consistent with the disclosed embodiments.

[0083] [Figure 42] The host vehicle in an exemplary environment consistent with the disclosed embodiments is shown.

[0084] [Figure 43] An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0085] [Figure 44] An exemplary vehicle, consistent with the disclosed embodiments, is shown.

[0086] [Figure 45] This flowchart shows exemplary processes for identifying navigation behavior for a host vehicle that is consistent with the disclosed embodiments. [Modes for carrying out the invention]

[0087] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numerals are used in the drawings and the following description to refer to the same or similar parts. While several exemplary embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, components shown in the drawings may be replaced, added, and modified, and the exemplary methods described herein may be modified by replacing, rearranging, deleting, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to the embodiments and examples disclosed. Instead, the appropriate scope is determined by the accompanying claims.

[0088] [Overview of Self-Driving Vehicles]

[0089] As used throughout this disclosure, the term “autonomous vehicle” means a vehicle capable of performing at least one navigation change without requiring driver input. “Navigation change” means a change in one or more of the vehicle’s steering, braking, or acceleration. To be autonomous, a vehicle does not have to be fully autonomous (e.g., fully operational without driver intervention or driver input). Rather, an autonomous vehicle may also be capable of operating under driver control for a certain period and without driver control for other periods. An autonomous vehicle may also be capable of controlling only certain aspects of vehicle navigation, such as steering (e.g., to maintain the vehicle’s path between lane markings), while leaving other aspects (e.g., braking) to the driver. In some cases, an autonomous vehicle may be capable of some or all aspects of the vehicle’s braking, speed control, and / or steering.

[0090] Human drivers typically control their vehicles using visual cues and observations, and traffic infrastructure is built upon this, so lane markings, traffic signs, and traffic lights are all designed to provide visual information to drivers. Taking these design features of traffic infrastructure into consideration, autonomous vehicles may include cameras and processing units that analyze visual information captured from the vehicle's environment. This visual information may include, for example, components of the traffic infrastructure observable by the driver (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, litter, etc.). Furthermore, autonomous vehicles may also use stored information, such as information that provides a model of the vehicle's environment, when navigating. For example, a vehicle may use GPS data, sensor data (e.g., accelerometer, speed sensor, suspension sensor, etc.), and / or other map data to provide information relevant to its environment while the vehicle is in motion, and the vehicle (and other vehicles) may use that information to determine its position on the model.

[0091] In some embodiments of this disclosure, an autonomous vehicle may use information acquired during navigation (e.g., from cameras, GPS devices, accelerometers, speed sensors, suspension sensors, etc.). In other embodiments, an autonomous vehicle may use information acquired from past navigation by the vehicle (or other vehicles) during navigation. In yet another embodiment, an autonomous vehicle may use a combination of information acquired during navigation and information acquired from past navigation. The following sections provide an overview of a system consistent with the embodiments disclosed, followed by an overview of a front imaging system and method consistent with the system. The following sections disclose a system and method for constructing, using, and updating sparse maps for autonomous vehicle navigation.

[0092] [System Overview]

[0093] Figure 1 is a block diagram of system 100 that is consistent with the exemplary embodiments disclosed. System 100 may include various components depending on the requirements of a specific implementation example. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. 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 for a particular application. In some embodiments, image acquisition unit 120 may include one or more image acquisition devices (e.g., cameras), such as image acquisition device 122, image acquisition device 124, and image acquisition device 126. System 100 may also include a data interface 128 that enables communication between the processing device 110 and the image acquisition device 120. For example, the data interface 128 may include one or more optional wired and / or wireless links for transmitting image data acquired by the image acquisition device 120 to the processing unit 110.

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

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

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

[0097] Any of the processing devices disclosed herein may be configured to perform a specific function. Configuring a processing device, such as one of the EyeQ processors or other controllers or microprocessors described herein, to perform a specific function may include programming computer executable instructions and making these instructions available for execution by the processing device when it is operating. 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, for example, using one or more hardware description languages ​​(HDLs).

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

[0099] Figure 1 shows two separate processing devices included in processing unit 110, but more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to accomplish the tasks of the application processor 180 and the image processor 190. In other embodiments, these tasks may be performed by two or more processing devices. Furthermore, in some embodiments, system 100 may include one or more of the processing units 110 without including other components such as the image acquisition unit 120.

[0100] The processing unit 110 may include various types of devices. For example, the processing unit 110 may include various devices such as a controller, an image preprocessor, a central processing unit (CPU), a graphics processing unit (GPU), support circuits, a digital signal processor, an integrated circuit, memory, or any other type of device for image processing and analysis. The image preprocessor may include a video processor for acquiring, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuits may be any number of circuits commonly known in the art, such as cache circuits, power supply circuits, clock circuits, 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 database and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage, tape storage, removable storage, and other types of storage. In one example, the memory may be separated from the processing unit 110. In another example, the memory may be integrated into the processing unit 110.

[0101] Each memory 140, 150 may contain software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), can control various aspects of the operation of system 100. For example, these memory units may contain various database and image processing software, as well as trained systems such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage, tape storage, removable storage, and / or any other type of storage. In some embodiments, the memory units 140, 150 may be separate from the application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into the application processor 180 and / or image processor 190.

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

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

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

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

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

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

[0108] System 100 or its various components may be incorporated into various other platforms. In some embodiments, System 100 may be included in a vehicle 200, as shown in Figure 2A. For example, the vehicle 200 may include a processing unit 110 and any of the other components of System 100, as described above in relation to Figure 1. In some embodiments, the vehicle 200 may have only one image acquisition device (e.g., a camera), but in other embodiments, such as those discussed in relation to Figures 2B to 2E, multiple image acquisition devices may be used. For example, as shown in Figure 2A, either of the image acquisition devices 122 and 124 of the vehicle 200 may be part of an ADAS (Advanced Driver-Assistance System) imaging device.

[0109] The image acquisition device included in the vehicle 200 as part of the image acquisition unit 120 may be placed in any suitable location. In some embodiments, the image acquisition device 122 may be placed near the rearview mirror, as shown in Figures 2A-2E and 3A-3C. This position can provide a line of sight similar to that of the driver of the vehicle 200, and thus can help determine what the driver can and cannot see. The image acquisition device 122 may be placed in any location close to the rearview mirror, but placing the image acquisition device 122 on the driver's side of the mirror may be even more helpful in acquiring images that represent the driver's field of view and / or line of sight.

[0110] Other locations may be used for the image acquisition device of the image acquisition unit 120. For example, the image acquisition device 124 may be placed on or inside the bumper of the vehicle 200. Such locations may be particularly suitable for image acquisition devices with a wide field of view. The line of sight of an image acquisition device placed on the bumper may differ from the line of sight of the driver, and therefore, the image acquisition device on the bumper and the driver may not always be looking at the same object. The image acquisition devices (e.g., image acquisition devices 122, 124, and 126) may also be placed in other locations. For example, the image acquisition devices may be located on or inside one or both 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 on one of the windows of the vehicle 200, positioned behind or in front of them, mounted inside or near lighting devices at the front and / or rear of the vehicle 200, etc.

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

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

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

[0114] In some embodiments, system 100 may upload data according to a "high" privacy level, and while the setting is being configured, system 100 may transmit data (e.g., location information related to the route, captured images, etc.) without using any details about a specific vehicle and / or driver / owner. For example, when uploading data according to a "high" privacy setting, system 100 may not include the vehicle registration number (VIN) or the name of the vehicle's driver or owner, and instead may transmit data such as captured images and / or limited location information related to the route.

[0115] Other privacy levels are also possible. For example, system 100 may send data to the server according to privacy level "medium" and include additional information not included in privacy level "high," such as the vehicle's manufacturer and / or model, and / or vehicle type (e.g., passenger car, sports utility vehicle, truck, etc.). In some embodiments, system 100 may upload data according to privacy level "low." With privacy level set to "low," system 100 may upload data that includes enough information to uniquely identify a particular vehicle, its owner / driver, and / or part or all of the route the vehicle is traveling. Such low-privacy-level data may include, for example, one or more of the following: VIN, driver / owner's name, vehicle's starting point before departure, vehicle's intended destination, vehicle's manufacturer and / or model, vehicle type, etc.

[0116] Figure 2A is a schematic side view of an exemplary vehicle imaging system consistent with the disclosed embodiment. Figure 2B is a schematic top view of the embodiment shown in Figure 2A. As shown in Figure 2B, the disclosed embodiment may include a vehicle 200, the vehicle body of which includes a system 100 having a first image acquisition device 122 located near the rearview mirror and / or near the driver of the vehicle 200, a second image acquisition device 124 located in or within the bumper area of ​​the vehicle 200 (e.g., one of the bumper areas 210), and a processing unit 110.

[0117] As shown in Figure 2C, both image acquisition devices 122 and 124 may be positioned near the rearview mirror and / or near the driver of the vehicle 200. Furthermore, although two image acquisition devices 122 and 124 are shown in Figures 2B and 2C, it should be understood that other embodiments may include more than two image acquisition devices. For example, in the embodiments shown in Figures 2D and 2E, a first image acquisition device 122, a second image acquisition device 124, and a third image acquisition device 126 are included in the system 100 of the vehicle 200.

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

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

[0120] The first image acquisition device 122 may include any preferred type of image acquisition device. The image acquisition device 122 may include an optical axis. In one example, the image acquisition device 122 may include an Aptina M9V024 WVGA sensor with a global shutter. In other embodiments, the image acquisition device 122 may provide a resolution of 1280 × 960 pixels and may also include a rolling shutter. The image acquisition device 122 may include various optical elements. In some embodiments, for example, one or more lenses may be included to provide the image acquisition device with a desired focal length and field of view. In some embodiments, the image acquisition device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, the image acquisition device 122 may be configured to acquire an image having a desired field of view (FOV) 202, as shown in Figure 2D. For example, the image acquisition device 122 may be configured to have a standard FOV, such as in the range of 40 to 56 degrees, including a 46-degree FOV, a 50-degree FOV, a 52-degree FOV, or a wider FOV. Alternatively, the image acquisition device 122 may be configured to have a narrow FOV in the range of 23 to 40 degrees, such as a 28-degree FOV or a 36-degree FOV. Furthermore, the image acquisition device 122 may be configured to have a wide FOV in the range of 100 to 180 degrees. In some embodiments, the image acquisition device 122 may include a wide-angle bumper camera, or one having an FOV of up to 180 degrees. In some embodiments, the image acquisition device 122 may be a 7.2M pixel image acquisition device having an aspect ratio of approximately 2:1 (e.g., H×V=3800×1900 pixels) and a horizontal FOV of approximately 100 degrees. Such an image acquisition device may be used instead of a three-image acquisition device configuration. The vertical field of view (FOV) of such image acquisition devices can be significantly less than 50 degrees in implementations where the image acquisition device uses a radially symmetric lens, due to significant lens distortion. For example, such a lens does not need to be radially symmetric, which would allow for a vertical FOV greater than 50 degrees with a horizontal FOV of 100 degrees.

[0121] The first image acquisition device 122 may acquire multiple first images for a scene related to the vehicle 200. Each of the multiple first images may be acquired as a series of image scan lines, and these images may be captured using a rolling shutter. Each scan line may contain multiple pixels.

[0122] The first image acquisition device 122 may have a scanning speed associated with acquiring each of the first series of image scan lines. The scanning speed may refer to the speed at which the image sensor can acquire image data associated with each pixel contained in a particular scan line.

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

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

[0125] Using a rolling shutter can result in pixels in different rows being exposed and captured at different times, potentially leading to skew and other image artifacts in the captured image frame. On the other hand, if the image acquisition device 122 is configured to operate with a global or synchronous shutter, all pixels can be exposed for the same period of time during a common exposure period. As a result, image data from a frame acquired by a system using a global shutter represents a snapshot of the entire FOV (FOV 202, etc.) at a specific time. In contrast, when a rolling shutter is applied, each row within the frame is exposed and data is captured at different times. Therefore, moving objects may appear distorted in image acquisition devices with a rolling shutter. This phenomenon will be explained in more detail below.

[0126] The second image acquisition device 124 and the third image acquisition device 126 may be any type of image acquisition device. Like the first image acquisition device 122, each of the image acquisition devices 124 and 126 may include an optical axis. In one embodiment, each of the image acquisition devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image acquisition devices 124 and 126 may include a rolling shutter. Like the image acquisition device 122, the image acquisition devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image acquisition devices 124 and 126 may provide the same or narrower FOV (e.g., FOV 204 and 206) as associated with the image acquisition device 122 (e.g., FOV 202). For example, the image acquisition devices 124 and 126 may have a field of view (FOV) of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or narrower.

[0127] Image acquisition devices 124 and 126 may acquire a plurality of second and third images for a scene related to 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, and these images may be acquired using a rolling shutter. Each scan line or line may contain a plurality of pixels. Image acquisition devices 124 and 126 may have second and third scanning speeds associated with acquiring each of the plurality of image scan lines included in the second and third series of image scan lines.

[0128] The image acquisition devices 122, 124, and 126 may each be positioned at any preferred position and orientation relative to the vehicle 200. The relative positions of the image acquisition devices 122, 124, and 126 may be selected to help in merging the information acquired from the image acquisition devices. For example, in some embodiments, the FOV associated with image acquisition device 124 (e.g., FOV 204) may partially or completely overlap with the FOV associated with image acquisition device 122 (e.g., FOV 202) and the FOV associated with image acquisition device 126 (e.g., FOV 206).

[0129] The image acquisition devices 122, 124, and 126 may be positioned in the vehicle 200 at any preferred relative height. In one example, there may be height differences between the image acquisition devices 122, 124, and 126, which may provide sufficient parallax information to enable stereo analysis. For example, as shown in Figure 2A, the heights of the two image acquisition devices 122 and 124 are different. For example, there may also be lateral displacement differences between the image acquisition devices 122, 124, and 126, which provide additional parallax information for stereo analysis by the processing unit 110. The difference in lateral displacement is as shown in Figures 2C and 2D, d xThis may be represented as follows. In some embodiments, a forward or backward displacement (e.g., range displacement) may exist between the image acquisition devices 122, 124, and 126. For example, image acquisition device 122 may be located 0.5 to 2 meters behind image acquisition devices 124 and / or image acquisition device 126, or even further back. This type of displacement may allow one of these image acquisition devices to compensate for a potential blind spot of one or more other image acquisition devices.

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

[0131] The frame rate (for example, the rate at which an image acquisition device acquires a set of pixel data for one image frame before moving on to acquiring pixel data related to the next image frame) may be controllable. The frame rate associated with image acquisition device 122 may be higher, lower, or the same as the frame rates associated with image acquisition devices 124 and 126. The frame rates associated with image acquisition 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 the image acquisition devices 122, 124, and 126 may include an optional pixel delay period that is imposed before or after acquiring image data related to one or more pixels of the image sensor included in image acquisition devices 122, 124, and / or 126. Generally, the image data corresponding to each pixel may be acquired according to the device's clock rate (for example, one pixel may be acquired per clock cycle). Furthermore, in embodiments including a rolling shutter, one or more of the image acquisition devices 122, 124, and 126 may include a selectable horizontal retrace period that is imposed before or after acquiring image data related to pixels in a certain row of image sensors included in the image acquisition devices 122, 124, and / or 126. Furthermore, one or more of the image acquisition devices 122, 124, and / or 126 may include a selectable vertical retrace period that is imposed before or after acquiring image data related to image frames of the image acquisition devices 122, 124, and 126.

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

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

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

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

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

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

[0138] According to some embodiments, the field of view (FOV) of one or more image acquisition devices 122, 124, and 126 may be wide-angle. For example, having a 140-degree FOV may be particularly advantageous for image acquisition devices 122, 124, and 126 that can be used to acquire images of areas close to the vehicle 200. For example, image acquisition device 122 may be used to acquire images of the right or left side of the vehicle 200, and in such embodiments, it may be desirable for image acquisition device 122 to have a wide FOV (e.g., at least 140 degrees).

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

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

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

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

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

[0144] Figures 3B to 3D illustrate an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and in contact with the windshield of a vehicle, consistent with the embodiments disclosed. As shown in Figure 3B, the camera mount 370 may include image acquisition devices 122, 124, and 126. The image acquisition devices 124 and 126 may be positioned behind a glare shield 380, which adheres directly to the windshield of a vehicle and may include components of a film material and / or anti-reflective material. For example, the glare shield 380 may be positioned so that it is in contact with and aligned with the windshield of a vehicle having the same inclination. In some embodiments, each of the image acquisition devices 122, 124, and 126 may be positioned behind the glare shield 380, as shown, for example, in Figure 3D. The embodiments disclosed are not limited to any particular configuration of the image acquisition devices 122, 124, and 126, the camera mount 370, and the glare shield 380. Figure 3C is a front view of the camera mount 370 shown in Figure 3B.

[0145] As those skilled in the art who benefit from this disclosure will understand, numerous modifications and / or changes can be made to the embodiments disclosed above. For example, not all components are essential for the operation of system 100. Furthermore, any component may be placed in any suitable part of system 100, and these components may be rearranged into various configurations, while still providing the functionality of the disclosed embodiments. Thus, the configurations described above are examples, and regardless of the configurations described above, system 100 can provide a wide range of functionality to analyze what is around vehicle 200 and navigate vehicle 200 in response to that analysis.

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

[0147] [Front multi-imaging system]

[0148] As described above, system 100 can provide a driver assistance function using a multi-camera system. The multi-camera system may use one or more cameras facing the forward direction of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side or rear of the vehicle. In one embodiment, for example, system 100 may use a two-camera imaging system in which a first camera and a second camera (e.g., image acquisition devices 122 and 124) may be positioned at the front and / or sides of the vehicle (e.g., vehicle 200). The first camera may have a field of view larger than that of the second camera, a field of view smaller than that of the second camera, or a field of view that partially overlaps with that of the second camera. 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 and perform stereo analysis. In another embodiment, system 100 may use a three-camera imaging system in which each of the multiple cameras has a different field of view. Thus, in such a system, decisions can be made based on information obtained from objects located at various distances to both the front and sides of the vehicle. A reference to monocular image analysis may mean performing image analysis based on an image acquired from a single viewpoint (e.g., from a single camera). Stereo image analysis may mean performing image analysis based on two or more images acquired with one or more changes in image acquisition parameters. For example, suitable acquired images for stereo image analysis may include images acquired from two or more different locations, images acquired from different fields of view, images acquired using different focal lengths, and images acquired with disparity information.

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

[0150] In another embodiment, as described above in relation to Figures 3B and 3C, the wide-field camera (e.g., image acquisition device 124 in the above example) may be mounted lower than the narrow-field camera and the main-field camera (e.g., image devices 122 and 126 in the above example). This configuration may provide a free line of sight from the wide-field camera. To reduce reflections, the camera may be mounted close to the windshield of the vehicle 200, and the camera may include a polarizer to attenuate reflected light.

[0151] A three-camera system can offer specific performance characteristics. For example, some embodiments may include a function to confirm object detection by one camera based on the detection results of another camera. In the three-camera configuration described above, the processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as described above), each processing device specializing in processing images captured by one or more of the image acquisition devices 122, 124, and 126.

[0152] In a three-camera system, a first processing device may receive images from both the main camera and the narrow-field-of-view camera, and perform vision processing using the narrow-field-of-view camera to detect, for example, other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. Furthermore, the first processing device may calculate the pixel parallax between the images from the main camera and the narrow-field-of-view camera to create a 3D reconstruction of the environment of the vehicle 200. The first processing device may then combine the 3D reconstruction with 3D information calculated based on 3D map data or information from another camera.

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

[0154] A third processing device may receive images from a wide-field-of-view camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. The third processing device may further execute additional processing commands and analyze the images to identify objects moving within the images, such as vehicles changing lanes or pedestrians.

[0155] In some embodiments, opportunities may be provided to introduce redundancy into the system by ensuring that streams of image-based information are captured and processed independently. Such redundancy may include, for example, using a first image capture device and the 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.

[0156] In some embodiments, the system 100 may use two image acquisition devices (e.g., image acquisition devices 122 and 124) when providing navigation assistance to the vehicle 200, and may also use a third image acquisition device (e.g., image acquisition device 126) to provide redundancy and verify the analysis of data received from the other two image acquisition devices. For example, in such a configuration, image acquisition devices 122 and 124 may provide images for stereo analysis by the system 100 to navigate the vehicle 200, while image acquisition device 126 may provide images for monocular analysis by the system 100 to provide redundancy and validity of the information obtained based on the images acquired from image acquisition devices 122 and / or image acquisition devices 124. That is, image acquisition device 126 (and the corresponding processing device) may be considered to provide a redundant subsystem to provide checks on the analysis obtained from image acquisition devices 122 and 124 (e.g., providing an automatic emergency braking (AEB) system). Furthermore, in some embodiments, the redundancy and validity 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 located outside the vehicle).

[0157] Those skilled in the art will recognize that the camera configuration, camera arrangement, number of cameras, camera positions, etc., described above are merely examples. These components, etc., described in relation to the overall system, may be organized 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 functions follow below.

[0158] Figure 4 is an exemplary functional block diagram of memories 140 and / or 150, which may store / program with instructions for performing one or more operations consistent with the disclosed embodiments. Hereafter, we will refer to memory 140, but those skilled in the art will recognize that instructions may be stored in memories 140 and / or 150.

[0159] As shown in Figure 4, the memory 140 may store a monocular image analysis module 402, a stereo image analysis module 404, a velocity acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of the memory 140. Furthermore, the application processor 180 and / or the image processor 190 may execute instructions stored in any of the modules 402, 404, 406, and 408 contained in the memory 140. Those skilled in the art will understand that references to the processing unit 110 in the following description may refer to the application processor 180 and the image processor 190 individually or collectively. Thus, each stage of any of the following processes may be performed by one or more processing devices.

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

[0161] In one embodiment, the stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by the processing unit 110, perform stereo image analysis of a first set and a second set of images acquired by a combination of image acquisition devices selected from among image acquisition devices 122, 124, and 126. In some embodiments, the processing unit 110 may perform stereo image analysis by combining information from the first and second sets of images with additional perceptual information (e.g., information from radar). For example, the stereo image analysis module 404 may include instructions for performing stereo image analysis based on a first set of images acquired by image acquisition device 124 and a second set of images acquired by image acquisition device 126. As described below in relation to Figure 6, the stereo image analysis module 404 may include instructions for detecting 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 hazardous objects. Based on the analysis, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as changes in turning, lane changes, and acceleration, as discussed below in relation to the navigation response module 408. Furthermore, in some embodiments, the stereo image analysis module 404 may implement techniques related to a trained system (such as a neural network or deep neural network) or an untrained system (such as a system that may be configured to detect and / or label objects in an environment where perceptual information has been taken in and processed using computer vision algorithms). In one embodiment, the stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

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

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

[0164] Furthermore, any of the modules disclosed herein (e.g., modules 402, 404, and 406) may perform techniques related to trained systems (such as neural networks or deep neural networks) or untrained systems.

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

[0166] In step 520, the processing unit 110 may also run the monocular image analysis module 402 to detect various road obstacles, such as parts of truck tires, fallen road signs, loose cargo, and small animals. Since road obstacles can vary in structure, shape, size, and color, detecting such hazards can be more difficult. In some embodiments, the processing unit 110 may run the monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road obstacles. For example, the processing unit 110 may estimate the camera movement between consecutive image frames and calculate the pixel parallax between frames to construct a 3D map of the road. The processing unit 110 may then use the 3D map to detect the road surface and any hazards present on the road surface.

[0167] In step 530, the processing unit 110 may execute the navigation response module 408 to generate one or more navigation responses in the vehicle 200 based on the analysis performed in step 520 and the method described above in relation to Figure 4. Navigation responses may include, for example, turns, lane changes, and changes in acceleration. In some embodiments, the processing unit 110 may generate one or more navigation responses using data obtained from the execution of the velocity acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 may, for example, sequentially transmit control signals to the steering device 240 and throttle device 220 of the vehicle 200 to move the vehicle 200 across one lane and then accelerate. Alternatively, the processing unit 110 may, for example, simultaneously transmit control signals to the brake device 230 and steering device 240 of the vehicle 200 to cause the vehicle 200 to brake while simultaneously changing lanes.

[0168] Figure 5B is a flowchart illustrating an exemplary process 500B for detecting one or more vehicles and / or one or more pedestrians in a set of images, consistent with the embodiments disclosed. Processing unit 110 may perform process 500B by running monocular image analysis module 402. 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 with one or more predetermined patterns to identify possible locations within each image that may contain an object of interest (e.g., a vehicle, a pedestrian, or part thereof). The predetermined patterns may be designed in such a way that they achieve a high probability of "false hits" and a low probability of "misses." For example, processing unit 110 may use a low threshold for similarity with the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. By doing so, it may be possible to reduce the probability that the processing unit 110 will miss (for example, fail to identify) a candidate object representing a vehicle or pedestrian.

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

[0170] In step 544, the processing unit 110 may analyze multiple frames of the image to determine whether any objects included in the set of candidate objects represent vehicles and / or pedestrians. For example, the processing unit 110 may track the detected candidate objects throughout a series of consecutive frames and accumulate frame-by-frame data related to the detected objects (e.g., size, position relative to vehicle 200, etc.). Furthermore, the processing unit 110 may estimate the parameters of the detected objects and compare the frame-by-frame position data of those objects with the predicted positions.

[0171] In step 546, the processing unit 110 may construct a set of measurements of the detected object. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to the vehicle 200) of the detected object. In some embodiments, the processing unit 110 may construct the measurements based on estimation methods that use a series of time-based observations, such as a Kalman filter or linear quadratic estimation (LQE), and / or based on modeling data available for various object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter may be based on a measurement of the object's scale, the scale measurement being proportional to the time to collision (e.g., the time it takes for the vehicle 200 to reach the object). Thus, by performing steps 540-546, the processing unit 110 can identify vehicles and pedestrians appearing in the set of captured images and obtain information (e.g., position, velocity, size) related to those vehicles and pedestrians. Based on this identification and the obtained information, the processing unit 110 can generate one or more navigation responses in the vehicle 200, as described above in relation to Figure 5A.

[0172] In step 548, the processing unit 110 may perform optical flow analysis on one or more images to reduce the probability of detecting a "false detection" and the probability of missing a candidate object representing a vehicle or pedestrian. Optical flow analysis may refer to, for example, the analysis of motion patterns relative to vehicle 200 in one or more images related to other vehicles and pedestrians, where these motion patterns are different from the motion of the road surface. The processing unit 110 may calculate the motion of a candidate object by observing the object's various positions across multiple image frames captured at different times. The processing unit 110 may use the position and time values ​​as input to a mathematical model for calculating the motion of the candidate object. Thus, optical flow analysis may provide an alternative method for detecting vehicles and pedestrians near vehicle 200. The processing unit 110 can perform optical flow analysis in combination with steps 540-546 to provide redundancy in vehicle and pedestrian detection and increase the reliability of system 100.

[0173] Figure 5C is a flowchart illustrating an exemplary process 500C for detecting road markings and / or lane geometric structure information contained in a set of images, consistent with the embodiments disclosed. Processing unit 110 may perform process 500C by running monocular image analysis module 402. In step 550, processing unit 110 may detect a set of objects by scanning one or more images. To detect lane markings, lane geometric structure information, and other relevant road marking segments, processing unit 110 may filter the set of objects to remove those determined to be irrelevant (e.g., small potholes, pebbles, etc.). In step 552, processing unit 110 may group together segments belonging to the same road marking or lane marking detected in step 550. Based on this grouping, processing unit 110 may develop a model, such as a mathematical model, representing the detected segments.

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

[0175] In step 556, the processing unit 110 may perform multi-frame analysis, for example, by tracking the detected segment through a series of image frames and accumulating frame-by-frame data associated with the detected segment. As the processing unit 110 performs multi-frame analysis, the set of measurements constructed in step 554 will become more reliable and increasingly associated with higher confidence levels. Thus, by performing steps 550, 552, 554, and 556, the processing unit 110 can identify road markings appearing in the acquired set of images and obtain lane geometric structure information. Based on this identification and the information obtained, the processing unit 110 can generate one or more navigation responses in the vehicle 200, as described above in relation to Figure 5A.

[0176] In step 558, the processing unit 110 may consider additional information sources to further develop the safety model of the vehicle 200 in relation to its surroundings. The processing unit 110 may use the safety model to define the conditions under which the system 100 can safely perform automatic control of the vehicle 200. To further develop the safety model, in some embodiments, the processing unit 110 may consider the positions and movements of other vehicles, detected road edges and road barriers, and / or general road shape descriptions extracted from map data (such as data from the map database 160). By considering additional information sources, the processing unit 110 can provide redundancy in the detection of road markings and lane geometry, thereby increasing the reliability of the system 100.

[0177] Figure 5D is a flowchart illustrating an exemplary process 500D for detecting traffic lights in a set of images, consistent with the embodiments disclosed. Processing unit 110 may perform process 500D by running monocular image analysis module 402. In step 560, processing unit 110 may scan the set of images to identify objects appearing at locations in the images that may contain traffic lights. For example, processing unit 110 may filter the identified objects to build a set of candidate objects, excluding objects that are less likely to correspond to traffic lights. This filtering may be based on various characteristics associated with traffic lights, such as shape, dimensions, texture, and location (e.g., location relative to vehicle 200). 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 multi-frame analysis on the set of candidate objects that reflect possible traffic lights. For example, the processing unit 110 may track candidate objects throughout a series of image frames, estimate their actual positions, and exclude moving objects (objects that are less likely to be traffic lights). In some embodiments, the processing unit 110 may perform color analysis on the candidate objects to identify the relative positions of detected colors appearing inside potential traffic lights.

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

[0179] As the vehicle 200 approaches the intersection, in step 564, the processing unit 110 may update the confidence level associated with the analyzed intersection geometry and detected traffic lights. For example, the estimated number of traffic lights that will appear at the intersection may affect the confidence level when compared to the number that actually appear at the intersection. Therefore, based on the confidence level, the processing unit 110 may delegate control to the driver of the vehicle 200 to improve safety conditions. By performing steps 560, 562, and 564, the processing unit 110 may identify the traffic lights that appear in the acquired set of images and analyze the intersection geometry information. Based on this identification and analysis, the processing unit 110 may generate one or more navigation responses in the vehicle 200, as described above in relation to Figure 5A.

[0180] Figure 5E is a flowchart illustrating an exemplary process 500E for generating one or more navigation responses in a vehicle 200 based on a vehicle path, consistent with the embodiments disclosed. In step 570, the processing unit 110 may construct an initial vehicle path associated with the vehicle 200. This vehicle path may be represented using a set of points expressed in coordinates (x,z), where d is the distance between any two points in this set of points. iThis can be within a range of 1 to 5 meters. In one embodiment, the processing unit 110 may construct an initial vehicle path using two polynomials, for example, left and right road polynomials. The processing unit 110 calculates the geometric midpoint between the two polynomials and, if there is an offset (an offset of zero may correspond to driving in the center of the lane), shifts each point in the resulting vehicle path by a predetermined offset (e.g., smart lane offset). This offset may be perpendicular to the segment between any two points in the vehicle path. In another embodiment, the processing unit 110 may use one polynomial and the estimated lane width to shift each point in the vehicle path by half the estimated lane width plus a predetermined offset (e.g., smart lane offset).

[0181] In step 572, the processing unit 110 may update the vehicle route constructed in step 570. The processing unit 110 may reconstruct the vehicle route constructed in step 570 using a high resolution, thereby improving the distance d between two points in the set of points representing the vehicle route. k The distance d is as described above. i It becomes smaller. For example, distance d k This can be in the range of 0.1 to 0.3 meters. The processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may yield a cumulative distance vector S corresponding to the total length of the vehicle path (i.e., based on a set of points representing the vehicle path).

[0182] In stage 574, the processing unit 110 uses the updated vehicle route constructed in stage 572 to determine the coordinates (x l ,z l) expressed as) may determine a look-ahead point. The processing unit 110 may extract a look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance may have a lower limit value in the range of 10 to 20 meters and may be calculated as the product of the speed of the vehicle 200 and the look-ahead time. For example, when the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower limit value). The look-ahead time may be in the range of 0.5 to 1.5 seconds and may be inversely proportional to the gain of one or more control loops (such as an azimuth error tracking control loop) associated with generating a navigation response in the vehicle 200. For example, the gain of the azimuth error tracking control loop may depend on the bandwidth of the yaw rate loop, the steering actuator loop, and the lateral dynamics of the vehicle, etc. Therefore, the higher the gain of the azimuth error tracking control loop, the shorter the look-ahead time.

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

[0184] Figure 5F is a flowchart illustrating an exemplary process 500F for determining whether a preceding vehicle is changing lanes, consistent with the embodiments disclosed. In step 580, the processing unit 110 may identify navigation information related to the preceding vehicle (e.g., a vehicle traveling ahead of vehicle 200). For example, the processing unit 110 may determine the position, speed (e.g., direction and velocity), and / or acceleration of the preceding vehicle using the methods described above in relation to Figures 5A and 5B. The processing unit 110 may determine one or more road polynomials, look-ahead points (related to vehicle 200), and / or snail trails (e.g., a set of points describing the path taken by the preceding vehicle) using the methods described above in relation to Figure 5E.

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

[0186] In another embodiment, the processing unit 110 may compare the instantaneous position of a preceding vehicle with a look-ahead point (related to the vehicle 200) over a specific period of time (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the preceding vehicle and the look-ahead point changes during the specific period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a gently curving road, and 1.3 to 1.7 meters on a sharply curving road), the processing unit 110 may determine that the preceding vehicle is likely changing lanes. In another embodiment, the processing unit 110 may analyze the geometry of the snail trail by comparing the lateral travel distance along the trail with the expected curvature of the snail trail. The expected radius of curvature is (δ z 2 +δ x 2 ) / 2 / (δ x It can be calculated according to the following formula: ) where δ x δ represents the lateral movement distance, z represents the vertical travel distance. If the difference between the horizontal travel distance and the expected curvature exceeds a predetermined threshold (e.g., 500-700 meters), the processing unit 110 may determine that the preceding vehicle is likely changing lanes. In another embodiment, the processing unit 110 may analyze the position of the preceding vehicle. If the position of the preceding vehicle obscures the road polynomial (e.g., the preceding vehicle is superimposed on the road polynomial), the processing unit 110 may then determine that the preceding vehicle is likely changing lanes. If the position of the preceding vehicle is such that another vehicle is detected in front of it and the snail trails of the two vehicles are not parallel, the processing unit 110 may determine that the (closer) preceding vehicle is likely changing lanes.

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

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

[0189] In step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis on multiple first and second images to create a 3D map of the road ahead of the vehicle and to detect features in these images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. The stereo image analysis may be performed in a manner similar to the steps described above in relation to Figures 5A to 5D. For example, the processing unit 110 may execute the stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road markings, traffic lights, road obstacles, etc.) in multiple first and second images, exclude a subset of candidate objects based on various criteria, further perform multi-frame analysis to construct measurements, and determine the confidence level of the remaining candidate objects. When performing the above steps, the processing unit 110 may consider information from both the first and second multiple images rather than from only one set of images. For example, the processing unit 110 may analyze differences in pixel-level data of candidate objects appearing in both the first and second sets of images (or in the other data subset of the two streams of captured images). As another example, the processing unit 110 may estimate the position and / or velocity of a candidate object (e.g., relative to the vehicle 200) by observing that the object appears in one of the sets of images but not in the other, and by comparing this with other differences that may exist in relation to the object appearing when there are two image streams. For example, the position, velocity, and / or acceleration relative to the vehicle 200 may be determined based on the trajectory, position, motion characteristics, etc., of features related to the object appearing in one or both of the two image streams.

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

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

[0192] In step 720, the processing unit 110 may analyze the first, second, and third sets of images to detect features within these images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. This analysis may be performed in a manner similar to the steps described above in relation to Figures 5A to 5D and Figure 6. For example, the processing unit 110 may perform monocular image analysis on each of the first, second, and third sets of images (for example, by running the monocular image analysis module 402 and based on the steps described above in relation to Figures 5A to 5D). Alternatively, the processing unit 110 may perform stereo image analysis on the first and second sets of images, the second and third sets of images, and / or the first and third sets of images (for example, by running the stereo image analysis module 404 and based on the steps described above in relation to Figure 6). The processed information corresponding to the analysis of the first, second, and / or third sets of images may be combined. In some embodiments, the processing unit 110 may perform a combination of monocular image analysis and stereo image analysis. For example, the processing unit 110 may perform monocular image analysis on a first set of images (e.g., by running the monocular image analysis module 402) and stereo image analysis on second and third sets of images (e.g., by running the stereo image analysis module 404). The configuration of the image acquisition devices 122, 124, and 126 (including their respective positions and fields of view 202, 204, and 206) may influence the type of analysis performed on the first, second, and third sets of images. The disclosed embodiments are not limited to the specific configuration of the image acquisition devices 122, 124, and 126, or the type of analysis performed on the first, second, and third sets of images.

[0193] In some embodiments, the processing unit 110 may perform tests on the system 100 based on the images acquired and analyzed in steps 710 and 720. Such tests can provide an indicator of the overall performance of the system 100 for specific configurations of the image acquisition devices 122, 124, and 126. For example, the processing unit 110 may determine the percentage of "false detections" (e.g., when the system 100 incorrectly identifies the presence of a vehicle or pedestrian) and "missed detections."

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

[0195] In some embodiments, the processing unit 110 may select information from two of the first, second, and third images by determining the degree to which information from one image source matches information from another image source. For example, the processing unit 110 may combine processed information obtained from each of the image acquisition devices 122, 124, and 126 (whether by monocular analysis, stereo analysis, or any combination thereof) to identify visual indicators consistent with the images acquired from each of the image acquisition devices 122, 124, and 126 (e.g., lane markings, detected vehicles and their location and / or route, detected traffic lights, etc.). The processing unit 110 may exclude information inconsistent with the acquired images (e.g., vehicles changing lanes, lane models indicating vehicles too close to vehicle 200, etc.). Thus, the processing unit 110 may select information from two of the first, second, and third images based on the determination of consistent and inconsistent information.

[0196] Navigation responses may include, for example, turns, lane changes, and changes in acceleration. Processing unit 110 may generate one or more navigation responses based on the analysis performed in step 720 and the methods described above in relation to Figure 4. Processing unit 110 may generate one or more navigation responses using data obtained from the execution of the velocity acceleration module 406. In some embodiments, processing unit 110 may generate one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration of the vehicle 200 with an object detected in any of the first, second, and third images. Multiple navigation responses may be generated simultaneously, sequentially, or in any combination thereof.

[0197] [Sparse road model for autonomous vehicle navigation]

[0198] In some embodiments, the disclosed systems and methods may utilize sparse maps for autonomous vehicle navigation. Specifically, the sparse maps may be for autonomous vehicle navigation along road segments. For example, sparse maps can provide sufficient information for navigating an autonomous vehicle without requiring the storage and / or updating of large amounts of data. As will be discussed in more detail below, an autonomous vehicle can use a sparse map to navigate one or more roads based on one or more stored trajectories.

[0199] [Sparse map for autonomous vehicle navigation]

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

[0201] For example, a sparse data map can store a three-dimensional polynomial representation of a preferred vehicle path along a road, rather than a detailed representation of road segments. These paths require little to no data storage space. Furthermore, in the sparse data map described, landmarks may be identified and included in the sparse map road model to aid in navigation. These landmarks may be placed at arbitrary intervals suitable for enabling vehicle navigation, but in some cases, it is not necessary to identify such landmarks or include them in the model at high density and close intervals. Rather, in some cases, navigation may be possible based on landmarks placed at intervals of at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers. As will be discussed in more detail in other sections, a sparse map may be generated based on data collected or measured by a vehicle equipped with various sensors and devices, such as image acquisition devices, sensors for global positioning systems, motion sensors, etc., as the vehicle travels along the roadway. In some cases, a sparse map may be generated based on data collected over multiple drives of one or more vehicles along a particular roadway. Generating a sparse map using multiple drives from one or more vehicles is sometimes referred to as "crowdsourcing" of sparse maps.

[0202] Without being inconsistent with the disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed system and method may deliver a sparse map to generate a road navigation model for an autonomous vehicle, and may use the sparse map and / or the generated road navigation model to navigate the autonomous vehicle along a road segment. A sparse map without being inconsistent with the disclosure may include one or more three-dimensional contour maps that can represent a predetermined trajectory that an autonomous vehicle may travel along a relevant road segment.

[0203] A sparse map consistent with this disclosure may also include data representing one or more road features. Such road features may include recognized landmarks, road signature profiles, and any other road-related features useful for navigating a vehicle. A sparse map consistent with this disclosure may enable automated vehicle navigation based on a relatively small amount of data contained in the sparse map. For example, embodiments of the disclosed sparse map may require relatively little storage space (and relatively little bandwidth when transferring each part of the sparse map to a vehicle) rather than including detailed representations of roads such as road edges, road curvature, images associated with road segments, or data detailing other physical features associated with road segments, yet may still be able to provide sufficient autonomous vehicle navigation. As will be discussed in more detail below, the small data footprint of the disclosed sparse map may be achieved in some embodiments by storing representations of road-related elements that require only a small amount of data but still enable automated navigation.

[0204] For example, the disclosed sparse map may store polynomial representations of one or more trajectories a vehicle could take along a road, rather than storing detailed representations of various aspects of the road. Therefore, rather than storing (or needing to transfer) details about the physical properties of the road to enable navigation along a road, using the disclosed sparse map may, in some cases, eliminate the need to interpret the physical aspects of the road. Instead, the vehicle can be navigated along a specific road segment by aligning the vehicle's travel path with a trajectory along that particular road segment (e.g., a polynomial spline). Thus, the vehicle may be navigated primarily based on the stored trajectory (e.g., a polynomial spline), which requires far less storage space than methods that require the storage of roadway images, road parameters, road layouts, etc.

[0205] In addition to the stored polynomial representation of the trajectory along the road segment, the disclosed sparse map may also include small data objects that may represent road features. In some embodiments, the small data objects may include a digital signature, which is obtained from a digital image (or digital signal) acquired by a sensor (e.g., a camera, or other sensors such as suspension sensors) mounted on a vehicle traveling along the road segment. The digital signature may be smaller in size than the signal acquired by the sensor. In some embodiments, the digital signature may be constructed to be compatible with a classifier function configured to detect and identify road features from signals acquired by sensors in subsequent drives, for example. In some embodiments, the digital signature may be constructed to have as small a footprint as possible and to retain the ability to associate or match road features with the stored signature based on an image of the road feature (or, if the stored signature is not image-based and / or contains other data, a digital signal generated by a sensor) captured on a subsequent occasion by a camera mounted on a vehicle traveling along the same road segment.

[0206] In some embodiments, the size of the data object may further relate to the uniqueness of the road feature. For example, if a camera mounted on a vehicle can detect a road feature, and the vehicle's camera system is coupled with a classifier that can distinguish the image data corresponding to the road feature as being associated with a particular type of road feature (e.g., a road sign), and such a road sign is locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), then it would be sufficient to store data indicating the type of road feature and its location.

[0207] As will be discussed in more detail below, road features (e.g., landmarks along a road segment) may be stored as small data objects that can represent road features with a relatively small number of bytes, while simultaneously providing sufficient information to recognize and use such features for navigation. In one example, a road sign may be identified as a recognized landmark on which vehicle navigation can be based. The representation of the road sign may be stored in a sparse map, which may contain, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign) and a few bytes of data indicating the location of the landmark (e.g., coordinates). Navigating based on such a data-light representation of a landmark (e.g., using a representation sufficient to locate, recognize, and navigate based on the landmark) can provide the desired level of navigation functionality associated with the sparse map without significantly increasing the data overhead associated with the sparse map. This efficient representation of landmarks (and other road features) may utilize on-board sensors and processors configured to detect, identify, and / or classify specific road features.

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

[0209] The sparse map may include any preferred representation of objects identified along road segments. In some cases, objects may be referred to as semantic or non-semantic objects. Semantic objects may include, for example, objects associated with a given type classification. This type classification may be useful in reducing the amount of data required to describe semantic objects perceived in the environment, which can be beneficial both during the data collection and navigation phases (e.g., reducing the cost associated with bandwidth usage for transferring drive information from multiple collection vehicles to a server) (for example, reducing map data can speed up the transfer of map tiles from the server to the navigating vehicle and reduce the cost associated with bandwidth usage for such transfers). Semantic object classification types may be assigned to any type of object or feature expected to be encountered along the roadway.

[0210] Semantic objects may be further divided into two or more logical groups. For example, in some cases, one group of semantic object types may be related to a given dimension. Such semantic objects may include specific speed limit signs, priority road signs, merge signs, stop signs, traffic lights, directional arrows on the roadway, manhole covers, or any other type of object that may be related to a standardized size. One benefit provided by such semantic objects is that little data may be required to represent / fully define the object. For example, if the standardized size of a speed limit sign is known, the collecting vehicle may then only need to identify the presence of the speed limit sign (of the recognized type) (by analyzing the captured image) along with an indication of the location of the detected speed limit sign (e.g., the 2D location of the center of the sign or a specific corner of the sign in the captured image (or, instead, the 3D location in actual coordinates)) to provide sufficient information for map generation on the server side. When 2D image locations are sent to the server, the server can determine the actual location of the sign (for example, through a structure in a motion technique that uses multiple images captured from one or more collection vehicles), so the location where the sign was detected, related to the captured image, may also be sent. Even with this limited information (requiring only a few bytes to define each detected object), the server may still construct a map containing speed limit signs that are fully represented based on type classifications (representing speed limit signs) received from one or more collection vehicles along with the location information of the detected signs.

[0211] Semantic objects may also include other recognized object or feature types that are not associated with specific standardized characteristics. Such objects or features may include potholes in the road, tar seams, lampposts, non-standardized signals, curbs, trees, tree branches, or any other type of recognized object with one or more variable characteristics (e.g., variable dimensions). In such cases, in addition to transmitting indications of the detected object or feature type (e.g., potholes in the road, poles, etc.) and location information of the detected object or feature to the server, the collection vehicle may also transmit indications of the size of the object or feature. The size may be represented by 2D image dimensions (e.g., bounding boxes, or one or more dimensional values) or actual dimensions (identified through structures in motion calculations based on the output of a LIDAR or RADAR system, the output of a trained neural network, etc.).

[0212] Non-semantic objects or features may include any detectable objects or features that fall outside the range of recognized types or categories but can still provide valuable information in map generation. In some cases, such non-semantic features may include a detected corner of a building or a detected corner of a building's windowpane, a distinctive stone or object near a driveway, concrete splatter on a roadside, or any other detectable object or feature. When detecting such objects or features, one or more collection vehicles may transmit the location of one or more points (2D image points or 3D real-world points) associated with the detected object / feature to the map generation server. Furthermore, a compressed or simplified image segment (e.g., an image hash) may be generated for the region of the captured image containing the detected object or feature. This image hash may be calculated based on a predetermined image processing algorithm and may form an effective signature for the detected non-semantic object or feature. Vehicles traveling on roadways may apply algorithms similar to those used to generate image hashes to verify / confirm the presence of non-semantic features or objects mapped in the captured images; such signatures may be useful for navigation related to sparse maps containing non-semantic features or objects. By using this technique, non-semantic features may add richness to sparse maps without adding significant data overhead (and may improve their usability in navigation, for example).

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

[0214] [Generating a sparse map]

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

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

[0217] In some embodiments, the sparse map 800 may be stored in a storage device mounted on the vehicle 200 or in a non-temporary computer-readable medium (for example, a storage device included in a navigation system mounted on the vehicle 200). A processor provided in the vehicle 200 (for example, a processing unit 110) may access the sparse map 800 stored in the storage device or computer-readable medium mounted on the vehicle 200 to generate navigation commands for guiding the autonomous vehicle 200 as it travels through a road segment.

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

[0219] Furthermore, in such embodiments, multiple vehicles traveling on various road segments (e.g., tens, hundreds, thousands, or millions of vehicles) may be able to access the sparse map 800. It should also be noted that the sparse map 800 may include multiple submaps. For example, in some embodiments, the sparse map 800 may include hundreds, thousands, millions, or more submaps (e.g., map tiles) that can be used when navigating vehicles. Such submaps may be called local maps or map tiles, and vehicles traveling along a roadway may access any number of local maps relevant to the location where the vehicle is traveling. The local map areas of the sparse map 800 may be stored together with Global Navigation Satellite System (GNSS) keys as indexes in the database of the sparse map 800. Thus, the calculation of steering angles for navigating a host vehicle in this system may be performed without relying on the host vehicle's GNSS position, road features, or landmarks, although such GNSS information may be used to look up relevant local maps.

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

[0221] The data recorded in the sparse map 800 may include location information based on Global Positioning System (GPS) data. For example, location information may be included in the sparse map 800 for various map elements, such as the locations of landmarks and road profiles. The locations of the map elements included in the sparse map 800 may be obtained using GPS data collected from vehicles traveling on 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 (for example, 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 each time a further vehicle passes over the location of the identified landmark. Some or all of the further location determinations may be used to fine-tune the location information for the identified landmark stored in the sparse map 800. 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 operations may be used to fine-tune the positions of the stored map elements based on multiple positions determined for the map elements.

[0222] In a specific example, the collection vehicle may travel along a specific road segment. Each collection vehicle captures images of its respective environment. The images may be collected at any preferred frame capture rate (e.g., 9 Hz). One or more image analysis processors mounted on each collection vehicle analyze the captured images to detect the presence of semantic and / or non-semantic features / objects. At a high level, the collection vehicle transmits indications of the detection of semantic and / or non-semantic objects / features, along with their locations, to the mapping server. More specifically, type indices, dimension indices, etc., may be transmitted along with the location information. The location information may include any information suitable for enabling the mapping server to aggregate the detected objects / features into a sparse map useful for navigation. In some cases, the location information may include one or more 2D image locations (e.g., XY pixel locations) where semantic or non-semantic features / objects were detected in the captured images. Such image locations may correspond to the center, corner, etc., of the feature / object. In this scenario, each collection vehicle may also provide the server with the location where each image was captured (e.g., GPS location) in order to help the mapping server reconstruct the drive information and gather drive information from multiple collection vehicles.

[0223] In other cases, the data collection vehicle may provide the server with one or more 3D real-world points associated with detected objects / features. Such 3D points may be associated with a predetermined origin (such as the origin of a drive segment) and may be identified by any preferred method. In some cases, a structure in a motion method may be used to determine the 3D real-world location of the detected object / feature. For example, a specific object, such as a particular speed limit sign, may be detected in two or more captured images. The actual location of one or more points associated with the speed limit sign may be identified and passed to the mapping server by using information such as the known ego-motion of the data collection vehicle across multiple captured images (velocity, trajectory, GPS position, etc.), along with observed changes in the speed limit sign in the captured images (changes in XY pixel position, changes in size, etc.). Such methods are optional as they require more computation in part of the data collection vehicle system. The sparse maps of the disclosed embodiments may enable automated vehicle navigation using relatively small amounts of stored data. In some embodiments, the sparse map 800 may have a data density of less than 2 MB per kilometer of road, less than 1 MB per kilometer of road, less than 500 kB per kilometer of road, or less than 100 kB per kilometer of road (e.g., including data representing target trajectories, landmarks, and any other stored road features). In some embodiments, the data density of the sparse map 800 may be less than 10 kB per kilometer of road, or even less than 2 kB per kilometer of road (e.g., 1.6 kB per kilometer), or 10 kB or less per kilometer of road, or 20 kB or less per kilometer of road. In some embodiments, most, if not all, of the roadways in the United States can be autonomously navigated using a sparse map with a total data of 4 GB or less. These data density values ​​may represent the average over the entire sparse map 800, the average over local maps within the sparse map 800, and / or the average over specific road segments within the sparse map 800.

[0224] As mentioned, the sparse map 800 may include representations 810 of multiple target trajectories for guiding autonomous driving or navigation along a road segment. Such target trajectories may be stored as three-dimensional splines. The target trajectories stored in the sparse map 800 may be determined, for example, based on two or more reconstructed trajectories relating to a vehicle's previous travel along a particular road segment. A road segment may be associated with a single target trajectory or with multiple target trajectories. For example, on a two-lane road, a first target trajectory may be stored to represent a target route traveling in a first direction along the road, and a second target trajectory may be stored to represent a target route traveling in another direction along the road (e.g., opposite to the first direction). Additional target trajectories may be stored for a particular road segment. For example, on a multi-lane road, one or more target trajectories may be stored to represent target travel routes for multiple vehicles in one or more lanes associated with the multi-lane road. In some embodiments, each lane of a multi-lane road may be associated with its own target trajectory. In other embodiments, fewer target trajectories than the lanes present on a multi-lane road may be stored. In such cases, a vehicle navigating a multi-lane road may use one of the stored target trajectories to guide navigation, taking into account the lane offset from the lane where the target trajectory is stored (for example, if a vehicle is traveling in the leftmost lane of a three-lane highway and only the target trajectory for the center lane of the highway is stored, the vehicle may use the target trajectory for the center lane to navigate by taking into account the lane offset between the center lane and the leftmost lane when generating navigation commands).

[0225] In some embodiments, the target trajectory may represent the ideal path that a vehicle should take when traveling. The target trajectory may be located, for example, approximately in the center of the driving lane. In other cases, the target trajectory may be located elsewhere relative to the road segment. For example, the target trajectory may approximately coincide with the center of the road, the edge of the road, or the edge of the lane. In such cases, navigation based on the target trajectory may include a predetermined offset amount maintained relative to the position of the target trajectory. Furthermore, in some embodiments, the predetermined offset amount maintained relative to the position of the target trajectory may differ based on the type of vehicle (for example, a passenger car with two axles may have a different offset along at least part of the target trajectory than a truck with more than two axles).

[0226] The sparse map 800 may also include data related to a plurality of predetermined landmarks 820 associated with specific road segments, local maps, etc. As will be discussed in more detail below, these landmarks may be used for the navigation of an autonomous vehicle. For example, in some embodiments, these 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 direction of travel to match the direction of the target trajectory at the determined position.

[0227] Multiple landmarks 820 may be identified at any preferred interval and stored in the sparse map 800. In some embodiments, landmarks may be stored at relatively high density (e.g., every few meters, or even higher density). However, in some embodiments, significantly large landmark spacing values ​​may be used. For example, in the sparse map 800, identified (or recognized) landmarks may be placed at intervals of 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers. In some cases, identified landmarks may even be placed at distances exceeding 2 kilometers.

[0228] Between landmarks, and therefore in determining the vehicle's position relative to a target trajectory, the vehicle can navigate using dead reckoning, in which the vehicle uses sensors to identify its own egomotion and estimate its position relative to the target trajectory. Because errors can accumulate in dead reckoning navigation, the accuracy of position determination relative to the target trajectory may gradually decrease over time. The vehicle can use landmarks (and their known positions) present in the sparse map 800 to eliminate errors in dead reckoning during position determination. Thus, identified landmarks included in the sparse map 800 can play a key role in navigation, enabling the precise determination of the vehicle's position relative to the target trajectory. Since a certain amount of error may be acceptable in position search, identified landmarks do not necessarily need to be available to the autonomous vehicle. Rather, preferred navigation may be possible based on landmark intervals of 10 meters, 20 meters, 50 meters, 100 meters, 500 meters, 1 kilometer, 2 kilometers, or even longer, as described above. In some embodiments, a density of one identified landmark per kilometer of road may be sufficient to maintain longitudinal positioning accuracy within 1 meter. Therefore, it is not necessary to store all possible landmarks appearing along the road segment in the sparse map 800.

[0229] Furthermore, in some embodiments, lane markings may be used to determine the vehicle's position between landmarks. Using lane markings between landmarks minimizes the accumulation of errors during dead reckoning navigation.

[0230] In addition to the target trajectory and identified landmarks, the sparse map 800 may include information related to various other road features. For example, Figure 9A shows a representation of a curve along a particular road segment that may be stored in the sparse map 800. In some embodiments, a single lane of a road may be modeled by describing the left and right sides of the road with three-dimensional polynomials. Such polynomials representing the left and right sides of a single lane are shown in Figure 9A. Regardless of how many lanes a road may have, the road can be represented using polynomials in a similar manner to that shown in Figure 9A. For example, the left and right sides of a multi-lane road may be represented by polynomials similar to those shown in Figure 9A, and intermediate lane markings included in a multi-lane road (e.g., dashed lines representing lane boundaries, solid yellow lines representing boundaries between lanes traveling in different directions, etc.) may also be represented using polynomials as shown in Figure 9A.

[0231] As shown in Figure 9A, lane 900 may be represented using a polynomial (e.g., a first-order, second-order, third-order, or any preferred degree polynomial). For illustrative purposes, lane 900 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. As shown in Figure 9A, lane 900 includes left lane 910 and right lane 920. In some embodiments, more than one polynomial may be used to represent the location of each side of the road or lane boundary. For example, each of left lane 910 and right lane 920 may be represented by multiple polynomials of any preferred length. In some cases, these polynomials may have a length of about 100m, but other lengths longer or shorter than 100m may also be used. Furthermore, these polynomials may overlap each other to facilitate a seamless transition when the host vehicle navigates based on the next polynomial encountered as it travels along the roadway. For example, each of the left 910 and the right 920 may be represented by a plurality of cubic polynomials, each divided into segments of approximately 100 meters in length (an example of a first predetermined range) with approximately 50 meters of overlap between them. The polynomials representing the left 910 and the right 920 may or may not be of the same degree. For example, in some embodiments, the polynomials may include quadratic, cubic, and quartic polynomials.

[0232] In the example shown in Figure 9A, the left side of lane 900, 910, is represented by a cubic polynomial in two groups. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. The two groups are substantially parallel to each other and extend along the positions on each side of the road. Polynomial segments 911, 912, 913, 914, 915, and 916 are approximately 100 meters long, with approximately 50 meters of continuous overlap with adjacent segments. However, as mentioned above, polynomials of different lengths and different amounts of overlap may also be used. For example, the polynomial may be 500m, 1km, or longer, and the amount of overlap may vary from 0 to 50m, 50m to 100m, or more than 100m. Furthermore, although Figure 9A is shown as representing polynomials extending in 2D space (e.g., on the plane of paper), it should be understood that these polynomials may represent curves extending in 3 dimensions (e.g., including height components) and may also represent elevation changes of road segments in addition to the curvature of the XY plane. In the example shown in Figure 9A, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922, and 923, and a second group having polynomial segments 924, 925, and 926.

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

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

[0235] SparseMap800 may describe a network of lanes using a combination of geometric structure descriptors and metadata. The geometric structure may be described by the polynomials or splines described above. The metadata may describe the number of lanes, special characteristics (such as carpooling lanes), and possibly other sparse labels. The total footprint of such metrics may be very small.

[0236] Accordingly, a sparse map according to an embodiment of the present disclosure may include at least one line representation of a road surface feature extending along a road segment, each line representation representing a path along the road segment substantially corresponding to the road surface feature. In some embodiments, as described above, the at least one line representation of a road surface feature may include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature may include at least one of road edges or lane markings. In addition, as discussed below with respect to "crowdsourcing," the road surface feature may be identified by image analysis of multiple images acquired as one or more vehicles travel along the road segment.

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

[0238] Figure 10 shows examples of types of landmarks that may be represented in the sparse map 800. These landmarks may include any visible and identifiable object along a road segment. Landmarks may be selected to be fixed and not subject to frequent changes in their location and / or content. Landmarks included in the sparse map 800 can help determine the position of a vehicle 200 relative to a target trajectory when the vehicle is traveling through a particular road segment. Examples of landmarks may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside fixtures (e.g., lampposts, reflectors, etc.), and any other suitable types. In some embodiments, lane markings on the road may also be included as landmarks in the sparse map 800.

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

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

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

[0242] Landmarks may also include beacons that can be specifically designed for use in autonomous vehicle navigation systems. For example, such beacons may include standalone structures placed at predetermined intervals to assist in navigating a host vehicle. Such beacons may also include visual / graphic information (e.g., icons, emblems, barcodes, etc.) added to existing road signs that can be identified or recognized by a vehicle traveling along a road segment. Such beacons may also include electronic components. In such embodiments, non-visual information may be transmitted to the host vehicle using electronic beacons (e.g., RFID tags, etc.). Such information may include, for example, landmark identification information and / or landmark location information that can be used by the host vehicle to determine its position along a target trajectory.

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

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

[0245] Therefore, for semantic road signs that do not require image signatures, the impact of data density on sparsemap800 can be around 760 bytes per kilometer (e.g., [20 landmarks per km] × [38 bytes per landmark] = 760 bytes), even with a relatively high landmark density of about one per 50m. Even for generic signs that include an image signature component, the impact of data density is about 1.72kB per kilometer (e.g., [20 landmarks per km] × [86 bytes per landmark] = 1,720 bytes). For semantic road signs, this impact corresponds to approximately 76kB of data usage per hour for a vehicle traveling at 100km / hr. For generic signs, this impact corresponds to approximately 170kB per hour for a vehicle traveling at 100km / hr. It should be noted that in some environments (e.g., urban environments), there may be a considerably higher density (perhaps more than one per meter) of detected objects available for inclusion in the sparsemap. In some embodiments, a generally rectangular object, such as a rectangular sign, may be represented in the sparse map 800 with data of 100 bytes or less. The representation of a generally rectangular object (e.g., general sign 1040) in the sparse map 800 may include a shortened image signature or image hash (e.g., shortened image signature 1045) associated with the generally rectangular object. This shortened image signature / image hash can be determined using any suitable image hash algorithm, and can be used to identify, for example, a general sign as a recognized landmark. Such a shortened image signature (e.g., image information obtained from actual image data representing an object) eliminates the need to store the actual image of the object and the need to perform comparative image analysis on the actual image to recognize the landmark.

[0246] Referring to Figure 10, the sparse map 800 may also store a shortened image signature 1045 associated with the general sign 1040, rather than an actual image of the general sign 1040. For example, after an image acquisition device (e.g., image acquisition devices 122, 124, or 126) has acquired an image of the general sign 1040, a processor (e.g., an image processor 190 or any other processor, mounted on or remotely located relative to the host vehicle, capable of processing the image) may perform image analysis to extract / create a shortened image signature 1045 containing a unique signature or pattern associated with the general sign 1040. In one embodiment, the shortened image signature 1045 may include a shape, a color pattern, a brightness pattern, or any other features that can be extracted from an image of the general sign 1040 to describe the general sign 1040.

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

[0248] Therefore, multiple landmarks may be identified by image analysis of multiple images taken when one or more vehicles travel through a road segment. In some embodiments, as described below with respect to "crowdsourcing," the image analysis for identifying multiple landmarks may include accepting potential landmarks if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold. Furthermore, in some embodiments, the image analysis for identifying multiple landmarks may include excluding potential landmarks if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold.

[0249] Returning to the target trajectory that a host vehicle can use to navigate a particular road segment, Figure 11A shows the trajectory of the polynomial representation incorporated in the process of constructing or maintaining the sparse map 800. The polynomial representation of the target trajectory included in the sparse map 800 may be derived based on two or more reconstructed trajectories of a vehicle's previous travel 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 a vehicle's previous travel along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map 800 may be the average of two or more reconstructed trajectories of a vehicle's previous travel along the same road segment. Other mathematical operations may also be used to construct the target trajectory along the road route based on reconstructed trajectories collected from vehicles traveling along a certain road segment.

[0250] As shown in Figure 11A, multiple vehicles 200 may travel along the road segment 1100 at different times. Each vehicle 200 may collect data related to the path it has taken along the road segment. The path taken 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. Using such data, the trajectories of vehicles traveling along the road segment can be reconstructed, and based on these reconstructed trajectories, target trajectories (or multiple target trajectories) may be determined for a particular road segment. Such target trajectories may represent the preferred path for a host vehicle when it travels along the road segment (e.g., guided by an automated navigation system).

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

[0252] Furthermore, or alternatively, such reconstructed trajectories may be determined on the server side based on information received from vehicles traveling along the road segment 1100. For example, in some embodiments, vehicle 200 may transmit data related to its movement along the road segment 1100 (e.g., in particular steering angle, direction of travel, time, position, speed, detected road geometry, and / or detected landmarks) to one or more servers. The servers may reconstruct the trajectory of vehicle 200 based on the received data. The servers may also generate target trajectories to guide the navigation of an autonomous vehicle traveling along the same road segment 1100 later, based on the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103. While the target trajectories may be associated with a single previous passage of the 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 traveling along the same road segment. In Figure 11A, the target trajectory is represented by 1110. In some embodiments, the target trajectory 1110 may be generated based on the average of a first trajectory 1101, a second trajectory 1102, and a third trajectory 1103. In some embodiments, the target trajectory 1110 included in the sparse map 800 may be a collection of two or more reconstructed trajectories (e.g., a weighted combination).

[0253] On the mapping server, the server may receive actual trajectories for a particular road segment from multiple collection vehicles traveling through the road segment. The received actual trajectories may be aligned to generate target trajectories for each valid path along the road segment (e.g., each lane, each direction of travel, each path through intersections, etc.). The alignment process may include using detected objects / features identified along the road segment, along with the collected locations of those detected objects / features, to correlate the actual collected trajectories with each other. Once aligned, an average or "best-fit" target trajectory for each available lane, etc., may be determined based on the aggregated and correlated / aligned actual trajectories.

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

[0255] As shown in Figure 11C, the sparse map 800 may include a local map 1140 containing a road model to assist vehicles in automated navigation within the geographical region 1111. For example, the local map 1140 may include one or more lane target trajectories associated with road segments 1120 and / or 1130 within the geographical region 1111. For example, the local map 1140 may include target trajectories 1141 and / or 1142 that can be accessed or used when an autonomous vehicle is traveling through lane 1122. Similarly, the local map 1140 may include target trajectories 1143 and / or 1144 that can be accessed or used when an autonomous vehicle is traveling through lane 1124. Furthermore, the local map 1140 may include target trajectories 1145 and / or 1146 that can be accessed or used when an autonomous vehicle is traveling through road segment 1130. Target trajectory 1147 may represent a preferred path that the autonomous vehicle should take when transitioning from lane 1120 (specifically, corresponding to target trajectory 1141 associated with the rightmost lane of lane 1120) to road segment 1130 (specifically, corresponding to target trajectory 1145 associated with the first side of road segment 1130). Similarly, target trajectory 1148 represents a preferred path that the autonomous vehicle should take when transitioning from road segment 1130 (specifically, corresponding to target trajectory 1146) to a portion of road segment 1124 (specifically, as shown in the figure, corresponding to target trajectory 1143 associated with the left lane of lane 1124).

[0256] The sparse map 800 may also include representations of other road-related features associated with the geographical area 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in the geographical area 1111. Such landmarks may include a first landmark 1150 associated with a stop line 1132, a second landmark 1152 associated with a stop sign 1134, a third landmark associated with a speed limit sign 1154, and a fourth landmark 1156 associated with a hazard sign 1138. Such landmarks may be used, for example, to assist an autonomous vehicle in determining its current position relative to one of the indicated target trajectories. This allows the vehicle to adjust its direction of travel at its determined position to align with the direction of the target trajectory.

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

[0258] Alternatively, or simultaneously, profile 1160 may represent a change in road width, which is identified based on image data acquired by a camera mounted on a vehicle traveling on a particular road segment. Such a profile may be useful, for example, in determining a specific position of an autonomous vehicle relative to a particular target trajectory. That is, when an autonomous vehicle travels on a road segment, it may measure a profile associated with one or more parameters associated with that road segment. If the measured profile can be associated with / matched with a predetermined profile plotting changes in parameters relating to position along the road segment, then the measured profile and the predetermined profile may be used (for example, by superimposing corresponding portions of the measured profile and the predetermined profile) to determine the current position along the road segment, and therefore the current position relative to the target trajectory of the road segment.

[0259] In some embodiments, the sparse map 800 may include various trajectories based on various characteristics associated with the user of the autonomous vehicle, environmental conditions, and / or other parameters related to driving. For example, in some embodiments, various trajectories may be generated based on various user preferences and / or profiles. Such sparse maps 800 containing various trajectories may be provided to various autonomous vehicles of various users. For example, some users may prefer to avoid toll roads, while others may prefer to take the shortest or fastest route, regardless of whether there are toll roads on the route. The disclosed system may generate various sparse maps having various trajectories based on such various user preferences or profiles. As another example, some users may prefer to drive in the high-speed lane, while others may prefer to always maintain their position in the center lane.

[0260] Various trajectories may be generated based on various environmental conditions such as daytime and nighttime, snow, rain, fog, etc., and may be included in the sparse map 800. Autonomous vehicles operating under various environmental conditions may be provided with such sparse maps 800 generated based on various environmental conditions. In some embodiments, cameras installed in the autonomous vehicle may detect environmental conditions and provide such information back to a server that generates and provides the sparse map. For example, the server may generate a sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions, or it may update an already generated sparse map 800. The updating of the sparse map 800 based on environmental conditions may be performed dynamically when the autonomous vehicle is traveling along the road.

[0261] Various other parameters related to driving may also be used as a basis for generating various sparse maps and providing them to various autonomous vehicles. For example, when an autonomous vehicle is traveling at high speed, turns may be sharper. When an autonomous vehicle is traveling along a particular trajectory, the sparse map 800 may include trajectories associated with a specific lane rather than a road so that the vehicle can maintain a specific lane. If images captured by a camera mounted on the autonomous vehicle indicate that the vehicle has moved out of its lane (for example, crossed a lane marking), an action may be activated within the vehicle to return the vehicle to the designated lane according to a specific trajectory.

[0262] [Crowdsourcing for sparse maps]

[0263] The disclosed sparse maps may be efficiently (and passively) generated by the power of crowdsourcing. For example, any private or commercial vehicle equipped with a camera (e.g., a simple low-resolution camera routinely included as OEM equipment in current vehicles) and a suitable image analysis processor can serve as a data collection vehicle. No special equipment (e.g., high-resolution imaging and / or positioning systems) is required. As a result of the disclosed crowdsourcing method, the generated sparse maps may be extremely accurate and may include highly fine-tuned positional information (enabling navigation error limits of 10 cm or less) without requiring any special-purpose imaging or sensing equipment as input to the map generation process. Crowdsourcing also enables much faster (and cheaper) updates to the generated maps, as the mapping server system can always utilize new drive information from any roads traveled by a minimally equipped private or commercial vehicle also serving as a data collection vehicle. The specified vehicles do not need to be equipped with high-resolution imaging and mapping sensors. Thus, the costs associated with building such special-purpose vehicles can be avoided. Furthermore, updating the currently disclosed sparse maps can be done much faster than using a system that utilizes dedicated, specialized mapping vehicles (which, due to their cost and special equipment, are typically limited to a fleet of specialized vehicles far fewer in number than the number of private or commercial vehicles already available to perform the disclosed collection methods).

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

[0265] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, the disclosed systems and methods may use crowdsourced data to generate sparse maps that one or more autonomous vehicles can use to navigate along a road in a given system. As used herein, “crowdsourcing” means receiving data from various vehicles (e.g., autonomous vehicles) traveling along a road segment at different times, and such data is used to generate and / or update a road model including sparse map tiles. This model, or any of its sparse map tiles, may then be transmitted to the vehicle or to other vehicles that subsequently travel along the road segment to assist in autonomous vehicle navigation. The road model may include a set of target trajectories representing preferred paths that an autonomous vehicle should take when traveling along a road segment. These target trajectories may be the same as reconstructions of actual trajectories collected from vehicles traveling along the road segment, which may be transmitted from the vehicles to a server. In some embodiments, the target trajectory may differ from the actual trajectory previously taken by one or more vehicles when traveling through the road segment. The target trajectory may be generated based on the actual trajectory (e.g., by averaging or any other preferred operation).

[0266] The vehicle trajectory data that a vehicle may upload to the server may correspond to the vehicle's actual reconstructed trajectory or to a recommended trajectory. The recommended trajectory may be based on or related to the vehicle's actual reconstructed trajectory, but may differ from the actual reconstructed trajectory. For example, a vehicle may modify its own actual reconstructed trajectory and submit (e.g., recommend) the modified actual trajectory to the server. The road model may use the recommended modified trajectory as a target trajectory for automatic navigation of other vehicles.

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

[0268] The reconstructed trajectory that a vehicle may generate as it travels along a road may be acquired in any preferred manner. In some embodiments, the reconstructed trajectory can be developed by piecing together multiple parts of the vehicle's motion, for example, using ego-motion estimation (e.g., 3D translation and 3D rotation of a camera, and therefore the vehicle body). The estimation of rotation and translation may be determined based on the results of analyzing images acquired by one or more image acquisition devices together with information from other sensors or devices (such as inertial sensors and velocity sensors). For example, the inertial sensor may include an accelerometer or other preferred sensor configured to measure changes in the translation and / or rotation of the vehicle body. The vehicle may include a velocity sensor to measure the vehicle's speed.

[0269] In some embodiments, the egomotion of the camera (and therefore the vehicle) may be estimated based on an optical flow analysis of the captured images. The optical flow analysis of a series of images identifies the motion of pixels in the series of images, and based on the identified motion, the motion of the vehicle is determined. The egomotion may be accumulated along the road segments over time to reconstruct a trajectory associated with the road segments the vehicle has traveled.

[0270] Data collected by multiple vehicles during multiple drives at different times along a road segment (e.g., reconstructed trajectories) may be used to construct a road model (e.g., including target trajectories) included in the sparse data map 800. The data collected by multiple vehicles during multiple drives at different times along a road segment may be averaged to improve the accuracy of the model. In some embodiments, data on the 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 for generating and / or updating the road model.

[0271] The geometry of the reconstructed trajectory along the road segment (and the geometry of 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 obtained from the 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 several meters ahead of the vehicle's current position. This position is where the vehicle is expected to travel after a predetermined period. This operation may be repeated for each frame, and simultaneously, the vehicle may calculate the camera's egomotion (rotation and translation). In each frame or image, a short-range model of the desired path is generated by the vehicle in a reference frame mounted on the camera. Multiple short-range models may be joined together to obtain a three-dimensional model of the road in some coordinate frame, which may be any coordinate frame or a predetermined coordinate frame. The three-dimensional model of the road may then be fitted to a spline, which may contain or connect one or more polynomials of a suitable degree.

[0272] One or more detection modules may be used to complete a short-distance road model in each frame. For example, a bottom-up lane detection module may be used. A bottom-up lane detection module can be useful when lane markings are drawn on the road. This module may find edges in the image and assemble these edges together to form lane markings. A second module may be used in conjunction with the bottom-up lane detection module. The second module may be an end-to-end deep neural network, which may be trained to predict an accurate short-distance path from the input image. In either module, the road model may be detected within the image coordinate frame and transformed into a three-dimensional space that can be virtually mounted on the camera.

[0273] While the modeling method for reconstructed trajectories may result in the accumulation of errors containing noise components due to the accumulation of egomotion over long periods, such errors may not be significant as the generated model may still provide sufficient accuracy for regional-scale navigation. Furthermore, it is possible to offset the accumulated errors by using external information sources such as satellite imagery or geodetic surveys. For example, the disclosed system and method may use a GNSS receiver to offset the accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed system and method may enable steering applications that are less dependent on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed system may use GNSS signals solely for the purpose of indexing a database.

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

[0275] As mentioned above, a 3D road model may be constructed by detecting short-distance sections and stitching them together. This stitching can be achieved by computing a six-stage ego-motion model using video and / or images captured by cameras, data from inertial sensors reflecting vehicle movement, and the host vehicle's speed signal. The cumulative error can be sufficiently small over a certain local range, such as around 100 meters. All of this may be completed in a single drive on a specific road segment.

[0276] In some embodiments, multiple drives may be used to average the resulting models and further improve accuracy. The same vehicle may travel the same route multiple times, and the model data collected by multiple vehicles may be transmitted to a central server. In any case, a matching procedure may be performed to identify and average overlapping models in order to generate a target trajectory. Once the constructed model (including, for example, the target trajectory) satisfies the convergence criteria, it may be used for driving. Subsequent drives may be used for further model improvement and to adapt to changes in infrastructure.

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

[0278] Information related to potential landmarks may also be identified and transmitted to a central server. For example, the disclosed systems and methods may identify one or more physical characteristics of a potential landmark based on one or more images containing the landmark. These physical characteristics may include the physical size of the landmark (e.g., height, width), the distance from the vehicle to the landmark, the distance from the landmark to the previous landmark, the lateral position of the landmark (e.g., the location of the landmark relative to the driving lane), the GPS coordinates of the landmark, the type of landmark, and the identification of text related to the landmark. For example, a vehicle may analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

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

[0280] In some embodiments, multiple autonomous vehicles traveling on a road segment may communicate with a server. A vehicle (or client) may generate a curve in an arbitrary coordinate frame that traces its own drive (for example, by aggregating egomotions). A vehicle may detect landmarks and place them in the same frame. A vehicle may upload the curve and landmarks to the server. The server may collect data from multiple drives from the vehicles and generate an integrated road model. For example, as discussed below with respect to Figure 19, the server may use the uploaded curve and landmarks to generate a sparse map with an integrated road model.

[0281] The server may distribute this model to clients (e.g., vehicles). For example, the server may distribute a sparse map to one or more vehicles. The server may update the model continuously or periodically when it receives new data from the vehicles. For example, the server may process the new data and evaluate whether the data contains information that should trigger the server to update the data or create new data. The server may distribute the updated model or update information to the vehicles in order to provide autonomous vehicle navigation.

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

[0283] The server may distribute the updated model (or updated portion of the model) to one or more vehicles traveling on the road segment to which the model update is associated. The server may also distribute the updated model to vehicles that are scheduled to travel on the road segment to which the model update is associated, or to vehicles whose travel plans include that road segment. For example, while an autonomous vehicle is traveling along another road segment before reaching the road segment associated with a particular update, the server may distribute the update information or the updated model to the autonomous vehicle before it reaches that road segment.

[0284] In some embodiments, a remote server may collect trajectories and landmarks from multiple clients (e.g., vehicles traveling along a common road segment). The server may use landmarks to match curves and create an average road model based on the trajectories collected from multiple vehicles. The server may also calculate a road graph and the most likely path at each intersection or connection point of the road segment. For example, the remote server may align the collected trajectories to generate a crowdsourced sparse map from them.

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

[0286] In some embodiments, the server may identify changes to the model, such as construction, detours, new signs, or removal of signs, based on 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 deliver model update information or the updated model to the vehicle to provide automated navigation. For example, as will be discussed further below, the server may use crowdsourced data to filter out “ghost” landmarks detected by the vehicle.

[0287] In some embodiments, the server may analyze driver interventions during autonomous driving. The server may analyze data received from the vehicle at the time and location of the intervention, and / or data received prior to the time of the intervention. The server may identify some portion of the data that triggered or is closely related to the intervention, such as data indicating the setting of a temporary lane closure, or data indicating the presence of pedestrians on the road. The server may update the model based on the identified data. For example, the server may modify one or more trajectories stored in the model.

[0288] Figure 12 is a schematic diagram of a system that generates a sparse map using crowdsourcing (and distributes the crowdsourced sparse map for navigation). Figure 12 shows a road segment 1200 containing one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 (shown in Figure 12 as appearing simultaneously on road segment 1200) may travel on road segment 1200 simultaneously or at different times. At least one of vehicles 1205, 1210, 1215, 1220, and 1225 may be an autonomous vehicle. For simplicity in this example, we assume that all of vehicles 1205, 1210, 1215, 1220, and 1225 are autonomous vehicles.

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

[0290] As vehicles 1205, 1210, 1215, 1220, and 1225 travel along road segment 1200, navigation information collected (e.g., detected, sensed, or measured) by vehicles 1205, 1210, 1215, 1220, and 1225 may be transmitted to server 1230. In some embodiments, the navigation information may be associated with a common road segment 1200. The navigation information may include trajectories associated with each of vehicles 1205, 1210, 1215, 1220, and 1225 as each vehicle travels along road segment 1200. In some embodiments, the trajectories may be reconstructed based on data detected by various sensors and devices provided on vehicle 1205. For example, the trajectories may be reconstructed based on at least one of accelerometer data, velocity 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 such as accelerometers and the speed of the vehicle 1205 detected by a velocity sensor. Furthermore, in some embodiments, the trajectory may be determined (for example, by a processor mounted on each of the vehicles 1205, 1210, 1215, 1220, and 1225) based on the detected camera egomotion which may exhibit three-dimensional translation and / or three-dimensional rotation (or rotational motion). The camera (and therefore the vehicle body) egomotion may be identified from an analysis of one or more images captured by the camera.

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

[0292] In some embodiments, the navigation information transmitted from vehicles 1205, 1210, 1215, 1220, and 1225 to the server 1230 may include data relating to the road surface, road geometry, or road profile. The geometry of road segment 1200 may include lane configuration and / or landmarks. The lane configuration may include the total number of lanes in road segment 1200, the type of lane (e.g., one-way lane, two-way lane, driving lane, passing lane, etc.), lane markings, lane width, etc. In some embodiments, the navigation information may include lane designations, for example, which of several lanes the vehicle will be traveling in. For example, the lane designation may be associated with a numerical value, such that "3" indicates the vehicle will be traveling in the third lane from the left or right. As another example, the lane designation may be associated with a text value, such that "center lane" indicates the vehicle will be traveling in the center lane.

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

[0294] As described above, the road navigation model for autonomous vehicles may be contained in a sparse map (for example, sparse map 800 shown in Figure 8). Sparse map 800 may contain a sparse record of data relating to the road geometry and / or roadside landmarks, which can provide sufficient information to guide the autonomous vehicle's automatic navigation without requiring excessive data storage. In some embodiments, the road navigation model for autonomous vehicles may be stored separately from sparse map 800, and when the model is run for navigation, it may use map data from sparse map 800. In some embodiments, the road navigation model for autonomous vehicles may use the map data contained in sparse map 800 to determine a target trajectory along road segment 1200 in order to guide the automatic navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles traveling along road segment 1200 later. For example, when a road navigation model for an autonomous vehicle is executed by a processor included in the navigation system of vehicle 1205, the model may cause the processor to compare the trajectory determined based on the navigation information received from vehicle 1205 with a predetermined trajectory included in the sparse map 800 to confirm and / or correct the current driving course of vehicle 1205.

[0295] In road navigation models for autonomous vehicles, the geometric structure of road features or target trajectories may be encoded by curves in three-dimensional space. In one embodiment, these curves may be three-dimensional splines containing one or more connected three-dimensional polynomials. As those skilled in the art will understand, a spline may be a numerical function piecewise defined by a set of polynomials for fitting data. Splines for fitting three-dimensional road geometric data may include linear splines (first order), quadratic splines (second order), cubic splines (cubic order), or any other splines (other orders), or combinations thereof. The splines may contain one or more three-dimensional polynomials of various orders that connect (e.g., fit) data points of the three-dimensional road geometric data. In some embodiments, road navigation models for autonomous vehicles may include three-dimensional splines corresponding to a common road segment (e.g., road segment 1200) or target trajectories along the lanes of road segment 1200.

[0296] As described above, the road navigation model for autonomous vehicles included in the sparse map may include other information, such as identification information for at least one landmark along road segment 1200. The landmark may be visible within the field of view of a camera (e.g., camera 122) installed in each of the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, camera 122 may capture an image of the landmark. A processor provided in vehicle 1205 (e.g., processors 180, 190, or processing unit 110) may process the image of the landmark to extract the landmark identification information. The landmark identification information, rather than the actual image of the landmark, may be stored in the sparse map 800. The landmark identification information may require far less storage space than the actual image. Other sensors or systems (e.g., a GPS system) may also provide specific identification information for the landmark (e.g., the location of the landmark). Landmarks may include at least one of the following: traffic signs, arrow markings, lane markings, dashed lane markings, traffic lights, stop lines, directional signs (e.g., highway exit signs with arrows indicating direction, highway signs with arrows indicating another direction or location), landmark beacons, or lampposts. A landmark beacon is a device (e.g., an RFID device) installed along a road segment that transmits or reflects signals to a receiver installed on a vehicle, and when a vehicle passes by this device, the beacon received by the vehicle and the location of the device (determined, for example, from the device's GPS location) may be used as landmarks to be included in the autonomous vehicle road navigation model and / or sparse map 800.

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

[0298] Landmark identification information may include the size of the landmark. A processor in a vehicle (e.g., 1205) may estimate the physical size of the landmark based on an analysis of the image. Server 1230 may receive multiple estimates of the physical size of the same landmark from different vehicles and different drives. Server 1230 may average the various estimates to arrive at the physical size of the landmark and store that size in the road model. The physical size estimate may further be used to determine or estimate the distance from the vehicle to the landmark. The distance to the landmark may be estimated based on the vehicle's current speed and an expanded scale based on the location of the landmark appearing in the image relative to the camera's expanded focus. For example, the distance to the landmark may be estimated as Z = V × dt × R / D, where V is the vehicle's speed, R is the distance in the image from the landmark to the expanded focus at time t1, and D is the change in distance for the landmark in the image from t1 to t2. dt represents (t2-t1). For example, the distance to a landmark can be estimated by Z = V × dt × R / D, where V is the vehicle speed, 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. Another equivalent formula, for example, Z = V × ω / Δω, can be used to estimate the distance to a landmark, where V is the vehicle speed, ω is the image length (similar to the width of an object), and Δω is the change in image length per unit time.

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

[0300] For landmarks of unknown dimensions, the distance to the landmark can be estimated by tracking feature points on the landmark across consecutive frames. For example, a specific feature appearing on a speed limit sign may be tracked across two or more image frames. Based on these tracked features, a distance distribution for each feature point may be generated. The distance estimate may be extracted from the distance distribution. For example, the distance that appears most frequently in the distance distribution may be used as the distance estimate. Alternatively, the mean of the distance distribution may be used as the distance estimate.

[0301] Figure 13 shows an exemplary road navigation model for an autonomous vehicle represented by several three-dimensional splines 1301, 1302, and 1303. The curves 1301, 1302, and 1303 shown in Figure 13 are for illustrative purposes only. Each spline may contain one or more three-dimensional polynomials connecting several data points 1310. Each polynomial may be a linear polynomial, a quadratic polynomial, a cubic polynomial, or any suitable combination of polynomials of different degrees. Each data point 1310 may be associated with navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with landmark-related data (e.g., landmark size, location, and identification information) and / or road signature profiles (e.g., road geometry, road unevenness profile, road curvature profile, road width profile). In some embodiments, some of the data points 1310 may be associated with data related to landmarks, and others may be associated with data related to load signature profiles.

[0302] Figure 14 shows raw location data 1410 (e.g., GPS data) received from five separate drives. A drive may be separated from other drives if different vehicles travel on it simultaneously, if the same vehicle travels on it at different times, or if different vehicles travel on it at different times. To account for errors in the location data 1410 and the different positions of multiple vehicles in the same lane (e.g., one vehicle may be traveling closer to the left side of the lane than another), the server 1230 may use one or more statistical methods to generate a map framework 1420 and determine whether changes in the raw location data 1410 represent actual differences or statistical errors. Each route included in the map framework 1420 may be reassociated with the raw data 1410 that formed that route. For example, the route between A and B included in the map framework 1420 may be associated with raw data 1410 from drives 2, 3, 4, and 5, but not with raw data from drive 1. The framework 1420 does not need to be detailed enough to be used for vehicle navigation (unlike the splines mentioned above, for example, because it combines drives from multiple lanes on the same road), but it can provide useful topological information and can be used to define intersections.

[0303] Figure 15 shows an example in which further detail may be generated for a sparse map contained in a segment of the map framework (e.g., segments A-B included in framework 1420). As shown in Figure 15, data (e.g., egomotion data, road marking data, etc.) may be indicated according to a location S (or S1 or S2) along the drive. Server 1230 may identify landmarks for the sparse map by identifying unique matches between landmarks 1501, 1503, and 1505 of drive 1510 and landmarks 1507 and 1509 of drive 1520. Such a matching algorithm may identify landmarks 1511, 1513, and 1515. However, those 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 matches. Server 1230 may align the drives longitudinally to align the matched landmarks. For example, server 1230 may select one drive (e.g., drive 1520) as the reference drive and then move and / or stretch elastically one or more other drives (e.g., drive 1510) to align with it.

[0304] Figure 16 shows an example of landmark data being compiled for use in a sparse map. In the example in Figure 16, landmark 1610 includes a road sign. The example in Figure 16 further shows data from multiple drives 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the example in Figure 16, the data from drive 1613 consists of "ghost" landmarks, and server 1230 may identify this data as such because none of drives 1601, 1603, 1605, 1607, 1609, and 1611 contain landmark identification information near the landmarks identified in drive 1613. Therefore, server 1230 may accept a potential landmark if the ratio of images in which landmarks appear to images in which landmarks do not appear exceeds a threshold, and / or may reject a potential landmark if the ratio of images in which landmarks appear to images in which landmarks do not appear exceeds a threshold.

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

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

[0307] System 1700 also includes a server (for example, server 1230). Server 1230 may receive drive segments 1705 from the vehicle and recombine these drive segments 1705 into a single drive 1707. Such a method may reduce the bandwidth requirements when transferring data between the vehicle and the server, and may also allow the server to store data related to the entire drive.

[0308] Figure 18 shows System 1700 of Figure 17, further configured to crowdsource sparse maps. As shown in Figure 17, System 1700 includes a vehicle 1810, which captures drive data using, for example, a camera (which generates, for example, ego-motion data, traffic sign data, or road data) and a location device (for example, a GPS locator). As shown in Figure 17, the vehicle 1810 divides the collected data into multiple drive segments (labeled “DS1 1”, “DS2 1”, and “DSN 1” in Figure 18). Server 1230 then receives the drive segments and reconstructs a single drive (labeled “Drive 1” in Figure 18) from these received segments.

[0309] As further shown in Figure 18, system 1700 also receives data from additional vehicles. For example, vehicle 1820 also acquires drive data using, for example, a camera (which generates, for example, ego-motion data, traffic sign data, or road data) and a location device (for example, a GPS locator). Similar to vehicle 1810, vehicle 1820 divides the collected data into multiple drive segments (shown as "DS1 2", "DS2 2", and "DSN 2" in Figure 18). Server 1230 then receives the drive segments and reconstructs a single drive (shown as "Drive 2" in Figure 18) from these received segments. Any number of additional vehicles may be used. For example, Figure 18 also includes vehicle N, which acquires drive data, divides that data into multiple drive segments (shown as "DS1 N", "DS2 N", and "DSN N" in Figure 18), and sends them to server 1230 to reconstruct a single drive (shown as "Drive N" in Figure 18).

[0310] As shown in Figure 18, server 1230 may construct a sparse map (indicated as "Map") using reconstructed drives (e.g., "Drive 1", "Drive 2", and "Drive N") collected from multiple vehicles (e.g., "Vehicle 1" (also indicated as Vehicle 1810), "Vehicle 2" (also indicated as Vehicle 1820), and "Vehicle N").

[0311] Figure 19 is a flowchart of an exemplary process 1900 for generating a sparse map for autonomous vehicle navigation along road segments. Process 1900 may be performed by one or more processing devices included in server 1230.

[0312] Process 1900 may include a step (step 1905) of receiving multiple images acquired when one or more vehicles travel along a road segment. Server 1230 may receive images from cameras included in one or more of the 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 also receive de-redundant image data, with redundancy removed by a processor mounted on vehicle 1205, as described above with respect to Figure 17.

[0313] Process 1900 may further include a step (step 1910) of identifying at least one line representation of a road surface feature extending along a road segment based on multiple images. Each line representation may represent a path along the road segment that substantially corresponds to a road surface feature. For example, server 1230 may analyze environmental images received from camera 122 to identify road edges or lane markings and determine the 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. Server 1230 may determine the trajectory of travel of vehicle 1205 based on camera egomotion (e.g., three-dimensional translational motion and / or three-dimensional rotational motion) received in step 1905.

[0314] Process 1900 may also include a step (step 1915) of identifying multiple landmarks associated with a road segment based on multiple images. For example, server 1230 may analyze environmental images received from camera 122 to identify one or more landmarks, such as road signs, along road segment 1200. Server 1230 may identify landmarks using an analysis of multiple images acquired when one or more vehicles travel along the road segment. To enable crowdsourcing, the analysis may include rules for accepting and excluding landmarks that may be associated with the road segment. For example, the analysis may include a step of 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 a step of excluding 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.

[0315] Process 1900 may include other operations or stages performed by Server 1230. For example, navigation information may include a target trajectory for a vehicle to travel along a road segment, and Process 1900 may include a stage in which Server 1230 clusters vehicle trajectories related to multiple vehicles traveling along a road segment and determines a target trajectory based on the clustered vehicle trajectories, as will be discussed in more detail below. The stage of clustering vehicle trajectories may include a stage in which Server 1230 clusters multiple trajectories related to vehicles traveling along a road segment based on at least one of the absolute direction of travel of the vehicles or the lane designation of the vehicles to form multiple clusters. The stage of generating a target trajectory may include a stage in which Server 1230 averages the clustered trajectories. As a further example, Process 1900 may include a stage of aligning the data received in Stage 1905. Other processes or stages performed by Server 1230 may also be included in Process 1900, as described above.

[0316] The disclosed systems and methods may include other features. For example, the disclosed systems may use local coordinates rather than global coordinates. In the case of autonomous driving, some systems may represent data in world coordinates. For example, coordinates using the longitude and latitude of the Earth's surface may be used. The host vehicle may determine its position and orientation relative to the map in order to use the map for steering. It seems natural to use an onboard GPS device to position the vehicle on the map and to determine the rotational transformation between the vehicle's reference frame and the world reference frame (e.g., north, east, and south). Once the vehicle's reference frame is aligned with the map reference frame, the desired route can then be represented in the vehicle's reference frame, and steering commands can be calculated or generated.

[0317] The disclosed systems and methods may enable autonomous vehicle navigation (e.g., steering control) using a low-footprint model, which may be collected by the autonomous vehicle itself without the assistance of expensive surveying equipment. To support autonomous navigation (e.g., steering applications), the road model may include a sparse map with the road's geometry, lane configuration, and landmarks, which can be used to determine the position or location of a 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 a vehicle traveling on the road. This data may include sensing data, a trajectory reconstructed based on the sensing data, and / or a suggested trajectory that may represent a change in the reconstructed trajectory. As discussed below, the server can then transmit the model to the vehicle or other vehicles traveling later on the road for use in autonomous navigation.

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

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

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

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

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

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

[0324] A road model and / or sparse map may store trajectories associated with road segments. These trajectories may be called target trajectories and are provided to autonomous vehicles for automated navigation. Target trajectories may be received from multiple vehicles and may be generated based on actual trajectories or recommended trajectories (actual trajectories with some modifications) received from multiple vehicles. Target trajectories contained in a road model or sparse map may be constantly updated (e.g., averaged) with new trajectories received from other vehicles.

[0325] A vehicle traveling on a road segment may collect data using various sensors. This data may include landmarks, road signature profiles, vehicle motion (e.g., accelerometer data, velocity data), and vehicle position (e.g., GPS data), and may either reconstruct the actual trajectory itself or transmit the data to a server, which will then reconstruct the actual trajectory for the vehicle. In some embodiments, the vehicle may transmit data related to the trajectory (e.g., curves in an arbitrary reference frame), landmark data, and lane designations along the travel route to the server 1230. Different vehicles traveling on multiple drives along the same road segment may have separate trajectories. The server 1230 may identify routes or trajectories associated with each lane from the trajectories received from the vehicles through a clustering process.

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

[0327] Clustering may be performed using various criteria. In some embodiments, all drives included in a cluster may be similar with respect to the absolute direction of travel along road segment 1200. The absolute direction of travel may be obtained from GPS signals received by vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the absolute direction of travel may be obtained using dead reckoning. Dead reckoning may be used to determine the current position, and therefore the direction of travel of vehicles 1205, 1210, 1215, 1220, and 1225, using previously determined positions, estimated speeds, etc., as can be understood by those skilled in the art. Trajectories clustered by absolute direction of travel may be useful in identifying routes along the roadway.

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

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

[0330] In some embodiments, landmarks may define a consistent arc length between different drives, which may be used to align the trajectory with the lane. In some embodiments, lane markings before and after intersections may be used to align the trajectory with the lane.

[0331] To organize the lanes from these trajectories, server 1230 may select a reference frame for any lane. Server 1230 may map partially overlapping lanes to the selected reference frame. Server 1230 may continue mapping until all lanes are within the same reference frame. Adjacent lanes may be aligned as if they were the same lane, and then they may be moved laterally.

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

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

[0334] For locating an autonomous vehicle, the disclosed systems and methods may use an extended Kalman filter. The vehicle's position may be determined based on 3D position data and / or 3D orientation data, and a prediction of the vehicle's future position ahead of its current position based on the accumulation of egomotion data. Vehicle locating may be corrected or adjusted by image observation of landmarks. For example, if the vehicle detects a landmark in an image captured by a camera, the landmark may be compared to a known landmark stored in the road model or sparse map 800. Known landmarks are obtained by having a known position (e.g., GPS data) along a target trajectory stored in the road model and / or sparse map 800. Based on the current speed and the image of the landmark, the distance from the vehicle to the landmark can be estimated. The vehicle's position along the target trajectory may be adjusted based on the distance to the landmark and the known position of the landmark (stored in the road model or sparse map 800). The location / location data of landmarks stored in the road model and / or sparse map 800 (e.g., average value from multiple drives) may be assumed to be accurate.

[0335] In some embodiments, the disclosed system may form a closed-loop subsystem in which the autonomous vehicle may be navigated (e.g., by steering the steering wheel of the autonomous vehicle) to reach a desired point (e.g., 1.3 seconds ahead of a stored point) using position estimation of the vehicle's six degrees of freedom (e.g., 3D position data and 3D orientation data). The positions of the six degrees of freedom may then be estimated using data measured from steering and actual navigation.

[0336] In some embodiments, roadside poles, such as lampposts and utility poles for power lines or cable lines, may be used as landmarks to locate a vehicle. Other landmarks, such as traffic signs, signals, road arrows, and stop lines, as well as static features or signatures of objects along road segments, may also be used as landmarks to locate a vehicle. When using poles for location, observations in the x-direction (i.e., the field of view from the vehicle) may be used rather than observations in the y-direction (i.e., the distance to the pole), because the lower part of the pole may be obstructed, and in some cases the pole may not be on the road surface.

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

[0338] The navigation system 2300 may include a communication unit 2305 configured to communicate with the server 1230 via a 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 mounted on 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 an autonomous vehicle road navigation model received from the server 1230. The road profile sensor 2330 may include different types of devices for measuring different types of road profiles, such as road surface irregularities, road width, road elevation, and road curvature. For example, the road profile sensor 2330 may include a device that measures the movement of the vehicle 2305's suspension in order to obtain a road surface profile. In some embodiments, the road profile sensor 2330 may include a radar sensor that measures the distance from the vehicle 1205 to the roadside (e.g., a roadside barrier), thereby measuring the width of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the elevation rise and fall of the road. In some embodiments, the road profile sensor 2330 may include a device configured to measure the curvature of the road. For example, a camera (e.g., camera 122 or another camera) may be used to capture an image of the road showing the curvature. The vehicle 1205 may use such an image to detect the curvature of the road.

[0339] At least one processor 2315 may be programmed to receive at least one environmental image related to the vehicle 1205 from the camera 122. At least one processor 2315 may analyze at least one environmental image to identify navigation information related to the vehicle 1205. The navigation information may include a trajectory related to the vehicle 1205's travel along the road segment 1200. At least one processor 2315 may determine the trajectory based on the movement of the camera 122 (and therefore the vehicle), such as three-dimensional translational motion and three-dimensional rotational motion. In some embodiments, at least one processor 2315 may identify the translational and rotational motion of the camera 122 based on an analysis of multiple images acquired by the camera 122. In some embodiments, the navigation information may include lane designation information (e.g., which lane the vehicle 1205 travels in 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 autonomous vehicles, and this information may be transmitted again from server 1230 to vehicle 1205 to provide automated navigation guidance to vehicle 1205.

[0340] At least one processor 2315 may also be programmed to transmit navigation information from the vehicle 1205 to the server 1230. In some embodiments, the navigation information may be transmitted to the server 1230 along with road information. The road location information may include at least one of the following: GPS signals received by the GPS unit 2310, landmark information, road geometry, lane information, etc. At least one processor 2315 may receive an autonomous vehicle road navigation model or a portion of that 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 the updated portion of the model. At least one processor 2315 may cause at least one navigation operation by the vehicle 1205 (for example, turning, braking, accelerating, overtaking another vehicle) based on a received road navigation model for an autonomous vehicle or an updated portion of the model.

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

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

[0343] [Navigation based on sparse maps]

[0344] As mentioned above, a road navigation model for autonomous vehicles, including the sparse map 800, may include multiple mapped lane markings and multiple mapped objects / features associated with road segments. These mapped lane markings, objects, and features may be used when the autonomous vehicle navigates, as will be discussed in more detail below. For example, in some embodiments, mapped objects and features may be used to locate the host vehicle's position relative to the map (e.g., relative to a mapped target trajectory). Mapped lane markings may be used (e.g., as a check) to determine the lateral position and / or orientation relative to a planned or target trajectory. Using this positional information, the autonomous vehicle may be able to adjust its direction of travel to match the direction of the target trajectory at the determined location.

[0345] Vehicle 200 may be configured to detect lane markings in a given road segment. The road segment may include any markings on the road for guiding vehicle traffic on the roadway. For example, lane markings may be solid or dashed lines defining the edges of the driving lane. Lane markings may also include double lines, such as double solid lines, double dashed lines, or combinations of solid and dashed lines, indicating, for example, whether overtaking is permitted in an adjacent lane. Lane markings may also include highway entrance and exit markings, which may show, for example, deceleration lanes for exit ramps, or dotted lines indicating that a lane is for turning only or that the lane ends. These markings may further indicate work zones, temporary lane changes, routes through intersections, median strips, dedicated lanes (e.g., bicycle lanes, HOV lanes, etc.), or various other markings (e.g., pedestrian crossings, speed bumps, railway crossings, stop lines, etc.).

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

[0347] Figures 24A to 24D show exemplary point locations for representing specific lane markings that can be detected by vehicle 200. Similar to the landmarks described above, vehicle 200 may use various image recognition algorithms or software to identify the locations of points in the captured image. For example, vehicle 200 may recognize the locations of a set of edge points, corner points, or various other points associated with a specific lane marking. Figure 24A shows a solid lane marking 2410 that can be detected by vehicle 200. The lane marking 2410 represents the outer edge of the roadway and may be represented by a solid white line. As shown in Figure 24A, vehicle 200 may be configured to detect multiple edge location points 2411 along the lane marking. These location points 2411 may be collected to represent the lane marking at any interval sufficient to create a lane marking mapped in a sparse map. For example, lane markings may be represented by one point every meter of the detected edge, one point every 5 meters of the detected edge, or other preferred intervals. In some embodiments, this interval may be determined by other factors rather than a predetermined interval, such as based on a point where vehicle 200 has the highest confidence ranking regarding the location of the detected point. Figure 24A shows edge position points on the inner edge of lane marking 2410, but points may be collected on the outer edge of the line, or along both edges. Furthermore, although Figure 24A shows a single line, similar edge points may be detected for a double solid line as well. For example, point 2411 may be detected along one or both edges of a solid line.

[0348] Vehicle 200 may represent lane markings differently depending on the type or shape of the lane markings. Figure 24B shows an exemplary dashed lane marking 2420 that can be detected by vehicle 200. Rather than identifying edge points as shown in Figure 24A, the vehicle may detect a series of corner points 2421 that represent the corners of the dashed lane markings that define the entire boundary of the dashed line. Figure 24B shows that each corner of a given dashed marking is localized, but vehicle 200 may detect or upload a subset of these points shown in the figure. For example, vehicle 200 may detect the leading edge or leading corner of a given dashed marking, or it may detect the two corner points closest to the inside of the lane. Furthermore, it is not necessary to capture all dashed line markings; for example, vehicle 200 may capture and / or record points representing samples of dashed line markings (e.g., every other, every three, every five, etc.) or points representing dashed line markings at predetermined intervals (e.g., every meter, every five meters, every ten meters, etc.). Corner points may also be detected for similar lane markings, such as markings indicating that a lane is for an exit ramp, markings indicating that a particular lane ends, or various other lane markings that may have detectable corner points. Corner points may also be detected for lane markings consisting of double dashed lines or a combination of solid and dashed lines.

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

[0350] In some embodiments, the vehicle 200 may identify points representing other features, such as the intersection of two intersecting lane markings. Figure 24D shows an exemplary point representing the intersection of two lane markings 2460 and 2465. The vehicle 200 may calculate the intersection 2466, which represents the intersection between the two lane markings. For example, one of the lane markings 2460 or 2465 may represent a train crossing area or other crossing area within a road segment. Although the lane markings 2460 and 2465 are shown intersecting perpendicularly to each other, various other configurations may be detected. For example, the lane markings 2460 and 2465 may intersect at other angles, and one or both of these lane markings may terminate at the intersection 2466. Similar techniques may be applied to intersections of dashed lines or other types of lane markings. In addition to intersection 2466, various other points 2467 may also be detected, providing further information regarding the direction of lane markings 2460 and 2465.

[0351] Vehicle 200 may associate actual coordinates with each detected point of the lane markings. For example, a position identifier containing the coordinates of each point may be generated and uploaded to a server for mapping the lane markings. The position identifier may further include other identifying information about these points, such as whether they represent corner points, edge points, or center points. Thus, vehicle 200 may be configured to determine the actual position of each point based on an analysis of the image. For example, vehicle 200 may detect other features in the image, such as the various landmarks described above, to determine the actual position of the lane markings. This may include determining the position of the lane markings in the image relative to the detected landmarks, or determining the position of the vehicle based on the detected landmarks and then determining the distance from the vehicle (or the vehicle's target trajectory) to the lane markings. If landmarks are unavailable, the position of the lane marking points may be determined relative to the vehicle's position determined by dead reckoning. The actual coordinates included in the location identifier may be expressed as absolute coordinates (e.g., coordinates in latitude / longitude), or they may be related to other features, such as being based on the longitudinal position along the target trajectory and the lateral distance from the target trajectory. The location identifier may then be uploaded to a server to generate lane markings mapped in a navigation model (e.g., sparse map 800). In some embodiments, the server may construct splines representing lane markings on road segments. Alternatively, the vehicle 200 may generate splines and upload them to the server so that these splines are recorded in the navigation model.

[0352] Figure 24E shows an exemplary navigation model or sparse map of a corresponding road segment, including mapped lane markings. The sparse map may include a target trajectory 2475 for a vehicle to travel along the road segment. As described above, the target trajectory 2475 may represent the ideal path a vehicle would take when traveling along the corresponding road segment, and may be located at other points on the road (e.g., the road's centerline). The target trajectory 2475 may be calculated in one of the various ways described above, for example, based on a collection of two or more reconstructed trajectories (e.g., weighted combinations) of vehicles traveling along the same road segment.

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

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

[0355] The generation of mapped lane markings in a sparse map may also include error detection and / or mitigation based on anomalies present in the image or the actual lane markings themselves. Figure 24F shows an exemplary anomaly 2495 related to the detection of lane markings 2490. Anomaly 2495 may appear in the image captured by the vehicle 200 due to, for example, an object obstructing the camera's view of the lane markings, or dust on the lens. In some cases, the anomaly may be attributable to the lane markings themselves, such as being damaged or worn, or partially covered by, for example, dirt, debris, water, snow, or other material on the road. Anomaly 2495 may result in the vehicle 200 detecting an incorrect point 2491. The sparse map 800 may correct the mapped lane markings and eliminate errors. In some embodiments, the vehicle 200 may detect an incorrect point 2491, for example, by detecting an anomaly 2495 in the image, or by identifying an error based on lane marking points detected before and after the anomaly. Based on the detection of the anomaly, the vehicle may exclude point 2491 and adjust it to conform to other detected points. In other embodiments, after the point has been uploaded, the error may be corrected by determining that the point is outside the expected threshold, for example, based on other points uploaded during the same trip, or based on a collection of data from previous trips along the same road segment.

[0356] Lane markings mapped in the navigation model and / or sparse map may also be used for navigation by autonomous vehicles traveling on the corresponding roadways. For example, a vehicle navigating along a target trajectory may periodically use the mapped lane markings in the sparse map to align the lane markings themselves with the target trajectory. As described above, between landmarks, a vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to identify its own egomotion and estimate its position relative to the target trajectory. Since errors can accumulate over time, the accuracy of determining the vehicle's position relative to the target trajectory may gradually decrease. Therefore, the vehicle can use the lane markings (and their known positions) present in the sparse map 800 to reduce errors in dead reckoning during position determination. In this way, the identified lane markings included in the sparse map 800 can play a key role in navigation, enabling the precise determination of the vehicle's position relative to the target trajectory.

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

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

[0359] The vehicle may also have its longitudinal position determined, which is represented by element 2520 and is located along the target trajectory. The longitudinal position 2520 may be determined from image 2500, for example, by detecting landmark 2521 in image 2500 and comparing the measured position with the position of a known landmark stored in the road model or sparse map 800. The vehicle's position along the target trajectory may then be determined based on the distance to the landmark and the known position of the landmark. The longitudinal position 2520 may also be determined from images other than the image used to determine the position of the lane markings. For example, the longitudinal position 2520 may be determined by detecting landmarks in images taken simultaneously or nearly simultaneously from other cameras in the image acquisition unit 120 that capture image 2500. In some cases, the vehicle may not be near any landmark or other reference point for determining the longitudinal position 2520. In such cases, the vehicle may navigate based on dead reckoning, and thus use sensors to identify its own egomotion and estimate its longitudinal position 2520 relative to the target trajectory. The vehicle may also determine a distance 2530 representing the actual distance between the vehicle and lane markings 2510 observed in one or more captured images. Camera angle, vehicle speed, vehicle width, or various other factors may be taken into consideration when determining the distance 2530.

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

[0361] Figures 25C and 25D provide diagrams related to another example of locating the host vehicle based on mapped landmarks / objects / features in a sparse map during navigation. Figure 25C conceptually represents a series of images captured from a vehicle navigating along road segment 2560. In this example, road segment 2560 includes a straight section of a highway divided into two lanes, described by road edges 2561 and 2562 and a center lane marking 2563. As shown, the host vehicle is navigating along lane 2564, which is related to the mapped target trajectory 2565. Therefore, in an ideal situation (and without influences such as the presence of a target vehicle or object on the roadway), the host vehicle, navigating along lane 2564 of road segment 2560, should be tracking the mapped target trajectory 2565 in close proximity. In reality, the host vehicle, navigating along the mapped target trajectory 2565, may experience drift. For effective and safe navigation, this drift should be maintained within acceptable limits (e.g., a lateral displacement of + / - 10 cm from the target trajectory 2565, or any other suitable threshold). To ensure that the host vehicle follows the target trajectory 2565 by periodically taking drift into account and making any necessary course corrections, the disclosed navigation system may be capable of using one or more mapped features / objects contained in a sparse map to determine the position of the host vehicle along the target trajectory 2565 (e.g., determining the lateral and longitudinal positions of the host vehicle relative to the target trajectory 2565).

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

[0363] These changes in the image space representation of an object, such as sign 2566, may be used to determine the position of a host vehicle whose location along a target trajectory has been identified. For example, as described herein, any detectable object or feature, such as a semantic feature like sign 2566 or a detectable and non-semantic feature, may be identified by one or more collecting vehicles that have previously traveled along a road segment (e.g., road segment 2560). A mapping server may collect drive information collected from multiple vehicles, aggregate and correlate the information, and generate a sparse map, for example, a target trajectory 2565 for lane 2564 of road segment 2560. The sparse map may also store the location of sign 2566 (along with type information, etc.). During navigation (e.g., before entering road segment 2560), the host vehicle may be supplied with a map tile containing the sparse map for road segment 2560. To navigate in lane 2564 of road segment 2560, the host vehicle may follow the mapped target trajectory 2565.

[0364] The mapped representation of marker 2566 may be used by the host vehicle to determine its own position relative to the target trajectory. For example, a camera on the host vehicle may capture an image 2570 of the host vehicle's environment, which may include an image representation of marker 2566 having a specific size and a specific XY image position, as shown in Figure 25D. This size and XY image position can be used to determine the position of the host vehicle relative to the target trajectory 2565. For example, based on a sparse map containing the representation of marker 2566, the host vehicle's navigation processor may determine, in response to the host vehicle traveling along the target trajectory 2565, that the representation of marker 2566 should appear in the captured image such that the center of marker 2566 moves along line 2567 (in image space). If an acquired image, such as image 2570, shows a center (or other reference point) that is shifted from line 2567 (e.g., the expected image spatial trajectory), then the host vehicle navigation system can determine that, at the time of the acquired image, it was not positioned on the target trajectory 2565. However, the navigation processor can determine from the image an appropriate navigation correction to return the host vehicle to the target trajectory 2565. For example, if the analysis results show that the image position of marker 2566 is shifted by a distance of 2572 to the left of the expected image spatial position on line 2567, then the navigation processor may cause the host vehicle to change direction (e.g., change the steering angle) to move the host vehicle by a distance of 2573 to the left. In this way, each acquired image can be used as part of a feedback loop process, and as a result, the difference between the observed image position of marker 2566 and the expected image trajectory 2567 may be minimized, ensuring that the host vehicle continues to follow the target trajectory 2565 with little deviation.Naturally, the more mapped objects available, the more frequently the described localization method can be used, which can reduce or eliminate deviations due to drift from the target trajectory 2565.

[0365] The processing described above may be useful for detecting the lateral orientation or displacement of the host vehicle relative to the target trajectory. Positioning the host vehicle relative to the target trajectory 2565 may also include determining the longitudinal position of the target vehicle along the target trajectory. For example, the captured image 2570 includes a representation of a marker 2566 having a specific image size (e.g., a 2D XY pixel region). Since it travels through the image space along line 2567 (for example, as shown in Figure 25C, the size of the marker increases progressively), this size can be compared to the expected image size of the mapped marker 2566. Based on the image size of the marker 2566 in image 2570, and based on the expected size progression in the image space related to the mapped target trajectory 2565, the host vehicle can determine its longitudinal position relative to the target trajectory 2565 (at the time image 2570 was captured). As described above, this longitudinal position, combined with any lateral displacement relative to the target trajectory 2565, enables the full positioning of the host vehicle in relation to the target trajectory 2565, since the host vehicle navigates along the road 2560.

[0366] Figures 25C and 25D provide just one example of the disclosed localization method using one mapped object and one target trajectory. In other examples, there may be many more target trajectories (e.g., one target trajectory for each feasible lane, such as in a multi-lane highway, urban street, or complex intersection), and many more mapped objects available for localization. For example, a sparse map representing an urban environment may contain numerous objects available for localization at every meter.

[0367] Figure 26A is a flowchart illustrating an exemplary process 2600A for mapping lane markings for use in autonomous vehicle navigation, consistent with the embodiments disclosed. In step 2610, process 2600A may include a step of receiving two or more location identifiers associated with the detected lane markings. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifiers may include the actual coordinate location of the point associated with the detected lane marking, as described above with respect to Figure 24E. In some embodiments, the location identifiers may also include other data, such as additional information about the road segment or lane markings. Additional data, such as accelerometer data, speed data, landmark data, road geometry or profile data, vehicle positioning data, egomotion data, or various other forms of data described above, may also be received in step 2610. Location identifiers may be generated by vehicles such as vehicles 1205, 1210, 1215, 1220, and 1225, based on images captured by these vehicles. For example, identifiers may be determined based on the acquisition of at least one image representing the host vehicle's environment from a camera associated with the host vehicle, the analysis of at least one image to detect lane markings included in the host vehicle's environment, and the analysis of at least one image to determine the position of the detected lane markings relative to the location associated with the host vehicle. As described above, lane markings may include various different marking types, and location identifiers may correspond to various points related to lane markings. For example, if the detected lane markings are part of dashed line markings representing lane boundaries, these points may correspond to the corners of the detected lane markings. If the detected lane markings are part of solid line markings representing lane boundaries, these points may correspond to the edges of the detected lane markings at the various intervals described above. In some embodiments, these points may correspond to the centerlines of the detected lane markings, as shown in Figure 24C, or to the intersection of two intersecting lane markings and at least two other points associated with the intersecting lane markings, as shown in Figure 24D.

[0368] In step 2612, process 2600A may include a step of associating the detected lane markings with the corresponding road segments. For example, server 1230 may analyze the actual coordinates or other information received in step 2610 and compare these coordinates or other information with location information stored in the road navigation model for autonomous vehicles. Server 1230 may determine the road segment in the model corresponding to the actual road segment in which the lane markings were detected.

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

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

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

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

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

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

[0375] In step 2623, process 2600B may include a step of determining the expected lateral distance to a lane marking based on the determined longitudinal position of the host vehicle along the target trajectory and based on two or more position identifiers associated with at least one lane marking. For example, vehicle 200 may determine the expected lateral distance to a lane marking using sparse map 800. As shown in Figure 25B, the longitudinal position 2520 along the target trajectory 2555 may be determined in step 2622. Using sparse map 800, vehicle 200 can determine the expected distance 2540 to the mapped lane marking 2550 corresponding to the longitudinal position 2520.

[0376] In step 2624, process 2600B may include a step of analyzing at least one image to identify at least one lane marking. The vehicle 200 may identify the lane marking in the image using various image recognition techniques or algorithms, as described above, for example. For example, the lane marking 2510 may be detected by image analysis of image 2500, as shown in Figure 25A.

[0377] In step 2625, process 2600B may include a step of determining the actual lateral distance to at least one lane marking based on the analysis of at least one image. For example, the vehicle may determine a distance 2530 representing the actual distance between the vehicle and the lane marking 2510, as shown in Figure 25A. Camera angle, vehicle speed, vehicle width, camera position relative to the vehicle, or various other factors may be taken into consideration when determining the distance 2530.

[0378] In step 2626, process 2600B may include a step of determining an autopilot action for the host vehicle based on the difference between the expected lateral distance to at least one lane marking and the determined actual lateral distance to at least one lane marking. For example, as described above with respect to Figure 25B, the vehicle 200 may compare the actual distance 2530 with the expected distance 2540. The difference between the actual distance and the expected distance may indicate the error (and its magnitude) between the actual position of the vehicle and the target trajectory the vehicle will follow. Therefore, the vehicle may determine an autopilot action or other automatic action based on this difference. For example, as shown in Figure 25B, if the actual distance 2530 is less than the expected distance 2540, the vehicle may determine an autopilot action to guide the vehicle to the left away from the lane marking 2510. Thus, the vehicle's position relative to the target trajectory can be corrected. For example, process 2600B may be used to improve the vehicle's navigation between landmarks.

[0379] Processes 2600A and 2600B provide merely examples of techniques that may be used to navigate a host vehicle using the disclosed sparse map. In other examples, processes consistent with those described in relation to Figures 25C and 25D may also be used.

[0380] [Ego-motion correction for LIDAR output]

[0381] As described elsewhere in this disclosure, a vehicle or driver may navigate the vehicle along a road segment in an environment. The vehicle may collect various types of road-related information. For example, the vehicle may be equipped with a LiDAR system that collects LiDAR reflections from one or more objects in its environment, and / or one or more cameras that capture images from the environment. Due to the movement of the host vehicle itself, a non-moving object (e.g., a lamppost) may be moving in the field of view of the LiDAR system, which may appear as a moving object in the collected data (e.g., a point cloud generated based on the reflection of laser radiation from an object), even if the object itself is not moving. Thus, in some cases, in complex and cluttered scenes, small and slowly moving objects may be difficult to detect. Also, conventional LiDAR systems may misidentify smaller objects as moving objects. Similarly, conventional LiDAR systems may misidentify a moving object (e.g., a target vehicle) moving with the host vehicle as a non-moving object. Therefore, it may be desirable to reduce or eliminate the possibility of misidentifying a non-moving object as a moving object (or vice versa). This disclosure describes a system and method for relating multiple LIDAR points across two or more frames and for eliminating depth effects caused by the ego-motion of a host vehicle. After such eff...

Claims

1. A navigation system for a host vehicle, wherein the navigation system is The host vehicle receives a sparse map from an entity located remotely from the host vehicle, which is associated with at least one road segment on which the host vehicle travels, wherein the sparse map includes a plurality of mapped navigation landmarks and at least one target trajectory, both of which are generated based on drive information collected from a plurality of vehicles that have previously traveled along the at least one road segment; The host vehicle receives point cloud information from a LiDAR system within the host vehicle, and the point cloud information represents the distance to various objects in the host vehicle's environment; The received point cloud information is compared with at least one of the plurality of mapped navigation landmarks in the sparse map to provide LIDAR-based positioning of the host vehicle relative to the at least one target trajectory; Based on the LIDAR-based positioning of the host vehicle with respect to the at least one target trajectory, determine at least one navigation operation for the host vehicle; and Causing the host vehicle to perform at least one of the aforementioned navigation operations A processor programmed to do so A navigation system equipped with the following features.

2. The LIDAR-based positioning of the host vehicle relative to the at least one target trajectory includes determining the current position of the host vehicle relative to the at least one target trajectory. The navigation system according to claim 1.

3. The at least one navigation operation includes maintaining the current direction of travel for the host vehicle. The navigation system according to claim 1 or 2.

4. The at least one navigation operation includes changing the current direction of travel for the host vehicle in order to reduce the distance between the host vehicle and the at least one target trajectory. The navigation system according to any one of claims 1 to 3.

5. The LIDAR-based positioning of the host vehicle with respect to the at least one target trajectory is as follows: Identifying at least two representations of the plurality of mapped navigation landmarks in the point cloud information; Based on the point cloud information, determine the relative distance between the reference point associated with the host vehicle and each of the at least two of the plurality of mapped navigation landmarks; and The current position of the host vehicle relative to the at least one target trajectory is determined based on the relative distance between the reference point associated with the host vehicle and each of the at least two of the plurality of mapped navigation landmarks. including, The navigation system according to claim 1.

6. The reference point associated with the host vehicle is located within the LIDAR system of the host vehicle. The navigation system according to claim 5.

7. The reference point associated with the host vehicle is positioned by a camera inside the host vehicle. The navigation system according to claim 5.

8. The identification of at least two representations of the plurality of mapped navigation landmarks in the point cloud information is performed by a trained neural network. The navigation system according to any one of claims 5 to 7.

9. The point cloud information includes at least a first LIDAR scan point cloud and a second LIDAR scan point cloud, and the LIDAR-based positioning of the host vehicle relative to the at least one target trajectory is as follows: Identifying at least one representation of the plurality of mapped navigation landmarks in the first LIDAR scanning point cloud; Based on the first LiDAR scanning point cloud, determine a first relative distance between a reference point associated with the host vehicle and at least one of the plurality of mapped navigation landmarks; Identifying at least one representation of the plurality of mapped navigation landmarks in the second LIDAR scanning point cloud; Based on the second LiDAR scanning point cloud, determine a second relative distance between the reference point associated with the host vehicle and at least one of the plurality of mapped navigation landmarks; and Based on the first relative distance and the second relative distance, the current position of the host vehicle relative to the at least one target trajectory is determined. The navigation system according to claim 1, including the following:

10. The LIDAR-based positioning of the host vehicle with respect to at least one target trajectory further includes taking into account the ego-motion of the host vehicle between a first time associated with acquiring the first LIDAR scan point cloud and a second time associated with acquiring the second LIDAR scan point cloud. The navigation system according to claim 9.

11. Identifying at least one representation of the plurality of mapped navigation landmarks in the first LiDAR scanning point cloud, and identifying at least one representation of the plurality of mapped navigation landmarks in the second LiDAR scanning point cloud, are performed by a trained neural network. The navigation system according to claim 9 or 10.

12. The LIDAR-based positioning of the host vehicle with respect to the at least one target trajectory is as follows: Identifying at least one representation of the plurality of mapped navigation landmarks in the point cloud information; Comparing one or more aspects of the at least one of the multiple mapped navigation landmarks represented in the point cloud information with the set of at least one expected features of the multiple mapped navigation landmarks determined based on the sparse map; and Based on the above comparison, the current position of the host vehicle relative to the at least one target trajectory is determined. The navigation system according to claim 1, including the following:

13. The set of features includes at least one of the size or two-dimensional location of the at least one of the multiple mapped navigation landmarks in the point cloud information, within a LiDAR scan frame. The navigation system according to claim 12.

14. The one or more embodiments of the plurality of mapped navigation landmarks include at least one of the size or two-dimensional location of the representation of the plurality of mapped navigation landmarks in the point cloud information within a LiDAR scan frame. The navigation system according to claim 12 or 13.

15. Identifying at least one representation of the plurality of mapped navigation landmarks in the point cloud information is performed by a trained neural network. The navigation system according to any one of claims 12 to 14.

16. The point cloud information is limited to point cloud depth information associated with one or more vertical objects in the environment of the host vehicle. The navigation system according to any one of claims 1 to 15.

17. The aforementioned vertical object includes at least one of the following: a signpost, a ramp post, a road barrier post, a guardrail support, or a tree trunk. The navigation system according to claim 16.

18. The aforementioned at least one target trajectory is represented by a three-dimensional spline in the sparse map. The navigation system according to any one of claims 1 to 17.

19. At least some of the aforementioned mapped navigation landmarks are represented in the sparse map by the location of the points and the classification of the object type. The navigation system according to any one of claims 1 to 18.

20. At least some of the aforementioned mapped navigation landmarks are represented in the sparse map by the positions of a plurality of points and one or more object descriptors. The navigation system according to any one of claims 1 to 18.

21. The aforementioned at least one processor is The host vehicle receives at least one captured image from a camera inside the host vehicle, which includes a representation of at least a part of the host vehicle's environment; In the at least one captured image, identify the representation of the plurality of mapped navigation landmarks; and Based on the sparse map and the representation of the plurality of mapped navigation landmarks in the at least one captured image, the position of the host vehicle relative to the at least one target trajectory is determined, and image-based localization is provided. It is further programmed The navigation system according to any one of claims 1 to 20.

22. The determination of the at least one navigation operation for the host vehicle is based on a combination of the LIDAR-based localization and the image-based localization. The navigation system according to claim 21.

23. The at least one processor is further programmed to determine the difference between the LIDAR-based localization and the image-based localization. The navigation system according to claim 21 or 22.

24. The at least one processor is further programmed to perform at least one repair operation if the difference exceeds a predetermined threshold. The navigation system according to claim 23.

25. The repair operation includes at least one of the following: slowing down the host vehicle, stopping the host vehicle, or issuing a warning about a system anomaly. The navigation system according to claim 24.

26. The at least one processor is further programmed to apply weights to each of the LIDAR-based localization and the image-based localization. The navigation system according to any one of claims 23 to 25.

27. The aforementioned weights are determined based on the environmental conditions detected in the host vehicle's environment. The navigation system according to claim 26.

28. A method for controlling a navigation system for a host vehicle, wherein the method is A step of receiving a sparse map from an entity located remotely from the host vehicle, associated with at least one road segment through which the host vehicle travels, wherein the sparse map includes a plurality of mapped navigation landmarks and at least one target trajectory, and both the plurality of mapped navigation landmarks and the at least one target trajectory are generated based on drive information collected from a plurality of vehicles that have previously traveled along the at least one road segment. The step of receiving point cloud information from the LIDAR system in the host vehicle, wherein the point cloud information represents the distance to various objects in the environment of the host vehicle, and the step of The steps include comparing the received point cloud information with at least one of the plurality of mapped navigation landmarks in the sparse map, and providing LIDAR-based positioning of the host vehicle relative to the at least one target trajectory, A step of determining at least one navigation operation for the host vehicle based on the LIDAR-based positioning of the host vehicle with respect to the at least one target trajectory, The step of causing the host vehicle to perform at least one of the aforementioned navigation operations. A method for providing this.

29. A program, which, when executed by at least one processor, causes the at least one processor to: A sparse map associated with at least one road segment on which the host vehicle travels is received from an entity located remotely from the host vehicle, wherein the sparse map includes a plurality of mapped navigation landmarks and at least one target trajectory, both of which are generated based on drive information collected from a plurality of vehicles that have previously traveled along the at least one road segment; The host vehicle receives point cloud information from its LiDAR system, the point cloud information representing the distance to various objects in the host vehicle's environment; The received point cloud information is compared with at least one of the plurality of mapped navigation landmarks in the sparse map to provide LIDAR-based positioning of the host vehicle relative to the at least one target trajectory; Based on the LIDAR-based positioning of the host vehicle with respect to the at least one target trajectory, determine at least one navigation operation for the host vehicle; and Causing the host vehicle to perform at least one of the aforementioned navigation operations program.

Images