Fusion architecture and batch alignment of navigation information for autonomous navigation

Abstract

The present disclosure relates to systems and methods for navigating a vehicle. In one embodiment, at least one processing device may receive a first output from a first data source and a second output from a second data source; identify a representation of a target object in the first output; determine whether a characteristic of the target object triggers at least one navigation constraint; if the characteristic of the target object does not trigger at least one navigation constraint, verify the identification of the representation of the target object based on a combination of the first output and the second output; if the characteristic of the target object triggers at least one navigation constraint, verify the identification of the representation of the target object based on the first output; and in response to the verification, cause at least one navigation change of the vehicle.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 519,471, filed on June 14, 2017, and U.S. Provisional Patent Application No. 62 / 519,493, filed on June 14, 2017. All of the foregoing applications are incorporated herein by reference in their entirety. Technical Field

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

[0004] As technology continues to advance, the goal of fully autonomous vehicles that can navigate on the road is about to appear. Autonomous vehicles may need to consider a variety of factors and make appropriate decisions based on those factors to safely and accurately reach the intended destination. For example, autonomous vehicles may need to process and interpret visual information (e.g., information captured from a camera), and may also use information obtained from other sources (e.g., from a GPS device, a speed sensor, an accelerometer, a suspension sensor, etc.). At the same time, in order to navigate to the destination, the autonomous vehicle may also need to identify its position in a specific road (e.g., a specific lane in a multi-lane road), navigate along the side of other vehicles, avoid obstacles and pedestrians, observe traffic signals and signs, and drive from one road to another at an appropriate intersection or junction. Utilizing and interpreting the large amount of information collected by the autonomous vehicle as it travels to its destination brings many design challenges. The absolutely large amount of data (e.g., captured image data, map data, GPS data, sensor data, etc.) that the autonomous vehicle may need to analyze, access and / or store brings challenges that may actually limit or even adversely affect autonomous navigation. Furthermore, if autonomous vehicles rely on traditional mapping technology for navigation, the sheer volume of data required to store and update maps presents a daunting challenge.

[0005] In addition to collecting data for updating maps, autonomous vehicles must also be able to use maps for navigation. Therefore, the size and detail of the maps, as well as their construction and transmission, must be optimized. Furthermore, autonomous vehicles must navigate using maps and using constraints based on the vehicle's surroundings to ensure the safety of its passengers and other drivers and pedestrians on the road. Summary of the invention

[0006] Embodiments consistent with the present disclosure provide systems and methods for autonomous vehicle navigation. The disclosed embodiments can use cameras to provide autonomous vehicle navigation features. For example, consistent with the disclosed embodiments, the disclosed system can include one, two or more cameras that monitor the vehicle environment. The disclosed system can provide navigation response based on, for example, analysis of images captured by one or more cameras. The disclosed system can also provide for building and navigating using crowdsourced sparse maps. Other disclosed systems can use correlation analysis of images to perform positioning, which can use sparse maps to supplement navigation. The navigation response can also consider other data, including, for example, global positioning system (global positioning system, GPS) data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data. Finally, the disclosed embodiments can use comfort and safety constraints to fuse data from multiple sources (such as, cameras, sensors, maps, etc.) to optimize the navigation of the vehicle without endangering other drivers and pedestrians.

[0007] In one embodiment, a navigation system for a host vehicle may include at least one processing device. The at least one processing device may be programmed to receive a first output from a first data source associated with the host vehicle and a second output from a second data source associated with the host vehicle. At least one of the first data source and the second data source may include a sensor on the host vehicle. The at least one processing device may be further programmed to: identify a representation of a target object in the first output; determine whether a characteristic of the target object triggers at least one navigation constraint; if the characteristic of the target object does not trigger at least one navigation constraint, verify the identification of the representation of the target object based on a combination of the first output and the second output; if the characteristic of the target object triggers at least one navigation constraint, verify the identification of the representation of the target object based on the first output; and in response to the verification, cause at least one navigation change of the host vehicle.

[0008] In one embodiment, a computer-implemented method for navigating a host vehicle may include receiving a first output from a first data source associated with the host vehicle and receiving a second output from a second data source associated with the host vehicle. At least one of the first data source and the second data source may include a sensor on the host vehicle. The method may further include: identifying a representation of a target object in the first output; determining whether a characteristic of the target object triggers at least one navigation constraint; if the characteristic of the target object does not trigger at least one navigation constraint, verifying the identification of the representation of the target object based on a combination of the first output and the second output; if the characteristic of the target object triggers at least one navigation constraint, verifying the identification of the representation of the target object based on the first output; and in response to the verification, causing at least one navigation change of the host vehicle.

[0009] In one embodiment, a server for aligning navigation information from multiple vehicles may include at least one processing device. The at least one processing device may be programmed to receive navigation information from the multiple vehicles. The navigation information from the multiple vehicles may be associated with a common road segment. The at least one processing device may be further programmed to align the navigation information within a coordinate system local to the common road segment. The local coordinate system may include a coordinate system based on multiple images captured by image sensors included on the multiple vehicles. The at least one processing device may be further programmed to store the aligned navigation information in association with the common road segment and distribute the aligned navigation information to one or more autonomous vehicles for autonomous navigation of the one or more autonomous vehicles along the common road segment.

[0010] In one embodiment, a computer-implemented method for aligning navigation information from a plurality of vehicles may include receiving navigation information from the plurality of vehicles. The navigation information from the plurality of vehicles may be associated with a common road segment. The method may further include aligning the navigation information within a coordinate system local to the common road segment. The local coordinate system may include a coordinate system based on a plurality of images captured by image sensors included on the plurality of vehicles. The method may further include storing the aligned navigation information in association with the common road segment, and distributing the aligned navigation information to one or more autonomous vehicles for autonomously navigating the one or more autonomous vehicles along the common road segment.

[0011] Consistent with other disclosed embodiments, a non-transitory computer-readable storage medium may store program instructions that are executed by at least one processing device and perform any of the methods described herein.

[0012] The foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate various disclosed embodiments.

[0014] In the attached picture:

[0015] Figure 1 are pictorial representations of exemplary systems consistent with the disclosed embodiments.

[0016] Figure 2A is a diagrammatic side view representation of an example vehicle including systems consistent with the disclosed embodiments.

[0017] Figure 2B is consistent with the disclosed embodiments Figure 2A A diagrammatic top view representation of the vehicle and systems shown in .

[0018] Figure 2C is a diagrammatic top view representation of another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0019] Figure 2D is a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0020] Figure 2E is a diagrammatic top view representation of yet another embodiment of a vehicle including a system consistent with the disclosed embodiments.

[0021] Figure 2F is a pictorial representation of an exemplary vehicle control system consistent with the disclosed embodiments.

[0022] Figure 3A is a pictorial representation of the interior of a vehicle including a rearview mirror and a user interface for a vehicle imaging system consistent with the disclosed embodiments.

[0023] Figure 3B is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.

[0024] Figure 3C is consistent with the disclosed embodiments Figure 3B Illustration of the camera installation from different viewing angles shown in FIG.

[0025] Figure 3D is an illustration of an example of a camera mount configured to be positioned behind a rearview mirror and against a vehicle windshield consistent with the disclosed embodiments.

[0026] Figure 4 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0027] Figure 5A is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments.

[0028] Figure 5B is a flow chart illustrating an exemplary process for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments.

[0029] Figure 5C is a flow chart illustrating an exemplary process for detecting road markings and / or lane geometry information in a set of images consistent with the disclosed embodiments.

[0030] Figure 5D is a flow chart illustrating an exemplary process for detecting traffic lights in a set of images consistent with the disclosed embodiments.

[0031] Figure 5E is a flow chart illustrating an exemplary process for inducing one or more navigation responses based on a vehicle path, consistent with the disclosed embodiments.

[0032] Fig. 5F is a flow chart illustrating an exemplary process for determining whether a leading vehicle is changing lanes, consistent with the disclosed embodiments.

[0033] Figure 6 is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on stereoscopic image analysis consistent with the disclosed embodiments.

[0034] Figure 7 is a flow chart illustrating an exemplary process for eliciting one or more navigation responses based on analysis of three sets of images consistent with the disclosed embodiments.

[0035] Fig. 8A A polynomial representation of a portion of a road segment consistent with disclosed embodiments is shown.

[0036] Figure 8B A curve in three-dimensional space is shown that represents a target trajectory for a vehicle for a particular road segment included in a sparse map consistent with the disclosed embodiments.

[0037] Fig. 9A A polynomial representation of a trajectory consistent with the disclosed embodiments is shown.

[0038] Fig. 9B and 9C A target trajectory along a multi-lane road is shown consistent with the disclosed embodiments.

[0039] Fig.9DAn example road signature distribution consistent with disclosed embodiments is shown.

[0040] Fig.10 An example autonomous vehicle road navigation model represented by a plurality of three-dimensional splines is shown consistent with the disclosed embodiments.

[0041] Fig.11 A map framework generated by combining position information from many trips consistent with the disclosed embodiments is shown.

[0042] Fig.12 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0043] Fig.13A and 13B Schematic diagrams of example safety and comfort constraints consistent with the disclosed embodiments are provided.

[0044] Fig. 13C and 13D Schematic diagrams of other example safety and comfort constraints consistent with the disclosed embodiments are provided.

[0045] Fig.14 A flow chart is provided that illustrates an exemplary process for navigating a host vehicle based on safety and comfort constraints consistent with the disclosed embodiments.

[0046] Fig.15 is an exemplary block diagram of a memory configured to store instructions for performing one or more operations consistent with the disclosed embodiments.

[0047] Fig.16 Example road data produced by combining navigation information from many trips and an example global map generated by combining the road data are shown consistent with the disclosed embodiments.

[0048] Fig.17 A flow chart is provided that illustrates an exemplary process for aligning navigation information from multiple vehicles consistent with the disclosed embodiments. DETAILED DESCRIPTION

[0049] The following detailed description refers to the accompanying drawings. Whenever possible, the same reference numerals are used in the drawings and the following description to refer to the same or similar parts. Although several exemplary embodiments are described herein, modifications, adjustments, and other implementations are possible. For example, the components shown in the drawings may be replaced, added, or modified, and the exemplary methods described herein may be modified by replacing, reordering, removing, 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.

[0050] Autonomous Vehicle Overview

[0051] As used throughout this disclosure, the term "autonomous vehicle" refers to a vehicle that is capable of implementing at least one navigation change without driver input. "Navigation change" refers to a change in one or more of the steering, braking, or acceleration of the vehicle. By autonomous, it is meant that the vehicle need not be fully automatic (e.g., fully operating without a driver or without driver input). In contrast, autonomous vehicles include those vehicles that are capable of operating under the control of a driver during certain time periods and operating without driver control during other time periods. Autonomous vehicles may also include vehicles that only control some aspects of vehicle navigation, such as steering (e.g., maintaining the vehicle route between vehicle lane constraints), but may leave other aspects to the driver (e.g., braking). In some cases, an autonomous vehicle may handle some or all aspects of braking, speed control, and / or steering of the vehicle.

[0052] Because human drivers typically rely on visual cues and observations in order to control vehicles, traffic infrastructure has been built with lane markings, traffic signs, and traffic lights that are all designed to provide visual information to drivers. In view of these design characteristics of the traffic infrastructure, 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, components of the traffic infrastructure (e.g., lane markings, traffic signs, traffic lights, etc.) that can be observed by the driver, as well as other obstacles (e.g., other vehicles, pedestrians, debris, etc.). In addition, autonomous vehicles may also use stored information, such as information that provides a model of the vehicle's environment when navigating. For example, a vehicle may use GPS data, sensor data (e.g., from accelerometers, speed sensors, suspension sensors, etc.), and / or other map data to provide information about its environment while the vehicle is traveling, and the vehicle (and other vehicles) may use the information to locate itself on the model.

[0053] In some embodiments of the present disclosure, an autonomous vehicle may use information obtained while navigating (e.g., from a camera, GPS device, accelerometer, speed sensor, suspension sensor, etc.). In other embodiments, an autonomous vehicle may use information obtained from past navigations of the vehicle (or other vehicles) while navigating. In other embodiments, an autonomous vehicle may use a combination of information obtained while navigating and information obtained from past navigations. The following sections provide an overview of systems consistent with the disclosed embodiments, followed by an overview of a forward imaging system and methods consistent with the system. The following sections disclose systems and methods for building, using, and updating sparse maps for autonomous vehicle navigation.

[0054] System Overview

[0055] Figure 1 1 is a block diagram representation of a system 100 consistent with the disclosed exemplary embodiments. Depending on the requirements of a particular implementation, the system 100 may include various components. In some embodiments, the system 100 may include a processing unit 110, an image acquisition unit 120, a position sensor 130, one or more memory units 140, 150, a map database 160, a user interface 170, and a wireless transceiver 172. The processing unit 110 may include one or more processing devices. In some embodiments, the processing unit 110 may include an application processor 180, an image processor 190, or any other suitable processing device. Similarly, depending on the requirements of a particular application, the image acquisition unit 120 may include any number of image acquisition devices and components. In some embodiments, the image acquisition unit 120 may include one or more image capture devices (e.g., cameras), such as an image capture device 122, an image capture device 124, and an image capture device 126. The system 100 may also include a data interface 128 that communicatively connects the processing device 110 to the image capture device 120. For example, the data interface 128 may include any wired and / or wireless link or links for transmitting image data acquired by the image acquisition device 120 to the processing unit 110 .

[0056] The wireless transceiver 172 may include one or more devices configured to exchange transmissions to one or more networks (e.g., cellular, Internet, etc.) over an air interface using radio frequencies, infrared frequencies, magnetic fields, or electric fields. The wireless transceiver 172 may send and / or receive data using any known standard (e.g., Wi-Fi, Bluetooth Smart, 802.15.4, ZigBee, etc.). Such transmissions may include communications from the host vehicle to one or more remotely located servers. Such transmissions may also include communications (one-way or two-way) between the host vehicle and one or more target vehicles in the host vehicle's environment (e.g., to coordinate navigation of the host vehicle with or in conjunction with target vehicles in the host vehicle's environment), or even broadcast transmissions to unspecified recipients in the vicinity of the sending vehicle.

[0057] 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), auxiliary circuits, a digital signal processor, an integrated circuit, a memory, or any other type of device suitable for running applications and suitable for 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, a mobile device microcontroller, a central processing unit, etc. Various processing devices may be used, including, for example, those available from, for example, processors from manufacturers such as GPUs from manufacturers such as wait).

[0058] In some embodiments, the application processor 180 and / or the image processor 190 may include a processor that can be Any of the EyeQ series processor chips available. These processor designs 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, Using 90 nanometer-micron technology operating at 332Mhz. The architecture consists of two floating-point hyperthreaded 32-bit RISC CPUs ( cores), five visual computing engines (VCEs), and three vector microcode processors The MIPS34K CPU manages five VCEs, three VMPTMs and DMA, a second MIPS34K CPU and multi-channel DMA, and other peripherals. and MIPS34K CPUs can perform the intensive visual calculations required for multi-function bundled applications. Six times stronger can be used in the disclosed embodiments. In other examples, can be used in the disclosed embodiments and / or Of course, any newer or future EyeQ processing devices may also be used with the disclosed embodiments.

[0059] Any of the processing devices disclosed herein may be configured to perform certain functions. Configuring a processing device (such as any described EyeQ processor or other controller or microprocessor) to perform certain functions may include programming computer executable instructions and making these instructions available to the processing device during its operation for execution. In some embodiments, configuring the processing device may include programming the processing device directly using architecture instructions. For example, a processing device such as a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. may be configured using, for example, one or more hardware description languages ​​(HDLs).

[0060] In other embodiments, configuring the processing device may include storing executable instructions on a memory accessible to the processing device during operation. For example, the processing device may access the memory during operation to obtain and execute the stored instructions. In either case, the processing device configured to perform the sensing, image analysis, and / or navigation functions disclosed herein represents a dedicated hardware-based system that controls multiple hardware-based components of the host vehicle.

[0061] although Figure 1 Two separate processing devices are depicted as included in processing unit 110, but more or fewer processing devices may be used. For example, in some embodiments, a single processing device may be used to complete the tasks of application processor 180 and image processor 190. In other embodiments, these tasks may be performed by more than two processing devices. Additionally, in some embodiments, system 100 may include one or more of processing units 110 without including other components such as image acquisition unit 120.

[0062] 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), a support circuit, a digital signal processor, an integrated circuit, a memory, or any other type of device for image processing and analysis. The image preprocessor may include a video processor for capturing, digitizing, and processing images from an image sensor. The CPU may include any number of microcontrollers or microprocessors. The GPU may also include any number of microcontrollers or microprocessors. The support circuit may be any number of circuits known in the art, including cache, power supply, clock, and input-output circuits. The memory may store software that controls the operation of the system when executed by the processor. The memory may include a database and image processing software. The memory may include any number of random access memories, read-only memories, flash memories, disk drives, optical storage, 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.

[0063] Each memory 140, 150 may include software instructions that, when executed by a processor (e.g., application processor 180 and / or image processor 190), may control the operation of various aspects of system 100. For example, these memory units may include various databases and image processing software, as well as trained systems such as neural networks or deep neural networks. The memory units may include random access memory (RAM), read-only memory (ROM), flash memory, disk drives, optical storage, 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.

[0064] Position sensor 130 may include any type of device suitable for determining a location associated with at least one component of system 100. In some embodiments, position sensor 130 may include a GPS receiver. Such a receiver may determine user location and velocity by processing signals broadcast by global positioning system satellites. Position information from position sensor 130 may be made available to application processor 180 and / or image processor 190.

[0065] In some embodiments, system 100 may include components such as a speed sensor (eg, tachometer, speedometer) for measuring the speed of vehicle 200 and / or an accelerometer (single-axis or multi-axis) for measuring the acceleration of vehicle 200 .

[0066] The user interface 170 may include any device suitable for providing information to or receiving input from one or more users of the system 100. In some embodiments, the user interface 170 may include a user input device including, for example, a touch screen, a microphone, a keyboard, a pointing device, a tracking wheel, a camera, knobs, buttons, etc. Using such input devices, a user may be able to provide information input or commands to the system 100 by typing instructions or information, providing voice commands, selecting menu options on a screen using buttons, a pointer, or eye tracking capabilities, or by any other suitable technique for communicating information to the system 100.

[0067] The user interface 170 may be provided with one or more processing devices configured to provide and receive information to and from a user, and to process the information for use by, for example, the application processor 180. In some embodiments, such processing devices may execute instructions to recognize and track eye movements, receive and interpret voice commands, recognize and interpret touches and / or gestures made on a touch screen, respond to keyboard input or menu selections, etc. In some embodiments, the user interface 170 may include a display, a speaker, a haptic device, and / or any other device for providing output information to a user.

[0068] The map database 160 may include any type of database for storing map data useful to the system 100. In some embodiments, the map database 160 may include data related to the location of various items in a reference coordinate system, including roads, water features, geographic features, commercial areas, points of interest, restaurants, gas stations, etc. The map database 160 may store not only the locations of these items, but also descriptors related to these items, including, for example, names associated with any stored features. In some embodiments, the map database 160 may be physically located with other components of the system 100. Alternatively or additionally, the map database 160 or a portion thereof may be remotely located relative to other components of the system 100 (e.g., the processing unit 110). In such embodiments, information from the map database 160 may be downloaded via a wired or wireless data connection to a network (e.g., via a cellular network and / or the Internet, etc.). In some cases, the map database 160 may store a sparse data model that includes a polynomial representation of certain road features (e.g., lane markings) or a target trajectory of the host vehicle. Systems and methods for generating such maps are discussed below with reference to FIGS. 8-17.

[0069] 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 acquire images for input to an image processor. Some embodiments may include only a single image capture device, while other embodiments may include two, three, or even four, or more image capture devices. FIG. 2B to FIG. 2E Image capture devices 122, 124, and 126 are further described.

[0070] The system 100 or its various components may be incorporated into a variety of different platforms. In some embodiments, the system 100 may be included in a vehicle 200, such as Figure 2A For example, vehicle 200 may be equipped with Figure 1 The processing unit 110 and any other components of the system 100 described above. In some embodiments, the vehicle 200 may be equipped with only a single image capture device (e.g., a camera), while in other embodiments, such as a combination of FIG. 2B to FIG. 2E As discussed above, multiple image capture devices may be used. For example, Figure 2A Either of the image capture devices 122 and 124 of the vehicle 200 shown in FIG. 2 may be part of an Advanced Driver Assistance System (ADAS) imaging set.

[0071] The image capture device included on the vehicle 200 as part of the image acquisition unit 120 may be placed in any suitable location. FIG. 2A to FIG. 2E ,as well as FIG. 3A to FIG. 3C As shown in , the image capture device 122 can be located near the rearview mirror. This location can provide a line of sight similar to that of the driver of the vehicle 200, which can help determine what is visible and invisible to the driver. The image capture device 122 can be placed anywhere near the rearview mirror, and placing the image capture device 122 on the driver's side of the mirror can also help obtain an image representing the driver's field of view and / or line of sight.

[0072] Other positions of the image capture device of the image acquisition unit 120 can also be used. For example, the image capture device 124 can be located on or in the bumper of the vehicle 200. Such a position can be particularly suitable for image capture devices with a wide field of view. The line of sight of the image capture device located at the bumper can be different from the line of sight of the driver, and therefore, the bumper image capture device and the driver may not always see the same object. The image capture device (e.g., image capture devices 122, 124 and 126) can also be located in other positions. For example, the image capture device can be located on or in one or both of the side mirrors of the vehicle 200, on the roof of the vehicle 200, on the hood of the vehicle 200, on the trunk of the vehicle 200, on the side of the vehicle 200, installed on any window of the vehicle 200, positioned behind any window of the vehicle 200, or positioned in front of any window of the vehicle 200, and installed in or near the lamps on the front and / or rear of the vehicle 200, etc.

[0073] In addition to the image capture device, the vehicle 200 may also include various other components of the system 100. For example, the processing unit 110 may be included on the vehicle 200, integrated with or separate from the vehicle's engine control unit (ECU). The vehicle 200 may also be equipped with a location sensor 130, such as a GPS receiver, and may also include a map database 160 and memory units 140 and 150.

[0074] As discussed earlier, the wireless transceiver 172 can send and / or receive data over one or more networks (e.g., a cellular network, the Internet, etc.). For example, the wireless transceiver 172 can upload data collected by the system 100 to one or more servers and download data from one or more servers. Via the wireless transceiver 172, the system 100 can receive, for example, periodic updates or on-demand updates to data stored in the map database 160, the memory 140, and / or the storage 150. Similarly, the wireless transceiver 172 can upload any data from the system 100 (e.g., images captured by the image acquisition unit 120, data received by the position sensor 130 or other sensors, the vehicle control system, etc.) and / or any data processed by the processing unit 110 to one or more servers.

[0075] The system 100 can upload data to a server (e.g., to the cloud) based on the privacy level setting. For example, the system 100 can implement a privacy level setting to specify or limit the type of data (including metadata) sent to the server that can uniquely identify the vehicle and / or the driver / owner of the vehicle. Such settings can be set by a user via, for example, the wireless transceiver 172, can be initialized by a factory default setting, or by data received by the wireless transceiver 172.

[0076] In some embodiments, the system 100 may upload data according to a "high" privacy level, and if the setting is set, the system 100 may send data (e.g., location information related to the route, captured images, etc.) without any details about the specific vehicle and / or driver / owner. For example, when uploading data according to the "high" privacy setting, the system 100 may not include the vehicle identification number (VIN) or the name of the driver or owner of the vehicle, and may instead send data (such as captured images and / or limited location information related to the route).

[0077] Other privacy levels are contemplated. For example, the system 100 may send data to a server according to a "medium" privacy level and may include additional information not included at a "high" privacy level, such as the make and / or model of the vehicle and / or the type of vehicle (e.g., a passenger vehicle, a sport utility vehicle, a truck, etc.). In some embodiments, the system 100 may upload data according to a "low" privacy level. Under the "low" privacy level setting, the system 100 may upload data and include information sufficient to uniquely identify a specific vehicle, the owner / driver, and / or a portion or the entire route traveled by the vehicle. Such "low" privacy level data may include one or more of the following: for example, the VIN, the driver / owner name, the source point of the vehicle before departure, the vehicle's desired destination, the make and / or model of the vehicle, the vehicle type, etc.

[0078] Figure 2A is a diagrammatic side view representation of an exemplary vehicle imaging system consistent with the disclosed embodiments. Figure 2B yes Figure 2A A pictorial top view of the embodiment shown in FIG. Figure 2B As shown, the disclosed embodiments may include a vehicle 200 including a system 100 in its body having a first image capture device 122 located near a rearview mirror of the vehicle 200 and / or close to a driver, a second image capture device 124 located on or in a bumper area (e.g., one of the bumper areas 210) of the vehicle 200, and a processing unit 110.

[0079] like Figure 2C As shown, both image capture devices 122 and 124 may be located near a rearview mirror of vehicle 200 and / or near the driver. Figure 2B and Figure 2C Two image capture devices 122 and 124 are shown, it should be understood that other embodiments may include more than two image capture devices. Figure 2D and Figure 2E In the embodiment shown in , a first image capture device 122 , a second image capture device 124 , and a third image capture device 126 are included in the system 100 of a vehicle 200 .

[0080] like Figure 2D As shown, image capture device 122 may be located near a rearview mirror of vehicle 200 and / or near the driver, and image capture devices 124 and 126 may be located on or in a bumper area (e.g., one of bumper areas 210) of vehicle 200. Figure 2E As shown, image capture devices 122, 124, and 126 may be located near rearview mirrors of vehicle 200 and / or near the driver's seat of vehicle 200. The disclosed embodiments are not limited to any particular number and configuration of image capture devices, and the image capture devices may be located in any suitable location within or on vehicle 200.

[0081] It should be understood that the disclosed embodiments are not limited to vehicles and can be applied in other scenarios. It should also be understood that the disclosed embodiments are not limited to a specific type of vehicle 200 and can be applicable to all types of vehicles, including cars, trucks, trailers, and other types of vehicles.

[0082] The first image capture device 122 may include any suitable type of image capture device. The image capture device 122 may include an optical axis. In one example, the image capture device 122 may include an Aptina M9V024WVGA sensor with a global shutter. In other embodiments, the image capture device 122 may provide a resolution of 1280×960 pixels and may include a rolling shutter. The image capture device 122 may include various optical elements. In some embodiments, one or more lenses may be included, for example, to provide a desired focal length and field of view for the image capture device. In some embodiments, the image capture device 122 may be associated with a 6 mm lens or a 12 mm lens. In some embodiments, as Figure 2DAs shown, the image capture device 122 can be configured to capture an image with a desired field of view (FOV) 202. For example, the image capture device 122 can be configured to have a conventional FOV such as in the range of 40 degrees to 56 degrees, including a 46 degree FOV, a 50 degree FOV, a 52 degree FOV, or a larger FOV. Alternatively, the image capture device 122 can be configured to have a narrow FOV in the range of 23 to 40 degrees, such as a 28 degree FOV or a 36 degree FOV. In addition, the image capture device 122 can be configured to have a wide FOV in the range of 100 to 180 degrees. In some embodiments, the image capture device 122 may include a wide-angle bumper camera or a camera with a FOV of up to 180 degrees. In some embodiments, the image capture device 122 may be a 7.2M (million) pixel image capture device with an aspect ratio of about 2:1 (e.g., H×V=3800×1900 pixels) and a horizontal FOV of about 100 degrees. Such an image capture device may be used in place of a three image capture device configuration. Due to significant lens distortion, in embodiments where the image capture device uses a radially symmetric lens, the vertical FOV of such an image capture device may be significantly less than 50 degrees. For example, such a lens may not be radially symmetric, which would allow a vertical FOV greater than 50 degrees with a 100 degree horizontal FOV.

[0083] The first image capture device 122 may acquire a plurality of first images of a scene associated with the vehicle 200. Each of the plurality of first images may be acquired as a series of image scan lines, which may be captured using a rolling shutter. Each scan line may include a plurality of pixels.

[0084] The first image capture device 122 may have a scan rate associated with the acquisition of each of the first series of image scan lines. The scan rate may refer to the scan rate at which the image sensor may acquire image data associated with each pixel included in a particular scan line.

[0085] Image capture devices 122, 124, and 126 may include any suitable type and number of image sensors, including, for example, CCD sensors or CMOS sensors, etc. In one embodiment, a CMOS image sensor may be employed with a rolling shutter so that each pixel in a row is read one at a time, and the scanning of the rows is performed on a row-by-row basis until the entire image frame has been captured. In some embodiments, the rows may be captured sequentially from top to bottom with respect to the frame.

[0086] In some embodiments, one or more of the image capture devices disclosed herein (e.g., image capture devices 122, 124, and 126) may constitute a high-resolution imager and may have a resolution greater than 5M pixels, 7M pixels, 10M pixels, or more.

[0087] The use of a rolling shutter may cause pixels in different rows to be exposed and captured at different times, which may cause skew and other image artifacts in the captured image frame. On the other hand, when the image capture device 122 is configured to operate using a global or synchronized shutter, all pixels may be exposed for the same amount of time and during a common exposure period. As a result, the image data in a frame collected from a system employing a global shutter represents a snapshot of the entire FOV (such as FOV 202) at a particular time. In contrast, in a rolling shutter application, each row in the frame is exposed and data is captured at a different time. As a result, in an image capture device with a rolling shutter, moving objects may appear distorted. This phenomenon will be described in more detail below.

[0088] The second image capture device 124 and the third image capture device 126 may be any type of image capture device. Similar to the first image capture device 122, each of the image capture devices 124 and 126 may include an optical axis. In one embodiment, each of the image capture devices 124 and 126 may include an Aptina M9V024 WVGA sensor with a global shutter. Alternatively, each of the image capture devices 124 and 126 may include a rolling shutter. Similar to the image capture device 122, the image capture devices 124 and 126 may be configured to include various lenses and optical elements. In some embodiments, the lenses associated with the image capture devices 124 and 126 may provide a FOV (such as FOV 204 and 206) that is equal to or narrower than the FOV (such as FOV 202) associated with the image capture device 122. For example, the image capture devices 124 and 126 may have a FOV of 40 degrees, 30 degrees, 26 degrees, 23 degrees, 20 degrees, or less.

[0089] Image capture devices 124 and 126 may acquire a plurality of second and third images of a scene associated with vehicle 200. Each of the plurality of second and third images may be acquired as a second and third series of image scan lines, which may be captured using a rolling shutter. Each scan line or row may have a plurality of pixels. Image capture devices 124 and 126 may have a second scan rate and a third scan rate associated with the acquisition of each image scan line included in the second and third series.

[0090] Each image capture device 122, 124, and 126 may be placed at any suitable position and orientation relative to vehicle 200. The relative positions of image capture devices 122, 124, and 126 may be selected to help fuse together information obtained from the image capture devices. For example, in some embodiments, a FOV associated with image capture device 124 (such as FOV 204) may partially or completely overlap with a FOV associated with image capture device 122 (e.g., FOV 202) and a FOV associated with image capture device 126 (e.g., FOV 206).

[0091] Image capture devices 122, 124, and 126 may be located at any suitable relative heights on vehicle 200. In one example, there may be height differences between image capture devices 122, 124, and 126 that may provide sufficient parallax information to enable stereo analysis. Figure 2A As shown, the two image capture devices 122 and 124 are at different heights. For example, there may also be lateral displacement differences between the image capture devices 122, 124, and 126, providing additional parallax information for the stereo analysis of the processing unit 110. Figure 2C and Figure 2D As shown, the difference in lateral displacement can be represented by dx. In some embodiments, there may be a forward or backward displacement (e.g., a range displacement) between image capture devices 122, 124, and 126. For example, image capture device 122 can be located 0.5 to 2 meters or more behind image capture device 124 and / or image capture device 126. This type of displacement can enable one of the image capture devices to cover a potential blind spot of the other (one or more) image capture devices.

[0092] Image capture device 122 may have any suitable resolution capability (e.g., the number of pixels associated with the image sensor), and the resolution of the image sensor(s) associated with image capture device 122 may be higher, lower, or the same as the resolution of the image sensor(s) associated with image capture devices 124 and 126. In some embodiments, the image sensor(s) associated with image capture device 122 and / or image capture devices 124 and 126 may have a resolution of 640×480, 1024×768, 1280×960, or any other suitable resolution.

[0093] The frame rate (e.g., the rate at which an image capture device acquires a set of pixel data for one image frame and then proceeds to capture pixel data associated with the next image frame) may be controllable. The frame rate associated with image capture device 122 may be higher, lower, or the same as the frame rate associated with image capture devices 124 and 126. The frame 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 that is applied before or after acquiring image data associated with one or more pixels of an image sensor in image capture devices 122, 124, and / or 126. Typically, image data corresponding to each pixel may be acquired based on a clock rate for the device (e.g., one pixel per clock cycle). Furthermore, in embodiments including a rolling shutter, one or more of the image capture devices 122, 124, and 126 may include a selectable horizontal blanking period that is applied before or after acquiring image data associated with a row of pixels of an image sensor in the image capture devices 122, 124, and / or 126. Furthermore, one or more of the image capture devices 122, 124, and 126 may include a selectable vertical blanking period that is applied before or after acquiring image data associated with an image frame of the image capture devices 122, 124, and 126.

[0094] These timing controls can enable synchronization of frame rates associated with image capture devices 122, 124, and 126, even if the line scan rate of each is different. In addition, as will be discussed in more detail below, these selectable timing controls and other factors (e.g., image sensor resolution, maximum line scan rate, etc.) can enable synchronization of image capture from areas where the FOV of image capture device 122 overlaps with one or more FOVs of image capture devices 124 and 126, even if the field of view of image capture device 122 is different from the FOV of image capture devices 124 and 126.

[0095] The frame rate timing in image capture devices 122, 124, and 126 may depend on the resolution of the associated image sensors. For example, assuming that the line scan rates are similar for both devices, if one device includes an image sensor with a resolution of 640×480 and the other device includes an image sensor with a resolution of 1280×960, more time is required to acquire a frame of image data from the sensor with the higher resolution.

[0096] 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, it will take a certain minimum amount of time to acquire a row of image data from the image sensors included in image capture devices 122, 124, and 126. Assuming that no pixel delay period is added, this minimum amount of time for acquiring a row of image data will be related to the maximum line scan rate for the particular device. Devices that provide a higher maximum line scan rate have the potential to provide a higher frame rate than devices with a lower maximum line scan rate. In some embodiments, one or more of image capture devices 124 and 126 may have a maximum line scan rate that is higher than the maximum line scan rate associated with image capture device 122. In some embodiments, the maximum line scan rate of image capture devices 124 and / or 126 may be 1.25, 1.5, 1.75, or 2 times or more the maximum line scan rate of image capture device 122.

[0097] 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 less than or equal to its maximum scan rate. The system may be configured such that one or more of image capture devices 124 and 126 operate at a line scan rate equal to the line scan rate of image capture device 122. In other examples, the system may be configured such that the line scan rate of image capture device 124 and / or image capture device 126 may be 1.25, 1.5, 1.75, or 2 or more times the line scan rate of image capture device 122.

[0098] In some embodiments, image capture devices 122, 124, and 126 may be asymmetric. That is, they may include cameras with different fields of view (FOV) and focal lengths. For example, the fields of view of image capture devices 122, 124, and 126 may include any desired area of ​​the environment of vehicle 200. In some embodiments, one or more of image capture devices 122, 124, and 126 may be configured to acquire image data from the environment in front of vehicle 200, behind vehicle 200, to the side of vehicle 200, or a combination thereof.

[0099] In addition, the focal length associated with each image capture device 122, 124, and / or 126 may be selectable (e.g., by including an appropriate lens, etc.) so that each device acquires images of objects at a desired range of distances relative to the vehicle 200. For example, in some embodiments, the image capture devices 122, 124, and 126 may acquire images of objects that are within a few meters of the vehicle. The image capture devices 122, 124, and 126 may also be configured to acquire images of objects at a greater range from the vehicle (e.g., 25 meters, 50 meters, 100 meters, 150 meters, or more). In addition, the focal lengths of image capture devices 122, 124, and 126 may be selected so that one image capture device (e.g., image capture device 122) may capture images of objects that are relatively close to the vehicle (e.g., within 10 meters or within 20 meters), while other image capture devices (e.g., image capture devices 124 and 126) may capture images of objects that are farther away from the vehicle 200 (e.g., greater than 20 meters, 50 meters, 100 meters, 150 meters, etc.).

[0100] According to some embodiments, the FOV of one or more image capture devices 122, 124, and 126 may have a wide angle. For example, having a FOV of 140 degrees may be advantageous, especially for image capture devices 122, 124, and 126 that may be used to capture images of areas near vehicle 200. For example, image capture device 122 may be used to capture images of areas to the right or left of vehicle 200, and in such embodiments, it may be desirable for image capture device 122 to have a wide FOV (e.g., at least 140 degrees).

[0101] The FOV associated with each image capture device 122, 124, and 126 may depend on the respective focal length. For example, as the focal length increases, the corresponding field of view decreases.

[0102] 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 of the FOV of image capture device 122 to the FOV of image capture device 124 and / or image capture device 126 may vary from 1.5 to 2.0. In other embodiments, the ratio may vary between 1.25 and 2.25.

[0103] System 100 may be configured such that the field of view of image capture device 122 at least partially or completely overlaps the field of view of image capture device 124 and / or image capture device 126. In some embodiments, system 100 may be configured such that the fields of view of image capture devices 124 and 126, for example, fall within (e.g., are narrower than) the field of view of image capture device 122 and share a common center with the field of view of image capture device 122. In other embodiments, image capture devices 122, 124, and 126 may capture adjacent FOVs, or may have partial overlap in their FOVs. In some embodiments, the fields of view of image capture devices 122, 124, and 126 may be aligned such that the center of the narrower FOV image capture device 124 and / or 126 may be located in the lower half of the field of view of the wider FOV device 122.

[0104] Figure 2F is a pictorial representation of an exemplary vehicle control system consistent with the disclosed embodiments. Figure 2F As indicated, the vehicle 200 may include a throttle adjustment system 220, a braking system 230, and a steering system 240. The system 100 may provide input (e.g., control signals) to one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 via one or more data links (e.g., any wired and / or wireless links for transmitting data). For example, based on analysis of images acquired by the image capture devices 122, 124, and / or 126, the system 100 may provide control signals to one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 to navigate the vehicle 200 (e.g., by causing acceleration, steering, lane changes, etc.). In addition, the system 100 may receive input from one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240 that indicates an operating condition of the vehicle 200 (e.g., speed, whether the vehicle 200 is braking and / or steering, etc.). The following is combined with Figures 4 to 7 Provide further details.

[0105] like Figure 3AAs shown, the vehicle 200 may also include a user interface 170 for interacting with a driver or passenger of the vehicle 200. For example, the user interface 170 in a vehicle application may include a touch screen 320, a knob 330, a button 340, and a microphone 350. The driver or passenger of the vehicle 200 may also interact with the system 100 using a handle (e.g., located on or near the steering column of the vehicle 200, including, for example, a turn signal handle), a button (e.g., located on the steering wheel of the vehicle 200), etc. In some embodiments, the microphone 350 may be positioned adjacent to the rearview mirror 310. Similarly, in some embodiments, the image capture device 122 may be located near the rearview mirror 310. In some embodiments, the user interface 170 may also include one or more speakers 360 (e.g., speakers of a vehicle audio system). For example, the system 100 may provide various notifications (e.g., alarms) via the speaker 360.

[0106] FIG. 3B to FIG. 3D is an illustration of an exemplary camera mount 370 configured to be located behind a rearview mirror (e.g., rearview mirror 310) and opposite a vehicle windshield in accordance with the disclosed embodiments. Figure 3B As shown, camera mount 370 may include image capture devices 122, 124, and 126. Image capture devices 124 and 126 may be located behind visor 380, where visor 380 may be flush with the vehicle windshield and include a film and / or a composite of anti-reflective materials. For example, visor 380 may be positioned so that the panel is aligned with the vehicle's windshield with a matching bevel. In some embodiments, each of image capture devices 122, 124, and 126 may be located behind visor 380, such as at Figure 3D The disclosed embodiments are not limited to any particular configuration of image capture devices 122 , 124 , and 126 , camera mount 370 , and visor 380 . Figure 3C yes Figure 3B The camera mount 370 is shown as an illustration from a front perspective.

[0107] As will be appreciated by those skilled in the art having the benefit of this disclosure, many changes and / or modifications may be made to the foregoing disclosed embodiments. For example, not all components are necessary for the operation of the system 100. In addition, any component may be located in any appropriate part of the system 100 and the components may be rearranged into various configurations while providing the functionality of the disclosed embodiments. Therefore, the foregoing configurations are exemplary, and regardless of the configurations discussed above, the system 100 may provide a wide range of functionality to analyze the surroundings of the vehicle 200 and navigate the vehicle 200 in response to the analysis.

[0108] As discussed in more detail below and in accordance with various disclosed embodiments, the system 100 can provide various features related to autonomous driving and / or driver assistance technology. For example, the system 100 can analyze image data, location data (e.g., GPS location information), map data, speed data, and / or data from sensors included in the vehicle 200. The system 100 can collect data for analysis from, for example, the image acquisition unit 120, the location sensor 130, and other sensors. In addition, the system 100 can analyze the collected data to determine whether the vehicle 200 should take a certain action, and then automatically take the determined action without human intervention. For example, when the vehicle 200 navigates without human intervention, the system 100 can automatically control the braking, acceleration, and / or steering of the vehicle 200 (e.g., by sending control signals to one or more of the throttle adjustment system 220, the braking system 230, and the steering system 240). In addition, the system 100 can analyze the collected data and issue warnings and / or alarms to the vehicle occupants based on the analysis of the collected data. Additional details of various embodiments provided by the system 100 are provided below.

[0109] Forward multi-imaging system

[0110] As discussed above, the system 100 can provide driving assistance functions using a multi-camera system. The multi-camera system can use one or more cameras facing the front of the vehicle. In other embodiments, the multi-camera system may include one or more cameras facing the side of the vehicle or facing the back of the vehicle. In one embodiment, for example, the system 100 can use a dual-camera imaging system, wherein the first camera and the second camera (e.g., image capture devices 122 and 124) can be located in front of and / or to the side of the vehicle (e.g., vehicle 200).

[0111] 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. In addition, the first camera may be connected to a first image processor to perform monocular image analysis of the image provided by the first camera, and the second camera may be connected to a second image processor to perform 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 camera and the second camera to perform stereo analysis. In another embodiment, the system 100 may use a three-camera imaging system, each camera having a different field of view. Therefore, such a system may make decisions based on information derived from objects at different distances in front of and to the side of the vehicle. References to monocular image analysis may refer to instances of image analysis based on images captured from a single viewpoint (e.g., from a single camera). Stereoscopic image analysis may refer to instances of image analysis based on two or more images captured using one or more changes in image capture parameters. For example, captured images suitable for performing stereoscopic image analysis may include the following captured images: images captured from two or more different positions, from different fields of view, using different focal lengths, together with parallax information, etc.

[0112] For example, in one embodiment, the system 100 can implement a three-camera configuration using image capture devices 122, 124, and 126. In such a configuration, image capture device 122 can provide a narrow field of view (e.g., 34 degrees or other values ​​selected from a range of about 20 degrees to 45 degrees, etc.), image capture device 124 can provide a wide field of view (e.g., 150 degrees or other values ​​selected from a range of about 100 degrees to about 180 degrees), and image capture device 126 can provide an intermediate field of view (e.g., 46 degrees or other values ​​selected from a range of about 35 degrees to about 60 degrees). In some embodiments, image capture device 126 can serve as a main camera or base camera. Image capture devices 122, 124, and 126 can be positioned behind rearview mirror 310 and positioned substantially side by side (e.g., 6 centimeters apart). In addition, in some embodiments, as discussed above, one or more of image capture devices 122, 124, and 126 can be mounted behind a sun visor 380 flush with the windshield of vehicle 200. Such shielding may be used to minimize the impact of any reflections from the interior of the vehicle on image capture devices 122 , 124 , and 126 .

[0113] In another embodiment, as above combined Figure 3B and 3CAs discussed, the wide field of view camera (e.g., image capture device 124 in the above example) can be mounted lower than the narrow field of view camera and the main field of view camera (e.g., image devices 122 and 126 in the above example). Such a configuration can provide a free line of sight from the wide field of view camera. To reduce reflections, the camera can be mounted closer to the windshield of the vehicle 200, and a polarizer can be included on the camera to dampen reflected light.

[0114] The three-camera system may provide certain performance characteristics. For example, some embodiments may include the ability to verify the detection of an object by one camera based on the detection results from another camera. In the three-camera configuration discussed above, the processing unit 110 may include, for example, three processing devices (e.g., three EyeQ series processor chips as discussed above), where each processing device is dedicated to processing images captured by one or more of the image capture devices 122, 124, and 126.

[0115] In a three-camera system, the first processing device can receive images from both the main camera and the narrow field of view camera and perform visual processing on the narrow FOV camera, for example to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. In addition, the first processing device can calculate the disparity of pixels between the images from the main camera and the narrow camera and create a 3D reconstruction of the environment of the vehicle 200. The first processing device can then combine the 3D reconstruction with 3D map data, or combine the 3D reconstruction with 3D information calculated based on information from another camera.

[0116] The second processing device can receive images from the main camera and perform visual processing to detect other vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. In addition, the second processing device can calculate the camera displacement, and based on the displacement, calculate the disparity of pixels between consecutive images and create a 3D reconstruction of the scene (e.g., structure from motion). The second processing device can send the structure from motion based on the 3D reconstruction to the first processing device to be combined with the stereoscopic 3D image.

[0117] The third processing device can receive images from the wide FOV camera and process the images to detect vehicles, pedestrians, lane markings, traffic signs, traffic lights, and other road objects. The third processing device can also execute additional processing instructions to analyze the images to identify moving objects in the images, such as vehicles changing lanes, pedestrians, etc.

[0118] In some embodiments, having the streams of image-based information captured and processed independently can provide an opportunity to provide redundancy in the system. Such redundancy can include, for example, using a first image capture device and images processed from that device to verify and / or supplement information obtained by capturing and processing image information from at least a second image capture device.

[0119] In some embodiments, system 100 uses two image capture devices (e.g., image capture devices 122 and 124) in providing navigation assistance to vehicle 200, and uses a third image capture device (e.g., image capture device 126) to provide redundancy and verify the analysis of data received from the other two image capture devices. For example, in such a configuration, image capture devices 122 and 124 may provide images for stereo analysis by system 100 to navigate vehicle 200, while image capture device 126 may provide images for monocular analysis by system 100 to provide redundancy and verification of information obtained based on images captured from image capture device 122 and / or image capture device 124. That is, image capture device 126 (and corresponding processing device) may be viewed as providing a redundant subsystem for providing a check on the analysis obtained from image capture devices 122 and 124 (e.g., to provide an automatic emergency braking (AEB) system). Additionally, in some embodiments, redundancy and verification of received data may be supplemented based on information received from one or more sensors (e.g., radar, lidar, acoustic sensors, information received from one or more transceivers outside the vehicle, etc.).

[0120] Those skilled in the art will recognize that the above-described camera configurations, camera placements, number of cameras, camera positions, etc. are merely examples. These components and other components described with respect to the overall system may be assembled and used in a variety of different configurations without departing from the scope of the disclosed embodiments. Further details regarding the use of a multi-camera system to provide driver assistance and / or autonomous vehicle functionality are as follows.

[0121] Figure 4 1 is an exemplary functional block diagram of memory 140 and / or memory 150, which may be stored / programmed with instructions for performing one or more operations consistent with the disclosed embodiments. Although the following refers to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or memory 150.

[0122] like Figure 4As shown, the memory 140 may store a monocular image analysis module 402, a stereo image analysis module 404, a velocity and acceleration module 406, and a navigation response module 408. The disclosed embodiments are not limited to any particular configuration of the memory 140. In addition, the application processor 180 and / or the image processor 190 may execute instructions stored in any of the modules 402, 404, 406, and 408 included in the memory 140. Those skilled in the art will appreciate that references to the processing unit 110 in the following discussion may refer individually or collectively to the application processor 180 and the image processor 190. Therefore, any of the following processing steps may be performed by one or more processing devices.

[0123] In one embodiment, monocular image analysis module 402 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform monocular image analysis on a set of images acquired by one of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from a set of images with additional sensory information (e.g., information from radar, lidar, etc.) to perform monocular image analysis. FIG. 5A to FIG. 5D As described, the monocular image analysis module 402 may include instructions for detecting a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, and any other features associated with the vehicle's environment. Based on the analysis, the system 100 (e.g., via the processing unit 110) may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in conjunction with the navigation response module 408.

[0124] In one embodiment, stereo image analysis module 404 may store instructions (such as computer vision software) that, when executed by processing unit 110, perform stereo image analysis of a first set of second sets of images acquired by a combination of image capture devices selected from any of image capture devices 122, 124, and 126. In some embodiments, processing unit 110 may combine information from the first set of 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 a first set of images acquired by image capture device 124 and a second set of images acquired by image capture device 126. As described below in conjunction with Figure 6As described, the stereo image analysis module 404 may include instructions for detecting a set of features within the first and second sets of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, hazardous objects, etc. Based on the analysis, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as steering, lane changes, changes in acceleration, etc., as discussed below in conjunction with the navigation response module 408. In addition, in some embodiments, the stereo image analysis module 404 may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system, such as a system that may be configured to use a computer vision algorithm to detect and / or mark objects in an environment from which sensory information is captured and processed. In one embodiment, the stereo image analysis module 404 and / or other image processing modules may be configured to use a combination of trained and untrained systems.

[0125] In one embodiment, the speed and acceleration module 406 may store software configured to analyze data received from one or more computing and electromechanical devices in the vehicle 200, the data being configured to cause a change in the speed and / or acceleration of the vehicle 200. For example, the processing unit 110 may execute instructions associated with the speed and acceleration module 406 to calculate a target speed for the vehicle 200 based on data derived from executing the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include, for example, target position, speed, and / or acceleration, the position and / or speed of the vehicle 200 relative to nearby vehicles, pedestrians, or road objects, position information of the vehicle 200 relative to lane markings of the road, etc. In addition, the processing unit 110 may calculate the target speed for the vehicle 200 based on sensory input (e.g., information from a radar) and input from other systems of the vehicle 200, such as the throttle adjustment system 220, the braking system 230, and / or the steering system 240. Based on the calculated target speed, the processing unit 110 can send an electrical signal to the throttle regulation system 220, the braking system 230 and / or the steering system 240 of the vehicle 200 to trigger a change in speed and / or acceleration by, for example, physically pressing the brake or releasing the accelerator of the vehicle 200.

[0126] In one embodiment, the navigation response module 408 may store software that is executable by the processing unit 110 to determine a desired navigation response based on data derived from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. Such data may include position and velocity information associated with nearby vehicles, pedestrians, and road objects, target position information for the vehicle 200, etc. In addition, in some embodiments, the navigation response may be based (partially or entirely) on map data, a predetermined position of the vehicle 200, and / or a relative velocity or relative acceleration between the vehicle 200 and one or more objects detected from the execution of the monocular image analysis module 402 and / or the stereo image analysis module 404. The navigation response module 408 may also determine the desired navigation response based on sensory input (e.g., information from a radar) and input from other systems of the vehicle 200, such as the throttle adjustment system 220, the braking system 230, and the steering system 240 of the vehicle 200. Based on the desired navigation response, the processing unit 110 may send electrical signals to the throttle adjustment system 220, the brake system 230, and the steering system 240 of the vehicle 200 to achieve a predetermined angle of rotation by, for example, turning the steering wheel of the vehicle 200, thereby triggering the desired navigation response. In some embodiments, the processing unit 110 may use the output of the navigation response module 408 (e.g., the desired navigation response) as an input to execute the speed and acceleration module 406 for calculating the change in the speed of the vehicle 200.

[0127] Furthermore, any modules disclosed herein (eg, modules 402, 404, and 406) may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system.

[0128] Figure 5A is a flow chart illustrating an exemplary process 500A for causing one or more navigation responses based on monocular image analysis consistent with the disclosed embodiments. At step 510, the processing unit 110 may receive a plurality of images via a data interface 128 between the processing unit 110 and the image acquisition unit 120. For example, a camera (such as an image capture device 122 having a field of view 202) included in the image acquisition unit 120 may capture a plurality of images of an area in front of the vehicle 200 (e.g., or to the side or rear of the vehicle) and send them to the processing unit 110 via a data connection (e.g., digital, wired, USB, wireless, Bluetooth, etc.). At step 520, the processing unit 110 may execute the monocular image analysis module 402 to analyze the plurality of images, as described below in conjunction with Figures 5B to 5D By performing this analysis, processing unit 110 may detect a set of features within the set of images, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, etc.

[0129] The processing unit 110 may also execute the monocular image analysis module 402 in step 520 to detect various road hazards, such as, for example, parts of a truck tire, fallen road signs, loose cargo, small animals, etc. Road hazards may vary in structure, shape, size, and color, which may make the detection of such hazards more difficult. In some embodiments, the processing unit 110 may execute the monocular image analysis module 402 to perform multi-frame analysis on multiple images to detect road hazards. For example, the processing unit 110 may estimate the camera motion between consecutive image frames and calculate the parallax in the pixels between frames to build a 3D map of the road. The processing unit 110 may then use the 3D map to detect the road surface and the hazards present on the road surface.

[0130] At step 530, the processing unit 110 may execute the navigation response module 408 to perform the navigation response based on the analysis performed at step 520 and the above combination. Figure 4 The described techniques may cause one or more navigation responses in the vehicle 200. The navigation responses may include, for example, steering, lane changes, acceleration changes, etc. In some embodiments, the processing unit 110 may use data obtained from executing the speed and acceleration module 406 to cause the one or more navigation responses. In addition, multiple navigation responses may occur simultaneously, sequentially, or in any combination thereof. For example, the processing unit 110 may cause the vehicle 200 to change a lane and then accelerate by, for example, sequentially transmitting control signals to the steering system 240 and the throttle adjustment system 220 of the vehicle 200. Alternatively, the processing unit 110 may cause the vehicle 200 to brake and change lanes simultaneously by, for example, simultaneously transmitting control signals to the braking system 230 and the steering system 240 of the vehicle 200.

[0131] Figure 5B is a flow chart showing an exemplary process 500B for detecting one or more vehicles and / or pedestrians in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500B. At step 540, the processing unit 110 may determine a set of candidate objects representing possible vehicles and / or pedestrians. For example, the processing unit 110 may scan one or more images, compare the images to one or more predetermined patterns, and identify possible locations within each image that may contain objects of interest (e.g., vehicles, pedestrians, or parts thereof). The predetermined patterns may be designed in such a way as to achieve a high "false hit" rate and a low "miss" rate. For example, the processing unit 110 may use a low similarity threshold on the predetermined pattern to identify the candidate object as a possible vehicle or pedestrian. Doing so may allow the processing unit 110 to reduce the likelihood of missing (e.g., not identifying) a candidate object representing a vehicle or pedestrian.

[0132] At step 542, processing unit 110 may filter the set of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria may be derived from various attributes associated with object types stored in a database (e.g., a database stored in memory 140). Attributes may include object shape, size, texture, location (e.g., relative to vehicle 200), etc. Thus, processing unit 110 may use one or more sets of criteria to reject pseudo candidates from the set of candidate objects.

[0133] At step 544, processing unit 110 may analyze multiple frames of images to determine whether an object in the set of candidate objects represents a vehicle and / or a pedestrian. For example, processing unit 110 may track detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to vehicle 200, etc.). In addition, processing unit 110 may estimate parameters of the detected object and compare the frame-by-frame position data of the object with the predicted position.

[0134] At step 546, the processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values ​​(relative to the vehicle 200) associated with the detected objects. In some embodiments, the processing unit 110 may construct the measurements based on estimation techniques such as a Kalman filter or linear quadratic estimation (LQE) using a series of time-based observations and / or based on modeling data available for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter may be based on a measurement of the scale of the object, where the scale measurement is proportional to the time to collision (e.g., the amount of time it takes the vehicle 200 to reach the object). Thus, by performing steps 540 to 546, the processing unit 110 may identify vehicles and pedestrians that appear within the set of captured images and obtain information associated with the vehicles and pedestrians (e.g., position, velocity, size). Based on the identification and the derived information, the processing unit 110 may cause one or more navigation responses in the vehicle 200, such as those described above in conjunction with Figure 5A as described.

[0135] In step 548, the processing unit 110 may perform an optical flow analysis on one or more images to reduce the likelihood of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis may refer to, for example, analyzing motion patterns relative to the vehicle 200, associated with other vehicles and pedestrians, and distinct from road motion in one or more images. The processing unit 110 may calculate the motion of the candidate objects by observing different positions of the objects across multiple image frames captured at different times. The processing unit 110 may use the position and time values ​​as input to a mathematical model for calculating the motion of the candidate objects. Therefore, optical flow analysis may provide another method for detecting vehicles and pedestrians near the vehicle 200. The processing unit 110 may perform optical flow analysis in conjunction with steps 540 to 546 to provide redundancy in detecting vehicles and pedestrians and improve the reliability of the system 100.

[0136] Figure 5C is a flow chart illustrating an exemplary process 500C for detecting road markings and / or lane geometry information in a set of images consistent with the disclosed embodiments. Processing unit 110 may execute monocular image analysis module 402 to implement process 500C. At step 550, processing unit 110 may detect a set of objects by scanning one or more images. In order to detect segments of lane markings, lane geometry information, and other relevant road markings, processing unit 110 may filter the set of objects to exclude those determined to be irrelevant (e.g., small potholes, small rocks, etc.). At step 552, processing unit 110 may group together segments belonging to the same road marking or lane marking detected in step 550. Based on the grouping, processing unit 110 may generate a model, such as a mathematical model, representing the detected segments.

[0137] At step 554, the processing unit 110 may construct a set of measurements associated with the detected segment. In some embodiments, the processing unit 110 may create a projection of the detected segment from the image plane onto the real world plane. The projection may be characterized using a cubic polynomial having coefficients corresponding to physical properties such as the position, slope, curvature, and curvature derivative of the detected road. In generating the projection, the processing unit 110 may take into account changes in the road surface, as well as the pitch and roll rates associated with the vehicle 200. In addition, the processing unit 110 may model the road elevation by analyzing the position and motion cues that appear on the road surface. In addition, the processing unit 110 may estimate the pitch and roll rates associated with the vehicle 200 by tracking a set of feature points in one or more images.

[0138] At step 556, processing unit 110 may perform a multi-frame analysis by, for example, tracking the detected segments across consecutive image frames and accumulating frame-by-frame data associated with the detected segments. As processing unit 110 performs multi-frame analysis, the set of measurements constructed in step 554 may become more reliable and associated with increasingly higher confidence levels. Thus, by performing steps 550, 552, 554, and 556, processing unit 110 may identify road markings present in the set of captured images and derive lane geometry information. Based on this identification and the derived information, processing unit 110 may cause one or more navigation responses in vehicle 200, such as those described above in conjunction with Figure 5A as described.

[0139] At step 558, processing unit 110 may consider additional information sources to further generate a safety model of vehicle 200 in its surrounding environment. Processing unit 110 may use the safety model to define an environment in which system 100 may perform autonomous control of vehicle 200 in a safe manner. To generate the safety model, in some embodiments, processing unit 110 may consider the positions and motions of other vehicles, detected curbs and guardrails, and / or general road shape descriptions extracted from map data (such as data from map database 160). By considering additional information sources, processing unit 110 may provide redundancy for detecting road markings and lane geometry and increase the reliability of system 100.

[0140] Figure 5D 5 is a flow chart showing an exemplary process 500D for detecting a traffic light in a set of images consistent with the disclosed embodiments. The processing unit 110 may execute the monocular image analysis module 402 to implement the process 500D. At step 560, the processing unit 110 may scan the set of images and identify objects that appear in the image at locations that may contain traffic lights. For example, the processing unit 110 may filter the identified objects to construct a set of candidate objects, excluding those objects that are unlikely to correspond to traffic lights. The filtering may be based on various attributes associated with traffic lights, such as shape, size, texture, position (e.g., relative to the vehicle 200), etc. Such attributes may be based on multiple examples of traffic lights and traffic control signals and stored in a database. In some embodiments, the processing unit 110 may perform a multi-frame analysis on the set of candidate objects that reflect possible traffic lights. For example, the processing unit 110 may track the candidate objects across consecutive image frames, estimate the real-world positions of the candidate objects, and filter out those moving objects (which are unlikely to be traffic lights). In some embodiments, processing unit 110 may perform color analysis on the candidate objects and identify relative locations of detected colors that appear within possible traffic lights.

[0141] At step 562, processing unit 110 may analyze the geometry of the intersection. The analysis may be based on any combination of: (i) the number of lanes detected on either side of vehicle 200, (ii) markings detected on the road (e.g., arrow markings), and (iii) a description of the intersection extracted from map data (e.g., data from map database 160). Processing unit 110 may use information obtained from execution of monocular analysis module 402 to perform the analysis. In addition, processing unit 110 may determine the correspondence between the traffic lights detected at step 560 and the lanes present near vehicle 200.

[0142] In step 564, as the vehicle 200 approaches the intersection, the processing unit 110 can update the confidence level associated with the analyzed intersection geometry and the detected traffic lights. For example, the number of traffic lights estimated to be present at the intersection compared to the number of traffic lights actually present at the intersection may affect the confidence level. Therefore, based on the confidence level, the processing unit 110 can delegate control to the driver of the vehicle 200 in order to improve safety conditions. By performing steps 560, 562 and 564, the processing unit 110 can identify the traffic lights that appear within the set of captured images and analyze the intersection geometry information. Based on this identification and analysis, the processing unit 110 can cause one or more navigation responses in the vehicle 200, such as those described above in conjunction with Figure 5A as described.

[0143] Figure 5E 5 is a flow chart showing an example process 500E for causing one or more navigation responses in a vehicle based on a vehicle path consistent with the disclosed embodiments. At step 570, the processing unit 110 may construct an initial vehicle path associated with the vehicle 200. The vehicle path may be represented by a set of points expressed in coordinates (x, z), and the distance d between two points in the set of points may be i Can fall within the range of 1 to 5 meters. In one embodiment, the processing unit 110 can use two polynomials, such as a left road polynomial and a right road polynomial, to construct an initial vehicle path. The processing unit 110 can calculate the geometric midpoint between the two polynomials and offset each point included in the resulting vehicle path by a predetermined offset (e.g., a smart lane offset), if any (a zero offset can correspond to driving in the middle of the lane). The offset can be in a direction perpendicular to the line segment between any two points in the vehicle path. In another embodiment, the processing unit 110 can use a polynomial and an estimated lane width to offset each point of the vehicle path by half the estimated lane width plus a predetermined offset (e.g., a smart lane offset).

[0144] At step 572, the processing unit 110 may update the vehicle path constructed at step 570. The processing unit 110 may reconstruct the vehicle path constructed at step 570 using a higher resolution so that the distance d between two points in the set of points representing the vehicle path is k Smaller than the above distance d i For example, the distance d k It may fall within the range of 0.1 to 0.3 meters. The processing unit 110 may reconstruct the vehicle path using a parabolic spline algorithm, which may produce a cumulative distance vector S corresponding to the total length of the vehicle path (ie, based on the set of points representing the vehicle path).

[0145] In step 574, the processing unit 110 may determine a look-ahead point (expressed in coordinates as (x1, z1)) based on the updated vehicle path constructed in step 572. The processing unit 110 may extract the look-ahead point from the accumulated 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 ranging from 10 meters to 20 meters and may be calculated as the product of the velocity of the vehicle 200 and the look-ahead time. For example, as the velocity of the vehicle 200 decreases, the look-ahead distance may also decrease (e.g., until it reaches the lower limit). The look-ahead time may range from 0.5 to 1.5 seconds and may be inversely proportional to the gain of one or more control loops associated with causing a navigation response in the vehicle 200, such as a heading error tracking control loop. For example, the gain of the heading error tracking control loop may depend on the bandwidth of a yaw rate loop, a steering actuator loop, vehicle lateral dynamics, etc. Therefore, the higher the gain of the heading error tracking control loop, the shorter the look-ahead time.

[0146] In step 576, the processing unit 110 may determine a heading error and a yaw rate command based on the foresight point determined in step 574. The processing unit 110 may determine the heading error by calculating the arc tangent of the foresight point, such as arctan(x1, z1). The processing unit 110 may determine the yaw rate command as the product of the heading error and the high level control gain. If the foresight distance is not at the lower limit, the high level control gain may be equal to: (2 / foresight time). Otherwise, the high level control gain may be equal to: (2*vehicle 200 rate / foresight distance).

[0147] Fig. 5Fis a flow chart illustrating an example process 500F for determining whether a leading vehicle is changing lanes consistent with the disclosed embodiments. In step 580, processing unit 110 may determine navigation information associated with a leading vehicle (e.g., a vehicle traveling in front of vehicle 200). For example, processing unit 110 may use the above combined Figure 5A and Figure 5B The described techniques can be used to determine the position, speed (e.g., direction and velocity), and / or acceleration of the vehicle ahead. The processing unit 110 can also use the above combined Figure 5E The described techniques determine one or more road polynomials, forward-looking points (associated with vehicle 200), and / or a snail trail (eg, a set of points describing a path taken by a leading vehicle).

[0148] In step 582, processing unit 110 may analyze the navigation information determined in step 580. In one embodiment, processing unit 110 may calculate the distance between the tracking trajectory and the road polynomial (e.g., along the trajectory). If the variance of this distance along the trajectory exceeds a predetermined threshold (e.g., 0.1 to 0.2 meters on a straight road, 0.3 to 0.4 meters on a moderately curved road, and 0.5 to 0.6 meters on a sharp curve road), processing unit 110 may determine that the leading vehicle is likely to be changing lanes. In the case where multiple vehicles are detected traveling in front of vehicle 200, processing unit 110 may compare the tracking trajectories associated with each vehicle. Based on the comparison, processing unit 110 may determine that the vehicle whose tracking trajectory does not match the tracking trajectories of other vehicles is likely to be changing lanes. Processing unit 110 may additionally compare the curvature of the tracking trajectory (associated with the leading vehicle) with the expected curvature of the road segment in which the leading vehicle is traveling. The expected curvature may be extracted from map data (e.g., data from map database 160), from a road polynomial, from tracking trajectories of other vehicles, from prior knowledge about the road, etc. If the difference between the curvature of the tracking trajectory and the expected curvature of the road segment exceeds a predetermined threshold, processing unit 110 may determine that the leading vehicle is likely to be changing lanes.

[0149] In another embodiment, the processing unit 110 may compare the instantaneous position of the leading vehicle with the forward view point (associated with the vehicle 200) over a specific time period (e.g., 0.5 to 1.5 seconds). If the distance between the instantaneous position of the leading vehicle and the forward view point changes during the specific time period, and the cumulative sum of the changes exceeds a predetermined threshold (e.g., 0.3 to 0.4 meters on a straight road, 0.7 to 0.8 meters on a moderately curved road, and 1.3 to 1.7 meters on a sharp curve road), the processing unit 110 may determine that the leading vehicle is likely to be changing lanes. In another embodiment, the processing unit 110 may analyze the geometry of the tracking track by comparing the lateral distance traveled along the tracking track with the expected curvature of the tracking track. The expected radius of curvature may be determined according to the formula: (δ z 2 +δ x 2 ) / 2 / (δ x ), where δ x represents the lateral distance traveled and δ z The longitudinal distance traveled is represented by the curvature. If the difference between the lateral distance traveled and the expected curvature exceeds a predetermined threshold (e.g., 500 to 700 meters), the processing unit 110 can determine that the leading vehicle is likely to be changing lanes. In another embodiment, the processing unit 110 can analyze the position of the leading vehicle. If the position of the leading vehicle obscures the road polynomial (e.g., the leading vehicle covers the top of the road polynomial), the processing unit 110 can determine that the leading vehicle is likely to be changing lanes. In the case where the position of the leading vehicle is such that another vehicle is detected in front of the leading vehicle and the tracking trajectories of the two vehicles are not parallel, the processing unit 110 can determine that the (closer) leading vehicle is likely to be changing lanes.

[0150] At step 584, processing unit 110 may determine whether leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make this determination based on a weighted average of the various analyses performed at step 582. Under such a scheme, for example, a determination made by processing unit 110 that a leading vehicle is likely to be changing lanes based on a particular type of analysis may be assigned a value of "1" (and "0" used to represent a determination that a leading vehicle is unlikely to be changing lanes). Different analyses performed at step 582 may be assigned different weights, and the disclosed embodiments are not limited to any particular combination of analyses and weights.

[0151] Figure 66 is a flow chart illustrating an example process 600 for causing one or more navigation responses based on stereo image analysis consistent with the disclosed embodiments. At step 610, the processing unit 110 may receive the first and second pluralities of images via the data interface 128. For example, a camera included in the image acquisition unit 120 (such as the image capture devices 122 and 124 having the fields of view 202 and 204) may capture the first and second pluralities of images of the area in front of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first 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.

[0152] At step 620, the processing unit 110 may execute the stereo image analysis module 404 to perform stereo image analysis on the first and second plurality of images to create a 3D map of the road ahead of the vehicle and detect features within the image, such as lane markings, vehicles, pedestrians, road signs, highway exit ramps, traffic lights, road hazards, etc. The stereo image analysis may be performed in a manner similar to the above combined Figure 5A-5D The processing unit 110 may perform the steps described above in the manner described above. For example, the processing unit 110 may execute the stereo image analysis module 404 to detect candidate objects (e.g., vehicles, pedestrians, road signs, traffic lights, road hazards, etc.) within the first and second multiple images, filter out a subset of the candidate objects based on various criteria, and perform multi-frame analysis, build measurements, and determine confidence levels for the remaining candidate objects. In performing the above steps, the processing unit 110 may consider information from both the first and second multiple images, rather than information from a single set of images. For example, the processing unit 110 may analyze the differences in pixel-level data (or other subsets of data from two streams of captured images) of candidate objects that appear in both the first and second multiple images. As another example, the processing unit 110 may estimate the position and / or speed of the candidate object (e.g., relative to the vehicle 200) by observing that the candidate object appears in one of the multiple images but not in the other, or with respect to other differences that may exist relative to the objects that appear in the two image streams. For example, the position, speed, and / or acceleration relative to the vehicle 200 may be determined based on features such as trajectories, positions, movement characteristics, etc. associated with objects that appear in one or both of the image streams.

[0153] At step 630, the processing unit 110 may execute the navigation response module 408 to perform the following operations based on the analysis performed at step 620 and the above combination. Figure 4The described techniques may cause one or more navigation responses in the vehicle 200. The navigation responses may include, for example, steering, lane changes, changes in acceleration, changes in speed, braking, etc. In some embodiments, the processing unit 110 may cause the one or more navigation responses using data obtained from executing the speed and acceleration module 406. Furthermore, multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0154] Figure 7 is a flow chart showing an exemplary process 700 for causing one or more navigation responses based on analysis of three sets of images consistent with the disclosed embodiments. At step 710, the processing unit 110 may receive the first, second, and third plurality of images via the data interface 128. For example, a camera included in the image acquisition unit 120 (such as the image capture devices 122, 124, and 126 having the fields of view 202, 204, and 206) may capture the first, second, and third plurality of images of the area in front of and / or to the side of the vehicle 200 and transmit them to the processing unit 110 via a digital connection (e.g., USB, wireless, Bluetooth, etc.). In some embodiments, the processing unit 110 may receive the first, second, and third plurality of images via three or more data interfaces. For example, each of the image capture devices 122, 124, 126 may have an associated data interface for transmitting data to the processing unit 110. The disclosed embodiments are not limited to any particular data interface configuration or protocol.

[0155] 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, road hazards, etc. This analysis may be performed in a manner similar to the above combined Figure 5A-5D and Figure 6 For example, the processing unit 110 may perform monocular image analysis on each of the first, second, and third plurality of images (e.g., via execution of the monocular image analysis module 402 and based on the above combination Figure 5A-5D Alternatively, the processing unit 110 may perform stereoscopic 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., via execution of the stereoscopic image analysis module 404 and based on the above combined Figure 64 and 5. The processing unit 110 may perform a combination of monocular and stereo image analysis. For example, the processing unit 110 may perform monocular image analysis on the first plurality of images (e.g., via execution by the monocular image analysis module 402) and perform stereo image analysis on the second and third plurality of images (e.g., via execution by the stereo image analysis module 404). The configuration of the image capture devices 122, 124, and 126 - including their respective 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 the image capture devices 122, 124, and 126 or the type of analysis performed on the first, second, and third plurality of images.

[0156] In some embodiments, processing unit 110 may perform tests on system 100 based on the images acquired and analyzed at steps 710 and 720. Such tests may provide indicators of the overall performance of system 100 for certain configurations of image acquisition devices 122, 124, and 126. For example, processing unit 110 may determine the proportion of "false hits" (e.g., instances where system 100 incorrectly determines the presence of a vehicle or pedestrian) and "misses."

[0157] At step 730, the processing unit 110 may cause one or more navigation responses in the 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, for example, the number, type, and size of objects detected in each of the plurality of images. The processing unit 110 may also make a selection based on image quality and resolution, the effective field of view reflected in the image, the number of frames captured, the degree to which one or more objects of interest actually appear in the frame (e.g., the percentage of frames in which an object appears, the proportion of objects appearing in each such frame), etc.

[0158] In some embodiments, processing unit 110 may select information obtained from two of the first, second, and third plurality of images by determining the degree to which information obtained from one image source is consistent with information obtained from other image sources. For example, processing unit 110 may combine processed information obtained from each of image capture devices 122, 124, and 126 (whether through monocular analysis, stereo analysis, or any combination of the two) and determine visual indicators (e.g., lane markings, detected vehicles and their positions and / or paths, detected traffic lights, etc.) that are consistent between each of the captured images from image capture devices 122, 124, and 126. Processing unit 110 may also exclude information that is inconsistent between the captured images (e.g., vehicles changing lanes, lane models indicating that vehicles are too close to vehicle 200, etc.). Thus, processing unit 110 may select information obtained from two of the first, second, and third plurality of images based on the determination of consistent and inconsistent information.

[0159] The navigation response may include, for example, steering, lane change, acceleration change, etc. The processing unit 110 may be based on the analysis performed in step 720 and the above combination Figure 4 The described techniques cause one or more navigation responses. Processing unit 110 may also cause one or more navigation responses using data resulting from execution of velocity and acceleration module 406. In some embodiments, processing unit 110 may cause one or more navigation responses based on the relative position, relative velocity, and / or relative acceleration between vehicle 200 and an object detected within any of the first, second, and third pluralities of images. Multiple navigation responses may occur simultaneously, sequentially, or any combination thereof.

[0160] The analysis of the captured images may allow the generation and use of a sparse map model for autonomous vehicle navigation. In addition, the analysis of the captured images may allow the use of identified lane markings to locate the autonomous vehicle. Embodiments for detecting specific features based on one or more specific analyses of the captured images and for navigating the autonomous vehicle using a sparse map model are discussed below with reference to FIGS. 8-17 .

[0161] Sparse road models for autonomous vehicle navigation

[0162] In some embodiments, the disclosed systems and methods may use sparse maps for autonomous vehicle navigation. Specifically, sparse maps may be used for autonomous vehicle navigation along road segments. For example, sparse maps may provide sufficient information for navigating an autonomous vehicle without storing and / or updating large amounts of data. As discussed in further detail below, an autonomous vehicle may use a sparse map to navigate one or more roads based on one or more stored trajectories.

[0163] Sparse maps for autonomous vehicle navigation

[0164] In some embodiments, the disclosed systems and methods can generate sparse maps for autonomous vehicle navigation. For example, a sparse map can provide sufficient information for navigation without excessive data storage or data transmission rates. As discussed in further detail below, a vehicle (which can be an autonomous vehicle) can use a sparse map to navigate one or more roads. For example, in some embodiments, a sparse map can include data related to roads and potential landmarks along the roads that may not only be sufficient for vehicle navigation but also present a small data footprint. For example, compared to a digital map that includes detailed map information (e.g., image data collected along a road), the sparse data map described in detail below can require significantly less storage space and data transmission bandwidth.

[0165] For example, a sparse data map can store a three-dimensional polynomial representation of a preferred vehicle path along a road, rather than a detailed representation of a road segment. These paths may require very little data storage space. In addition, in the described sparse data map, landmarks can be identified and included in a sparse map road model to help navigation. These landmarks can be located at any spacing suitable for enabling vehicle navigation, but in some cases, it is not necessary to identify these landmarks with high density and short spacing and include them in the model. On the contrary, in some cases, it is possible to navigate based on landmarks that are at least 50 meters, at least 100 meters, at least 500 meters, at least 1 kilometer or at least 2 kilometers apart. As will be discussed in more detail in other parts, a sparse map can be generated based on data collected or measured by a vehicle equipped with various sensors and devices (such as image capture devices, global positioning system sensors, motion sensors, etc.) when the vehicle is traveling along a road. In some cases, a sparse map can be generated based on data collected during multiple drivings of one or more vehicles along a specific road. Using multiple drivings of one or more vehicles to generate a sparse map can be called a "crowdsourcing" sparse map.

[0166] Consistent with the disclosed embodiments, an autonomous vehicle system may use a sparse map for navigation. For example, the disclosed systems and methods may allocate a sparse map to generate a road navigation model for an autonomous vehicle, and may use the sparse map and / or the generated road navigation model to navigate the autonomous vehicle along a road segment. A sparse map consistent with the present disclosure may include one or more three-dimensional contours that may represent a predetermined trajectory that an autonomous vehicle may traverse as it moves along an associated road segment.

[0167] Sparse maps 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 in navigating a vehicle. Sparse maps consistent with the present disclosure may enable autonomous navigation of a vehicle based on a relatively small amount of data included in the sparse map. For example, in addition to including a detailed representation of a road (such as road edges, road curvature, images associated with a road segment, or data detailing other physical features associated with a road segment), a disclosed embodiment of a sparse map may require relatively little storage space (and relatively little bandwidth when a portion of the sparse map is transmitted to a vehicle), but may still be adequately provided for autonomous vehicle navigation. In some embodiments, the small data footprint of the disclosed sparse map may be achieved by storing representations of road-related elements that require a small amount of data but are still capable of autonomous navigation, which will be discussed in further detail below.

[0168] For example, rather than storing a detailed representation of every aspect of a road, the disclosed sparse map may store a polynomial representation of one or more trajectories that a vehicle may travel along the road. Thus, rather than storing (or having to transmit) details about the physical properties of a road to enable navigation along the road, using the disclosed sparse map, in some cases a vehicle may be navigated along a particular road segment without having to interpret the physical aspects of the road, but rather by aligning its travel path with a trajectory (e.g., a polynomial spline) along the particular road segment. In this manner, a vehicle may be navigated primarily based on a stored trajectory (e.g., a polynomial spline), which may require less storage space than methods involving storing road images, road parameters, road layouts, etc.

[0169] In addition to the polynomial representation of the stored trajectory along the road segment, the disclosed sparse map may also include small data objects that can represent road features. In some embodiments, the small data object may include a digital signature derived from a digital image (or digital signal) obtained by a sensor (e.g., a camera or other sensor, such as a suspension sensor) on a vehicle traveling along the road segment. The digital signature may have a reduced size relative to the signal obtained by the sensor. In some embodiments, the digital signature may be created to be compatible with a classifier function that is configured to detect and identify road features from the signal obtained by the sensor during subsequent driving, for example. In some embodiments, a digital signature may be created so that the digital signature has as small a footprint as possible while retaining the ability to correlate or match road features with stored signatures based on images of road features captured by a camera on a vehicle traveling along the same road segment at a subsequent time (or digital signals generated by a sensor if the stored signature is not based on an image and / or includes other data).

[0170] In some embodiments, the size of the data object may be further associated with the uniqueness of the road feature. For example, for a road feature that is detectable by a camera on a vehicle, and where the camera system on the vehicle is coupled to a classifier capable of distinguishing image data corresponding to the road feature as being associated with a particular type of road feature (e.g., a road sign), and where such a road sign is locally unique in the area (e.g., there are no identical road signs or road signs of the same type nearby), it may be sufficient to store data indicating the type of road feature and its location.

[0171] As will be discussed in further detail below, road features (e.g., landmarks along road segments) can be stored as small data objects that can represent road features with relatively few bytes, while providing enough information to identify and use such features for navigation. In one example, road signs can be identified as recognized landmarks based on which vehicle navigation can be performed. Representations of road signs can be stored in sparse maps to include, for example, a few bytes of data indicating the type of landmark (e.g., a stop sign) and a few bytes of data indicating the location of the landmark (e.g., coordinates). Navigation based on a light data representation of such landmarks (e.g., using a representation sufficient to locate, identify, and navigate based on the landmark) can provide the desired level of navigation functionality associated with sparse maps without significantly increasing the data overhead associated with sparse maps. This condensed representation of landmarks (and other road features) can utilize sensors and processors included on such vehicles that are configured to detect, identify, and / or classify certain road features.

[0172] For example, when a sign or even a particular type of sign is locally unique in a given area (e.g., when there are no other signs or other signs of the same type), the sparse map can use data indicating the type of landmark (the sign or the specific type of sign), and during navigation (e.g., autonomous navigation) when a camera on an autonomous vehicle captures an image of an area that includes the sign (or the specific type of sign), the processor can process the image, detect the sign (if indeed present in the image), classify the image as a sign (or the specific type of sign), and associate the location of the image with the location of the sign for storage in the sparse map.

[0173] Road feature representation

[0174] In some embodiments, the sparse map may include at least one line representation of road features extending along a road segment and a plurality of landmarks associated with the road segment. In some aspects, the sparse map may be generated via "crowd sourcing," e.g., by image analysis of a plurality of images acquired as one or more vehicles traverse the road segment.

[0175] In addition to the target track and identified landmarks, the sparse map can also include information about various other road features. For example, Fig. 9A A representation of a curve along a particular road segment that may be stored in a sparse map is shown. In some embodiments, a single lane of a road may be modeled by a three-dimensional polynomial description of the left and right sides of the road. Fig. 8A Such polynomials for the left and right sides of a single lane are shown in . Regardless of how many lanes a road may have, it is possible to express the polynomials in a manner similar to Fig. 8A The method shown in Figure 1 uses polynomials to represent roads. For example, a polynomial can be represented by Fig. 8A The polynomials shown are used to represent the left and right sides of a multi-lane road, and can also be used such as Fig. 8A The polynomial shown in is used to represent the middle lane markings included on a multi-lane road (for example, a dotted line marking indicating a lane boundary, a solid yellow line indicating a boundary between lanes traveling in different directions, etc.).

[0176] like Fig. 8A As shown, a polynomial (e.g., a first order, a second order, a third order, or any suitable order) may be used to represent lane 800. For illustration, lane 800 is shown as a two-dimensional lane, and the polynomial is shown as a two-dimensional polynomial. Fig. 8A As shown, lane 800 includes a left side 810 and a right side 820. In some embodiments, more than one polynomial may be used to represent the position of each side of the road or lane boundary. For example, each of the left side 810 and the right side 820 may be represented by a plurality of polynomials of any suitable length. In some cases, the length of the polynomial may be about 100m, but other lengths greater than or less than 100m may also be used. In addition, the polynomials may overlap with each other so as to facilitate seamless transformation in navigation based on subsequently encountered polynomials when the host vehicle travels along the road. For example, each of the left side 810 and the right side 820 may be represented by a plurality of third-order polynomials separated into segments with a length of about 100 meters (an example of a first predetermined range) and overlapped with each other by about 50 meters. The polynomials representing the left side 810 and the right side 820 may or may not have the same order. For example, in some embodiments, some polynomials may be second-order polynomials, some may be third-order polynomials, and some may be fourth-order polynomials.

[0177] exist Fig. 8AIn the example shown, the left side 810 of lane 800 is represented by two sets of third-order polynomials. The first set includes polynomial segments 811, 812, and 813. The second set includes polynomial segments 814, 815, and 816. The two sets, while being substantially parallel to each other, follow the positions of their respective sides of the road. Polynomial segments 811, 812, 813, 814, 815, and 816 are approximately 100 meters in length and overlap adjacent segments in the sequence by approximately 50 meters. However, as previously described, polynomials of different lengths and different amounts of overlap may also be used. For example, the polynomials may have a length of 500m, 1km, or longer, and the amount of overlap may vary from 0 to 50m, 50m to 100m, or more than 100m. In addition, while Fig. 8A The polynomials are shown as representing polynomials extending in 2D space (e.g., on the surface of paper), but it will be appreciated that these polynomials may represent curves extending in three dimensions (e.g., including a height component) to represent elevation changes in a road segment in addition to XY curvature. Fig. 8A In the example shown, the right side 820 of lane 800 is further represented by a first group having polynomial segments 821 , 822 , and 823 and a second group having polynomial segments 824 , 825 , and 826 .

[0178] Return to the target trajectory of the sparse map, Figure 8B A three-dimensional polynomial is shown that represents a target trajectory for a vehicle traveling along a particular road segment. The target trajectory not only represents the XY path that the host vehicle should travel along a particular road segment, but also represents the elevation changes that the host vehicle will experience while traveling along that road segment. Therefore, each target trajectory in the sparse map can be represented by one or more three-dimensional polynomials (such as Figure 8B The sparse map may include multiple tracks (e.g., millions or billions or more to represent vehicle tracks along various road segments of roads around the world). In some embodiments, each target track may correspond to a spline connecting the three-dimensional polynomial segments.

[0179] Regarding the data footprint of the polynomial curves stored in the sparse map, in some embodiments, each cubic polynomial can be represented by four parameters, each requiring four bytes of data. A suitable representation can be obtained using a cubic polynomial requiring approximately 192 bytes of data per 100m. For a host vehicle traveling at a speed of approximately 100km / hr, this may translate into a data usage / transmission requirement of approximately 200kB per hour.

[0180] Sparse maps can use a combination of geometric descriptors and metadata to describe the lane network. The geometry can be described by polynomials or splines as described above. The metadata can describe the number of lanes, special features (such as car pool lanes), and possibly other sparse labels. The total footprint of such indicators can be negligible.

[0181] Thus, a sparse map according to an embodiment of the present disclosure may include at least one line representation of a road surface feature extending along a road segment, each line representation representing a path along the road segment that substantially corresponds to the road surface feature. In some embodiments, as described above, at least one line representation of a road surface feature may include a spline, a polynomial representation, or a curve. Further, in some embodiments, the road surface feature may include at least one of a road edge or a lane marking. Further, as discussed below with respect to "crowdsourcing," road surface features may be identified by image analysis of multiple images acquired as one or more vehicles traverse a road segment.

[0182] Fig. 9A A polynomial representation of a trajectory captured in the process of establishing or maintaining a sparse map is shown. The polynomial representation of a target trajectory included in the sparse map can be determined based on two or more reconstructed trajectories of a vehicle along a previous traversal of the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map can be an aggregation of two or more reconstructed trajectories of a vehicle along a previous traversal of the same road segment. In some embodiments, the polynomial representation of the target trajectory included in the sparse map can be an average of two or more reconstructed trajectories of a vehicle along a previous traversal of the same road segment. Other mathematical operations can also be used to construct a target trajectory along a road path based on reconstructed trajectories collected from vehicles traversing along a road segment.

[0183] like Fig. 9A As shown, a road segment 900 may be traveled by multiple vehicles 200 at different times. Each vehicle 200 may collect data related to the path taken by the vehicle along the road segment. The travel path of a particular vehicle may be determined based on camera data, accelerometer information, speed sensor information, and / or GPS information, as well as other potential sources. Such data may be used to reconstruct the trajectory of the vehicle traveling along the road segment, and based on these reconstructed trajectories, a target trajectory (or multiple target trajectories) may be determined for a particular road segment. Such a target trajectory may represent a preferred path for the host vehicle (e.g., guided by an autonomous navigation system) as the vehicle travels along the road segment.

[0184] exist Fig. 9AIn the example shown, a first reconstructed trajectory 901 may be determined based on data received from a first vehicle traversing the road segment 900 at a first time period (e.g., day 1), a second reconstructed trajectory 902 may be obtained from a second vehicle traversing the road segment 900 at a second time period (e.g., day 2), and a third reconstructed trajectory 903 may be obtained from a third vehicle traversing the road segment 900 at a third time period (e.g., day 3). Each trajectory 901, 902, and 903 may be represented by a polynomial, such as a three-dimensional polynomial. It should be noted that in some embodiments, any reconstructed trajectory may be equipped on a vehicle traversing the road segment 900.

[0185] Additionally or alternatively, such a reconstructed trajectory may be determined on the server side based on information received from vehicles traversing the road segment 900. For example, in some embodiments, the vehicle 200 may transmit data related to its movement along the road segment 900 (e.g., steering angle, heading, time, location, speed, sensed road geometry and / or sensed landmarks, etc.) to one or more servers. The server may reconstruct the trajectory of the vehicle 200 based on the received data. The server may also generate a target trajectory for guiding navigation of an autonomous vehicle that will travel along the same road segment 900 at a later time based on the first, second, and third trajectories 901, 902, and 903. Although the target trajectory may be associated with a single previous traversal of the road segment, in some embodiments, each target trajectory included in the sparse map may be determined based on two or more reconstructed trajectories of vehicles traversing the same road segment. Fig. 9A , the target track is represented by 910. In some embodiments, the target track 910 may be generated based on an average of the first, second, and third tracks 901, 902, and 903. In some embodiments, the target track 910 included in the sparse map may be an aggregation (e.g., a weighted combination) of two or more reconstructed tracks.

[0186] Fig. 9B and 9C The concept of target trajectories associated with road segments present in the geographic area 911 is further illustrated. Fig. 9BAs shown in , a first road segment 920 within geographic area 911 may include a multi-lane road including two lanes 922 designated for vehicles traveling in a first direction and two additional lanes 924 designated for vehicles traveling in a second direction opposite to the first direction. Lanes 922 and lanes 924 may be separated by double yellow lines 923. Geographic area 911 may also include a branch road segment 930 intersecting road segment 920. Road segment 930 may include a two-lane road, each lane designated for a different direction of travel. Geographic area 911 may also include other road features, such as stop lines 932, stop signs 934, speed limit signs 936, and hazard signs 938.

[0187] like Fig. 9C As shown, the sparse map may include a local map 940 that includes a road model for assisting in autonomous navigation of a vehicle within geographic area 911. For example, local map 940 may include target tracks for one or more lanes associated with road segment 920 and / or road segment 930 within geographic area 911. For example, local map 940 may include target tracks 941 and / or 942 that the autonomous vehicle may enter or rely on when traversing lane 922. Similarly, local map 940 may include target tracks 943 and / or 944 that the autonomous vehicle may enter or rely on when traversing lane 924. In addition, local map 940 may include target tracks 945 and / or 946 that the autonomous vehicle may enter or rely on when traversing road segment 930. Target trajectory 947 represents a preferred path that the autonomous vehicle should follow when transitioning from lane 920 (and specifically, relative to target trajectory 941 associated with the rightmost lane of lane 920) to road segment 930 (and specifically, relative to target trajectory 941 associated with the first side of road segment 930). Similarly, target trajectory 948 represents a preferred path that the autonomous vehicle should follow when transitioning from road segment 930 (and specifically, relative to target trajectory 946) to a portion of road segment 924 (and specifically, as shown, relative to target trajectory 943 associated with the left lane of lane 924).

[0188] The sparse map may also include representations of other road-related features associated with geographic area 911. For example, the sparse map may also include representations of one or more landmarks identified in geographic area 911. Such landmarks may include a first landmark 950 associated with stop line 932, a second landmark 952 associated with stop sign 934, a third landmark associated with speed limit sign 954, and a fourth landmark 956 associated with hazard sign 938. Such landmarks may be used, for example, to assist the autonomous vehicle in determining its current position relative to any target track shown so that the vehicle can adjust its heading to match the direction of the target track at the determined location.

[0189] In some embodiments, the sparse map may also include a road signature distribution. Such a road signature distribution may be associated with any discernible / measurable change in at least one parameter associated with the road. For example, in some cases, such a distribution may be associated with a change in road surface information, such as a change in surface roughness of a particular road segment, a change in road width over a particular road segment, a change in the distance between dashed lines drawn along a particular road segment, a change in road curvature along a particular road segment, etc. Fig.9D An example of a road signature distribution 960 is shown. Distribution 960 may represent any of the parameters described above or other parameters, and in one example, distribution 960 may represent a measurement of road surface roughness, such as obtained by monitoring one or more sensors that provide an output indicative of the amount of suspension displacement when the vehicle is traveling on a particular road segment.

[0190] Alternatively or concurrently, distribution 960 may represent changes in road width as determined based on image data obtained via a camera on a vehicle traveling on a particular road segment. Such a distribution may be useful, for example, in determining a particular position of an autonomous vehicle relative to a particular target track. That is, as the autonomous vehicle traverses a road segment, it may measure a distribution associated with one or more parameters associated with the road segment. If the measured distribution can be correlated / matched with a predetermined distribution that plots changes in the parameters relative to position along the road segment, the measured distribution and the predetermined distribution may be used (e.g., by overlaying corresponding portions of the measured distribution and the predetermined distribution) in order to determine a current position along the road segment, and therefore a current position of the target track relative to the road segment.

[0191] In some embodiments, the sparse map may include different trajectories based on different characteristics associated with users of the autonomous vehicle, environmental conditions, and / or other parameters related to driving. For example, in some embodiments, different trajectories may be generated based on different user preferences and / or distributions. Sparse maps including such different trajectories may be provided to different autonomous vehicles of different users. For example, some users may prefer to avoid toll roads, while other users may prefer to take the shortest or fastest route, regardless of whether there are toll roads on the route. The disclosed system may generate different sparse maps with different trajectories based on such different user preferences or distributions. As another example, some users may prefer to travel in a fast-moving lane, while other users may prefer to always maintain a position in the center lane.

[0192] Different trajectories may be generated and included in a sparse map based on different environmental conditions such as day and night, snow, rain, fog, etc. Sparse maps generated based on such different environmental conditions may be provided to autonomous vehicles driving under different environmental conditions. In some embodiments, a camera provided on an autonomous vehicle may detect environmental conditions, and such information may be provided back to a server that generates and provides sparse maps. For example, a server may generate or update an already generated sparse map to include trajectories that may be more appropriate or safer for autonomous driving under detected environmental conditions. Updates to the sparse map based on environmental conditions may be performed dynamically as the autonomous vehicle travels along a road.

[0193] Other different parameters related to driving can also be used as the basis for generating different sparse maps and providing them to different autonomous vehicles. For example, when the autonomous vehicle is traveling at high speed, the turns may be tighter. Tracks associated with specific lanes rather than roads can be included in the sparse map so that when the autonomous vehicle follows the specific track, the vehicle can be maintained in the specific lane. When the image captured by the camera on the autonomous vehicle indicates that the vehicle has deviated from the lane (e.g., crossed the lane marking), an action can be triggered in the vehicle to bring the vehicle back to the designated lane according to the specific track.

[0194] Fig.10 An example autonomous vehicle road navigation model represented by a plurality of three-dimensional splines 1001 , 1002 , and 1003 is shown. Fig.10The curves 1001, 1002, and 1003 shown are for illustration purposes only. Each spline may include one or more three-dimensional polynomials connecting multiple data points 1010. Each polynomial may be a first-order polynomial, a second-order polynomial, a third-order polynomial, or a combination of any suitable polynomials of different orders. Each data point 1010 may be associated with navigation information received from multiple vehicles. In some embodiments, each data point 1010 may be associated with data about landmarks (e.g., size, location, and identification information of landmarks) and / or road signature distributions (e.g., road geometry, road roughness distribution, road curvature distribution, road width distribution). In some embodiments, some data points 1010 may be associated with data about landmarks, while other data points may be associated with data about road signature distributions.

[0195] Fig.11 Raw location data 1110 (e.g., GPS data) received from five separate drives is shown. A drive may be separated from another drive if it is traversed by separate vehicles at the same time, traversed by the same vehicle at separate times, or traversed by separate vehicles at separate times. To account for errors in the location data 1110 and different positions of vehicles in the same lane (e.g., one vehicle may be driving closer to the left side of the lane than another vehicle), the remote server may generate a map frame 1120 using one or more statistical techniques to determine whether changes in the raw location data 1110 represent actual differences or statistical errors. Each path within the frame 1120 may be linked back to the raw data 1110 that formed the path. For example, the path between A and B within the frame 1120 is linked to the raw data 1110 from drives 2, 3, 4, and 5, but not the raw data from drive 1. The frame 1120 may not be detailed enough to be used to navigate a vehicle (e.g., unlike the spline described above, because it combines drives from multiple lanes on the same road), but it may provide useful topological information and may be used to define intersections.

[0196] Safety and comfort constraints for navigation

[0197] In addition to navigation models, autonomous vehicles (whether fully autonomous, such as a self-driving vehicle, or partially autonomous, such as one or more driver assistance systems or features) typically use driving strategies to ensure the safety of other drivers and pedestrians and the comfort of interior passengers.

[0198] Therefore, the autonomous vehicle can sense the navigation state in the host vehicle environment. For example, these tasks can rely on inputs from various sensors and sensing systems associated with the host vehicle. These inputs can include images or image streams from one or more on-board cameras, GPS location information, accelerometer outputs, user feedback or user input to one or more user interface devices, radar, laser radar, etc. The sensing of data from cameras and / or any other available sensors and map information can be collected, analyzed and formulated into "sensed states", which describe information extracted from the scene in the host vehicle environment. The sensed state can include target vehicles, lane markings, pedestrians, traffic lights, road geometry, lane shapes, obstacles, distances to other objects / vehicles, relative speeds, relative accelerations, and any other potential sensed information. Supervised machine learning can be implemented to generate sensed state outputs based on the sensed data provided. The output of the sensing module can represent the sensed navigation "state" of the host vehicle that can be used in the driving strategy, as described below.

[0199] Although the sensed state can be generated based on image data received from one or more cameras or image sensors associated with the main vehicle, any suitable sensor or sensor combination can also be used to generate the sensed state used in navigation. In some embodiments, the sensed state can be generated without relying on captured image data. In fact, any navigation principle described herein can be applied to sensed states generated based on captured image data and sensed states generated using other non-image-based sensors. The sensed state can also be determined via a source outside the main vehicle. For example, the sensed state can be generated in whole or in part based on information received from a source away from the main vehicle (e.g., based on sensor information shared from other vehicles, shared from a central server, or from any other information source related to the navigation state of the main vehicle, processed state information, etc.).

[0200] The autonomous vehicle can implement a desired driving strategy to determine one or more navigation actions taken by the host vehicle in response to the sensed navigation state. If there are no other agents (e.g., target vehicles or pedestrians) in the host vehicle environment, the sensed state input can be processed in a relatively direct manner. When the sensed state needs to be negotiated with one or more other agents, the task becomes more complicated. Techniques for generating outputs from driving strategies can include reinforcement learning (discussed in more detail below). The output of the driving strategy may include at least one navigation action of the host vehicle, and may include a desired acceleration (which can be converted into an updated speed of the host vehicle), a desired yaw rate of the host vehicle, a desired trajectory, and other potential desired navigation actions.

[0201] Based on the output from the driving strategy, the autonomous vehicle can develop control instructions for one or more actuators or controlled devices associated with the host vehicle. Such actuators and devices can include accelerators, one or more steering controllers, brakes, signal transmitters, displays, or any other actuators or devices that can be controlled as part of the navigation operation associated with the host vehicle. Aspects of control theory can be used to generate control instructions. Instructions to the controllable components of the host vehicle can achieve the desired navigation goals or requirements of the driving strategy.

[0202] Returning to the driving strategy discussed above, in some embodiments, a trained system trained by reinforcement learning can be used to implement the driving strategy. In other embodiments, the driving strategy can be implemented without machine learning methods by using specified algorithms to "manually" solve various scenarios that may arise during autonomous navigation. However, such an approach, while feasible, may result in oversimplification of the driving strategy and may lack the flexibility of a trained system based on machine learning. For example, a trained system may be better equipped to handle complex navigation states and may better determine whether a taxi is stopping or stopping to pick up / drop off passengers; determine whether a pedestrian intends to cross the street in front of the main vehicle; defensively balance the unexpected behavior of other drivers; negotiate in dense traffic involving target vehicles and / or pedestrians; decide when to suspend certain navigation rules or augment other rules; anticipate unsensed but expected conditions (e.g., whether a pedestrian will emerge from behind a car or obstacle); and so on. A trained system based on reinforcement learning may also be better equipped to solve continuous and high-dimensional state spaces and continuous action spaces.

[0203] Training the system using reinforcement learning can involve learning a driving policy to map from sensed states to navigation actions. The driving policy can be a function π: S→A, where S is a set of states and is the action space (e.g., desired velocity, acceleration, yaw command, etc.). The state space is S = S s x S p , where S s is the sensing state, and S p is additional information about the state saved by the strategy. Working in discrete time intervals, at time t, the current state s can be observed t ∈S, and the policy can be applied to obtain the desired action a t =π(s t ).

[0204] The system can be trained by exposing it to various navigation states, causing it to apply the policy, and providing rewards (based on a reward function designed to reward the desired navigation behavior). Based on the reward feedback, the system can "learn" the policy and become trained in producing the desired navigation actions. For example, the learning system can observe the current state s t ∈S, and based on the strategy To decide action a t ∈A. Based on the action decided (and the execution of that action), the environment moves to the next state s t+1 ∈S, to be observed by the learning system. For each action taken in response to the observed state, the feedback to the learning system is a reward signal r1, r2, ...

[0205] The goal of reinforcement learning (RL) is usually to find a policy π. It is usually assumed that at time t, there exists a reward function r t , whose measurement is in state s t and take action a t However, taking action a at time t t affects the environment and therefore the value of future states. Therefore, when deciding which action to take, not only the current reward should be considered, but also the future reward. In some cases, when the system determines that a higher reward may be achieved in the future if a lower reward option is taken now, then the system should take an action even if that action is associated with a lower reward than another available option. To formalize this, observe that the policy π and the initial state s are summarized in distribution over , where if the agent starts at state s0=s and follows policy π from there, then the vector (r1, ..., r T ) is the probability of observing rewards r1,…,r T The value of the initial state s can be defined as:

[0206]

[0207] Instead of limiting the time horizon to T, one can discount future rewards to define, for some fixed γ∈(0,1),

[0208]

[0209] In any case, the best strategy is the solution to:

[0210]

[0211] Among them, the expectation is above the initial state s.

[0212] There are several possible approaches for training a driving policy system. For example, one can use imitation methods (e.g., behavioral cloning), in which the system learns from state / action pairs, where the actions are those that a good actor (e.g., a human) would choose in response to a particular observed state. Suppose that a human driver is observed. From this observation, many forms of (st, a t ) (where s t is the state, and a t is the action of a human driver) can be obtained, observed, and used as the basis for training a driving policy system. For example, supervised learning can be used to learn a policy π such that π(s t )≈a t This approach has many potential advantages. First, it does not require the definition of a reward function. Second, the learning is supervised and occurs offline (no actor needs to be applied during the learning process). A disadvantage of this approach is that different human drivers, or even the same human driver, are not deterministic in their choice of strategy. Therefore, for ||π(s t )-a t ||Learning of very small functions is usually not feasible. Moreover, even small errors may accumulate to produce larger errors over time.

[0213] Another technique that can be used is policy-based learning. Here, the policy can be expressed in parameterized form and optimized directly using a suitable optimization technique (e.g., stochastic gradient descent). There are many other ways to solve this problem. One advantage of this approach is that it solves the problem directly, so it often leads to good practical results. A potential disadvantage is that it often requires "online policy" training, that is, the learning of π is an iterative process, where at iteration j, there is a non-perfect policy π j , and in order to construct the next strategy π j , must be based on π j Interact with the environment while performing actions.

[0214] The system can also be trained by value-based learning (learning Q or V functions). Assume that a good approximation can be learned to the optimal value function V*. The optimal policy can be constructed (e.g., relying on the Bellman equation). Some versions of value-based learning can be implemented offline (called "off-policy" training). Some disadvantages of value-based methods may be due to their strong reliance on Markovian assumptions and the need to approximate complex functions (which may be more difficult to approximate the value function than to directly approximate the policy).

[0215] Another technique can include model-based learning and planning (learning the probabilities of state transitions and solving the optimization problem of finding the optimal V). A combination of these techniques can also be used to train a learning system. In this approach, the dynamics of the process can be learned, i.e., taking (s t , a t ) and in the next state s t+1 Once this function is learned, the optimization problem can be solved to find the policy π whose value is optimal. This is called "planning". One advantage of this approach may be that the learning is partially supervised and can be obtained by observing the triples (s t , a t ,s t+1 ) and are applied offline. Similar to the “imitation” approach, a drawback of this approach may be that small errors in the learning process may accumulate and produce an underperforming strategy.

[0216] Another method for training the driving strategy module 803 may include decomposing the driving strategy function into semantically meaningful components. This allows manual implementation of certain parts of the strategy, which can ensure the safety of the strategy; and other parts of the strategy can be implemented using reinforcement learning techniques, which can be adaptively implemented in many scenarios, a human-like balance between defensive / aggressive behavior, and human-like negotiation with other drivers. From a technical perspective, reinforcement learning methods can combine several methods and provide an easy-to-operate training program, most of which can be performed using recorded data or self-built simulators.

[0217] In some embodiments, the training of the driving policy module 803 may rely on an "option" mechanism. To illustrate, consider a simple scenario of a driving policy on a two-lane highway. In a direct RL approach, policy π maps states to , where the first component of π(s) is the desired acceleration command and the second component of π(s) is the yaw rate. In the modified approach, the following strategy can be constructed:

[0218] Automatic Cruise Control (ACC) Strategy ACC : S → A: This strategy always outputs a yaw rate of 0 and only changes the rate to achieve smooth and accident-free driving.

[0219] ACC+Left Strategy o L : S → A: The longitudinal commands for this strategy are the same as the ACC commands. The yaw rate is a direct implementation of centering the vehicle towards the middle of the left lane while ensuring safe lateral movement (e.g., not moving to the left if there is a car on the left).

[0220] ACC+Right Strategy R :S→A:with o L Same, but the vehicle may center toward the center of the right lane.

[0221] These strategies can be called "options". Based on these "options", we can learn a strategy π that selects the option o : S→O, where O is a set of available options. In one case, O={o ACC , o L , o R}. Option selector strategy π o By setting To define the actual policy π: S→A.

[0222] In practice, the policy function can be decomposed into an option graph. The option graph can represent a hierarchical decision set organized as a directed acyclic graph (DAG). There is a special node called the root node of the graph. This node has no incoming nodes. The decision process traverses the entire graph starting from the root node until it reaches a "leaf" node, which refers to a node with no outgoing decision lines. When encountering a leaf node, the driving policy module 803 can output acceleration and steering commands associated with the desired navigation action, which is associated with the leaf node.

[0223] An internal node may cause the implementation of a policy that selects children among its available options. The set of available children of an internal node includes all nodes associated with the particular internal node via a decision line.

[0224] Flexibility in the decision-making system can be achieved by enabling nodes to adjust their positions in the hierarchy of the option graph. For example, any node can be allowed to declare itself as "critical". Each node can implement an "is critical" function that outputs "true" if the node is in a critical part of its policy implementation. For example, a node responsible for overtaking can declare itself as critical in the middle of a maneuver. This can impose constraints on the set of available children of node u, which can include all nodes v that are children of node u, and there is a path from v to a leaf node that passes through all nodes designated as critical. On the one hand, such an approach can allow the expected path to be declared on the graph at each time step, while on the other hand, the stability of the policy can be retained, especially when the critical part of the policy is being implemented.

[0225] By defining an option graph, the problem of learning a driving policy π: S→A can be decomposed into the problem of defining a policy for each node in the graph, where the policy at the internal node should be selected from the available child nodes. For some nodes, the corresponding policy can be implemented manually (for example, by specifying a set of actions in response to the observed state through an if-then type algorithm), while for other policies, a trained system built by reinforcement learning can be used for implementation. The choice between manual or trained / learned methods can depend on the safety aspects associated with the task and on its relative simplicity. The option graph can be constructed in such a way that some nodes are implemented directly, while other nodes can rely on trained models. Such an approach can ensure the safe operation of the system.

[0226] As mentioned above, the input to the driving policy is a "sensed state" that summarizes the environment map, for example, obtained from available sensors. The output of the driving policy is a set of expectations (optionally together with a set of hard constraints) that define the trajectory as a solution to the optimization problem.

[0227] As described above, the option graph represents a hierarchical decision set organized as a DAG. There is a special node called the "root" of the graph. The root node is the only node with no incoming edges (e.g., decision lines). The decision process traverses the graph starting from the root node until it reaches a "leaf" node, i.e., a node with no outgoing edges. Each internal node should implement a strategy of selecting a child from its available children. Each leaf node should implement a strategy that defines a set of expectations (e.g., a set of navigation goals for the main vehicle) based on the entire path from the root to the leaf. This set of expectations directly defined based on the sensed state, together with a set of hard constraints, establishes an optimization problem, the solution of which is the trajectory of the vehicle. Hard constraints can be used to further improve the safety of the system, and the expectation can be used to provide the system with driving comfort and human-like driving behavior. The trajectory provided as a solution to the optimization problem further defines the commands that should be provided to the steering, braking and / or engine actuators in order to complete the trajectory.

[0228] Various semantic meanings may be assigned to target vehicles in the host vehicle's environment. For example, in some embodiments, the semantics may include any of the following designations: 1) Not relevant: indicates that the sensed vehicle in the scene is currently not relevant; 2) Next lane: indicates that the sensed vehicle is in an adjacent lane and an appropriate offset should be maintained relative to the vehicle (the exact offset may be calculated in an optimization problem that constructs a trajectory given a desired and hard constraint, and the exact offset may potentially be vehicle-dependent - the hold leaf of the option map sets the semantic type of the target vehicle, which defines the desired relative to the target vehicle); 3) Give way: the host vehicle will attempt to give way to the sensed target vehicle by, for example, reducing speed (especially if the host vehicle determines that the target vehicle may cut into the host vehicle's lane); 4) Take way: the host vehicle will attempt to take the right of way by, for example, increasing speed; 5) Follow: the host vehicle expects to follow the target vehicle and maintain a smooth drive; 6) Left / right overtaking: this means that the host vehicle wants to initiate a lane change to the left or right lane.

[0229] Another example of a node is a Select Gap node. This node may be responsible for selecting a gap between two target vehicles in a particular target lane that the subject vehicle desires to enter. By selecting a node of the form IDj, for some value of j, the subject vehicle arrives at a leaf that specifies a desire for the trajectory optimization problem - for example, the subject vehicle desires to maneuver in order to reach the selected gap. Such a maneuver may involve first accelerating / braking in the current lane, then heading to the target lane at the appropriate time to enter the selected gap. If the Select Gap node cannot find an appropriate gap, it may transition to a Stop node, which defines the desire to return to the center of the current lane and cancel the overtaking.

[0230] As described above, nodes of the option graph can declare themselves as "critical", which can ensure that the selected option passes through critical nodes. Formally, each node can implement an IsCritical function. After performing a forward pass from root to leaf on the option graph, and solving the trajectory planner's optimization problem, a backward pass can be performed from the leaf back to the root. Along this backward pass, the IsCritical function of all nodes in the pass can be called, and a list of all critical nodes can be saved. In the forward path corresponding to the next time frame, the driving policy may need to choose a path from the root node to the leaf that passes through all critical nodes.

[0231] For example, in the case where an overtaking action is initiated and the driving strategy reaches the leaf corresponding to IDk, such as when the host vehicle is in the middle of an overtaking maneuver, it would be undesirable to select the hold node. To avoid such a jump, the IDj node can designate itself as critical. During the maneuver, the success of the trajectory planner can be monitored, and if the overtaking maneuver is performed as expected, the function IsCritical will return a "true" value. This method can ensure that in the next time frame, the overtaking maneuver will continue (rather than jumping to another potentially inconsistent maneuver before completing the initially selected maneuver). On the other hand, if the monitoring of the maneuver indicates that the selected maneuver is not performed as expected, or if the maneuver becomes unnecessary or impossible, the IsCritical function can return a "false" value. This can allow the selection gap node to select a different gap in the next time frame, or to completely abort the overtaking maneuver. On the one hand, this method can allow the desired path to be declared on the option graph at each time step, while on the other hand, it can help improve the stability of the strategy during the critical part of the execution.

[0232] Hard constraints may differ from navigation expectations, which will be discussed in more detail below. For example, hard constraints may ensure safe driving by applying an additional layer of filtering to planned navigation actions. The hard constraints involved may be determined based on the sensed state, and the hard constraints may be manually programmed and defined, rather than by using a trained system built on reinforcement learning. However, in some embodiments, the trained system may learn applicable hard constraints to be applied and followed. Such an approach may cause the driving strategy module 803 to arrive at a selected action that already complies with the applicable hard constraints, which may reduce or eliminate the selected action that may need to be modified later to comply with the applicable hard constraints. Nevertheless, as a redundant safety measure, hard constraints may be applied to the output of the driving strategy even when the driving strategy has been trained to cope with predetermined hard constraints.

[0233] There are many potential examples of hard constraints. For example, a hard constraint may be defined in conjunction with a guardrail at the edge of the road. The host vehicle is not allowed to pass the guardrail under any circumstances. Such a rule creates a hard lateral constraint on the trajectory of the host vehicle. Another example of a hard constraint may include a road bump (e.g., a rate control bump), which may cause a hard constraint on the driving speed before and while traversing the bump. Hard constraints may be considered safety critical and therefore may be defined manually rather than relying solely on a trained system that learns the constraints during training.

[0234] In contrast to hard constraints, a desired goal may be to achieve or attain comfortable driving. As discussed above, an example of a desire may include a goal to place the host vehicle within a lane at a lateral position corresponding to the center of the host vehicle's lane. Another desire may include an ID of a gap suitable for entry. Note that the host vehicle need not be exactly in the center of the lane, but rather, a desire to be as close to it as possible may ensure that the host vehicle tends to migrate to the center of the lane even when off-center. Expectations may not be safety critical. In some embodiments, expectations may require negotiation with other drivers and pedestrians. One method of constructing expectations may rely on an option graph, and the policies implemented in at least some nodes of the graph may be based on reinforcement learning.

[0235] For nodes implemented as option graphs of nodes trained based on learning, the training process may include decomposing the problem into a supervised learning phase and a reinforcement learning phase. In the supervised learning phase, it is possible to learn from (s t , a t )arrive A differentiable map of This can be similar to "model-based" reinforcement learning. However, in the forward loop of the network, s t+1 The actual value is replaced by This eliminates the problem of error accumulation. The role of prediction is to propagate messages from the future back to past actions. In this sense, the algorithm can be a combination of "model-based" reinforcement learning and "policy-based learning".

[0236] An important element that can be provided in some scenarios is a differentiable path from future loss / reward back to the decision on the action. With the option graph structure, the implementation of options involving safety constraints is usually not differentiable. To overcome this problem, the selection of children in the learned policy node can be random. That is, the node can output a probability vector p that assigns the probability of each child for selecting a particular node. Suppose the node has k children, and let a (1) , ..., a (k)is the action of the path from each child to the leaf. The resulting predicted action is thus This may lead to a differentiable path from that action to p. In practice, action a can be chosen to be a for i~p (i) , and a and The difference between can be called additive noise.

[0237] For a given s t 、a t Down For training, supervised learning can be used with real data. For training of node policies, a simulator can be used. Afterwards, fine-tuning of the policy can be done using real data. Two concepts can make simulation more realistic. First, using imitation, the "behavioral cloning" paradigm can be used to build an initial policy using a large real-world dataset. In some cases, the resulting actor can be suitable. In other cases, the resulting actor at least forms a very good initial policy for other actors on the road. Second, using self-play, our own policy can be used to reinforce training. For example, given a preliminary implementation of other actors (cars / pedestrians) that can be experienced, the policy can be trained based on a simulator. Some other actors can be replaced by new policies and the process can be repeated. Therefore, the policy can continue to improve because it should respond to a wider variety of other actors with different levels of complexity.

[0238] Furthermore, in some embodiments, the system may implement a multi-actor approach. For example, the system may consider data from various sources and / or images captured from multiple angles. Furthermore, some disclosed embodiments may provide energy economy because anticipation of events that do not directly involve the host vehicle but may have an impact on the host vehicle may be considered, or even anticipation of events that may lead to unpredictable situations involving other vehicles may be a consideration (e.g., radar may "see through" the vehicle ahead and unavoidably anticipate, or even have a high probability of an event that will affect the host vehicle).

[0239] Global and local precision

[0240] In the context of autonomous driving, loss functions can be defined so as to appropriately define (and thereby impose conditions on) the accuracy of measurements from cameras, sensors, etc. Thus, a scene can be defined as a finite set S of objects (such as vehicles, pedestrians, lane markings, etc.). S contains the host vehicle, which can be denoted as h. In this case, localization can include mapping Where p(h)=0=(0,0,0). Therefore, the first coordinate of p(a) may include the lateral position of object a, the second coordinate may include the longitudinal position of object a, and the last coordinate may include the height of object a.

[0241] Therefore, we can have two positions p and b relative to two objects a and b in the set S. The loss function is defined between . The loss function can be defined as

[0242]

[0243] It is usually impractical to impose constraints on this loss function. For example, if object a is a vehicle at position p(a) = (α, z, 0) and object b is a lane marker at position p(b) = (-α, z, 0), then and A second positioning of a and b at 150 m will result in a loss β. Thus, if objects a and b are at a longitudinal position of 150 m, and the loss β is 0.2 (ie 20%), it is not possible to impose an absolute loss constraint of 20 cm, as this would result in an unacceptable maximum loss.

[0244] Therefore, the relative loss function can be defined as follows:

[0245]

[0246] where v is (0, 1].

[0247] By normalizing this loss function, realistic loss constraints can be imposed, coping with larger losses for more distant objects. However, there are two ways to define accuracy using a normalized loss function. One is ego accuracy, and is measured relative to the host vehicle h:

[0248]

[0249] where ε is the loss constraint.

[0250] However, this requirement relies on the range z of the objects detected in the vehicle's field of view, since if p(a)=(α,z,0) and but

[0251]

[0252] To avoid dependence on the range z, another pairwise definition of precision can be used:

[0253]

[0254] where ε is the loss constraint.

[0255] For p(a)=(α,z,0), p(b)=(-α,z,0), and Then the pairwise accuracy is simplified to:

[0256]

[0257] therefore,

[0258]

[0259] It is independent of z.

[0260] In addition, there are cases where there is self-precision but no pairwise precision. Specifically, if but So that β = εz. Therefore,

[0261]

[0262] This means that z > 2 will result in a loss of pairwise accuracy.

[0263] In a specific example, if ε = 0.2 and z = 100 meters, then β = 2 meters, which is a reasonable loss constraint of 2 meters per 100 meters. However, this leads to This means that this case is 50 times better than the pairwise accuracy of 0.02. To achieve paired accuracy, one can set z = 1 meter and β = 0.02, which results in a 2 cm error over a range of 100 meters. However, this is not realistic considering most existing sensors. On the other hand, paired accuracy can be practically implemented without considering ego accuracy. To enhance this accuracy, a reference coordinate system can be used in which the relevant objects of the scene (such as vehicles, pedestrians, lanes, etc.) reside simultaneously. However, this may involve using cameras instead of lidar, GPS or other sensors.

[0264] Thus, in some embodiments, the host vehicle navigation system may use the camera's 2D coordinate system rather than the vehicle's 3D coordinate system. The system may then convert the map (e.g., landmarks and splines of a sparse map) to a 2-D coordinate system and perform navigation in the 2-D coordinate system. Furthermore, the system may perform navigation in a 3-D coordinate system by converting determinations made in the 2-D coordinate system to a 3-D coordinate system. This enhances pairwise accuracy rather than ego accuracy, thereby providing greater safety and reliability. Additionally, because converting a map to 2-D is faster than converting an image to 3-D, and because performing predictions and navigation in 2-D is faster than performing in 3-D, this technique improves the efficiency of the system.

[0265] In one example embodiment, the navigation system may determine the location of the host vehicle. For example, the location may be within a geographic area. The navigation system may further access a map that includes the geographic area. For example, the navigation system may access a stored map or access a map from one or more remote servers that includes the geographic area. In some embodiments, the map may include a sparse map or roadbook (described below) based on the geographic area or a portion thereof. As described above, the sparse map may include at least one spline and / or at least one landmark representing a predetermined driving path. Thus, at least one feature may include at least one landmark.

[0266] The navigation system may extract at least one feature from the map based on the position of the host vehicle. For example, the navigation system may determine a field of view of the host vehicle and extract at least one feature expected in the field of view based on the position. In some embodiments, the at least one feature may include a lane marking, a road edge, or other landmark included in the map. For example, the road edge may include at least one of: a lane marking, a curb, a guardrail, or a Jersey wall.

[0267] The navigation system may receive at least one image representing the host vehicle environment from at least one image sensor, and convert the coordinates of at least one feature from a coordinate system of the map to a coordinate system of the at least one image sensor. For example, the coordinate system of the map may include a three-dimensional coordinate system (e.g., a global coordinate system based on GPS, a coordinate system local to a road segment included in a geographic area, etc.), and the coordinate system of the at least one image sensor may include a two-dimensional coordinate system based on a field of view of the at least one image sensor. In some embodiments, the at least one feature may be transformed from the three-dimensional coordinate system of the map into a three-dimensional coordinate system centered on the host vehicle (e.g., using a location), and then projected onto a two-dimensional plane of the at least one image sensor (e.g., using a known relationship between the host vehicle and the field of view).

[0268] The navigation system may analyze at least one image to identify at least one feature in the host vehicle environment and cause at least one navigation change to the host vehicle based on a comparison between the transformed coordinates and the coordinates of the at least one feature identified in the at least one image. For example, the navigation system may determine an expected location of the at least one feature in a two-dimensional coordinate system of the at least one image sensor based on the transformed coordinates and search one or more images from the at least one image sensor at and / or near the expected location. The proximity may be determined absolutely, e.g., within 10 pixels, within 20 pixels, etc. of the expected location, or relatively, e.g., within 10% of an expected dimension (such as length or width) of the at least one feature, etc.

[0269] In some embodiments, at least one of the navigation changes may include decelerating the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle. For example, based on a difference between the position of at least one feature in the identified at least one image and an expected position based on the transformed coordinates, the host vehicle may decelerate, accelerate, and / or steer.

[0270] In some embodiments, at least one navigation change can be determined within the coordinate system of at least one image sensor. For example, a vector can be determined based on the difference between the position of at least one feature in the at least one image identified and the expected position based on the transformed coordinates. The vector can represent at least one navigation change so that the at least one feature will appear in the expected position. In such an embodiment, the navigation system can convert the at least one navigation change to the coordinate system of the map. For example, the navigation system can project the difference vector to a three-dimensional coordinate system (e.g., a global coordinate system or a coordinate system centered on the host vehicle) based on the depth of at least one feature in the at least one image and / or the expected depth of at least one feature from the map.

[0271] Fusion of comfort and safety restraints

[0272] In some embodiments, the host vehicle may receive data from multiple sources, such as map data coupled with cameras, lidars, radars, etc. The navigation system of the host vehicle may use different schemes to fuse data from these various sources. For example, in a unified scheme, if a target object is detected by at least one source, the navigation system may verify the target object (i.e., confirm that a potential object should actually be considered a detected object), which is a fast but less accurate detection technique. In a cross scheme, if a target object is detected by multiple sources, the navigation system may recognize the target object; in a collaborative scheme, if a target object is detected using a combination of data from multiple sources, the navigation system may recognize the target object. Cross schemes and collaborative schemes are slower but more accurate than unified schemes. Therefore, by selectively using cross and collaborative schemes and unified schemes, the accuracy of system reactions can be optimized without sacrificing safety. This solves the technical problem of how to accurately interpret sensor data from autonomous vehicles without sacrificing safety.

[0273] Fig.12 1 is an exemplary functional block diagram of memory 140 and / or 150, which may be stored / programmed with instructions for performing one or more operations consistent with the embodiments of the present disclosure. Although the following refers to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0274] like Fig.12As shown, the memory 140 may store an object recognition module 1202, a constraint module 1204, a verification module 1206, and a navigation change module 1208. The disclosed embodiments are not limited to any particular configuration of the memory 140. In addition, the application processor 180 and / or the image processor 190 may execute instructions stored in any of the modules 1202, 1204, 1206, and 1208 included in the memory 140. Those skilled in the art will appreciate that references to the processing unit 110 in the following discussion may refer individually or collectively to the application processor 180 and the image processor 190. Therefore, the steps of any of the following processes may be performed by one or more processing devices.

[0275] In one embodiment, the object identification module 1202 may store instructions (such as computer vision software) that, when executed by the processing unit 110, receive a first output from a first data source associated with the host vehicle and receive a second output from a second data source associated with the host vehicle. At least one of the first data source and the second data source includes a sensor on the host vehicle. For example, the object identification module 1202 may receive a first output from a first sensor on the host vehicle and receive a second output from a second sensor on the host vehicle. Thus, the first data source may include at least one of the following: a camera, a lidar, or a radar on the host vehicle, and the second data source may include at least one of the following that is different from the first data source: a camera, a lidar, or a radar on the host vehicle.

[0276] Alternatively, the object identification module 1202 may receive a first output from a first sensor on the host vehicle and a second output from a map accessed by the processing unit 110. Thus, the first data source may include at least one of: a camera, lidar, or radar on the host vehicle, and the second data source may include map data.

[0277] In one embodiment, object identification module 1202 may store instructions (such as computer vision software) that, when executed by processing unit 110, identify a representation of a target object in the first output. For example, object identification module 1202 may perform all or a portion of process 500B described above to identify a representation of a target object.

[0278] In one example, the object recognition module 1202 can determine a set of candidate objects representing a target object (e.g., a vehicle, a pedestrian, a static object, a lane marking, etc.) by scanning the first output, comparing the first output to one or more predetermined patterns, and identifying possible locations in the first output that may contain objects of interest (e.g., vehicles, pedestrians, static objects, lane markings, etc.). The predetermined pattern can match the type of output from the first sensor. For example, if the first sensor is a camera, the predetermined pattern can be visual, and if the first sensor is a microphone, the predetermined pattern can be auditory. In some embodiments, the predetermined pattern can be configured to achieve a high "false hit" rate and a low "miss" rate. For example, the object recognition module 1202 can use a low similarity threshold for identifying a candidate object as a predetermined pattern of a possible target object so as to reduce the possibility of missing (e.g., not identifying) a candidate object representing a target object.

[0279] The object identification module 1202 can further filter the set of candidate objects based on classification criteria to exclude certain candidates (e.g., irrelevant or less relevant objects). Such criteria can be derived from various attributes associated with object types stored in a database (e.g., a database (not shown) stored in the memory 140 and / or a database accessed from one or more remote servers). The attributes can include object shape, size, texture, location (e.g., relative to the host vehicle), speed (e.g., relative to the host vehicle), etc. Thus, the object identification module 1202 can use one or more sets of criteria to reject pseudo candidates from the set of candidate objects.

[0280] In an embodiment where the first output includes multiple frames over time, the object recognition module 1202 can also analyze multiple frames of the first output to determine whether an object in the set of candidate objects represents a target object. For example, the object recognition module 1202 can track detected candidate objects across consecutive frames and accumulate frame-by-frame data associated with the detected objects (e.g., size, position relative to the host vehicle, speed relative to the host vehicle, etc.). Additionally or alternatively, the object recognition module 1202 can estimate parameters of the detected object and compare the frame-by-frame position data of the object with the predicted position. Although the first output may be an image, the use of "frame" does not mean that the first output must be an image. As used herein, "frame" refers to any discrete measurement sequence across time received from a first sensor, a second sensor, or any other sensor.

[0281] The object identification module 1202 can further construct a set of measurements for the detected object. Such measurements can include, for example, position, velocity, and acceleration values ​​associated with the detected object (e.g., relative to the host vehicle). In some embodiments, the target object module 2004 can construct the measurements based on an estimation technique using a series of time-based observations (such as a Kalman filter or linear quadratic estimation (LQE)) and / or based on modeling data available for different object types (e.g., cars, trucks, pedestrians, bicycles, road signs, etc.). The Kalman filter can be based on a measure of the scale of the object, where the scale measure is proportional to the time to collision (e.g., the amount of time it takes the host vehicle to reach the object).

[0282] In an embodiment where the first output includes multiple frames over time, the object recognition module 1202 can perform an optical flow analysis on one or more images to reduce the likelihood of detecting "false hits" and missing candidate objects representing vehicles or pedestrians. Optical flow analysis can refer to, for example, analyzing motion patterns relative to the vehicle 200, associated with other vehicles and pedestrians, and distinguished from road motion in one or more images. The processing unit 110 can calculate the motion of the candidate object by observing different positions of the object across multiple image frames captured at different times. The processing unit 110 can use the position and time values ​​as input to a mathematical model for calculating the motion of the candidate object. Therefore, optical flow analysis can provide another method for detecting vehicles and pedestrians near the vehicle 200. The processing unit 110 can perform optical flow analysis in conjunction with steps 540 to 546 to provide redundancy in detecting vehicles and pedestrians and improve the reliability of the system 100.

[0283] Additionally or alternatively, the object recognition module 1202 may perform all or part of the above process 500C to identify a representation of a target object. In an embodiment where the object recognition module 1202 is implemented as an additional processing layer of a selected action of a trained system, the object recognition module 1202 may receive an identification of the target object from the trained system. Thus, the object recognition module 1202 may scan the first output, compare the first output with a pattern matching the target object received from the trained system, and identify the location of the target object within the first output. For example, the object recognition module 1202 may receive an identification of another vehicle from the trained network, extract a pattern stored in a database (e.g., a database (not shown) stored in the memory 140 and / or a database accessed from one or more remote servers), the pattern being indexed as a pattern of the vehicle and matching the type of the first output (e.g., visual, auditory, thermal, etc.), and identify the location of the other vehicle in the first output by comparing the first output with the extracted pattern.

[0284] Alternatively, in an embodiment where the object recognition module 1202 is implemented as an additional processing layer of the selected action of the trained system, the object recognition module 1202 may receive the identification of the target object and the location of the target object from the trained system. If the received location is in the first output, the object recognition module 1202 may perform classification (e.g., using the above comparison) at and / or near the received location to identify the target object in the first output. If the received location is in another output (e.g., from another sensor), the object recognition module 1202 may extract a pattern stored in a database (e.g., a database (not shown) stored in the memory 140 and / or a database accessed from one or more remote servers), the pattern being indexed as a pattern of a type of object that matches the target object (e.g., a vehicle, a pedestrian, a static object, etc.) and matching the type of the first output (e.g., visual, auditory, thermal, etc.), and identifying the location of the target object within the first output by comparing the first output with the extracted pattern. In addition, or as an alternative to the comparison, the object identification module 1202 can construct an atlas that includes information that maps locations on the output used by the trained system to locations on the first output. Based on this, the object identification module 1202 can determine the location of the representation of the desired target object in the first output based on the location of the target object in the output used by the trained system, and perform classification (e.g., using the above-mentioned comparison) to identify the location of the target object within the first output.

[0285] In one embodiment, the navigation constraint module 1204 may store software executable by the processing unit 110 to determine whether the characteristics of the target object trigger at least one navigation constraint. The characteristics of the target object may trigger a hard (safety) constraint or a soft (comfort) constraint. For example, the distance of the target object may trigger a hard constraint based on a minimum distance or a maximum distance (e.g., to other vehicles, to pedestrians, to the edge of the road, to lane markings, etc.) and / or trigger a soft constraint based on a preferred distance. In another example, the size of the target object may trigger a hard constraint based on a minimum size or a maximum size (e.g., the height of an obstacle, the height of a gap, etc.) and / or trigger a soft constraint based on a preferred size. In yet another example, the location of the target object may trigger a hard constraint based on a restricted area (e.g., within the current driving lane of the main vehicle, within a specific threshold distance of the planned trajectory of the main vehicle, etc.) and / or trigger a soft constraint based on a preferred area (e.g., on a lane or sidewalk near the current driving lane, within the range of the planned trajectory, etc.).

[0286] In one embodiment, if the characteristics of the target object do not trigger at least one navigation constraint, the verification module 1206 can verify the identification of the representation of the target object based on the combination of the first output and the second output. For example, the combination may include a cross scheme or a collaborative scheme. The cross scheme may include the requirement that the target object is identified in both the first output and the second output for verification. For example, it may be necessary to identify the target object in a radar, a laser radar, or a camera including a first data source and in a radar, a laser radar, or a camera including a second data source for verification. That is, if the target object is detected by multiple data sources, it can be considered that the target object is recognized. The collaborative scheme may include a combination of the first data source and the second data source to verify the target object. For example, the collaborative scheme may involve identifying or recognizing the target object based on combining partial data obtained from multiple data sources. An example of a collaborative scheme may include a camera estimate of the range of the target object, which is measured from a road elevation model (e.g., based on another camera) or from a laser radar. Another example may include detection of the target object using a laser radar and measurement of the target object using a road elevation model based on optical flow from one or more cameras. Yet another example may include lane detection using a camera (e.g., where the target object includes a road edge or lane marking), and then confirming the detection using map data. Yet another example may include target object detection using one or more cameras, and using lidar to determine free space in the host vehicle environment.

[0287] On the other hand, if the characteristics of the target object trigger at least one navigation constraint, the verification module 1206 can verify the recognition of the representation of the target object based on the first output.For example, a unified approach can be used so that only the first output is used to recognize or verify the target object.

[0288] The navigation change module 1208 can use the output of the object recognition module 1202 and / or the verification module 1206 to implement a decision tree for navigation adjustments. The navigation adjustment can be based on data derived from the first sensor, the second sensor, any other sensor, map data, and one or more objects detected from the first output, the second output, and any other output. The navigation change module 1208 can also determine the desired navigation response based on inputs from other systems of the vehicle 200, such as the throttle adjustment system 220, the braking system 230, and the steering system 240 of the vehicle 200. Additionally or alternatively, as described above, the navigation change module 1208 can receive one or more navigation adjustments from other memory modules (not shown) and / or from a trained system. Therefore, the navigation change module 1208 can be implemented as an additional processing layer for the selected action of the trained system.

[0289] Thus, the navigation change module 1208 can cause at least one navigation change of the host vehicle in response to the verification. To cause the at least one navigation change, the navigation change module 1208 can transmit electronic signals to the throttle adjustment system 220, the braking system 230, and the steering system 240 of the vehicle 200 to trigger the desired navigation response, such as by turning the steering wheel of the vehicle 200 to achieve a predetermined angle of rotation. In some embodiments, the at least one navigation change can include any of the aforementioned adjustments to one or more navigation actuators of the host vehicle in response to the verification.

[0290] Furthermore, any module disclosed herein (e.g., modules 1202, 1204, 1206, and 1208) may implement techniques associated with a trained system (such as a neural network or a deep neural network) or an untrained system. Additionally or alternatively, any module disclosed herein (e.g., modules 1202, 1204, 1206, and 1208) may implement techniques as an additional processing layer for selected actions of a trained system.

[0291] Fig.13A and 13B Provides a schematic diagram of example safety and comfort constraints. Fig.13A As shown, the main vehicle 1300 can detect other vehicles in front of the main vehicle 1300 (such as vehicle 1301), other vehicles behind the main vehicle 1300 (such as vehicle 1303), and other vehicles in lanes other than the lane in which the main vehicle 1300 is traveling (e.g., vehicle 1307) as target objects.

[0292] Such characteristics of detected objects may trigger navigation constraints. For example, distance 1309 between host vehicle 1300 and another vehicle 1301, distance 1311 between host vehicle 1300 and another vehicle 1307, and / or distance 1313 between host vehicle 1300 and another vehicle 1303 may trigger navigation constraints. Fig.13A and 13B , but other characteristics associated with one or more of vehicles 1301, 1303, and 1305 may include a relative speed between the host vehicle 1300 and one or more of vehicles 1301, 1303, and 1305, a collision time with one or more of vehicles 1301, 1303, and 1305, etc.

[0293] In the above example, the triggered navigation constraint can be associated with a distance to one or more of vehicles 1301, 1303, and 1305 (such as a minimum distance), a relative speed between the host vehicle 1300 and one or more of vehicles 1301, 1303, and 1305 (such as a maximum relative speed, e.g., close to zero), a collision time with one or more of vehicles 1301, 1303, and 1305 (such as a minimum collision time, e.g., close to infinity), etc. Thus, a characteristic can trigger a hard (or safety) constraint. Alternatively, a characteristic may not trigger a navigation constraint. For example, one or more soft constraints (or "expectations") may be associated with a characteristic.

[0294] Fig. 13C and 13D Schematic diagrams of other example safety and comfort constraints consistent with the disclosed embodiments are provided. Fig. 13C and 13D As shown, host vehicle 1300 may detect static object 1315 on the road on which host vehicle 1300 is traveling as a target object. Additionally or alternatively, host vehicle 1300 may detect lane markings as target objects.

[0295] exist Fig. 13C and 13D In the example of FIG. 1 , the distance 1317 between the host vehicle 1300 and the static object 1315 may be a characteristic that triggers the navigation constraint. Additionally or alternatively, the distance 1319 between the host vehicle 1300 and the lane marking may be a characteristic that triggers the navigation constraint. Fig. 13C and 13D , but other characteristics associated with static object 1315 or lane marking may include a relative speed between host vehicle 1300 and static object 1315 or lane marking, a collision time with static object 1315 or lane marking, etc.

[0296] In the above examples, the navigation constraint can be associated with a distance to a static object 1315 or lane marking (such as a minimum distance), a relative speed between the host vehicle 1300 and the static object 1315 or lane marking (such as a maximum relative speed, e.g., close to zero), a collision time with the static object 1315 or lane marking (such as a minimum collision time, e.g., close to infinity), etc. Thus, a characteristic can trigger a hard (or safety) constraint. Alternatively, a characteristic may not trigger a navigation constraint. For example, one or more soft constraints (or "expectations") can be associated with a characteristic.

[0297] Fig.14A flow chart representing an example process 1400 for navigating a host vehicle based on safety and comfort constraints consistent with the disclosed embodiments is provided. Process 1400 may be performed by at least one processing device, such as processing device 110.

[0298] At step 1402, the processing device 110 may receive a first output from a first data source associated with a host vehicle. For example, as explained above with respect to the object recognition module 1202, the first data source may include at least one of the following: a camera, a lidar, or a radar on the host vehicle.

[0299] At step 1404, the processing device 110 may receive a second output from a second data source associated with the host vehicle. For example, as explained above with respect to the object identification module 1202, the second data source may include map data accessed by at least one processing device.

[0300] Then, in some embodiments, at least one of the first data source and the second data source includes a sensor on the host vehicle. In some embodiments, both the first data source and the second data source may include sensors. For example, the first data source and the second data source may include different cameras, the first data source may include a camera and the second data source may include a radar, the first data source may include a camera and the second data source may include a lidar, etc. In other embodiments, the other of the first data source and the second data source may include another data source, such as map data.

[0301] At step 1406 , the processing device 110 may identify a representation of the target object in the first output. For example, the processing device 110 may identify the target object as described above with respect to the object identification module 1202 .

[0302] At step 1408, the processing device 110 may determine whether a characteristic of the target object triggers at least one navigation constraint. For example, as explained above with respect to the navigation constraint module 1204, the characteristic may include the size of the target object, the distance from the host vehicle to the target object, or the location of the target object in the host vehicle environment.

[0303] At step 1410a, as explained above with respect to verification module 1206, if the characteristic of the target object does not trigger at least one navigation constraint, processing device 110 may verify recognition of the representation of the target object based on a combination of the first output and the second output.

[0304] In some embodiments, verifying the identification of the representation of the target object based on the combination of the first output and the second output may include determining whether the representation of the target object is identified in both the first output and the second output. For example, as explained above with respect to the verification module 1206, the combination may include a crossover scheme.

[0305] Additionally or alternatively, verifying the recognition of the representation of the target object based on the combination of the first output and the second output may include: using the second output projected onto the first output to determine the characteristics of the target object. For example, as explained above with respect to the verification module 1206, the combination may include a collaborative scheme. In one example, if the second output includes map data and the first output includes at least one image of the host vehicle environment, the projection may include using the map data to detect one or more road edges in the at least one image. In another example, if the second output includes output from a lidar and the first output includes at least one image of the host vehicle environment, the projection may include using the second output to detect free space in the at least one image.

[0306] At step 1410b, the processing device 110 may verify the identification of the representation of the target object based on the first output if the characteristic of the target object triggers at least one navigation constraint, as explained above with respect to the verification module 1206.

[0307] In response to the verification, the processing device 110 may cause at least one navigation change of the host vehicle at step 1412. For example, as explained above with respect to the navigation change module 1208, the at least one navigation change may include slowing down the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle.

[0308] Method 1400 may further include additional steps. For example, method 1400 may include determining at least one navigation change based on whether at least one navigation constraint is triggered. For example, as explained above with respect to navigation change module 1208, if at least one navigation constraint is triggered, at least one navigation change may include a first change, and if at least one navigation constraint is not triggered, at least one navigation change may include a different second change. In such an embodiment, the second change may include a narrower steering mechanism adjustment angle, a lighter braking mechanism application, a lighter acceleration, etc., compared to the first change.

[0309] Batch alignment for navigation

[0310] As mentioned above, a remote server can crowdsource sparse maps from multiple vehicles. However, global alignment of multiple drives leads to error accumulation in the sparse map. For example, ego-motion drift in a drive may distort the geometry of the road and may be exaggerated during global aggregation. In addition, performing global alignment using GPS data is often inaccurate due to errors in GPS measurements.

[0311] Thus, (one or more) remote servers may locally align a batch of driving to develop a roadmap, rather than globally aligning driving to develop a sparse map. As used herein, the term "roadmap" may refer to a sparse map (as described above) or other representations of location data (e.g., stored as one or more splines) and / or landmark data stored in coordinates local to a road segment rather than in global coordinates (e.g., stored as the location of a landmark and / or descriptive data related to the appearance, identification, etc. of the landmark). Alignment of such data may result in more reliable alignments and smaller, more local maps. In addition, local roadmaps may be extrapolated to global coordinates with higher accuracy than aligning driving in global coordinates without first performing local alignment. For example, ego drift may be dealt with during local alignment, so if the local roadmap is extrapolated to global coordinates, the ego drift will not be propagated. In addition, local alignment may be performed using visual cues (such as lane markings), which may be more accurately located than GPS data including inherent errors and drift.

[0312] Furthermore, global alignment may not cope with motion shadows, varying lighting, reflections due to rain, and other variations in images and data from multiple drives due to different times and dates when the drives were performed. Therefore, batch alignment of drives performed on the same date, similar times, and / or during similar weather conditions further improves the accuracy of the roadmap.

[0313] Fig.15 1 is an exemplary functional block diagram of memory 140 and / or 150, which may be stored / programmed with instructions for performing one or more operations consistent with the embodiments of the present disclosure. Although the following refers to memory 140, those skilled in the art will recognize that instructions may be stored in memory 140 and / or 150.

[0314] like Fig.15 As shown, the memory 140 may store a navigation information receiving module 1502, an alignment module 1504, a storage module 1506, and an allocation module 1508. The disclosed embodiments are not limited to any particular configuration of the memory 140. In addition, the application processor 180 and / or the image processor 190 may execute instructions stored in any of the modules 1502, 1504, 1506, and 1508 included in the memory 140. Those skilled in the art will appreciate that references to the processing unit 110 in the following discussion may refer to the application processor 180 and the image processor 190 individually or collectively. Alternatively, at least one processing device of a server remote from the host vehicle may execute instructions stored in any of the modules 1502, 1504, 1506, and 1508 included in the memory 140. Therefore, the steps of any of the following processes may be performed by one or more processing devices.

[0315] In one embodiment, the navigation information receiving module 1502 may store instructions (such as computer vision software) that, when executed by the processing unit 110, receive navigation information from multiple vehicles. For example, the navigation information from the multiple vehicles may be associated with a common road segment. The navigation information may be received over one or more computer networks. For example, multiple vehicles may upload information during a drive, or multiple vehicles may upload information after completing a drive (e.g., in an upload session that is hourly, daily, weekly, etc.).

[0316] In some embodiments, the navigation information may include one or more images captured by one or more image sensors of the vehicle during driving. Additionally or alternatively, the navigation information may include processed information from the images, such as location and / or descriptive information about one or more landmarks identified in the images. The navigation information may additionally or alternatively include location information of the vehicle, such as GPS data, etc.

[0317] In one embodiment, the alignment module 1504 may store instructions (such as computer vision software) that, when executed by the processing unit 110, align the navigation information within a coordinate system local to the common road segment. For example, the navigation information may be aligned using landmarks identified in an image from an image sensor of the vehicle. In a simple scheme, the alignment may include averaging the locations of the landmarks detected in the image. In a more complex scheme, the alignment may include linear regression or other statistical techniques to converge the locations of the landmarks detected in the image. By using the image, the alignment module 1504 may, for example, align the navigation information in a local coordinate system based on GPS data rather than a global coordinate system. In practice, the alignment module 1504 may adjust the GPS data included in the navigation information based on the alignment of the landmarks, rather than adjusting the landmarks based on the alignment of the GPS data.

[0318] In one embodiment, the storage module 1506 may store instructions (such as computer vision software) that, when executed by the processing unit 110, store the aligned navigation information in association with the common road segment. For example, the navigation information may be stored in a database such that an identifier of the common road segment is stored with the aligned navigation information and used for indexing. The identifier of the common road segment may include one or more coordinates for describing the common road segment (e.g., global coordinates of a start point of the common road segment and / or an end point of the common road segment).

[0319] In one embodiment, distribution module 1508 may store instructions (such as computer vision software) that, when executed by processing unit 110, distributes the aligned navigation information to one or more autonomous vehicles for autonomous navigation of the one or more autonomous vehicles along a common road segment. For example, one or more vehicles may request navigation information when the vehicles approach or otherwise anticipate traversing a common road segment. Distribution module 1508 may transmit the aligned navigation information to the requesting vehicles via one or more computer networks.

[0320] Fig.16 Example roadmaps 1620 and 1640 generated by combining navigation information from many drives and an example global map 1650 generated by combining roadmaps are shown consistent with the disclosed embodiments. Fig.16 As shown, a first set of driving 1610 may include location data (e.g., 6PS data) received from five separate drivings along a common road segment. A driving may be separated from another driving if it is traversed by separate vehicles at the same time, traversed by the same vehicle at separate times, or traversed by separate vehicles at separate times. The remote server may generate a roadmap 1620 using one or more statistical techniques to align the location data along the road segment. For example, the remote server may determine whether the changes in the location data represent actual differences or statistical errors, and may align the location data using a coordinate system determined by images captured during the driving. Therefore, the alignment will be local to the road segment and will be self-consistent, rather than consistent with an external coordinate system (such as a global coordinate system).

[0321] Similarly, a second set of drives 1630 may include location data (e.g., GPS data) received from five additional drives along a common road segment. The remote server may generate a roadmap 1640 using one or more statistical techniques to align the location data along the road segment. For example, the remote server may determine whether the changes in the location data represent actual differences or statistical errors, and may align the location data using a coordinate system determined by images captured during the drive. Thus, the alignment will be local to the road segment and will be self-consistent, rather than consistent with an external coordinate system (such as a global coordinate system).

[0322] First set of drives 1610 and second set of drives 1630 may be clustered by a remote server, for example, based on the time of day the drives were performed, the date the drives were performed, one or more weather conditions during the drives, etc. Thus, route map 1620 and route map 1640 may have improved accuracy compared to conventional techniques in which drives from different times of day, from different dates, and / or from different weather conditions are aligned with each other.

[0323] like Fig.16 As further shown, the route map 1620 and the route map 1640 can be extrapolated to a global coordinate system and aligned as part of the global map 1650. For example, the remote server can again use one or more statistical techniques to align the location data along the road segment. The remote server can use GPS data or other data in a global coordinate system, rather than images captured during the drive, to ensure that the alignment of the route map 1620 and the route map 1640 is performed in a global coordinate system rather than a local coordinate system. Because the route map 1620 and the route map 1640 provide more accurate input than a single drive, the global map 1650 has a higher accuracy than if the first set of drives 1610 and the second set of drives 1630 had been aligned directly on the global coordinate system.

[0324] Although depicted using driving data, roadmaps 1620 and 1640 (and global map 1650) may further include one or more landmarks associated with the road segment and present in the image. For example, the landmarks may be aligned when forming roadmaps 1620 and 1640 (or even the landmarks may be used to align the driving data forming roadmaps 1620 and 1640). Similarly, the landmarks may be aligned when forming global map 1650 (or even the landmarks may be used to globally align roadmaps 1620 and 1640).

[0325] Fig.17 A flow chart representing an example process 1700 for aligning navigation information from multiple vehicles consistent with the disclosed embodiments is provided. Process 1700 may be performed by at least one processing device, such as processing device 110. Alternatively, process 1700 may be performed by at least one processing device at a server remote from the host vehicle.

[0326] At step 1710, the server may receive navigation information from the plurality of vehicles. For example, the navigation information from the plurality of vehicles may be associated with a common road segment. In some embodiments, as explained above with respect to the navigation information receiving module 1502, the navigation information may include global positioning system (GPS) information and / or one or more landmarks included in an image captured by an image sensor included on the plurality of vehicles. For example, the one or more landmarks may include visible objects along the common road segment. In such embodiments, the objects may include at least one of a road marking and a road sign.

[0327] In some embodiments, navigation information may be received over a computer network (e.g., cellular, Internet, etc.) using radio frequencies, infrared frequencies, magnetic fields, electric fields, etc. The navigation information may be transmitted using any known standard for sending and / or receiving data (e.g., Wi-Fi, Bluetooth Smart, 802.15.4, ZigBee, etc.).

[0328] At step 1720, the server may align the navigation information within a coordinate system local to the common road segment, as explained above with respect to the alignment module 1504. For example, the local coordinate system may include a coordinate system based on a plurality of images captured by image sensors included on a plurality of vehicles.

[0329] In some embodiments, the alignment of navigation information can be based on one or more landmarks. For example, as described above, the server can adjust the GPS data included in the navigation information based on the alignment of the landmarks, rather than adjusting the landmarks based on the alignment of the GPS data.

[0330] At step 1730, the server may store the aligned navigation information in association with the common road segment as explained above with respect to storage module 1506. For example, the navigation information may be stored in a database such that an identifier of the common road segment is stored with the aligned navigation information and used to index the aligned navigation information.

[0331] At step 1740, as explained above with respect to distribution module 1508, the server may distribute the aligned navigation information to one or more autonomous vehicles for autonomous navigation of the one or more autonomous vehicles along the common road segment. For example, one or more vehicles may request navigation information, and the server may respond to the request(s) and transmit the aligned navigation information over a computer network (e.g., cellular, Internet, etc.) using radio frequencies, infrared frequencies, magnetic fields, electric fields, etc. The aligned navigation information may be transmitted using any known standard for sending and / or receiving data (e.g., Wi-Fi, Bluetooth Smart, 802.15.4, ZigBee, etc.).

[0332] The method 1700 may further include additional steps. For example, in some embodiments, a plurality of vehicles may have captured navigation information during a particular time period. In such embodiments, the method 1700 may further include: receiving additional navigation information from a second plurality of vehicles, the additional navigation information from the second plurality of vehicles being captured during a second time period and associated with the common road segment, and aligning the additional navigation information within a coordinate system local to the common road segment, the local coordinate system being a coordinate system based on a plurality of images captured by image sensors included on the second plurality of vehicles, and storing the aligned additional navigation information in association with the common road segment.

[0333] Additionally or alternatively, the plurality of vehicles may have captured navigation information on a plurality of drives, the number of drives not exceeding a threshold number of drives. In such an embodiment, the method 1700 may further include: receiving additional navigation information from a second plurality of vehicles, the additional navigation information from the second plurality of vehicles being captured on additional drives and associated with the common road segment, and aligning the additional navigation information within a coordinate system local to the common road segment, the local coordinate system being a coordinate system based on a plurality of images captured by image sensors included on the second plurality of vehicles, and storing the aligned additional navigation information in association with the common road segment.

[0334] In any of the above embodiments, the method 1700 may further include extrapolating the aligned navigation information to a set of global coordinates and storing the globally aligned navigation information in association with the common road segment. Additionally, in embodiments that include additional navigation information, the method 1700 may further include extrapolating the aligned navigation information and the aligned additional navigation information to a set of global coordinates and storing the globally aligned navigation information and the additional navigation information in association with the common road segment.

[0335] The foregoing description has been presented for purposes of illustration. It is not exhaustive and is not limited to the precise forms or embodiments disclosed. Modifications and adaptations will be apparent to those skilled in the art in view of the specification and practice of the disclosed embodiments. Furthermore, while various aspects of the disclosed embodiments are described as being stored in a memory, those skilled in the art will appreciate that these aspects may also be stored on other types of computer-readable media, such as secondary storage devices, e.g., a hard disk or CD ROM, or other forms of RAM or ROM, USB media, DVD, Blu-ray, 4K Ultra HD Blu-ray, or other optical drive media.

[0336] Computer programs based on the written description and disclosed methods are within the skill of experienced developers. Various programs or program modules may be created using any technology known to those skilled in the art or may be designed in conjunction with existing software. For example, program parts or program modules may be designed in or by .Net Framework, .Net Compact Framework (and related languages, such as Visual Basic, C, etc.), Java, C++, Objective-C, HTML, HTML / AJAX combinations, XML, or HTML including Java applets.

[0337] In addition, although illustrative embodiments have been described herein, those skilled in the art will recognize the scope of any and all embodiments with equivalent elements, modifications, omissions, combinations (e.g., throughout aspects of the various embodiments), adaptations and / or changes based on this disclosure. The limitations in the claims will be interpreted broadly based on the language adopted in the claims and are not limited to the examples described in this specification or during the examination of this application. The examples will be interpreted as non-exclusive. In addition, the steps of the disclosed method may be modified in any way, including by reordering steps and / or inserting or deleting steps. Therefore, it is intended that the description and examples be regarded as illustrative only, and the true scope and spirit are represented by the full scope of the following claims and their equivalents.

Claims

1. A device for a host vehicle, the device comprising: At least one processing device programmed to: receiving a first output from a first data source associated with the host vehicle and receiving a second output from a second data source associated with the host vehicle, wherein at least one of the first data source and the second data source comprises a sensor on the host vehicle; identifying a target object in the first output; determining whether a characteristic of the target object triggers at least one navigation constraint; If the characteristic of the target object triggers the at least one navigation constraint, verifying identification of the target object based on the first output; as well as If the characteristic of the target object does not trigger the at least one navigation constraint, verifying identification of the target object based on a combination of the first output and the second output; as well as responsive to the verifying, causing at least one navigation change to the host vehicle, wherein the at least one navigation constraint comprises at least one safety constraint, and Wherein the at least one navigation change comprises at least one of: decelerating the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle.

2. The apparatus of claim 1, wherein the first data source comprises at least one of: a camera, a lidar, or a radar on the host vehicle. 3 . The apparatus of claim 1 , wherein the second data source comprises map data accessed by the at least one processing device.

4. The apparatus of claim 1 , wherein verifying identification of the target object based on a combination of the first output and the second output comprises: A determination is made as to whether the target object is identified in both the first output and the second output.

5. The apparatus of claim 1 , wherein verifying identification of the target object based on a combination of the first output and the second output comprises: The second output projected onto the first output is used to determine a characteristic of the target object.

6. The apparatus of claim 5, wherein the second output comprises map data, the first output comprises at least one image of an environment of the host vehicle, and the projecting comprises using the map data to detect one or more road edges in the at least one image.

7. The apparatus of claim 5, wherein the second output comprises an output from a lidar, the first output comprises at least one image of an environment of the host vehicle, and the projecting comprises using the second output to detect free space in the at least one image. 8 . The apparatus of claim 1 , wherein the characteristic of the target object comprises at least one of: a size of the target object, a distance from the host vehicle to the target object, or a location of the target object in an environment of the host vehicle.

9. The apparatus of claim 1, wherein the target object can be identified by confirming that a potential target object is the target object using a threshold or confidence level of similarity.

10. A computer-implemented method for a host vehicle, the method comprising: receiving a first output from a first data source associated with the host vehicle and receiving a second output from a second data source associated with the host vehicle, wherein at least one of the first data source and the second data source comprises a sensor on the host vehicle; identifying a target object in the first output; determining whether a characteristic of the target object triggers at least one navigation constraint; If the characteristic of the target object triggers the at least one navigation constraint, verifying identification of the target object based on the first output; as well as If the characteristic of the target object does not trigger the at least one navigation constraint, verifying identification of the target object based on a combination of the first output and the second output; as well as responsive to the verifying, causing at least one navigation change to the host vehicle, wherein the at least one navigation constraint comprises at least one safety constraint, and Wherein the at least one navigation change comprises at least one of: decelerating the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle.

11. The method of claim 10, wherein the first data source comprises at least one of: a camera, a lidar, or a radar on the host vehicle. 12 . The method of claim 10 , wherein the second data source includes map data accessed by the host vehicle.

13. The method of any one of claims 10 to 12, wherein verifying the identification of the target object based on a combination of the first output and the second output comprises: A determination is made as to whether the target object is identified in both the first output and the second output.

14. The method of any one of claims 10 to 12, wherein verifying the identification of the target object based on a combination of the first output and the second output comprises: The second output projected onto the first output is used to determine a characteristic of the target object.

15. A non-transitory computer readable medium storing instructions that, when executed by at least one processing device of a host vehicle, cause the at least one processing device to: receiving a first output from a first data source associated with a host vehicle and receiving a second output from a second data source associated with the host vehicle, wherein at least one of the first data source and the second data source comprises a sensor on the host vehicle; identifying a target object in the first output; determining whether a characteristic of the target object triggers at least one navigation constraint; If the characteristic of the target object triggers the at least one navigation constraint, verifying identification of the target object based on the first output; If the characteristic of the target object does not trigger the at least one navigation constraint, verifying identification of the target object based on a combination of the first output and the second output; as well as responsive to the verifying, causing at least one navigation change to the host vehicle, wherein the at least one navigation constraint comprises at least one safety constraint, and Wherein the at least one navigation change comprises at least one of: decelerating the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle.

16. The computer-readable medium of claim 15, wherein the first data source comprises at least one of: a camera, a lidar, or a radar on the host vehicle.

17. The computer-readable medium of claim 15, wherein the second data source comprises map data accessed by the at least one processing device.

18. The computer-readable medium of any one of claims 15-17, wherein verifying identification of the target object based on a combination of the first output and the second output comprises: determining whether the target object is identified in both the first output and the second output; Alternatively, the second output projected onto the first output is used to determine a characteristic of the target object.

19. An apparatus for a host vehicle, the apparatus comprising: at least one processor component comprising an input component, an identification component, a determination component, a verification component, and an output component, the processor component being programmed to: causing the input component to receive a first output from a first data source associated with the host vehicle and a second output from a second data source associated with the host vehicle, wherein at least one of the first data source and the second data source comprises a sensor on the host vehicle; causing the recognition component to recognize a target object in the first output; causing the determining component to determine whether a characteristic of the target object triggers at least one navigation constraint; If the characteristic of the target object triggers the at least one navigation constraint, causing the verification component to verify the identification of the target object based on the first output; If the characteristic of the target object does not trigger the at least one navigation constraint, causing the verification component to verify identification of the target object based on a combination of the first output and the second output; as well as responsive to the verifying, causing the output component to output a signal initiating at least one navigation change to the host vehicle, wherein the at least one navigation constraint comprises at least one safety constraint, and Wherein the at least one navigation change comprises at least one of: decelerating the host vehicle, accelerating the host vehicle, or activating a steering mechanism of the host vehicle.

20. The apparatus of claim 19, wherein the first data source comprises at least one of: a camera, a lidar, or a radar on the host vehicle.

21. The apparatus of claim 19, wherein the second data source includes map data accessed by the host vehicle.

Images