Systems and methods for vehicle navigation

Abstract

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

Description

[Technical Field]

[0001] [CROSS-REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 957,000, filed January 3, 2020, and U.S. Provisional Patent Application No. 63 / 082,619, filed September 24, 2020. The foregoing applications are incorporated herein by reference in their entireties.

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

[0003] As technology continues to develop, the goal of fully autonomous vehicles capable of navigating roadways is approaching. An autonomous vehicle may need to consider various factors and make appropriate decisions based on those factors to safely and accurately reach its intended destination. For example, an autonomous vehicle may need to process and interpret visual information (e.g., information captured from a camera) and may also use information obtained from other sources (e.g., a GPS unit, speed sensors, accelerometers, suspension sensors, etc.). At the same time, to navigate to its destination, an autonomous vehicle may need to identify its position on a particular roadway (e.g., a particular 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. Utilizing and interpreting the vast amount of information an autonomous vehicle collects as it navigates to its destination poses many design challenges. The vast amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that an autonomous vehicle may need to analyze, access, and / or store poses challenges that may limit or even adversely affect autonomous navigation in practice. Furthermore, if an autonomous vehicle were to navigate using traditional mapping technologies, the vast amount of data required to store and update maps poses significant challenges. Summary of the Invention

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

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

[0006] In one embodiment, a method for detecting an object in an environment of a host vehicle may comprise determining at least one indicator of egomotion of the host vehicle. The method may also comprise receiving, from a LIDAR system associated with the host vehicle, a first point cloud including a first representation of at least a portion of the object based on a first LIDAR scan of a field of view of the LIDAR system. The method may further comprise receiving, from the LIDAR system, a second point cloud including a second representation of at least a portion of the object based on a second LIDAR scan of a field of view of the LIDAR system. The method may also comprise determining a velocity of the object based on the at least one indicator of egomotion of the host vehicle and based on a comparison of the first point cloud including the first representation of at least a portion of the object with 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, from an entity remotely located relative to the vehicle, a sparse map associated with at least one road segment traversed by the vehicle. The sparse map may include a plurality of mapped navigation landmarks and at least one target trajectory. Both the plurality of mapped navigation landmarks and the at least one target trajectory may be generated based on driving 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 within the vehicle. The point cloud information may represent distances to various objects in the vehicle's environment. The at least one processor may further be programmed to compare the received point cloud information with at least one of the plurality of mapped navigation landmarks in the sparse map to provide a LIDAR-based localization of the vehicle relative to the at least one target trajectory. The at least one processor may also be programmed to determine at least one navigation operation for the vehicle based on the LIDAR-based localization of the vehicle relative to the at least one target trajectory. The at least one processor may be further 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, from an entity remotely located relative to the vehicle, a sparse map associated with at least one road segment traversed by the vehicle. The sparse map may include a plurality of mapped navigation landmarks and at least one target trajectory. Both the plurality of mapped navigation landmarks and the at least one target trajectory may be generated based on driving 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 the at least one target trajectory. The method may further include determining at least one navigation operation for the vehicle based on the LIDAR-based localization of the vehicle relative to the at least one target trajectory. The method may also include causing the vehicle to perform the at least one navigation operation.

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

[0010] In one embodiment, a method for determining a navigation operation for a host vehicle may comprise receiving point cloud information from a LIDAR system within the host vehicle. The point cloud information may represent distances to a plurality of objects in an environment of the host vehicle. The method may also comprise associating the point cloud information with at least one captured image to provide per-pixel depth information for one or more regions of the at least one captured image. The method may further comprise determining at least one navigation operation for the host vehicle based on the per-pixel depth information for the one or more regions of the at least one captured image, and causing the host vehicle to perform the 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 representing an environment of the host vehicle from a camera within 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 within the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be located at a second location relative to the host vehicle, which may be different from the first location. The field of view of the camera may at least partially overlap with the field of view of the LIDAR system to provide a shared field of view. The at least one processor may further be programmed to analyze the at least one captured image and the received point cloud information to detect one or more objects in the shared field of view. 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 at least one processor may also be programmed to determine whether a difference in perspective between the first location of the camera and the second location of the LIDAR system accounts for one or more detected objects represented in only one of the at least one captured image or the received point cloud information. The at least one processor may be programmed to cause at least one remedial action to be performed on the host vehicle based on the one or more detected objects if the difference in perspective does not account for one or more detected objects represented in only one of the at least one captured image or the received point cloud information. The at least one processor may be programmed to determine at least one navigation action to be performed on the host vehicle based on the one or more detected objects if the difference in perspective does not account for one or more detected objects represented in only one of the at least one captured image or the received point cloud information, and cause the host vehicle to perform the at least one navigation action.

[0012] In one embodiment, a method for determining a navigation operation for a host vehicle may include receiving at least one captured image representing an environment of the host vehicle from a camera within 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 within the host vehicle. The point cloud information may represent distances to various objects in the environment of the host vehicle. The LIDAR system may be located at a second location relative to the host vehicle, which may be different from the first location. The field of view of the camera may at least partially overlap with the field of view of the LIDAR system to provide a shared field of view area. The method may further include analyzing the at least one captured image and the received point cloud information to detect one or more objects in the shared field of view 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 a difference in perspective between the first location of the camera and the second location of the LIDAR system accounts for one or more detected objects represented in only one of the at least one captured image or the received point cloud information. The method may further comprise, if the viewpoint difference does not account for one or more detected objects represented in only one of the at least one captured image or the received point cloud information, then causing at least one remedial action to be performed. The method may also comprise, if the viewpoint difference does not account for one or more detected objects represented in only one of the at least one captured image or the received point cloud information, then determining at least one navigation action to be performed by the host vehicle based on the one or more detected objects, and causing the host vehicle to perform the at least one navigation action.

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

[0014] In one embodiment, a method for determining a navigation operation for a host vehicle may include receiving at least one captured center image from a center camera within the host vehicle, the captured center image including a representation of at least a portion of the host vehicle's environment, from a left surround camera within the host vehicle, and receiving at least one captured right surround image from a right surround camera within the host vehicle, the captured center image including a representation of at least a portion of the host vehicle's environment. The field of view of the center camera at least partially overlaps 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 center 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 center image based on an analysis of the at least one captured center image, the at least one captured left surround image, and the at least one captured right surround image. The generated output includes per-pixel depth information for at least one region of the captured center image. The method may further comprise causing 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] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that, when executed by at least one processing device, may perform any of the methods described herein.

[0016] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the scope of the claims. [Brief explanation of the drawings]

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

[0018] [Figure 1] FIG. 1 is a schematic diagram of an exemplary system consistent with disclosed embodiments.

[0019] [Figure 2A] FIG. 1 is a schematic side view of an exemplary vehicle including a system consistent with disclosed embodiments.

[0020] [Figure 2B] FIG. 2B is a schematic top view of the vehicle and system shown in FIG. 2A consistent with disclosed embodiments.

[0021] [Figure 2C] FIG. 10 is a schematic top view of another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0022] [Figure 2D] FIG. 10 is a schematic top view of yet another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0023] [Figure 2E] FIG. 10 is a schematic top view of yet another embodiment of a vehicle including a system consistent with disclosed embodiments.

[0024] [Figure 2F] FIG. 1 is a schematic diagram of an exemplary vehicle control system consistent with disclosed embodiments.

[0025] [Figure 3A] FIG. 1 is a schematic diagram of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with disclosed embodiments.

[0026] [Figure 3B]FIG. 1 illustrates an example camera mount configured to be placed against the windshield of a vehicle behind a rearview mirror, consistent with disclosed embodiments.

[0027] [Figure 3C] FIG. 3C is another view of the camera mount shown in FIG. 3B consistent with disclosed embodiments.

[0028] [Figure 3D] FIG. 1 illustrates an example camera mount configured to be placed against the windshield of a vehicle behind a rearview mirror, consistent with disclosed embodiments.

[0029] [Figure 4] FIG. 1 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with disclosed embodiments.

[0030] [Figure 5A] 1 is a flowchart illustrating an exemplary process for generating one or more navigational responses based on monocular image analysis consistent with disclosed embodiments.

[0031] [Figure 5B] 1 is a flowchart illustrating an example process for detecting one or more vehicles and / or one or more pedestrians in a set of images consistent with disclosed embodiments.

[0032] [Figure 5C] 1 is a flowchart illustrating an example process for detecting road markings and / or lane geometry information in a set of images consistent with disclosed embodiments.

[0033] [Figure 5D]1 is a flowchart illustrating an exemplary process for detecting traffic lights in a set of images consistent with disclosed embodiments.

[0034] [Figure 5E] 1 is a flowchart illustrating an example process for generating one or more navigational responses based on a vehicle path, consistent with disclosed embodiments.

[0035] [Figure 5F] 10 is a flowchart illustrating an example process for determining whether a leading vehicle is changing lanes, consistent with disclosed embodiments.

[0036] [Figure 6] 1 is a flowchart illustrating an example process for generating one or more navigation responses based on stereo image analysis consistent with disclosed embodiments.

[0037] [Figure 7] 10 is a flowchart illustrating an exemplary process for generating one or more navigational responses based on an analysis of three sets of images, consistent with disclosed embodiments.

[0038] [Figure 8] FIG. 1 illustrates a sparse map for providing autonomous vehicle navigation consistent with disclosed embodiments.

[0039] [Figure 9A] FIG. 10 illustrates a polynomial representation of a portion of a road segment consistent with disclosed embodiments.

[0040] [Figure 9B] FIG. 2 illustrates a curve in three-dimensional space representing a target trajectory of a vehicle for a particular road segment, included in a sparse map consistent with disclosed embodiments.

[0041] [Figure 10] FIG. 10 illustrates example landmarks that may be included in a sparse map consistent with disclosed embodiments.

[0042] [Figure 11A] FIG. 10 illustrates a polynomial representation of a trajectory consistent with disclosed embodiments.

[0043] [Figure 11B] FIG. 10 illustrates a target trajectory along a multi-lane road consistent with disclosed embodiments. [Figure 11C] FIG. 10 illustrates a target trajectory along a multi-lane road consistent with disclosed embodiments.

[0044] [Figure 11D] FIG. 1 illustrates an exemplary road signature profile consistent with disclosed embodiments.

[0045] [Figure 12] FIG. 1 is a schematic diagram of a system for using crowdsourced data received from multiple vehicles for autonomous vehicle navigation consistent with disclosed embodiments.

[0046] [Figure 13] FIG. 1 illustrates an exemplary road navigation model for an autonomous vehicle represented by 3D splines consistent with disclosed embodiments.

[0047] [Figure 14] FIG. 10 illustrates a map skeleton generated by combining location information from multiple drives consistent with disclosed embodiments.

[0048] [Figure 15] FIG. 10 illustrates an example of longitudinal alignment of exemplary landmarks and two drives consistent with disclosed embodiments.

[0049] [Figure 16] FIG. 10 illustrates an example of longitudinal alignment of exemplary signs as landmarks and multiple drives consistent with disclosed embodiments.

[0050] [Figure 17] FIG. 1 is a schematic diagram of a system for generating driving data using a camera, a vehicle, and a server consistent with disclosed embodiments.

[0051] [Figure 18] FIG. 1 is a schematic diagram of a system for crowdsourcing a sparse map consistent with disclosed embodiments.

[0052] [Figure 19] 1 is a flowchart illustrating an example process for generating a sparse map for autonomous vehicle navigation along road segments consistent with disclosed embodiments.

[0053] [Figure 20] FIG. 1 illustrates a block diagram of a server consistent with disclosed embodiments.

[0054] [Figure 21] FIG. 1 illustrates a block diagram of a memory consistent with disclosed embodiments.

[0055] [Figure 22] FIG. 1 illustrates a process for clustering vehicle trajectories associated with a vehicle consistent with disclosed embodiments.

[0056] [Figure 23] FIG. 1 illustrates a vehicle navigation system that may be used for automated navigation consistent with disclosed embodiments.

[0057] [Figure 24A] FIG. 10 illustrates exemplary lane markings that may be detected consistent with disclosed embodiments. [Figure 24B] FIG. 10 illustrates exemplary lane markings that may be detected consistent with disclosed embodiments. [Figure 24C] FIG. 10 illustrates exemplary lane markings that may be detected consistent with disclosed embodiments. [Figure 24D] FIG. 10 illustrates exemplary lane markings that may be detected consistent with disclosed embodiments.

[0058] [Figure 24E] FIG. 1 illustrates an example mapped lane marking consistent with disclosed embodiments.

[0059] [Figure 24F] FIG. 10 illustrates an example anomaly associated with lane marking detection consistent with disclosed embodiments.

[0060] [Figure 25A] FIG. 1 illustrates an example image of a vehicle's surroundings for navigation based on mapped lane markings, consistent with disclosed embodiments.

[0061] [Figure 25B] FIG. 10 illustrates correction of a vehicle's lateral localization based on mapped lane markings in a road navigation model consistent with disclosed embodiments.

[0062] [Figure 25C] The mapped features contained in the sparse map are used to provide a conceptual representation of a localization technique for locating a host vehicle along a target trajectory. [Figure 25D] The mapped features contained in the sparse map are used to provide a conceptual representation of a localization technique for locating a host vehicle along a target trajectory.

[0063] [Figure 26A]1 is a flowchart illustrating an example process for mapping lane markings for use in automated vehicle navigation, consistent with disclosed embodiments.

[0064] [Figure 26B] 1 is a flowchart illustrating an exemplary process for autonomously navigating a host vehicle along a road segment using mapped lane markings, consistent with disclosed embodiments.

[0065] [Figure 27] 1 illustrates an exemplary system for determining the velocity of an object consistent with disclosed embodiments.

[0066] [Figure 28] 1 illustrates an exemplary server consistent with disclosed embodiments.

[0067] [Figure 29] 1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0068] [Figure 30A] 1 illustrates an exemplary object in a field of view associated with a navigation system consistent with disclosed embodiments.

[0069] [Figure 30B] 1 illustrates an exemplary object in a field of view associated with a navigation system consistent with disclosed embodiments.

[0070] [Figure 31] 1 is a flowchart illustrating an exemplary process for determining the velocity of an object consistent with disclosed embodiments.

[0071] [Figure 32] 1 illustrates an exemplary system for determining navigation operations for a host vehicle consistent with disclosed embodiments.

[0072] [Figure 33] 1 illustrates an exemplary server consistent with disclosed embodiments.

[0073] [Figure 34] 1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0074] [Figure 35A] 1 illustrates an example road segment consistent with disclosed embodiments.

[0075] [Figure 35B] 1 illustrates an example sparse map associated with an example road segment consistent with disclosed embodiments.

[0076] [Figure 35C] 1 illustrates an example road segment consistent with disclosed embodiments.

[0077] [Figure 36] 1 is a flowchart illustrating an example process for determining a navigation operation for a host vehicle consistent with disclosed embodiments.

[0078] [Figure 37] 1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0079] [Figure 38] 1 is a flowchart illustrating an example process for identifying a navigation operation for a host vehicle consistent with disclosed embodiments.

[0080] [Figure 39A] 1 illustrates exemplary point cloud information and images consistent with disclosed embodiments. [Figure 39B] 1 illustrates exemplary point cloud information and images consistent with disclosed embodiments.

[0081] [Figure 40]1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0082] [Figure 41] 1 is a flowchart illustrating an example process for identifying a navigation operation for a host vehicle consistent with disclosed embodiments.

[0083] [Figure 42] 1 illustrates a host vehicle in an exemplary environment consistent with disclosed embodiments.

[0084] [Figure 43] 1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0085] [Figure 44] 1 illustrates an exemplary vehicle consistent with disclosed embodiments.

[0086] [Figure 45] 1 is a flowchart illustrating an example process for identifying a navigation operation for a host vehicle consistent with disclosed embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0087] In the following detailed description, reference is made to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar parts. While several exemplary embodiments are described herein, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, and changes may be made to the components shown in the drawings, and the exemplary methods described herein may be modified by substituting, rearranging, deleting, or adding steps to the disclosed methods. Therefore, the following detailed description is not limited to the disclosed embodiments and examples. Instead, the appropriate scope is defined by the appended claims.

[0088] [Autonomous driving car overview]

[0089] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that can make at least one navigation change without requiring driver input. A "navigation change" refers to a change in one or more of the vehicle's steering, braking, or acceleration. To be autonomous, a vehicle need not be fully automatic (e.g., completely operating without a driver or driver input). Rather, autonomous vehicles include those that can operate under driver control for certain periods and without driver control at other periods. Autonomous vehicles may also include vehicles that control only some aspects of vehicle navigation, such as steering (e.g., to maintain the vehicle's course between vehicle lane lines), but leave other aspects (e.g., braking) to the driver. In some cases, the autonomous vehicle may be responsible for some or all aspects of the vehicle's braking, speed control, and / or steering.

[0090] Because human drivers typically use visual cues and observations to control their vehicles, transportation infrastructure is built around that. Accordingly, lane markings, traffic signs, and traffic lights are all designed to provide visual information to drivers. Taking these design features of transportation infrastructure into account, an autonomous vehicle may include a camera and a processing unit that analyzes visual information captured from the vehicle's environment. Visual information may include, for example, driver-observable elements of the transportation infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) and other obstacles (e.g., other vehicles, pedestrians, debris, etc.). Furthermore, an autonomous vehicle may use stored information, such as information that provides a model of the vehicle's environment, when navigating. For example, a vehicle may use GPS data, sensor data (e.g., accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information related to its environment while the vehicle is traveling, and the vehicle (and other vehicles) may use the information to locate itself within the model.

[0091] In some embodiments of the present disclosure, an autonomous vehicle may use information acquired while navigating (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) while navigating. In still other embodiments, an autonomous vehicle may use a combination of information acquired while navigating and information acquired from past navigation. The following sections provide an overview of systems consistent with disclosed embodiments, followed by an overview of front-facing imaging systems and methods consistent with the systems. Subsequent sections disclose systems and methods for building, using, and updating sparse maps for autonomous vehicle navigation.

[0092] [System Overview]

[0093] FIG. 1 is a block diagram of a system 100 consistent with the disclosed exemplary embodiments. System 100 may include various components depending on the requirements of a particular implementation. In some embodiments, system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. Processing unit 110 may include one or more processing devices. In some embodiments, processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, image acquisition unit 120 may include any number of image acquisition devices and components depending on the requirements of a particular application. In some embodiments, image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as image capture device 122, image capture device 124, and image capture device 126. System 100 may also include a data interface 128 that communicatively connects processing device 110 to image acquisition device 120. For example, data interface 128 may include any one or more wired and / or wireless links for transmitting image data acquired by image acquisition device 120 to processing unit 110.

[0094] 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. Wireless transceiver 172 may transmit and / or receive data using any known standard (e.g., Wi-Fi, Bluetooth, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications to one or more servers located remotely from the host vehicle. Such transmissions may include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to facilitate adjusting the host vehicle's navigation in light of or together with target vehicles in the host vehicle's environment), or even broadcast transmissions to unspecified recipients in the vicinity of the transmitting vehicle.

[0095] Both application processor 180 and image processor 190 may include various types of processing devices. For example, either or both of application processor 180 and image processor 190 may include a microprocessor, a preprocessor (such as an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), support circuitry, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for executing applications and image processing and analysis. In some embodiments, application processor 180 and / or image processor 190 may include any type of single-core or multi-core processor, mobile device microcontroller, central processing unit, etc. Various processing devices may be used, including, for example, processors available from manufacturers such as Intel®, AMD®, etc., or GPUs available from manufacturers such as NVIDIA®, ATI®, etc., and may include various architectures (e.g., x86 processor, ARM®, etc.).

[0096] In some embodiments, application processor 180 and / or image processor 190 may include any of the EyeQ series of processor chips available from Mobileye®. These processor designs each include multiple processing units with local memory and instruction sets. Such processors may include video inputs for receiving image data from multiple image sensors and may also include video output capabilities. In one example, the EyeQ2® uses 90 nm technology and operates at 332 MHz. The EyeQ2® architecture consists of two floating-point, hyper-threaded 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, dual 16-bit video input and 18-bit video output controllers, a 16-channel DMA, and several peripherals. The MIPS34K CPU manages five VCEs, three VMPs and DMA, 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 calculations required by feature-rich bundled applications. In another example, the EyeQ3, a third-generation processor with six times more processing power than the EyeQ2, may be used in the disclosed embodiments. In another example, the EyeQ4 and / or EyeQ5 may be used in the disclosed embodiments. Of course, any new or future EyeQ processing devices may also be used with the disclosed embodiments.

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

[0098] In other embodiments, configuring the processing device may include storing executable instructions in a memory that the processing device can access 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 that controls multiple hardware-based components of a host vehicle.

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

[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 capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuits may be any number of circuits commonly known in the art, including, for example, cache circuits, power circuits, clock circuits, and input / output circuits. The memory may store software that, when executed by the processor, controls the operation of the system. The memory may include databases and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage, tape storage, removable storage, and other types of storage. In one example, the memory may be separate from the processing unit 110. In another example, the memory may be integrated 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), may control the operation of various aspects of system 100. For example, these memory units may contain various databases and image processing software, as well as trained systems such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage, tape storage, removable storage, and / or any other type of storage. In some embodiments, memory units 140, 150 may be separate from application processor 180 and / or image processor 190. In other embodiments, these memory units may be integrated into application processor 180 and / or image processor 190.

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

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

[0104] User interface 170 may include any device suitable for providing information to or receiving input from one or more users of system 100. In some embodiments, user interface 170 may include user input devices, including, for example, a touchscreen, a microphone, a keyboard, a pointer device, a trackwheel, a camera, a knob, a button, etc. Using such input devices, a user may provide information input or commands to system 100, for example, by typing instructions or information, providing voice commands, selecting on-screen menu options using buttons, a pointer, or eye tracking, or any other suitable technique for conveying information to system 100.

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

[0106] Map database 160 may include any type of database for storing map data useful to system 100. In some embodiments, map database 160 may include data related to the locations in a reference coordinate system of various items, including roads, water features, geographical features, businesses, particular points of interest, restaurants, gas stations, etc. Map database 160 may store not only the locations of such items but also descriptors related to these items, including, for example, names associated with any of the stored features. In some embodiments, map database 160 may be physically located with other components of system 100. Alternatively, or in addition, map database 160, or portions thereof, may be located remotely relative to other components of system 100 (e.g., processing unit 110). In such embodiments, information from map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, map database 160 may store sparse data models that include polynomial representations of particular road features (e.g., lane markings) or target trajectories of the host vehicle. Systems and methods for generating such maps are discussed below with reference to Figures 8-19.

[0107] Image capture devices 122, 124, and 126 may each include any type of device suitable for capturing at least one image from an environment. Furthermore, any number of image capture devices may be used to obtain images for input to the image processor. Some embodiments may include only one image capture device, while other embodiments may include two, three, or even four or more image capture devices. Image capture devices 122, 124, and 126 are further described below with reference to Figures 2B-2E.

[0108] System 100 or various components thereof may be incorporated into a variety of other platforms. In some embodiments, system 100 may be included in vehicle 200, as shown in FIG. 2A. For example, vehicle 200 may include processing unit 110 and any of the other components of system 100, as described above in connection with FIG. 1. In some embodiments, vehicle 200 may include only one image capture device (e.g., a camera), while other embodiments, such as those discussed in connection with FIGS. 2B-2E, may use multiple image capture devices. For example, as shown in FIG. 2A, either of image capture devices 122 and 124 of vehicle 200 may be part of an ADAS (Advanced Driver Assistance Systems) imaging system.

[0109] The image capture device included in vehicle 200 as part of image acquisition unit 120 may be located in any suitable location. In some embodiments, image capture device 122 may be located near the rearview mirror, as shown in Figures 2A-2E and 3A-3C. This location may provide a line of sight similar to that of the driver of vehicle 200 and may therefore be useful in determining what the driver can and cannot see. While image capture device 122 may be located anywhere near the rearview mirror, locating image capture device 122 on the driver's side of the mirror may be more useful in capturing images representative of the driver's field of view and / or line of sight.

[0110] Other locations for the image capture devices of image acquisition unit 120 may also be used. For example, image capture device 124 may be located on or in the bumper of vehicle 200. Such a location may be particularly suitable for an image capture device with a wide field of view. The line of sight of an image capture device located on a bumper may differ from the line of sight of the driver, and thus the bumper image capture device and the driver may not always see the same object. Image capture devices (e.g., image capture devices 122, 124, and 126) may also be located in other locations. For example, the image capture devices may be located on or in one or both side mirrors of vehicle 200, on the roof of vehicle 200, on the hood of vehicle 200, on the trunk of vehicle 200, on the sides of vehicle 200, attached to, located behind, or located in front of any of the window panes of vehicle 200, attached to or near lighting devices at the front and / or rear of vehicle 200, etc.

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

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

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

[0114] In some embodiments, system 100 may upload data according to a "high" privacy level, and during configuration, system 100 may transmit data (e.g., location information associated with a route, captured images, etc.) without any details about the 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 driver or owner, and instead may transmit data such as captured images and / or limited location information associated with a route.

[0115] Other privacy levels are contemplated. For example, system 100 may transmit data to a server according to a "medium" privacy level and include additional information not included in a "high" privacy level, such as the vehicle make and / or model and / or vehicle type (e.g., car, sport utility vehicle, truck, etc.). In some embodiments, system 100 may upload data according to a "low" privacy level. At a "low" privacy level setting, system 100 may upload data and include sufficient information to uniquely identify a particular vehicle, owner / driver, and / or part or all of the route traveled by the vehicle. Such "low" privacy level data may include, for example, one or more of the VIN, driver / owner name, vehicle origin prior to departure, vehicle's intended destination, vehicle make and / or model, vehicle type, etc.

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

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

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

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

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

[0121] First image capture device 122 may acquire a plurality of first images of a scene associated with vehicle 200. Each of the plurality of first images may be acquired as a series of image scan lines, which may be captured using a rolling shutter. Each scan line may include a plurality of pixels.

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

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

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

[0125] A rolling shutter can result in different rows of pixels being exposed and captured at different times, which can introduce skew and other image artifacts into the captured image frame. On the other hand, if image capture device 122 is configured to operate with a global or synchronous shutter, all pixels can be exposed to a common exposure period for the same amount of time. As a result, image data for a frame collected in a system using a global shutter represents a snapshot of the entire FOV (e.g., FOV 202) at a particular time. In contrast, when a rolling shutter is applied, each row in a frame is exposed and data is captured at a different time. Therefore, moving objects can appear distorted in an image capture device with a rolling shutter. This phenomenon is explained in more detail below.

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

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

[0128] Image capture devices 122, 124, and 126 may each be positioned at any suitable position and orientation relative to vehicle 200. The relative placement of image capture devices 122, 124, and 126 may be selected to facilitate fusing information obtained from the image capture devices. For example, in some embodiments, the FOV associated with image capture device 124 (e.g., FOV 204) may partially or completely overlap with the FOV associated with image capture device 122 (e.g., FOV 202) and the FOV associated with image capture device 126 (e.g., FOV 206).

[0129] Image capture devices 122, 124, and 126 may be positioned on vehicle 200 at any suitable relative height. In one example, there may be a height difference between image capture devices 122, 124, and 126, which may provide sufficient parallax information to enable stereo analysis. For example, as shown in FIG. 2A, the two image capture devices 122 and 124 are at different heights. For example, there may also be a lateral displacement difference between image capture devices 122, 124, and 126, which provides additional parallax information for stereo analysis by processing unit 110. The lateral displacement difference may be calculated as d xIn some embodiments, a forward or rearward displacement (e.g., range displacement) may exist between image capture devices 122, 124, and 126. For example, image capture device 122 may be located 0.5 to 2 meters behind image capture device 124 and / or image capture device 126, or further behind. This type of displacement may allow one of the image capture devices to fill in the potential blind spot of one or more of the other image capture devices.

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

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

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

[0133] The frame rate timing in image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, if one device includes an image sensor with a 640x480 resolution and another device includes an image sensor with a 1280x960 resolution, assuming both devices have similar line scan rates, the sensor with the higher resolution will require more time to acquire one frame of image data.

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

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

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

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

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

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

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

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

[0142] 2F is a schematic diagram of an exemplary vehicle control system consistent with disclosed embodiments. As shown in FIG. 2F , vehicle 200 may include a throttle device 220, a braking device 230, and a steering device 240. System 100 may provide inputs (e.g., control signals) to one or more of throttle device 220, braking device 230, and steering device 240 via one or more data links (e.g., any one or more wired and / or wireless links for data transmission). For example, based on analysis of images acquired by image capture devices 122, 124, and / or 126, system 100 may provide control signals to one or more of throttle device 220, braking device 230, and steering device 240 to navigate vehicle 200 (e.g., by causing acceleration, turning, lane shifting, etc.). Additionally, system 100 may receive inputs indicative of the operating state of vehicle 200 (e.g., speed, whether vehicle 200 is braking and / or turning, etc.) from one or more of throttle device 220, braking device 230, and steering device 240. Further details are provided below in connection with Figures 4-7.

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

[0144] 3B-3D are diagrams of an exemplary camera mount 370 configured to be positioned behind a rearview mirror (e.g., rearview mirror 310) and against a vehicle windshield, consistent with disclosed embodiments. As shown in FIG. 3B , camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be positioned behind glare shield 380, which may adhere directly to the vehicle windshield and may include a film material and / or anti-reflective material composition. For example, glare shield 380 may be positioned to align with a vehicle windshield having the same slope. In some embodiments, each of image capture devices 122, 124, and 126 may be positioned behind glare shield 380, for example, as shown in FIG. 3D . The disclosed embodiments are not limited to any particular configuration of image capture devices 122, 124, and 126, camera mount 370, and glare shield 380. FIG. 3C is a front view of the camera mount 370 shown in FIG. 3B.

[0145] As will be appreciated by those skilled in the art having the benefit of this disclosure, numerous variations and / or modifications can be made to the above-disclosed embodiments. For example, not all components are essential to the operation of system 100. Furthermore, any component may be located in any suitable portion of system 100, and these components may be rearranged in various configurations while still providing the functionality of the disclosed embodiments. Thus, the above-described configurations are examples, and regardless of the configuration described above, system 100 can provide a wide range of functionality to analyze the surroundings of vehicle 200 and navigate vehicle 200 in response to that analysis.

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

[0147] [Front multi-imaging system]

[0148] As described above, system 100 can provide driver assistance features using a multi-camera system. The multi-camera system may use one or more cameras facing forward of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side of the vehicle or the rear of the vehicle. In one embodiment, for example, system 100 may use a two-camera imaging system in which a first camera and a second camera (e.g., image capture devices 122 and 124) may be located at the front and / or sides of the vehicle (e.g., vehicle 200). The first camera may have a field of view that is larger than, smaller than, or partially overlaps the field of view of the second camera. Furthermore, the first camera may be connected to a first image processor that performs monocular image analysis of the image provided by the first camera, and the second camera may be connected to a second image processor that performs monocular image analysis of the image provided by the second camera. The outputs (e.g., processed information) of the first and second image processors may be combined. In some embodiments, the second image processor may receive images from both the first and second cameras to perform stereo analysis. In another embodiment, system 100 may use a three-camera imaging system in which each camera has a different field of view. Thus, such a system may make decisions based on information obtained from objects located at various distances to both the front and sides of the vehicle. References to monocular image analysis may refer to image analysis based on images captured from a single viewpoint (e.g., from a single camera). Stereo image analysis may refer to image analysis based on two or more images captured with one or more variations in image capture parameters. For example, captured images suitable for performing stereo image analysis may include images captured from two or more different positions, images captured from different fields of view, images captured using different focal lengths, images captured with parallax information, etc.

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

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

[0151] A three-camera system may offer certain performance characteristics. For example, some embodiments may include the ability to confirm the detection of an object by one camera based on the detection results of another camera. In the three-camera configuration described above, processing unit 110 may include, for example, three processing devices (e.g., three processor chips from the EyeQ series, as described above), each specialized in processing images captured by one or more of image capture 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 FOV camera and perform vision processing with the narrow FOV camera to detect, for example, other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. Additionally, the first processing device may calculate pixel disparity between the images from the main camera and the narrow FOV camera to create a 3D reconstruction of the environment of 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 and perform vision processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road features. Additionally, the second processing device may calculate camera displacement and, based on the displacement, calculate pixel disparity between successive images to create a 3D reconstruction (e.g., structure from motion (SfM)) of the scene. The second processing device may send the SfM-based 3D reconstruction to the first processing device, which is combined with the stereo 3D images.

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

[0155] In some embodiments, having streams of image-based information captured and processed independently may provide an opportunity for redundancy in the system, which may include, for example, using a first image capture device and processed images therefrom to confirm and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

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

[0157] Those skilled in the art will recognize that the above camera configurations, camera placements, camera numbers, camera locations, etc. are merely examples. These components, etc. described for 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] 4 is an exemplary functional block diagram of memories 140 and / or 150, which may be stored / programmed with instructions for performing one or more operations consistent with the disclosed embodiments. While reference is made below to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0159] 4 , 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 memory 140. Furthermore, application processor 180 and / or image processor 190 may execute instructions stored in any of modules 402, 404, 406, and 408 included in memory 140. Those skilled in the art will understand that references to processing unit 110 in the following description may refer to application processor 180 and image processor 190 individually or collectively. Accordingly, each stage of any of the following processes may be performed by one or more processing devices.

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

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

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

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

[0164] Additionally, 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] 5A is a flowchart illustrating an example process 500A for generating one or more navigation responses based on monocular image analysis, consistent with disclosed embodiments. At step 510, processing unit 110 may receive a plurality of images via data interface 128 between processing unit 110 and image acquisition unit 120. For example, a camera (e.g., image capture device 122 having field of view 202) included in image acquisition unit 120 may capture a plurality of images of an area ahead of vehicle 200 (or, for example, to the side or rear of the vehicle) and transmit these images to processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). At step 520, processing unit 110 may execute monocular image analysis module 402 to analyze the plurality of images, as described in further detail below in connection with FIGS. 5B-5D . By performing the analysis, processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, and traffic lights.

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

[0167] In step 530, processing unit 110 may execute navigation response module 408 to generate one or more navigation responses in vehicle 200 based on the analysis performed in step 520 and the techniques described above in connection with FIG. 4 . Navigation responses may include, for example, a turn, a lane shift, and an acceleration change. In some embodiments, processing unit 110 may generate one or more navigation responses using data obtained from execution of speed / acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof. For example, processing unit 110 may cause vehicle 200 to move across a lane and then accelerate, e.g., by sequentially sending control signals to steering device 240 and throttling device 220 of vehicle 200. Alternatively, processing unit 110 may cause vehicle 200 to brake and simultaneously move lanes, e.g., by simultaneously sending control signals to braking device 230 and steering device 240 of vehicle 200.

[0168] FIG. 5B is a flowchart illustrating an example process 500B for detecting one or more vehicles and / or one or more pedestrians in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500B. At stage 540, processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, processing unit 110 may scan one or more images, compare the images with one or more predetermined patterns, and identify possible locations within each image that may contain an object of interest (e.g., a vehicle, a pedestrian, or portions thereof). The predetermined patterns may be designed in a manner to 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 to the predetermined patterns to identify candidate objects as possible vehicles or pedestrians. Doing so may allow processing unit 110 to reduce the probability of missing (e.g., not identifying) a candidate object representing a vehicle or a pedestrian.

[0169] At stage 542, processing unit 110 may filter the set of candidate objects to eliminate certain candidates (e.g., irrelevant or less relevant objects) based on classification criteria. Such criteria may be derived from various characteristics associated with the object type stored in a database (e.g., a database stored in memory 140). These characteristics may include object shape, dimensions, texture, and location (e.g., location relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to eliminate false candidates from the set of candidate objects.

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

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

[0172] In step 548, processing unit 110 may perform optical flow analysis of one or more images to reduce the probability of detecting “false positives” and the probability of missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to the analysis of movement patterns relative to vehicle 200 in one or more images associated with other vehicles and pedestrians, for example, which are distinct from road surface movement. Processing unit 110 may calculate the movement of candidate objects by observing various positions of the objects throughout multiple image frames captured at different times. Processing unit 110 may use the position and time values ​​as inputs to a mathematical model that calculates the candidate object's movement. Thus, optical flow analysis may provide another method for detecting vehicles and pedestrians near vehicle 200. Processing unit 110 may 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] FIG. 5C is a flowchart illustrating an example process 500C for detecting road markings and / or lane geometry information in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500C. At stage 550, processing unit 110 may detect a set of objects by scanning one or more images. To detect lane markings, lane geometry information, and other related road marking segments, processing unit 110 may filter the set of objects to eliminate those determined to be irrelevant (e.g., small potholes, pebbles, etc.). At stage 552, processing unit 110 may group together segments detected at stage 550 that belong to the same road or lane marking. Based on this grouping, processing unit 110 may develop a model, such as a mathematical model, to represent the detected segments.

[0174] At stage 554, processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, processing unit 110 may create a projection of the detected segment from the image plane onto a real plane. This projection may be characterized by using a third-order polynomial with coefficients corresponding to physical properties of the detected road, such as its position, slope, curvature, and curvature derivative. In generating the projection, processing unit 110 may consider variations in the road surface and pitch and roll rates associated with vehicle 200. Furthermore, processing unit 110 may model road elevation by analyzing motion cues present on the position and road surface. Furthermore, processing unit 110 may estimate pitch and roll rates associated with vehicle 200 by tracking a set of feature points in one or more images.

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

[0176] In stage 558, processing unit 110 may consider additional sources of information to further develop a safety model of vehicle 200 in relation to its surroundings. Processing unit 110 may use the safety model to define situations in which system 100 may safely execute automatic control of vehicle 200. To develop the safety model, in some embodiments, 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 map database 160). By considering additional sources of information, processing unit 110 can provide redundancy in the detection of road markings and lane geometry, increasing the reliability of system 100.

[0177] FIG. 5D is a flowchart illustrating an example process 500D for detecting traffic lights in a set of images, consistent with disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to perform process 500D. At stage 560, processing unit 110 may scan the set of images to identify objects appearing at locations within the images that may contain traffic lights. For example, processing unit 110 may filter the identified objects to eliminate objects that are unlikely to correspond to traffic lights, to build a set of candidate objects. This filtering may be performed based on various characteristics associated with traffic lights, such as shape, size, texture, and location (e.g., 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 a multi-frame analysis on the set of candidate objects reflecting potential traffic lights. For example, processing unit 110 may track candidate objects throughout successive image frames, estimate the actual location of the candidate objects, and filter out moving objects (objects that are unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects to identify the relative location of detected colors appearing inside potential traffic lights.

[0178] In stage 562, processing unit 110 may analyze the geometry of the intersection. This analysis may be based on any combination of (i) the number of lanes detected on either side of vehicle 200, (ii) markings (such as arrow markings) detected on the road, and (iii) a description 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 execution of monocular analysis module 402. Furthermore, processing unit 110 may identify a correspondence between the traffic lights detected in stage 560 and lanes appearing near vehicle 200.

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

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

[0181] In step 572, processing unit 110 may update the vehicle path constructed in step 570. Processing unit 110 may reconstruct the vehicle path constructed in step 570 using a higher resolution, such that the distance d between two points in the set of points representing the vehicle path is k is the distance d i For example, the distance d k may be in the range of 0.1 to 0.3 meters. Processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may result in 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 step 574, the processing unit 110 calculates the coordinates (x l ,z lThe processing unit 110 may determine a look-ahead point (expressed as ) from the cumulative distance vector S. The processing unit 110 may extract the look-ahead point from the cumulative distance vector S, and the look-ahead point may be associated with a look-ahead distance and a look-ahead time. The look-ahead distance may have a lower limit 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, as the speed of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until the lower limit is reached). 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 (e.g., a heading error tracking control loop) associated with generating a navigation response in the vehicle 200. For example, the gain of the heading error tracking control loop may depend on the bandwidth of the yaw rate loop, the steering actuator loop, the lateral dynamics of the vehicle, etc. Thus, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

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

[0184] 5F is a flowchart illustrating an example process 500F for determining whether a leading vehicle is changing lanes, consistent with disclosed embodiments. In stage 580, processing unit 110 may identify navigation information associated with a leading vehicle (e.g., a vehicle traveling ahead of vehicle 200). For example, processing unit 110 may determine the position, velocity (e.g., direction and speed), and / or acceleration of the leading vehicle using the techniques described above in connection with FIGS. 5A and 5B. Processing unit 110 may determine one or more road polynomials, look-ahead points (associated with vehicle 200), and / or a snail trail (e.g., a set of points describing the path taken by the leading vehicle) using the techniques described above in connection with FIG. 5E.

[0185] In step 582, processing unit 110 may analyze the navigation information identified in step 580. In one embodiment, 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), processing unit 110 may determine that the leading vehicle is likely changing lanes. If multiple vehicles are detected traveling ahead of vehicle 200, processing unit 110 may compare the snail trails associated with each vehicle. Based on this comparison, processing unit 110 may determine that a vehicle whose snail trail does not match the snail trails of the other vehicles is likely changing lanes. Processing unit 110 may further compare the curvature of the snail trail (associated with the leading vehicle) with the expected curvature of the road segment along which the leading 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, prior knowledge about the road, etc. If the difference between the snail trail curvature and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is probably changing lanes.

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

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

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

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

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

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

[0192] At step 720, processing unit 110 may analyze the first, second, and third plurality of images to detect features within the images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, and road obstacles. This analysis may be performed in a manner similar to the steps described above in connection with FIGS. 5A-5D and 6. For example, processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., by execution of monocular image analysis module 402 and based on the steps described above in connection with FIGS. 5A-5D). Alternatively, processing unit 110 may perform stereo image analysis on the first and second plurality of images, the second and third plurality of images, and / or the first and third plurality of images (e.g., by execution of stereo image analysis module 404 and based on the steps described above in connection with FIG. 6). Processed information corresponding to the analysis of the first, second, and / or third plurality of images may be combined. In some embodiments, processing unit 110 may perform a combination of monocular image analysis and stereo image analysis. For example, processing unit 110 may perform monocular image analysis on a first plurality of images (e.g., by executing monocular image analysis module 402) and stereo image analysis on a second and third plurality of images (e.g., by executing stereo image analysis module 404). The configuration of image capture devices 122, 124, and 126 (including their respective positions and fields of view 202, 204, and 206) may affect the type of analysis performed on the first, second, and third plurality of images. The disclosed embodiments are not limited to a particular configuration of image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

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

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

[0195] In some embodiments, processing unit 110 may select information from two of the first, second, and third plurality of images by determining the degree to which information from one image source matches information from the other image sources. For example, processing unit 110 may combine processed information from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination of the two) to identify visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.) that are consistent with the images captured from each of image capture devices 122, 124, and 126. Processing unit 110 may reject information that is inconsistent with the captured images (e.g., a vehicle changing lanes, a lane model showing a vehicle too close to vehicle 200, etc.). Thus, processing unit 110 may select information from two of the first, second, and third plurality of images based on a determination of consistent and inconsistent information.

[0196] The navigational responses may include, for example, turning, shifting lanes, and changing acceleration. Processing unit 110 may generate one or more navigational responses based on the analysis performed in step 720 and the techniques described above in connection with FIG. 4. Processing unit 110 may generate one or more navigational responses using data obtained from execution of velocity / acceleration module 406. In some embodiments, processing unit 110 may generate one or more navigational responses based on the relative position, relative velocity, and / or relative acceleration of vehicle 200 and objects detected in any of the first, second, and third plurality of images. The multiple navigational responses may be performed simultaneously, sequentially, or any combination thereof.

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

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

[0199] [Sparse maps for autonomous vehicle navigation]

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

[0201] For example, rather than storing detailed representations of road segments, a sparse data map may store three-dimensional polynomial representations of preferred vehicle paths along roads. These paths may require little data storage space. Furthermore, in the described sparse data maps, landmarks may be identified and included in the sparse map road model to aid in navigation. These landmarks may be spaced at any suitable interval to enable vehicle navigation, although in some cases, such landmarks need not be identified or included in the model at a high density and closely spaced interval. Rather, in some cases, navigation may be possible based on landmarks spaced at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer, or at least 2 kilometers apart. As will be discussed in more detail in other sections, the sparse map may be generated based on data collected or measured by vehicles equipped with various sensors and devices, such as image capture devices, sensors for global positioning systems, motion sensors, etc., as the vehicles travel along the roadway. In some cases, the 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 of one or more vehicles is sometimes called "crowdsourcing" the sparse map.

[0202] Consistent with disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed systems and methods may deliver the sparse map to generate a road navigation model for the autonomous vehicle, and may use the sparse map and / or the generated road navigation model to navigate the autonomous vehicle along road segments. Consistent with this disclosure, a sparse map may include one or more three-dimensional contour maps that may represent predetermined trajectories that the autonomous vehicle may traverse as it travels along the associated road segment.

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

[0204] For example, rather than storing a detailed representation of various aspects of a road, the disclosed sparse map may store a polynomial representation of one or more trajectories that a vehicle may take along a road. Thus, rather than storing details about the physical properties of the road (or having to transfer details) to enable navigation along the road, the disclosed sparse map may, in some cases, allow a vehicle to navigate along a particular road segment without having to interpret the physical aspects of the road, but rather by aligning the vehicle's travel path with a trajectory (e.g., a polynomial spline) along the particular road segment. In this manner, the vehicle may be navigated primarily based on the stored trajectory (e.g., a polynomial spline), which may require much less storage space than approaches requiring 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 digital signatures, which are obtained from digital images (or digital signals) acquired by sensors (e.g., cameras or other sensors, such as suspension sensors) mounted on vehicles traveling along the road segment. The digital signatures may be small in size compared to the signals acquired by the sensors. In some embodiments, the digital signatures may be created to be compatible with classifier functions configured to detect and identify road features from signals acquired by the sensors on subsequent drives, for example. In some embodiments, the digital signatures may be created so that they have as small a footprint as possible while retaining the ability to associate or match road features to the stored signatures based on subsequent images of the road features captured by a camera mounted on a vehicle traveling along the same road segment (or digital signals generated by a sensor, if the stored signature is not based on an image and / or includes other data).

[0206] In some embodiments, the size of the data object may further be related to the uniqueness of the road feature. For example, for a road feature detectable by a vehicle-mounted camera, if the vehicle-mounted camera system is coupled to a classifier that can distinguish image data corresponding to the road feature as being associated with a particular type of road feature (e.g., a road sign), and if such road signs are locally unique in the region (e.g., there are no identical road signs or road signs of the same type nearby), it may 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 road segments) may be stored as small data objects that can represent the road features using a relatively small number of bytes while providing sufficient information to recognize and use such features for navigation. In one example, road signs may be identified as recognized landmarks upon which vehicle navigation may be based. Representations of road signs may be stored in a sparse map, including, for example, a few bytes of data indicating the landmark's type (e.g., a stop sign) and a few bytes of data indicating the landmark's location (e.g., coordinates). Navigating based on such data-light representations of landmarks (e.g., using representations sufficient to locate, recognize, and navigate based on landmarks) may provide a desired level of navigation functionality associated with sparse maps without significantly increasing the data overhead associated with sparse maps. This efficient representation of landmarks (and other road features) may take advantage of sensors and processors onboard the vehicle that are 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 area (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), and during navigation (e.g., automated navigation), when a camera on an autonomous vehicle captures an image of an area containing a sign (or a particular type of sign), a processor may process the image, detect the sign (if in fact present in the image), classify the image as a sign (or as a particular type of sign), and associate the location of the image with the location of the sign stored in the sparse map.

[0209] The sparse map may include any suitable representation of objects identified along a road segment. In some cases, objects may be referred to as semantic objects or non-semantic objects. Semantic objects may include, for example, objects associated with a predetermined type classification. This type classification may be useful in reducing the amount of data needed to describe semantic objects recognized in the environment, which may be beneficial both during the collection phase (e.g., reducing the cost associated with using bandwidth to transfer driving information from multiple collection vehicles to a server) and during the navigation phase (e.g., reduced map data may speed the transfer of map tiles from a server to a navigating vehicle and also reduce the cost associated with using bandwidth for such transfer). Semantic object classification types may be assigned to any type of object or feature expected to be encountered along a 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 associated with a predetermined dimension. Such semantic objects may include specific speed limit signs, priority road signs, merge signs, stop signs, traffic lights, directional arrows on roadways, manhole covers, or any other type of object that may be associated with a standardized size. One benefit provided by such semantic objects is that very little data may be required to represent / fully define the object. For example, if the standardized size of the speed limit size is known, the collection vehicle may then only need to identify (by analysis of the captured image) the presence of a speed limit sign (a recognized type) along with an indication of the location of the detected speed limit sign (e.g., the 2D location (or alternatively, the 3D location in real-world coordinates) of the center of the sign or a specific corner of the sign in the captured image) to provide sufficient information for map generation on the server side. If the 2D image location is sent to the server, the location where the sign was detected relative to the captured image may also be sent, since the server can determine the actual location of the sign (e.g., via a structure in motion approach using multiple images captured from one or more collection vehicles). Even with this limited information (requiring only a few bytes to define each detected object), the server may still build a map with speed limit signs fully represented based on the type classification (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, tar seams, lampposts, non-standardized traffic lights, curbs, trees, tree branches, or any other type of recognized object type with one or more variable characteristics (e.g., variable dimensions). In such cases, in addition to sending an indication of the detected object or feature type (e.g., pothole, pole, etc.) and the location information of the detected object or feature to the server, the collection vehicle may also send an indication of the size of the object or feature. The size may be expressed in 2D image dimensions (e.g., with a bounding box or one or more dimension values) or actual dimensions (determined via a structure in a motion calculation based on the output of a LIDAR or RADAR system, the output of a trained neural network, etc.).

[0212] Non-semantic objects or features may include any detectable object or feature that is outside the range of recognized kinds or types but may still contribute 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 window pane on a building, a distinctive stone or object near a roadway, concrete splatter on the roadside, or any other detectable object or feature. Upon detecting such an object or feature, 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. Additionally, a condensed or simplified image segment (e.g., an image hash) may be generated for the region of the captured image that contains 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. Such signatures may be useful for navigation involving sparse maps that include non-semantic features or objects, since vehicles traveling on roadways may apply algorithms similar to those used to generate image hashes to verify / prove the presence of mapped non-semantic features or objects in captured images. Using this approach, non-semantic features may add richness to sparse maps (and may improve their usefulness in navigation, for example) without adding significant data overhead.

[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 path through an intersection, for merges and exits, etc. In addition to the target trajectories, other road features may also be detected, collected, and incorporated into the sparse map in the form of representative splines. Such features may include, for example, road edges, lane markings, curbs, guardrails, or any other objects or features extending along a roadway or road segment.

[0214] [Generate Sparse Map]

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

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

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

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

[0219] Further, in such embodiments, sparse map 800 may be accessible to multiple vehicles (e.g., tens, hundreds, thousands, or millions of vehicles) traveling various road segments. It should also be noted that sparse map 800 may include multiple sub-maps. For example, in some embodiments, sparse map 800 may include hundreds, thousands, millions, or more sub-maps (e.g., map tiles) that may be used in navigating a vehicle. Such sub-maps may be referred to as local maps or map tiles, and a vehicle traveling along a roadway may access any number of local maps relevant to its location. The local map areas of sparse map 800 may be stored with Global Navigation Satellite System (GNSS) keys as indexes into the sparse map 800 database. Thus, calculations of steering angles for navigating a host vehicle in the 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] In general, 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 (e.g., cameras, speedometers, GPS, accelerometers, etc.) on one or more vehicles may be used to record the trajectory of one or more vehicles traveling along the roadway, and a polynomial representation of a preferred trajectory for subsequent vehicle movement along the roadway may be determined based on the collected trajectories of the one or more vehicles. Similarly, data collected by one or more vehicles may help identify 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 roughness profile, lane spacing profile, road conditions, etc. Using the collected information, sparse map 800 may be generated and distributed (e.g., for local storage or via on-the-fly data transmission) for use in navigating one or more autonomous vehicles. 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 constantly or periodically based on data collected from the vehicle as it continues to travel 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, including, for example, the location of landmarks, the location of road profiles, etc. The locations of 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 (e.g., based on image analysis of data collected from one or more cameras mounted on the vehicle). Such location determination of the identified landmark (or any other feature included in the sparse map 800) may be repeated each time an additional vehicle passes the location of the identified landmark. Some or all of the additional 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 operation may be used to fine-tune the stored positions of the map elements based on multiple positions determined for the map elements.

[0222] In a particular example, collection vehicles may travel a particular road segment. Each collection vehicle captures images of its respective environment. The images may be collected at any suitable frame capture rate (e.g., 9 Hz, etc.). One or more image analysis processors on board 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 vehicles transmit indications of the detection of semantic and / or non-semantic objects / features to a mapping server along with locations associated with these objects / features. More specifically, type indicators, dimensional indicators, etc. may be transmitted along with the location information. The location information may include any information suitable to enable the mapping server to aggregate the detected objects / features into a sparse map useful in navigation. In some cases, the location information may include one or more 2D image locations (e.g., XY pixel locations) at which the semantic or non-semantic features / objects were detected in the captured images. Such image locations may correspond to the centers, corners, etc. of the features / objects. In this scenario, to help the mapping server reconstruct driving information and align driving information from multiple collection vehicles, each collection vehicle may also provide the server with the location (e.g., GPS location) where each image was captured.

[0223] In other cases, the collection vehicle may provide the server with one or more 3D real-world points associated with the detected object / feature. Such 3D points may be relative to a predetermined origin (such as the origin of the drive segment) and may be identified by any suitable technique. In some cases, a structure in motion technique may be used to identify the 3D real-world location of the detected object / feature. For example, a particular object, such as a particular speed limit sign, may be detected in two or more captured images. Using information such as the known ego-motion (speed, trajectory, GPS location, etc.) of the collection vehicle between multiple captured images, along with observed changes of the speed limit sign in the captured images (changes in XY pixel position, changes in size, etc.), the actual location of one or more points associated with the speed limit sign may be identified and passed to the mapping server. Such techniques require more computation on the part of the collection vehicle system and are therefore optional. The sparse map of the disclosed embodiments may enable automated vehicle navigation using a relatively small amount of stored data. In some embodiments, sparse map 800 may have a data density (e.g., including data representing target trajectories, landmarks, and any other stored road features) of less than 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. In some embodiments, the data density of 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 less than 10 kB per kilometer of road, or less than 20 kB per kilometer of road. In some embodiments, most, if not all, U.S. roadways may be navigated autonomously using a sparse map having a total of 4 GB or less of data. These data density values ​​may represent averages for sparse map 800 as a whole, for local maps within sparse map 800, and / or for specific road segments within sparse map 800.

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

[0225] In some embodiments, the target trajectory may represent an ideal path that the vehicle should follow as it travels. The target trajectory may be located approximately in the center of the travel lane, for example. 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, an edge of the road, or an edge of a lane. In such cases, navigation based on the target trajectory may include a determined offset amount maintained relative to the position of the target trajectory. Furthermore, in some embodiments, the determined offset amount maintained relative to the position of the target trajectory may differ based on the type of vehicle (e.g., a passenger car including two axles may have a different offset than a truck including more than two axles along at least a portion of the target trajectory).

[0226] The sparse map 800 may also include data related to a number of predetermined landmarks 820 associated with particular road segments, local maps, etc. As discussed in more detail below, these landmarks may be used for navigation of the 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 heading at the determined location to match the direction of the target trajectory.

[0227] A plurality of landmarks 820 may be identified and stored in the sparse map 800 at any suitable interval. In some embodiments, landmarks may be stored relatively densely (e.g., every few meters or even more densely). However, in some embodiments, significantly larger landmark spacing values ​​may be used. For example, in the sparse map 800, identified (or recognized) landmarks may be spaced 10 meters, 20 meters, 50 meters, 100 meters, 1 kilometer, or 2 kilometers apart. In some cases, identified landmarks may even be spaced more than 2 kilometers apart.

[0228] Between landmarks, and thus between determining the vehicle's position relative to the target trajectory, the vehicle can navigate based on dead reckoning, in which the vehicle uses sensors to identify its own ego-motion and estimate its position relative to the target trajectory. Because errors can accumulate in dead reckoning navigation, over time, the accuracy of position determination relative to the target trajectory can become increasingly poor. The vehicle can use landmarks (and their known locations) present in the sparse map 800 to eliminate dead reckoning errors in position determination. In this manner, the identified landmarks included in the sparse map 800 can serve as a navigational anchor that can determine the vehicle's precise position relative to the target trajectory. Because a certain amount of error in location location may be acceptable, the identified landmarks do not necessarily need to be available to the autonomous vehicle. Rather, suitable navigation may be possible based on landmark spacing 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, and therefore it is not necessary to store every possible landmark that appears along a road segment in sparse map 800.

[0229] Additionally, in some embodiments, lane markings may be used to locate the vehicle between landmarks, which can minimize error accumulation when navigating using dead reckoning.

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

[0231] As shown in FIG. 9A , lane 900 may be represented using polynomials (e.g., linear, quadratic, cubic, or any suitable order polynomials). For purposes of illustration, lane 900 is shown as a two-dimensional lane, and the polynomials are shown as two-dimensional polynomials. As shown in FIG. 9A , lane 900 includes a left side 910 and a right side 920. In some embodiments, more than one polynomial may be used to represent each side of the road or the location of the lane boundaries. For example, left side 910 and right side 920 may each be represented by multiple polynomials of any suitable length. In some cases, these polynomials may have a length of approximately 100 m, although other lengths greater or less than 100 m may also be used. Furthermore, such polynomials may overlap one another to facilitate seamless transitions when navigating based on the next polynomial encountered as the host vehicle travels along the roadway. For example, each of the left side 910 and the right side 920 may be represented by a plurality of third-order polynomials divided into segments approximately 100 meters long (an example of a first predetermined range) and overlapping each other by approximately 50 meters. The polynomials representing the left side 910 and the right side 920 may or may not be of the same order. For example, in some embodiments, some of the polynomials may be second-order, some may be third-order, and some may be fourth-order.

[0232] In the example shown in FIG. 9A , the left side 910 of lane 900 is represented by two groups of third-order polynomials. The first group includes polynomial segments 911, 912, and 913. The second group includes polynomial segments 914, 915, and 916. The two groups are substantially parallel to each other and extend along their respective sides 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 previously mentioned, polynomials of different lengths and overlap amounts may also be used. For example, the polynomials may be 500 meters, 1 km, or longer, and the overlap amount may vary from 0 to 50 meters, from 50 to 100 meters, or by amounts greater than 100 meters. 9A is shown as representing polynomials that extend in 2D space (e.g., on the plane of a piece of paper), it should be understood that these polynomials may represent curves that extend in three dimensions (e.g., including a height component) and may represent elevation variations of the road segment in addition to curvature in the XY plane. In the example shown in FIG. 9A, the right side 920 of lane 900 is further represented by a first group having polynomial segments 921, 922, and 923, and a second group having polynomial segments 924, 925, and 926.

[0233] Returning to the target trajectories in sparse map 800, FIG. 9B illustrates a cubic polynomial representing a target trajectory of a vehicle traveling along a particular road segment. The target trajectory represents not only the path in the XY plane 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 sparse map 800 may be represented by one or more cubic polynomials, such as cubic polynomial 950 shown in FIG. 9B. Sparse map 800 may include multiple trajectories (e.g., millions or billions or 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 cubic polynomial segments.

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

[0235] The sparse map 800 may describe a network of lanes using a combination of geometric descriptors and metadata. The geometry may be described by polynomials or splines as described above. The metadata may describe the number of lanes, special characteristics (such as carpool lanes), and possibly other sparse labels. The total footprint of such metrics may be negligible.

[0236] Thus, a sparse map according to embodiments of the present disclosure may include at least one line representation of a road surface feature extending along a road segment, with each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as described above, the at least one line representation of the road surface feature may include a spline, a polynomial representation, or a curve. Furthermore, in some embodiments, the road surface feature may include at least one of a road edge or a lane marking. Furthermore, 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 traverse the road segment.

[0237] As previously described, sparse map 800 may include a plurality of predetermined landmarks associated with a road segment. Rather than storing actual images of the landmarks and, for example, utilizing image recognition analysis based on captured and stored images, each landmark included in sparse map 800 may be represented and recognized using less data than would be necessary if actual images were stored. The data representing the landmarks may still include sufficient information to describe or identify the landmarks along the road. Storing data describing characteristics of the landmarks, rather than actual images of the landmarks, may reduce the size of sparse map 800.

[0238] FIG. 10 shows examples of types of landmarks that may be represented in 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. The landmarks included in sparse map 800 may help determine the position of vehicle 200 relative to a target trajectory as the vehicle traverses a particular road segment. Examples of landmarks may include traffic signs, directional signs, general signs (e.g., rectangular signs), roadside 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 sparse map 800.

[0239] 10 includes traffic signs, directional signs, roadside fixtures, and general signs. Traffic signs may include, for example, speed limit signs (e.g., speed limit sign 1000), right-of-way signs (e.g., right-of-way sign 1005), route number signs (e.g., route number sign 1010), traffic light signs (e.g., traffic light sign 1015), and stop signs (e.g., stop sign 1020). Directional signs may include signs including one or more arrows indicating one or more directions to different locations. For example, directional signs may include highway signs 1025 with arrows directing vehicles to different roads or locations, exit signs 1030 with arrows directing vehicles to exit a road, and the like. Thus, at least one of the plurality of landmarks may include a road sign.

[0240] A general sign may be non-traffic related. For example, a general sign may include a billboard used for advertising or a welcome sign adjacent the boundary between two countries, states, counties, cities, or towns. A general sign 1040 ("Joe's Restaurant") is shown in FIG. 10. While the general sign 1040 may be rectangular in shape as shown in FIG. 10, the general sign 1040 may also be other shapes, such as a square, circle, triangle, etc.

[0241] Landmarks may also include roadside fixtures. Roadside fixtures may be objects that are not signs and may not be traffic-related or directional-related. For example, roadside fixtures may include lampposts (e.g., lamppost 1035), utility poles, traffic light poles, etc.

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

[0243] In some embodiments, landmarks included in sparse map 800 may be represented by data objects of a predetermined size. Data representing a landmark may include any parameters suitable for identifying a particular landmark. For example, in some embodiments, landmarks stored in sparse map 800 may include parameters such as the landmark's physical size (e.g., to aid in estimating the distance to the landmark based on a known size / scale), the distance to the previous landmark, a lateral offset, height, a 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 aid in long-range location), 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, a lateral offset, and height may be specified using 12 bytes of data. A type code associated with a landmark such as a directional sign or traffic sign may require approximately 2 bytes of data. For a general sign, an image signature that allows for 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 in sparse map 800 in this manner may provide 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 characteristics exists (e.g., speed limit signs, warning signs, directional signs, traffic lights, etc., with known dimensions or other characteristics). Non-standard semantic objects may include any object not associated with a standardized set of characteristics (e.g., generic advertising signs, signs identifying businesses, potholes, trees, etc., which may have variable dimensions).Each non-standard semantic object may be represented with 38 bytes of data (e.g., 8 bytes for size, 12 bytes for distance to previous landmark, lateral offset and height, 2 bytes for type code, 16 bytes for location coordinates). Standard semantic objects may be represented using even less data, since the mapping server may not require size information to completely represent the object in the sparse map.

[0244] The sparse map 800 may use a tag system to represent landmark types. In some cases, each traffic or directional sign may be associated with a unique tag, which may be stored in the database as part of the landmark identification information. For example, the database may include on the order of 1,000 different tags to represent various traffic signs and on the order of 10,000 different tags to represent directional signs. Of course, any suitable number of tags may be used, and additional tags may be created as needed. In some embodiments, a generic landmark 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] Thus, for semantic road signs that do not require image signatures, the data density impact on sparse map 800 can be on the order of approximately 760 bytes per kilometer (e.g., [20 landmarks per km] × [38 bytes per landmark] = 760 bytes), even at a relatively high landmark density of approximately one per 50 meters. Even for generic signs that include an image signature component, the data density impact is approximately 1.72 kB per kilometer (e.g., [20 landmarks per km] × [86 bytes per landmark] = 1,720 bytes). For semantic road signs, this impact corresponds to a data usage of approximately 76 kB per hour for a vehicle traveling at 100 km / hr. For generic signs, this impact corresponds to a data usage of approximately 170 kB per hour for a vehicle traveling at 100 km / hr. It should be noted that in some environments (e.g., urban environments), there may be a significantly higher density of detected objects available for inclusion in the sparse map (perhaps greater than one per meter). In some embodiments, a generally rectangular object, such as a rectangular landmark, may be represented in the sparse map 800 with 100 bytes or less of data. The representation of the generally rectangular object (e.g., generic landmark 1040) in the sparse map 800 may include an abbreviated image signature or image hash (e.g., abbreviated image signature 1045) associated with the generally rectangular object. This abbreviated image signature / image hash may be determined using any suitable image hashing algorithm and may be used to help identify, for example, the generic landmark, as a recognized landmark. Such an abbreviated image signature (e.g., image information obtained from real image data representing an object) may eliminate the need to store a real image of the object or perform comparative image analysis on the real image to recognize the landmark.

[0246] 10 , the sparse map 800 may include or store an abbreviated image signature 1045 associated with the generic sign 1040, rather than an actual image of the generic sign 1040. For example, after an image capture device (e.g., image capture device 122, 124, or 126) captures an image of the generic sign 1040, a processor (e.g., image processor 190 or any other processor capable of processing images onboard the host vehicle or remotely located with respect to the host vehicle) may perform image analysis to extract / create the abbreviated image signature 1045 that includes a unique signature or pattern associated with the generic sign 1040. In one embodiment, the abbreviated image signature 1045 may include a shape, a color pattern, a brightness pattern, or any other feature to describe the generic sign 1040 that can be extracted from an image of the generic sign 1040.

[0247] For example, in FIG. 10 , the circles, triangles, and stars shown in the abbreviated image signature 1045 may represent regions of different colors. The patterns represented by the circles, triangles, and stars may be stored in the sparse map 800, for example, within the 50 bytes designated to include the image signature. Notably, the circles, triangles, and stars are not necessarily meant to indicate that such shapes are stored as part of the image signature. Rather, these shapes are intended to conceptually represent recognizable regions with distinguishable color differences, textured regions, graphic shapes, or other variations in characteristics that may be associated with generic signs. Such abbreviated image signatures can be used to identify landmarks in the form of generic signs. For example, abbreviated image signatures can be used to perform identification analysis based on a comparison of the stored abbreviated image signature with image data captured, for example, using a camera mounted on a self-driving vehicle.

[0248] Thus, the plurality of landmarks may be identified by image analysis of a plurality of images acquired as one or more vehicles traverse the road segment. As described below with respect to "crowdsourcing," in some embodiments, the image analysis to identify the plurality of landmarks may include accepting a potential landmark if a ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold. Further, in some embodiments, the image analysis to identify the plurality of landmarks may include rejecting a potential landmark if a 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 the host vehicle may use to navigate a particular road segment, FIG. 11A illustrates a polynomial representation of a trajectory captured in the process of building or maintaining sparse map 800. The polynomial representation of the target trajectory included in sparse map 800 may be determined based on two or more reconstructed trajectories for the vehicle's previous passage along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in sparse map 800 may be an aggregation of two or more reconstructed trajectories for the vehicle's previous passage along the same road segment. In some embodiments, the polynomial representation of the target trajectory included in sparse map 800 may be an average of two or more reconstructed trajectories for the vehicle's previous passage along the same road segment. Other mathematical operations may also be used to construct a target trajectory along a road path based on reconstructed trajectories collected from vehicles traveling along a road segment.

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

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

[0252] Additionally, or instead, such a reconstructed trajectory may be determined on the server side based on information received from vehicles traversing the road segment 1100. For example, in some embodiments, the vehicle 200 may transmit data related to its movement along the road segment 1100 (e.g., steering angle, heading, time, position, speed, detected road geometry, and / or detected landmarks, among others) to one or more servers. The server may reconstruct the trajectory of the vehicle 200 based on the received data. The server may also generate a target trajectory based on the first trajectory 1101, the second trajectory 1102, and the third trajectory 1103 for guiding the navigation of an autonomous vehicle that subsequently travels along the same road segment 1100. While a target trajectory may be associated with a single previous trajectory 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 traversing the same road segment. 11A, the target trajectory is represented at 1110. In some embodiments, the target trajectory 1110 may be generated based on an 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 an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories.

[0253] In a mapping server, the server may receive actual trajectories for a particular road segment from multiple collection vehicles traversing the road segment. The received actual trajectories may be aligned to generate a target trajectory 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 positions 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] 11B and 11C further illustrate the concept of a target trajectory associated with road segments present in the geographic region 1111. As shown in FIG. 11B, a first road segment 1120 within the geographic region 1111 may include a multi-lane road that includes two lanes 1122 designated for vehicle travel in a first direction and two additional lanes 1124 designated for vehicle travel in a second direction opposite the first direction. The lanes 1122 and 1124 may be separated by a double yellow line 1123. The geographic region 1111 may also include a branch road segment 1130 that intersects with the road segment 1120. The road segment 1130 may include a two-lane road, with each lane designated for travel in a different direction. The geographic region 1111 may also include other road features, such as a stop line 1132, a stop sign 1134, a speed limit sign 1136, and a hazard sign 1138.

[0255] 11C , sparse map 800 may include local map 1140, which includes a road model for assisting a vehicle in automated navigation within geographic region 1111. For example, local map 1140 may include target trajectories for one or more lanes associated with road segments 1120 and / or 1130 within geographic region 1111. For example, local map 1140 may include target trajectories 1141 and / or 1142 that are accessible or available to the automated vehicle when traversing lane 1122. Similarly, local map 1140 may include target trajectories 1143 and / or 1144 that are accessible or available to the automated vehicle when traversing lane 1124. Additionally, local map 1140 may include target trajectories 1145 and / or 1146 that are accessible or available to the automated vehicle when traversing road segment 1130. Target trajectory 1147 may represent a preferred path for the automated vehicle to follow 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 a first side of road segment 1130). Similarly, target trajectory 1148 represents a preferred path for the automated vehicle to follow when transitioning from road segment 1130 (specifically, corresponding to target trajectory 1146) to a portion of road segment 1124 (specifically, corresponding to target trajectory 1143 associated with the left lane of lane 1124, as shown).

[0256] The sparse map 800 may also include representations of other road-related features associated with the geographic region 1111. For example, the sparse map 800 may also include representations of one or more landmarks identified in the geographic region 1111. Such landmarks may include a first landmark 1150 associated with a stop line 1132, a second landmark 1152 associated with a stop sign 1134, a third landmark 1154 associated with a speed limit sign 1154, and a fourth landmark 1156 associated with a hazard sign 1138. Such landmarks may be used, for example, to assist the automated vehicle in determining its current position relative to any of the indicated target trajectories. This may enable the vehicle, at its determined position, to adjust its heading to match 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 road surface roughness of a particular road segment, changes in road width across a particular road segment, changes in the distance between painted dashed lines along a particular road segment, changes in road curvature along a particular road segment, etc. FIG. 11D illustrates an example of a road signature profile 1160. While the profile 1160 may represent any of the parameters described above, in one example, the profile 1160 may represent measurements of road surface roughness, for example, obtained by monitoring one or more sensors that provide an output indicative of the amount of suspension displacement as the vehicle travels along a particular road segment.

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

[0259] In some embodiments, sparse map 800 may include different trajectories based on different characteristics associated with the user of the automated vehicle, environmental conditions, and / or other parameters related to the trip. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or profiles. Sparse map 800 including such different trajectories may be provided to different automated vehicles of different users. For example, some users may prefer to avoid toll roads, while other users may prefer to take the shortest or fastest route, regardless of whether there are toll roads along the route. The disclosed system may generate different sparse maps with different trajectories based on such different user preferences or profiles. As another example, some users may prefer to drive in the fast lane, while other users may prefer to always maintain a position in the center lane.

[0260] Various trajectories may be generated and included in the sparse map 800 based on various environmental conditions, such as daytime and nighttime, snow, rain, fog, etc. An autonomous vehicle traveling under various environmental conditions may be provided with the sparse map 800 generated based on such various environmental conditions. In some embodiments, a camera on the autonomous vehicle may detect the environmental conditions and provide such information back to the server that generates and provides the sparse map. For example, the server may generate the sparse map 800 or update an already generated sparse map 800 to include trajectories that may be more suitable or safer for autonomous driving under the detected environmental conditions. Updating the sparse map 800 based on the environmental conditions may occur dynamically as the autonomous vehicle travels along the road.

[0261] Various other parameters related to driving may also be used as the basis for generating and providing various sparse maps to various autonomous vehicles. For example, when an autonomous vehicle is driving at a high speed, turns may be tighter. Trajectories associated with particular lanes rather than roads may be included in sparse map 800 to enable the autonomous vehicle to stay in a particular lane as it follows a particular trajectory. If images captured by a camera onboard the autonomous vehicle indicate that the vehicle has moved out of its lane (e.g., crossed a lane marking), actions may be initiated within the vehicle to return the vehicle to the designated lane by following the particular trajectory.

[0262] [Crowdsourcing of Sparse Maps]

[0263] The disclosed sparse maps may be generated efficiently (and passively) through 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 an appropriate image analysis processor can serve as a collection vehicle. No special equipment (e.g., high-resolution imaging and / or positioning systems) is required. As a result of the disclosed crowdsourcing approach, the generated sparse map can be highly accurate and can include extremely fine-tuned position information (enabling navigation error limits of 10 cm or narrower) 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 map, because the mapping server system can constantly utilize new driving information from any roads traveled by minimally equipped private or commercial vehicles that also serve as collection vehicles. The designated vehicle does 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, updates to the presently disclosed sparse map can occur much faster than systems utilizing dedicated, special-purpose mapping vehicles, the cost and specialized equipment of which typically limit fleets of special-purpose vehicles to a much smaller number than the number of private or commercial vehicles already available to perform the disclosed collection techniques.

[0264] The disclosed crowdsourced sparse map can be highly accurate because it can be generated based on multiple inputs from multiple (e.g., tens, hundreds, or millions) collection vehicles with driving information collected along a particular road segment. For example, each collection vehicle driving along a particular road segment may record its actual trajectory and identify location information associated with objects / features detected along the road segment. This information is passed from the multiple collection vehicles to a server. The actual trajectories are aggregated to generate a fine-tuned target trajectory for each valid driving path along the road segment. Furthermore, the location information of each object / feature (semantic or non-semantic) detected along the road segment collected from the multiple collection vehicles may also be aggregated. As a result, the mapped location of each detected object / feature may constitute an average of hundreds, thousands, or millions of locations individually identified for each detected object / feature. Such an approach can yield highly accurate mapped locations for detected objects / features.

[0265] In some embodiments, the disclosed systems and methods may generate sparse maps for autonomous vehicle navigation. For example, the disclosed systems and methods may use crowdsourced data to generate a sparse map that one or more autonomous vehicles can use to navigate along roads in a system. As used herein, "crowdsourcing" refers to receiving data from various vehicles (e.g., autonomous vehicles) traveling a road segment at different times, which 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 autonomous vehicle or to other vehicles that subsequently travel along the road segment to assist in autonomous vehicle navigation. The road model may include multiple target trajectories that represent preferred trajectories for the autonomous vehicle to follow when traveling along a road segment. These target trajectories may be the same as reconstructions of actual trajectories collected from vehicles traveling 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 traversed by one or more vehicles when traveling the road segment, and the target trajectory may be generated based on the actual trajectory (e.g., by averaging or any other suitable operation).

[0266] The vehicle trajectory data that a vehicle may upload to the server may correspond to the vehicle's actual reconstructed trajectory or may correspond 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 automated navigation of other vehicles.

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

[0268] A reconstructed trajectory that a vehicle may generate as it travels along a road may be obtained in any suitable manner. In some embodiments, the reconstructed trajectory may be developed by piecing together multiple portions of the vehicle's motion using, for example, egomotion estimation (e.g., 3D translation and 3D rotation of the camera, and therefore the vehicle body). Estimates of rotation and translation may be determined based on analysis of images captured by one or more image capture devices along with information from other sensors or devices (such as inertial sensors and speed sensors). For example, the inertial sensors may include accelerometers or other suitable sensors configured to measure changes in translation and / or rotation of the vehicle body. The vehicle may include a speed sensor to measure the vehicle's speed.

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

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

[0271] The geometry of the reconstructed trajectory along the road segment (as well as the geometry of the target trajectory) may be represented by a curve in three-dimensional space, which may be a spline connecting three-dimensional polynomials. The reconstructed trajectory curve may be determined from an analysis of a video stream or multiple images captured by a camera mounted on the vehicle. In some embodiments, a position is identified in each frame or image that is several meters ahead of the vehicle's current position. This position is where the vehicle is expected to travel after a predetermined period of time. This operation may be repeated for each frame, while the vehicle may simultaneously calculate the egomotion (rotation and translation) of the camera. For each frame or image, a short-range model of the desired path is generated with the vehicle in the camera-mounted reference frame. Multiple short-range models may be stitched 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 include 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 for each frame. For example, a bottom-up lane detection module may be used. The bottom-up lane detection module may be useful when lane markings are painted on the road. This module may locate edges in the image and organize 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 that may be trained to predict an accurate short-distance path from the input image. In either module, the road model may be detected in the image coordinate frame and transformed into a three-dimensional space that may be virtually attached to the camera.

[0273] In the reconstructed trajectory modeling method, the accumulation of egomotion over a long period of time can result in accumulated errors that may include noise components. However, such errors may be insignificant because the generated model may provide sufficient accuracy for navigation on a regional scale. Furthermore, the accumulated errors can be offset using external information sources, such as satellite imagery or geodetic surveys. For example, the disclosed systems and methods may use a GNSS receiver to offset the accumulated errors. However, GNSS positioning signals may not always be available and accurate. The disclosed systems and methods may enable steering applications that are less dependent on the availability and accuracy of GNSS positioning. In such systems, the use of GNSS signals may be limited. For example, in some embodiments, the disclosed systems may use GNSS signals only for database indexing purposes.

[0274] In some embodiments, distance ranges (e.g., area-scale) that may be appropriate for autonomous vehicle navigation steering applications may be on the order of 50 meters, 100 meters, 200 meters, 300 meters, etc. Such distances may be used because geometric road models are used primarily for two purposes: to pre-plan a trajectory and to localize a vehicle 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 distance ahead, e.g., 20 meters, 30 meters, 50 meters), with the control algorithm steering the vehicle according to a target point located 1.3 seconds ahead (or any other time, e.g., 1.5 seconds, 1.7 seconds, 2 seconds, etc.). The localization task uses a road model spanning a typical range of 60 meters behind the automobile (or any other suitable distance, e.g., 50 meters, 100 meters, 150 meters, etc.), following a method called “tail alignment,” which is described in more detail in another section. The disclosed systems and methods may generate geometric models with sufficient accuracy over a particular range, such as 100 meters, so that the planned trajectory does not deviate from the lane center by more than 30 cm, for example.

[0275] As described above, a three-dimensional road model may be constructed by detecting short-distance segments and stitching them together. This stitching may be possible by calculating a six-stage egomotion model using video and / or images captured by cameras, data from inertial sensors reflecting vehicle motion, and the host vehicle's speed signal. The cumulative error may be small enough at some local scale, such as 100 meters. All of this may be completed in one drive of a particular road segment.

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

[0277] Sharing of driving experiences (such as sensing data) between multiple vehicles becomes feasible when the vehicles are connected to a central server. Each vehicle client may store a partial copy of a generic road model that may be relevant to its current location. A two-way update procedure between the vehicle and the server may be performed by the vehicle and the server. The small footprint concept described above enables the disclosed system and method to perform two-way updates using very little bandwidth.

[0278] Information related to potential landmarks may also be identified and forwarded 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 that include the landmark. These physical characteristics may include the landmark's physical size (e.g., height, width), the distance from the vehicle to the landmark, the distance from the landmark to the immediately preceding landmark, the landmark's lateral position (e.g., the landmark's location relative to the lane of travel), the landmark's GPS coordinates, the landmark's type, text identification related to the landmark, etc. For example, the vehicle may analyze one or more images captured by a camera to detect potential landmarks, such as speed limit signs.

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

[0280] In some embodiments, multiple autonomous vehicles traveling along a road segment may communicate with a server. The vehicles (or clients) may generate curves in any coordinate frame that describe their own drives (e.g., by egomotion aggregation). The vehicles may detect landmarks and place the landmarks in the same frame. The vehicles may upload the curves 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 FIG. 19, the server may use the uploaded curves 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 constantly or periodically update the model as 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 an update of the data or the creation of new data at the server. The server may distribute the updated model or update information to the vehicles to provide autonomous vehicle navigation.

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

[0283] The server may distribute the updated model (or an updated portion of the model) to one or more vehicles traveling on the road segment with which the model update is associated. The server may also distribute the updated model to vehicles that plan to travel on the road segment with which the model update is associated or that have the road segment included in their own travel plans. For example, while an autonomous vehicle is traveling along a road segment before reaching the road segment associated with an update, the server may distribute the update or updated model to the autonomous vehicle before the vehicle reaches the 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 the landmarks to match curves and create an average road model based on the collected trajectories from multiple vehicles. The server may also calculate a road graph and most likely paths at each intersection or junction of road segments. For example, the remote server may align the collected trajectories to generate a crowdsourced sparse map from these trajectories.

[0285] The server may average landmark characteristics received from multiple vehicles that traveled along a common road segment, such as distances between one landmark and another landmark (e.g., the previous landmark along the road segment) measured by the multiple vehicles, to determine an arc-length parameter to assist in along-route localization and speed calibration for each client vehicle. The server may average physical dimensions of landmarks measured by multiple vehicles that traveled along a common road segment and recognized the same landmark. The averaged physical dimensions may be used to assist in distance estimation, such as the distance from the vehicle to the landmark. The server may average lateral positions of landmarks (e.g., the position of the landmark from the lane in which the vehicle is traveling) measured by multiple vehicles that traveled along a common road segment and recognized the same landmark. The averaged lateral positions may be used to assist in lane assignment. The server may average GPS coordinates of landmarks measured by multiple vehicles that traveled along the same road segment and recognized the same landmark. The averaged GPS coordinates of the landmark may be used to assist in global localization or positioning of the landmark in the road model.

[0286] In some embodiments, the server may identify changes to the model, such as construction, detours, new signs, removed signs, etc., based on data received from the vehicle. The server may constantly, periodically, or immediately update the model as it receives new data from the vehicle. The server may deliver model updates or updated models to the vehicle to provide automated navigation. For example, as 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 intervention during automated driving. The server may analyze data received from the vehicle at the time and location of the intervention and / or data received before the time of the intervention. The server may identify data that caused or is closely related to the intervention, such as data indicating the establishment of a temporary lane closure or a certain portion of 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] FIG. 12 is a schematic diagram of a system for generating a sparse map using crowdsourcing (and distributing and navigating using the crowdsourced sparse map). FIG. 12 shows a road segment 1200 including one or more lanes. Multiple vehicles 1205, 1210, 1215, 1220, and 1225 (although shown in FIG. 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. To simplify this example, we will 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 other embodiments (e.g., vehicle 200) and may include components or devices included in or associated with a vehicle disclosed in other embodiments. Each vehicle may include an image capture device or camera (e.g., image capture device 122 or camera 122). Each vehicle may communicate with a remote server 1230 via one or more networks (e.g., via a cellular network and / or the Internet) through a wireless communication path 1235, shown by the dashed line. Each vehicle may send data to and receive data from server 1230. For example, server 1230 may collect data from multiple vehicles traveling road segment 1200 at different times and process the collected data to generate an autonomous vehicle road navigation model or updates to the model. Server 1230 may transmit the autonomous vehicle road navigation model or updates to the model to the vehicles that sent data to server 1230. Server 1230 may transmit the autonomous vehicle road navigation model or updates to the model to other vehicles that subsequently travel road segment 1200.

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

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

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

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

[0294] As described above, the road navigation model for the autonomous vehicle may be included in a sparse map (e.g., sparse map 800 shown in FIG. 8 ). Sparse map 800 may include a sparse record of data related to road geometry and / or roadside landmarks, which may provide sufficient information to guide the automated navigation of the autonomous vehicle without requiring excessive data storage. In some embodiments, the road navigation model for the autonomous vehicle may be stored separately from sparse map 800, and map data from sparse map 800 may be used when the model is executed for navigation. In some embodiments, the road navigation model for the autonomous vehicle may use the map data included in sparse map 800 to determine a target trajectory along road segment 1200 to guide the automated navigation of autonomous vehicles 1205, 1210, 1215, 1220, and 1225, or other vehicles that subsequently travel along road segment 1200. For example, when the road navigation model for autonomous vehicles is executed by a processor included in the navigation system of vehicle 1205, the model may cause the processor to compare a trajectory determined based on navigation information received from vehicle 1205 with a predetermined trajectory included in sparse map 800 to confirm and / or correct the current course of vehicle 1205.

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

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

[0297] The identification information of the at least one landmark may include a location of the at least one landmark. The location of the landmark may be determined based on location measurements made using sensor systems (e.g., global positioning systems, inertial-based positioning systems, landmark beacons, etc.) associated with multiple vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, the location of the landmark may be determined by averaging location measurements detected, collected, or received over multiple drives by sensor systems in different vehicles 1205, 1210, 1215, 1220, and 1225. For example, the vehicles 1205, 1210, 1215, 1220, and 1225 may transmit data of the location measurements to the server 1230, which may average the location measurements and use the averaged location measurements as the location of the landmark. The location of the landmark may be continually refined by measurements received from the vehicles on subsequent drives.

[0298] The landmark's identification information may include the landmark's size. A processor in the vehicle (e.g., 1205) may estimate the landmark's physical size based on an analysis of the image. The server 1230 may receive multiple estimates of the same landmark's physical size from different vehicles and different drives. The server 1230 may average the various estimates to arrive at the landmark's physical size and store the landmark's size in the road model. The physical size estimate may then 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 position of the landmark 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 to the landmark in the image from t1 to t2. dt represents (t2 - t1). For example, the distance to a landmark may be estimated as 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. Other formulas equivalent to the above formula, such as Z=V×ω / Δω, may be used to estimate the distance to a landmark, where V is the vehicle speed, ω is the image length (such as the object width), and Δω is the change in image length per unit time.

[0299] If the physical size of the landmark is known, the distance to the landmark may also be determined based on the following formula: Z=f×W / ω, where f is the focal length, W is the size (e.g., height or width) of the landmark, and ω is the number of pixels the landmark leaves the image. From the above formula, the change in distance Z is given by ΔZ=f×W×Δω / ω 2+f×ΔW / ω, where ΔW decays to zero with averaging and Δω is the number of pixels that represent the bounding box precision of the image. An estimate of the physical size of the landmark may be calculated by averaging multiple observations on the server side. The resulting error in the distance estimation can be very small. There are two possible sources of error when using the above formula: ΔW and Δω. Their respective contributions to the distance error are: ΔZ=f×W×Δω / ω 2 +f × ΔW / ω. However, since ΔW decays to zero through averaging, ΔZ is determined by Δω (e.g., the inaccuracy of the image's bounding box).

[0300] For landmarks of unknown dimensions, the distance to the landmark may be estimated by tracking feature points on the landmark across successive frames. For example, a particular feature appearing on a speed limit sign may be tracked across two or more image frames. Based on these tracked features, a distribution of distances for each feature point may be generated. A distance estimate may be extracted from the distribution of distances. For example, the most frequently occurring distance in the distribution of distances may be used as the distance estimate. As another example, the mean of the distribution of distances may be used as the distance estimate.

[0301] FIG. 13 illustrates an exemplary road navigation model for an autonomous vehicle, represented by multiple 3-dimensional splines 1301, 1302, and 1303. The curves 1301, 1302, and 1303 illustrated in FIG. 13 are for illustrative purposes only. Each spline may include one or more 3-dimensional polynomials connecting multiple data points 1310. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or any suitable combination of polynomials having different orders. Each data point 1310 may be associated with navigation information received from the vehicles 1205, 1210, 1215, 1220, and 1225. In some embodiments, each data point 1310 may be associated with data related to a landmark (e.g., landmark size, location, and identification information) and / or a road signature profile (e.g., road geometry, road roughness 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 some may be associated with data related to road signature profiles.

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

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

[0304] FIG. 16 shows an example of landmark data collation for use in a sparse map. In the example of FIG. 16, landmark 1610 includes a road sign. The example of FIG. 16 further shows data from multiple drives 1601, 1603, 1605, 1607, 1609, 1611, and 1613. In the example of FIG. 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 landmark identified in drive 1613. Thus, server 1230 may accept a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or may reject a potential landmark if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

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

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

[0307] System 1700 also includes a server (e.g., server 1230), which may receive drive segments 1705 from the vehicles and recombine these drive segments 1705 into a single drive 1707. Such an approach may reduce bandwidth requirements when transferring data between the vehicles and the server, and may also allow the server to store data related to the entire drive.

[0308] FIG. 18 illustrates the system 1700 of FIG. 17 further configured to crowdsource the sparse map. As shown in FIG. 17, the system 1700 includes a vehicle 1810 that captures driving data using, for example, a camera (which generates, for example, ego-motion data, traffic sign data, or road data) and a location device (e.g., a GPS locator). As shown in FIG. 17, the vehicle 1810 divides the collected data into multiple driving segments (shown in FIG. 18 as "DS1 1," "DS2 1," and "DSN 1"). The server 1230 then receives the driving segments and reconstructs one driving segment (shown in FIG. 18 as "Drive 1") from the received segments.

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

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

[0311] 19 is a flowchart illustrating an example 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 receiving (step 1905) a plurality of images captured as one or more vehicles traverse the road segment. Server 1230 may receive the images from cameras included in one or more of vehicles 1205, 1210, 1215, 1220, and 1225. For example, camera 122 may capture one or more images of the environment surrounding vehicle 1205 as vehicle 1205 travels along road segment 1200. In some embodiments, server 1230 may also receive clean image data in which redundancy has been removed by a processor onboard vehicle 1205, as described above with respect to FIG. 17 .

[0313] Process 1900 may further include identifying (step 1910) at least one line representation of a road surface feature extending along the road segment based on the 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 the environmental images received from camera 122, identify road edges or lane markings, and determine a trajectory of travel along 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 a trajectory of travel of vehicle 1205 based on the egomotion (e.g., three-dimensional translational and / or three-dimensional rotational) of the camera received in step 1905.

[0314] Process 1900 may also include identifying a plurality of landmarks associated with the road segment based on the plurality of images (step 1915). 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 analysis of a plurality of images acquired as one or more vehicles traverse the road segment. To enable crowdsourcing, the analysis may include rules for accepting and rejecting potential landmarks associated with the road segment. For example, the analysis may include accepting a potential landmark if the ratio of images in which the landmark appears to images in which the landmark does not appear exceeds a threshold, and / or rejecting a potential landmark if the ratio of images in which the landmark does not appear to images in which the landmark appears exceeds a threshold.

[0315] Process 1900 may include other operations or steps performed by server 1230. For example, the navigation information may include a target trajectory for a vehicle to travel along a road segment, and process 1900 may include server 1230 clustering vehicle trajectories associated with multiple vehicles traveling on the road segment and determining the target trajectory based on the clustered vehicle trajectories, as discussed in further detail below. Clustering the vehicle trajectories may include server 1230 clustering multiple trajectories associated with vehicles traveling on the road segment into multiple clusters based on at least one of the absolute heading of the vehicles or the lane designation of the vehicles. Generating the target trajectory may include server 1230 averaging the clustered trajectories. As a further example, process 1900 may include aligning the data received in step 1905. Other processes or steps performed by server 1230 may also be included in process 1900, as described above.

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

[0317] The disclosed systems and methods may enable autonomous vehicle navigation (e.g., steering control) using a low-footprint model, which may be collected by the autonomous vehicle itself without the aid of expensive surveying equipment. To assist in autonomous navigation (e.g., steering applications), the road model may include a sparse map having the road's geometry, its lane configuration, and landmarks that can be used to determine the vehicle's position or location along a trajectory contained in the model. As described above, generation of the sparse map may be performed by a remote server that communicates with and receives data from vehicles traveling on the road. This data may include sensory data, a reconstructed trajectory based on the sensory data, and / or a suggested trajectory that may represent a modification to the reconstructed trajectory. As discussed below, the server can subsequently transmit the model to the vehicle or to other vehicles traveling on the road to aid in autonomous navigation.

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

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

[0320] In addition to, or instead of, storage device 2010, server 1230 may include memory 2015. Memory 2015 may be similar to or different from memory 140 or 150. Memory 2015 may be non-transitory memory such as flash memory, random access memory, etc. Memory 2015 may be configured to store data, such as computer code or instructions executable by a processor (e.g., processor 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 execute computer codes or instructions stored in memory 2015 to perform various functions. For example, processing device 2020 may analyze navigation information received from vehicles 1205, 1210, 1215, 1220, and 1225 and generate a road navigation model for the autonomous vehicle based on the analysis. Processing device 2020 may control communication unit 1405 to distribute the road navigation model for the autonomous vehicle to one or more autonomous vehicles (e.g., one or more of vehicles 1205, 1210, 1215, 1220, and 1225, or any vehicles that subsequently travel road segment 1200). Processing device 2020 may be similar to or different from processor 180, 190, or processing unit 110.

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

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

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

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

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

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

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

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

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

[0331] To organize lanes from these trajectories, server 1230 may select a frame of reference for any lane. Server 1230 may map overlapping lanes into the selected frame of reference. Server 1230 may continue mapping until all lanes are in the same frame of reference. Adjacent lanes may be aligned as if they were the same lane, and may then 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 about the same landmark received on different drives may be slightly different. Such data may be averaged and mapped to the same reference frame, such as the C0 reference frame. Additionally or alternatively, the variance of data for the same landmark received on multiple drives may be calculated.

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

[0334] For localization of an autonomous vehicle, the disclosed system and method may use an extended Kalman filter. The vehicle's position may be determined based on a prediction of the vehicle's future position ahead of its current position through the integration of three-dimensional position data and / or three-dimensional orientation data and egomotion. The vehicle's localization 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 known landmarks stored in the road model or sparse map 800. The known landmark may have a known position (e.g., GPS data) along the target trajectory stored in the road model and / or sparse map 800. Based on the current speed and images 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 landmark position / location data (e.g., average values ​​from multiple drives) stored in the road model and / or sparse map 800 may be assumed to be accurate.

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

[0336] In some embodiments, poles along roads, such as lampposts and power or cable poles, may be used as landmarks for locating vehicles. Other landmarks, such as traffic signs, traffic lights, road arrows, stop lines, and static features or signatures of objects along road segments, may also be used as landmarks for locating vehicles. When using poles for location, observations of the pole in the x direction (i.e., the viewing angle from the vehicle) may be used rather than observations of the pole in the y direction (i.e., the distance to the pole), because the bottom of the pole may be obstructed and in some cases the pole may not be above the road surface.

[0337] FIG. 23 illustrates a navigation system for a vehicle, which may be used for automated navigation using a crowdsourced sparse map. For purposes of illustration, the vehicle is referred to as vehicle 1205. The vehicle illustrated in FIG. 23 may be any other vehicle disclosed herein, including, for example, vehicles 1210, 1215, 1220, and 1225, as well as vehicle 200 illustrated in other embodiments. As illustrated in FIG. 12, vehicle 1205 may be in communication with server 1230. Vehicle 1205 may include image capture device 122 (e.g., camera 122). Vehicle 1205 may include navigation system 2300 configured to provide navigation guidance for vehicle 1205 to travel along a road (e.g., road segment 1200). Vehicle 1205 may also include other sensors, such as a speed sensor 2320 and an accelerometer 2325. 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 the 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 the communication path 1235. The navigation system 2300 may also include a GPS unit 2310 configured to receive and process GPS signals. The navigation system 2300 may further include at least one processor 2315 configured to process data such as the GPS signals, map data from the sparse map 800 (which may be stored in a storage device onboard the vehicle 1205 and / or received from the server 1230), road geometry detected by the road profile sensor 2330, images captured by the camera 122, and / or 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 roughness, road width, road elevation, road curvature, etc. For example, the road profile sensor 2330 may include a device that measures the suspension movement of the vehicle 2305 to obtain a road unevenness 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 rise and fall of the road elevation. In some embodiments, the road profile sensor 2330 may include a device configured to measure road curvature. For example, a camera (e.g., camera 122 or another camera) may be used to capture images of the road that show the road curvature. The vehicle 1205 may use such images to detect the road curvature.

[0339] The at least one processor 2315 may be programmed to receive at least one environmental image associated with the vehicle 1205 from the camera 122. The at least one processor 2315 may analyze the at least one environmental image to determine navigation information associated with the vehicle 1205. The navigation information may include a trajectory associated with the vehicle 1205 traveling along the road segment 1200. The at least one processor 2315 may determine the trajectory based on the movement of the camera 122 (and thus the vehicle), such as three-dimensional translational and three-dimensional rotational movement. In some embodiments, the at least one processor 2315 may determine the translational and rotational movement 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 will travel in along the road segment 1200). The navigation information transmitted from vehicle 1205 to server 1230 may be used by server 1230 to generate and / or update a road navigation model for the autonomous vehicle, and this information may be transmitted from server 1230 to vehicle 1205 to provide automated navigation guidance to vehicle 1205.

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

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

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

[0343] [Navigation based on sparse maps]

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

[0345] Vehicle 200 may be configured to detect lane markings on a given road segment. A road segment may include any markings on a roadway for guiding vehicular traffic on the roadway. For example, lane markings may be solid or dashed lines that define the edges of travel lanes. Lane markings may also include double lines, such as double solid lines, double dashed lines, or a combination of solid and dashed lines, to indicate whether passing is permitted in an adjacent lane. Lane markings may also include highway on- and off-ramp markings, such as deceleration lanes for exit ramps or dotted lines indicating that a lane is for turning only or that the lane is ending. These markings may also indicate work zones, temporary lane shifts, routes through intersections, medians, reserved lanes (e.g., bicycle lanes, HOV lanes, etc.), or various other markings (e.g., crosswalks, vehicle slowdown humps, railroad crossings, stop lines, etc.).

[0346] Vehicle 200 may capture images of surrounding lane markings using cameras, such as image capture devices 122 and 124 included in image acquisition unit 120. Vehicle 200 may analyze these images to detect the locations of points associated with the lane markings based on features identified in one or more of the captured images. These point locations may be uploaded to a server to represent the lane markings in 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 captured using various cameras mounted on multiple sides of the vehicle. Rather than uploading actual images of the lane markings, these marks may be stored in sparse map 800 as a spline or a series of points, thus reducing the size of sparse map 800 and / or the data that the vehicle needs to upload remotely.

[0347] 24A-24D illustrate exemplary locations of points representing a particular lane marking that may be detected by vehicle 200. Similar to the landmarks described above, vehicle 200 may use various image recognition algorithms or software to identify the location of points within a captured image. For example, vehicle 200 may recognize the location of a series of edge points, corner points, or various other points associated with a particular lane marking. FIG. 24A illustrates a solid lane marking 2410 that may be detected by vehicle 200. Lane marking 2410 represents the outer edge of the roadway and may be represented by a solid white line. As shown in FIG. 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 mapped lane marking in a sparse map. For example, lane markings may be represented at one point every meter of the detected edge, one point every five meters of the detected edge, or other suitable intervals. In some embodiments, the intervals may be determined by other factors rather than a predetermined interval, such as based on the point where the vehicle 200 has the highest confidence ranking for the location of the detected point. While FIG. 24A shows edge location points on the inside edge of the lane marking 2410, points may also be collected on the outside edge of the line or along both edges. Furthermore, while FIG. 24A shows a single line, similar edge points may be detected for double solid lines. For example, points 2411 may be detected along one or both edges of the solid line.

[0348] Vehicle 200 may also represent lane markings differently depending on the type or shape of the lane marking. FIG. 24B shows an example dashed lane marking 2420 that may be detected by vehicle 200. Rather than identifying edge points as in FIG. 24A, the vehicle may detect a series of corner points 2421 that represent the corners of the lane dashes that define the entire boundary of the dashed line. While FIG. 24B shows each corner of a given dashed line marking being located, 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 line marking, or may detect the two corner points closest to the inside of the lane. Further, not all dashed line markings need to be captured; for example, vehicle 200 may capture and / or record points representing a sample of dashed line markings (e.g., every other, every third, every fifth, etc.) or points representing dashed line markings at predetermined intervals (e.g., every meter, every 5 meters, every 10 meters, etc.). Corner points may also be detected for similar lane markings, such as markings indicating that a lane is for an exit ramp, 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 that consist of double dashed lines or a combination of solid and dashed lines.

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

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

[0351] Vehicle 200 may associate actual coordinates with each detected point of the lane markings. For example, a location identifier including the coordinates of each point may be generated and uploaded to a server for mapping the lane markings. The location identifier may further include other identifying information about the points, including whether the points represent corner points, edge points, center points, etc. Accordingly, vehicle 200 may be configured to determine the actual location 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 identify the actual locations of the lane markings. This may include determining the location of the lane markings in the image relative to the detected landmarks, or determining the location 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 not available, the location of the lane marking points may be determined relative to the vehicle's location determined based on dead reckoning. The actual coordinates included in the location identifiers may be expressed as absolute coordinates (e.g., latitude / longitude coordinates) or may be related to other features, such as based on longitudinal position along the target trajectory and lateral distance from the target trajectory. The location identifiers may then be uploaded to a server to generate mapped lane markings in a navigation model (e.g., sparse map 800). In some embodiments, the server may construct splines representing the lane markings of the road segment. Alternatively, vehicle 200 may generate the splines and upload them to the server so that they are recorded in the navigation model.

[0352] 24E illustrates an example navigation model or sparse map of a corresponding road segment including mapped lane markings. The sparse map may include a target trajectory 2475 for the vehicle to follow along the road segment. As described above, the target trajectory 2475 may represent an ideal path for the vehicle to follow when traveling the corresponding road segment, or may be located elsewhere on the road (e.g., the centerline of the road, etc.). The target trajectory 2475 may be calculated in various ways as described above, for example, based on an aggregation (e.g., a weighted combination) of two or more reconstructed trajectories of vehicles traveling the same road segment.

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

[0354] The sparse map may also include mapped lane markings 2470 and 2480 representing lane markings along the road segment. The mapped lane markings may be represented by multiple location identifiers 2471 and 2481. As described above, the location identifiers may include locations in actual coordinates of points associated with the detected lane markings. Like 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, the curve may be a spline connecting three-dimensional polynomials of a suitable degree, which may be calculated based on the location identifiers. The mapped lane markings may also include other information or metadata about the lane markings, such as an identifier for the type of lane marking (e.g., between two lanes of the same direction of travel, between two lanes of opposite directions of travel, edge of a roadway, etc.) and / or other characteristics of the lane markings (e.g., solid line, dashed line, single line, double line, yellow line, white line, etc.). In some embodiments, the mapped lane markings may be constantly updated within the model, for example, using crowdsourcing techniques. The same vehicle may upload location identifiers on multiple occasions traveling the same road segment, or data may be selected from multiple vehicles (e.g., 1205, 1210, 1215, 1220, and 1225) traveling the road segment at different times. 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. As the mapped lane markings are updated and fine-tuned, the updated road navigation model and / or sparse map may be distributed to multiple autonomous vehicles.

[0355] Generating mapped lane markings in the sparse map may also include detecting and / or mitigating errors based on anomalies in the image or the actual lane markings themselves. FIG. 24F illustrates an example anomaly 2495 associated with detecting lane markings 2490. Anomalies 2495 may appear in images captured by vehicle 200 due to, for example, an object blocking the camera's view of the lane markings, dust on the lens, etc. In some cases, anomalies may be caused by the lane markings themselves, such as when the lane markings are damaged or worn, or are partially covered by, for example, dirt, debris, water, snow, or other roadway material. Anomalies 2495 may result in incorrect points 2491 being detected by vehicle 200. Sparse map 800 may correct the mapped lane markings to eliminate the errors. In some embodiments, vehicle 200 may detect erroneous point 2491, for example, by detecting anomaly 2495 in the image or by identifying the error based on lane marking points detected before and after the anomaly. Based on the detection of the anomaly, the vehicle may exclude point 2491 or adjust the point to follow other detected points. In other embodiments, the error may be corrected after the point is uploaded, for example, by determining that the point falls outside of an expected threshold based on other points uploaded during the same journey or based on an aggregation of data from previous journeys along the same road segment.

[0356] The lane markings mapped in the navigation model and / or sparse map may also be used for navigation by an autonomous vehicle traveling on the corresponding roadway. For example, a vehicle navigating along a target trajectory may periodically use the mapped lane markings in the sparse map to align itself with the target trajectory. As described above, between landmarks, a vehicle may navigate based on dead reckoning, in which the vehicle uses sensors to identify its own ego-motion and estimate its position relative to the target trajectory. Errors may accumulate over time, causing the vehicle's position determination relative to the target trajectory to become increasingly less accurate. Therefore, the vehicle can use the lane markings present in the sparse map 800 (and their known positions) to reduce dead reckoning errors in its position determination. In this way, the identified lane markings included in the sparse map 800 can serve as a navigation linchpin that can determine the vehicle's precise position relative to the target trajectory.

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

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

[0359] The vehicle may also determine its longitudinal position, represented by element 2520, along the target trajectory. The longitudinal position 2520 may be determined from the image 2500, for example, by detecting landmarks 2521 in the image 2500 and comparing the measured positions with the positions of known landmarks 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 landmarks and the known positions of the landmarks. The longitudinal position 2520 may also be determined from images other than those used to determine the positions of the lane markings. For example, the longitudinal position 2520 may be determined by detecting landmarks in images taken at or near the same time as the image 2500 from other cameras in the image acquisition unit 120. In some cases, the vehicle may not be near any landmarks or other reference points to determine the longitudinal position 2520. In such cases, the vehicle may navigate based on dead reckoning, and thus may use sensors to identify the egomotion of the vehicle and estimate its longitudinal position relative to the target trajectory 2520. The vehicle may also determine distance 2530, which represents the actual distance between the vehicle and the lane markings 2510 observed in one or more captured images. Camera angle, vehicle speed, vehicle width, or various other factors may be considered in determining distance 2530.

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

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

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

[0363] These changes in the image space representation of objects, such as signs 2566, may be exploited to determine the location of the located host vehicle along the target trajectory. For example, as described in this disclosure, any detectable object or feature, such as a semantic feature, such as signs 2566, or detectable and non-semantic features, may be identified by one or more collection vehicles that have previously traversed a road segment (e.g., road segment 2560). A mapping server may collect the collected driving information from multiple vehicles, aggregate and correlate the information, and generate a sparse map including the target trajectory 2565, for example, lane 2564 of road segment 2560. The sparse map may also store the locations of signs 2566 (along with type information, etc.). During navigation (e.g., before entering road segment 2560), the host vehicle may be provided with map tiles including the sparse map for road segment 2560. To navigate in lane 2564 of road segment 2560, the host vehicle may follow mapped target trajectory 2565.

[0364] The mapped representation of landmark 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, and the captured image 2570 may include an image representation of landmark 2566 having a particular size and a particular XY image location, as shown in FIG. 25D . This size and XY image location can be used to determine the host vehicle's position relative to the target trajectory 2565. For example, based on the sparse map including the representation of landmark 2566, the host vehicle's navigation processor may determine that, in the captured image, the representation of landmark 2566 should appear such that the center of landmark 2566 moves (in image space) along line 2567, in response to the host vehicle traveling along the target trajectory 2565. If a captured image, such as image 2570, shows a center (or other reference point) that is displaced from line 2567 (e.g., the expected image space trajectory), then the host vehicle navigation system can determine that it was not located on target trajectory 2565 at the time of the captured image. However, the navigation processor can determine from the image appropriate navigation corrections to return the host vehicle to target trajectory 2565. For example, if the analysis results show the image position of landmark 2566 in the image to be displaced a distance 2572 to the left of its expected image space location on line 2567, the navigation processor may then cause the host vehicle to make a heading change (e.g., change the steering angle of the steering wheel) to move the host vehicle a distance 2573 to the left. In this manner, each captured image can be used as part of a feedback loop process so that the difference between the observed image position of landmark 2566 and the expected image trajectory 2567 is minimized to ensure that the host vehicle continues along target trajectory 2565 with little deviation.Of course, the more mapped objects available, the more frequently the described localization techniques can be used, which can reduce or eliminate deviations due to drift from the target trajectory 2565.

[0365] The above-described processing may be useful for detecting the lateral orientation or displacement of the host vehicle relative to the target trajectory. Locating the host vehicle relative to the target trajectory 2565 may also include determining the target vehicle's longitudinal position along the target trajectory. For example, captured image 2570 includes a representation of landmark 2566 as having a particular image size (e.g., 2D XY pixel area). This size can be compared to the expected image size of the mapped landmark 2566 as it travels through image space along line 2567 (e.g., as the landmark size progressively increases, as shown in FIG. 25C ). Based on the image size of landmark 2566 in image 2570 and the expected size progression in image space relative to the mapped target trajectory 2565, the host vehicle can determine its longitudinal position relative to the target trajectory 2565 (at the time image 2570 was captured). This longitudinal position combined with any lateral displacement relative to target trajectory 2565 allows for full localization of the host vehicle relative to target trajectory 2565 as the host vehicle navigates along road 2560, as described above.

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

[0367] FIG. 26A is a flowchart illustrating an example process 2600A for mapping lane markings for use in automated vehicle navigation, consistent with disclosed embodiments. At step 2610, process 2600A may include receiving two or more location identifiers associated with the detected lane markings. For example, step 2610 may be performed by server 1230 or one or more processors associated with the server. The location identifiers may include locations in actual coordinates of points associated with the detected lane markings, as described above with respect to FIG. 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 types of data as described above, may also be received at step 2610. The position identifiers may be generated by vehicles, such as vehicles 1205, 1210, 1215, 1220, and 1225, based on images captured by the vehicles. For example, the identifiers may be determined based on obtaining at least one image representing the host vehicle's environment from a camera associated with the host vehicle, analyzing the at least one image to detect lane markings in the host vehicle's environment, and analyzing the at least one image to determine the positions of the detected lane markings relative to a location associated with the host vehicle. As described above, lane markings may include a variety of different marking types, and the position identifiers may correspond to various points associated with the lane markings. For example, if the detected lane markings are part of dashed line markings representing lane boundaries, the points may correspond to corners of the detected lane markings. If the detected lane markings are part of solid line markings representing lane boundaries, the points may correspond to edges of the lane markings detected at the various intervals described above. In some embodiments, these points may correspond to the centerlines of the detected lane markings, as shown in FIG. 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 FIG. 24D.

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

[0369] At step 2614, process 2600A may include updating an automated 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 automated road navigation model may be sparse map 800, and server 1230 may update the sparse map to include or adjust the mapped lane markings in the model. Server 1230 may update the model based on various methods or processes described above with respect to FIG. 24E. In some embodiments, updating the automated vehicle road navigation model may include storing one or more indicators of the locations of the detected lane markings in actual coordinates. The automated 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 FIG. 24E.

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

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

[0372] FIG. 26B is a flowchart illustrating an example process 2600B for autonomously navigating a host vehicle along a road segment using mapped lane markings. Process 2600B may be performed, for example, by processing unit 110 of autonomous vehicle 200. At step 2620, process 2600B may include receiving 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 location identifiers associated with one or more lane markings associated with the road segment. For example, vehicle 200 may receive sparse map 800 or another road navigation model developed using process 2600A. In some embodiments, the target trajectory may be represented as a cubic spline, for example, as shown in FIG. 9B. As discussed above with respect to Figures 24A-24F, the location identifiers may include the location in actual coordinates of points associated with lane markings (e.g., corner points of dashed lane markings, edge points of solid lane markings, intersections of two intersecting lane markings and other points associated with intersecting lane markings, centerlines associated with lane markings, etc.).

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

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

[0375] In step 2623, process 2600B may include determining an expected lateral distance to the 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 the at least one lane marking. For example, vehicle 200 may determine the expected lateral distance to the lane marking using sparse map 800. As shown in FIG. 25B , a longitudinal position 2520 along target trajectory 2555 may be determined in step 2622. Using sparse map 800, vehicle 200 can determine an expected distance 2540 to a mapped lane marking 2550 that corresponds to longitudinal position 2520.

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

[0377] In step 2625, process 2600B may include determining an actual lateral distance to at least one lane marking based on analysis of the at least one image. For example, the vehicle may determine distance 2530, which represents the actual distance between the vehicle and lane marking 2510, as shown in FIG. 25A. The camera angle, the speed of the vehicle, the width of the vehicle, the position of the camera relative to the vehicle, or various other factors may be considered in determining distance 2530.

[0378] In step 2626, process 2600B may include determining an autopilot action of the host vehicle based on a difference between the expected lateral distance to the at least one lane marking and the determined actual lateral distance to the at least one lane marking. For example, as described above with respect to FIG. 25B , vehicle 200 may compare actual distance 2530 with expected distance 2540. The difference between the actual distance and the expected distance may indicate an error (and its magnitude) between the vehicle's actual position and a target trajectory along which the vehicle will travel. Thus, the vehicle may determine an autopilot action or other automated action based on this difference. For example, as shown in FIG. 25B , if actual distance 2530 is less than expected distance 2540, the vehicle may determine an autopilot action to guide the vehicle to the left, away from lane marking 2510. Thus, the vehicle's position relative to the target trajectory may 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 maps. In other examples, processes consistent with those described in connection with Figures 25C and 25D may also be used.

[0380] [Ego-motion correction of 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 information related to the road. 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 by the object) even though the object itself is not moving. As such, in some cases, small and slowly moving objects may be difficult to detect in complex, cluttered scenes. Also, conventional LIDAR systems may erroneously identify smaller objects as moving objects. Similarly, conventional LIDAR systems may erroneously identify a moving object (e.g., a target vehicle) that is moving with the host vehicle as a non-moving object. Therefore, it may be desirable to reduce or eliminate the possibility of erroneously identifying a non-moving object as a moving object (or vice versa). This disclosure describes systems and methods for correlating multiple LIDAR points across two or more frames and removing depth effects caused by egomotion of a host vehicle. After the effects caused by egomotion are removed, stationary objects (e.g., non-moving background objects) may exhibit no velocity (i.e., their velocity is equal to zero), and moving objects may be identified as having multiple points with velocities greater than zero.

[0382] The present disclosure provides, for example, a system that may determine at least one indicator of egomotion of a host vehicle. Egomotion of a host vehicle may refer to any environmental displacement of the host vehicle relative to a non-moving reference point or object. For example, as described elsewhere in this disclosure, egomotion of a camera (and therefore a vehicle body) may be estimated based on optical flow analysis of captured images. The optical flow analysis of a series of images identifies pixel movement in the series of images, and vehicle movement is determined based on the identified movement. The system may also be configured to receive, from a LIDAR system associated with the host vehicle, a first point cloud, e.g., at a first time point, based on a first LIDAR scan of a field of view of the LIDAR system. The first point cloud may include a first representation of at least a portion of the object. The system may further be configured to receive, from the LIDAR system, a second point cloud, e.g., at a second time point, based on a second LIDAR scan of a field of view of the LIDAR system. The second point cloud may include a second representation of at least a portion of the object. The system may also determine a velocity of the object based on at least one indicator of egomotion of the host vehicle and based on a comparison of a first point cloud including a first representation of at least a portion of the object and a second point cloud including a second representation of at least a portion of the object.

[0383] 27 illustrates an example system 2700 for detecting one or more objects in an environment of a host vehicle consistent with disclosed embodiments. As shown in FIG. 27, system 2700 may include a server 2710, one or more vehicles 2720 (e.g., vehicle 2720a, vehicle 2720b, ..., vehicle 2720n), a network 2730, and a database 2740.

[0384] Vehicle 2720 may collect information from its environment and transmit the collected information to server 2710, for example, via network 2730. For example, vehicle 2720 may include one or more sensors configured to collect data and information from its environment. Vehicle 2720 may transmit the data and information (or data obtained therefrom) to server 2710. As an example, vehicle 2720 may include an image sensor (e.g., a camera) configured to capture one or more images of its environment. As another example, vehicle 2720 may include a LIDAR system configured to collect LIDAR reflectance information within a 360-degree field of view around vehicle 2720, or from any subportion of the 360-degree field of view (e.g., one or more FOVs each representing less than 360 degrees). In some embodiments, vehicle 2720 may include a LIDAR system and one or more cameras.

[0385] Server 2710 may process data and / or information received from one or more vehicles 2720. For example, server 2710 may receive information related to objects (e.g., locations of objects) from vehicles 2720. Server 2710 may update a map to add objects to (or remove objects from) the map. In some embodiments, server 2710 may transmit the updated map (or at least a portion thereof) to one or more vehicles 2720.

[0386] While FIG. 27 illustrates one server 2710, those skilled in the art will understand that system 2700 may include one or more servers 2710 performing the functions of server 2710 disclosed herein, individually or in combination. For example, server 2710 may comprise a cloud server group including two or more servers performing the functions disclosed herein. The term "cloud server" refers to a computer platform that provides services over a network such as the Internet. In this example configuration, server 2710 may use a virtual machine that may not correspond to individual hardware. For example, computing and / or storage capabilities may be implemented by allocating appropriate portions of computing / storage power from a scalable repository, such as a data center or distributed computing environment. In one example, server 2710 may implement the methods described herein using customized hardwired logic, one or more application-specific integrated circuits (ASICs) or field-programmable gate arrays (FPGAs), firmware, and / or program logic that, in combination with a computer system, renders server 2710 a dedicated machine.

[0387] The network 2730 may be configured to facilitate communication between multiple components of the system 2700. The network 2730 may comprise wired and wireless communication networks, such as a local area network (LAN), a wide area network (WAN), a computer network, a wireless network, a telecommunications network, etc., or a combination thereof.

[0388] Database 2740 may be configured to store information and data for one or more components of system 2700. For example, database 2740 may store data (e.g., map data) for server 2710. One or more vehicles 2720 may obtain the map data stored in database 2740, for example, via network 2730.

[0389] 28 is a block diagram of an example server 2710 consistent with the disclosed embodiments. As shown in FIG. 28, the server 2710 may include at least one processor (e.g., processor 2801), memory 2802, at least one storage device (e.g., storage device 2803), communication port 2804, and I / O device 2805.

[0390] The processor 2801 may be configured to perform one or more functions of the server 2710 described in this disclosure. The processor 2801 may include a microprocessor, a preprocessor (such as an image preprocessor), a graphics processing unit (GPU), a central processing unit (CPU), support circuitry, a digital signal processor, an integrated circuit, memory, or any other type of device suitable for running applications or perf...

Claims

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

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

3. The LIDAR point cloud information is treated as reference depth information or actual depth values ​​for training the neural network. The navigation system according to claim 2 .

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

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

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

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

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

8. The navigation system according to claim 7.

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

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

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

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

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

13. the at least one navigation operation includes at least one of accelerating, braking, or turning the host vehicle; A navigation system according to any one of claims 1 to 12.

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

15. the per-pixel depth information for the at least one region of the captured central image provides depth information for one or more objects represented in the captured central image; the one or more objects are not in contact with the ground; A navigation system according to any one of claims 1 to 14.

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

17. The ground surface includes a road surface.

17. A navigation system according to claim 15 or 16.

18. the per-pixel depth information for the at least one region of the captured central image provides depth information for a surface of at least one object represented in the captured central image; the surface of the at least one object includes a reflection of one or more other objects; A navigation system according to any one of claims 1 to 17.

19. the per-pixel depth information for the at least one region of the captured center image provides depth information related to objects that are at least partially obscured from view in one or more of the at least one captured center image, the at least one captured left surround image, or the at least one captured right surround image.

19. A navigation system according to any one of claims 1 to 18.

20. each of the training data includes three images each captured by one of a group of cameras including the center camera, the left surround camera, and the right surround camera; 20. A navigation system according to any one of claims 1 to 19.

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

Images