• 专利附录
  • 专利说明
  • 权利要求
  • 类似技术
  • 同族专利
  • 引用文献
  • 法律状态
  • 优先权
    • 专利摘要:
    A device and method for autonomous vehicle routing based on chaos assessment. A plurality of route options (420, 422, 424, 426) based on destination goal data (224) relative to current autonomous vehicle position data are generated. For each of the plurality of route options, an associated chaos level (W1, W3, W4, W5) may be evaluated, and an autonomous co-operation metric may be generated based on the associated chaos level. The autonomous selection of a route option of the plurality of route options is based on a favorable autonomous cooperative metrics, and autonomous mission description data (220) is generated based on the route option which includes the favorable autonomous co-operation metric. The autonomous mission description data may be transmitted to autonomously commit to a destination that is defined by the destination goal data (224).
    公开号:FR3070066A1
    申请号:FR1857487
    申请日:2018-08-14
    公开日:2019-02-15
    发明作者:Nathan C. Westover；Benjamin M. Geller；Justin J. Chow
    申请人:Toyota Motor Engineering and Manufacturing North America Inc；Toyota Engineering and Manufacturing North America Inc；
    IPC主号:
    专利说明:

    FIELD [0001] The object described in this presentation generally relates to destination routing devices and, more particularly, the routing of autonomous vehicles based on an assessment of chaos of several route options.
    BACKGROUND [0002] Vehicle navigation systems have generally been used to provide a vehicle user with driving directions to a selected destination. Such navigation includes basic directional instructions, such as turning left or right at an intersection and announcements of approaching the destination. Navigation systems have improved to provide route options for the driver, such as avoiding toll highways, historically high collision areas, shortest journey times, etc. Subsequent developments have implemented crowd-source data based on cellular devices of vehicle users, in conjunction with on-board location devices, to further relay traffic congestion. traffic, traffic collisions, work in progress, and the like. With the advent of autonomous vehicles, route options have simply relied on basic routing for the autonomous vehicle to arrive at a destination. However, such roads present associated chaos scenarios with which an autonomous vehicle may not be able to cooperate - that is, the artificial intelligence engine of the autonomous vehicle may not be able to compensate or overcome chaos and being able to accomplish the destination mission.
    SUMMARY A device and method for autonomous vehicle routing based on the assessment of routing chaos are described.
    In one implementation, a method for the routing of an autonomous vehicle is described. The method includes generating a plurality of route options based on destination goal data relative to current autonomous vehicle position data. For each of the plurality of route options, an associated level of chaos can be evaluated, and an autonomous cooperability metric generated on the basis of the associated level of chaos. The method provides autonomous selection of a route option from the plurality of route options which includes favorable autonomous cooperability metrics and generation of autonomous mission description data based on the route option which includes the favorable autonomous cooperability metric. The autonomous mission description data can be transmitted to engage autonomously to a destination which is defined by the destination objective data.
    [0005] Optionally, the favorable autonomous cooperability metric falls within the limits of the autonomous cooperability metric threshold.
    [0006] Optionally, the favorable autonomous cooperability metric also enters a travel time parameter.
    Optionally, the favorable autonomous cooperability metric is also included in the respective options of the plurality of route options.
    Optionally, which generation of the plurality of route options further includes classifying the plurality of route options based on a first criterion and a second criterion.
    [0009] Optionally, the first criterion includes a journey distance parameter and the second criterion includes a journey time parameter.
    Optionally, the first criterion and the second criterion are provided as a user preference.
    [00011] Optionally, the associated level of chaos is based on road condition data including at least one of: map layer data; data obtained by participatory production in near real time; near real-time vehicle metric data; and data obtained by participatory production.
    In another implementation, a method for the routing of an autonomous vehicle is described. The method includes: generating a plurality of route options based on destination objective data relative to autonomous vehicle position data; analyzing each of the plurality of route options to form a section data set; for each of the plurality of route options: evaluating an associated level of chaos for each of the section data set; weighting the associated chaos level for each of the section dataset which includes a high chaos level to produce a plurality of weighted chaos levels corresponding to each of the section data set; generating a route chaos level for the section data set based on the weighted chaos level of each of the section data set; and generating an autonomous cooperability metric for the section dataset based on the weighted level of chaos; the autonomous selection of a route option from the plurality of route options which includes a favorable autonomous cooperability metric; generating autonomous mission description data on the basis of the route option which includes the favorable autonomous cooperability metric; and transmitting the autonomous mission description data to engage autonomously to a destination defined by the destination objective data.
    [00013] Optionally, the favorable autonomous cooperability metric falls within the limits of the autonomous cooperability metric threshold.
    [00014] Optionally, the favorable autonomous cooperability metric also comes within a travel time parameter.
    Optionally, the favorable autonomous cooperability metric is also included in the respective options of the plurality of route options.
    Optionally, which generation of the plurality of route options further includes ranking the plurality of route options based on a first criterion and a second criterion.
    [00017] Optionally, the first criterion includes a travel distance parameter and the second criterion includes a travel time parameter.
    Optionally, the first criterion and the second criterion are provided as a user preference.
    Optionally, the associated level of chaos is based on road condition data including at least one of: map layer data; data obtained by participatory production in near real time; near real-time vehicle metric data; and data obtained by participatory production.
    In another implementation, a vehicle control unit is described. The vehicle control unit includes a wireless communication interface, a processor, and a memory. The wireless communication interface operates to service communication with a vehicle network. The processor is communicatively coupled to the wireless communication interface, and the memory is communicatively coupled to the processor and stores a route generation module and an autonomous mission description module. The route generation module includes instructions which, when executed by the processor, cause the processor to generate a plurality of route options based on the destination objective data relative to current position data of autonomous vehicle. For each of the plurality of route options, the instructions cause the processor to evaluate an associated level of chaos and generate an autonomous cooperability metric based on the associated level of chaos to produce an evaluated route option. The autonomous mission description module includes instructions which, when executed by the processor, cause the processor to receive the route option evaluated for each of the plurality of route options and independently select the option of the evaluated route of each of the plurality of route options which includes a favorable autonomous cooperability metric for producing a selected route option. The instructions cause the processor to generate autonomous mission description data based on the route option selected for the transmission to autonomously engage with a destination which is defined by the destination objective data.
    Optionally, the autonomous cooperability metric falls within the limits of an autonomous cooperability metric threshold.
    Optionally, the selected route option also enters a travel time parameter.
    Optionally, the associated level of chaos being based on road condition data including at least one of: map layer data; data obtained by participatory production in near real time; near real-time vehicle metric data; and historical data obtained by participatory production.
    BRIEF DESCRIPTION OF THE DRAWINGS The description refers to the accompanying drawings in which the same reference numbers refer to the same parts through the various views, and in which:
    Figure 1 is a schematic illustration of a vehicle including a vehicle control unit in the context of a vehicle environment;
    Figure 2 illustrates a block diagram of the vehicle control unit of Figure 1;
    Figure 3 illustrates a functional block diagram of the vehicle control unit of Figure 1 for providing autonomous vehicle routing;
    FIG. 4 illustrates an example of a graphical user interface representing the underlying data and the associated chaos levels for a plurality of route options superimposed with a cartographic representation;
    FIG. 5 illustrates an example of a graphical user interface representing the selected route option of the route options of FIG. 4; and [0030] FIG. 6 shows an example of a process for the routing of an autonomous vehicle based on the assessment of chaos.
    DETAILED DESCRIPTION Autonomous vehicle routing techniques based on the assessment of chaos are provided in this presentation. For example, multiple route options can be generated based on a destination and current position data of an autonomous vehicle. Vehicle operators can then select a route option for navigation to the destination. Such a selection can be based on subjective vehicle operator criteria or user preferences, such as opting for tourist country roads rather than interstate freeways, avoiding roads toll, etc. Although a vehicle operator can provide similar selection preferences in an autonomous vehicle route selection, autonomous vehicles base their route selection on respective chaos levels of each route option, and autonomous cooperability metrics. In other words, the autonomous vehicle can consider its ability to engage in the selected route option and achieve the mission objective (i.e., the destination) in view of an assessed level of chaos of the selected route option. By doing so, an autonomous vehicle can make intelligent route selections that avoid roads with excessive levels of chaos that may exceed the capabilities of the vehicle's autonomous system.
    Figure 1 is a schematic illustration of a vehicle 100 including a vehicle control unit 110, in the context of a vehicle environment 116. Even if the vehicle control unit 110 can be shown in In addition to other vehicle components, the vehicle control unit 110 may be combined with other system components of the vehicle 100. In addition, the vehicle 100 may also be an automobile or any other vehicle with or without passenger such as, for example, a land, water, and / or air vehicle. In some cases, the vehicle 100 may also be a space vehicle, relating to a vehicle environment 116 having space waste, other vehicles and / or space debris.
    A plurality of sensor devices 102 are in communication with the control unit 110. The plurality of sensor devices 102 can be positioned on the exterior surface of the vehicle 100 or can be positioned concealed for aesthetic purposes as regards relates to vehicle 100. In addition, the sensors can operate at frequencies at which the vehicle body or parts thereof appear transparent to the respective sensor device.
    The communication between the sensor devices 102 can be done on a bus base and can also be used or exploited by other systems of the vehicle 100. For example, the sensor input devices 102 can be coupled by a combination of network architectures such as a BEAN network (for “Body Electronic Area Network” in English), a CAN bus configuration (for “Controller Area Network” in English), an AVC-LAN configuration (for “Audio Visual Communication” -Local Area Network (in English), automotive Ethernet LAN configuration and / or automotive wireless LAN configuration, and / or other combinations of additional communication system architectures to provide communications between devices and systems vehicle 100.
    The sensor devices 102 can operate to monitor local conditions relating to the vehicle 100, including audio, visual, and tactile changes in the vehicle environment 116. The sensor devices 102 can include sensor input devices, audio sensor devices, video sensor devices, and / or combinations thereof.
    The sensor devices 102 can provide tactile or relational changes in the ambient conditions of the vehicle, such as a person, an object, a vehicle (s), etc. One or more of the sensor input devices can be configured to capture changes in speed, acceleration, and / or distance from these objects under the ambient conditions of the vehicle 100, as well as the approach angle for the vehicle 100.
    The sensor devices 102 can be provided by a lidar system (LIDAR for “Light Detection and Ranging” in English), 5 in which the sensor input devices can capture data related to laser light returns from physical objects in the environment of the vehicle 100. Since light travels at a constant speed, the lidar can be used to determine a distance between a sensor input device and another object with a high degree of accuracy. In addition, measurements take into account the displacement of a sensor input device (such as height, location and orientation of the sensor). In addition, a GPS location can be associated with each of the sensor input devices to determine a sensor displacement. The sensor input devices may also include a combination of laser devices (lidar) and millimeter wave radar devices.
    The audio sensor devices can provide audio detection of the ambient conditions of the vehicle. With a speech recognition capability, the audio sensor devices may also be given instructions to move the vehicle 100, or to receive other such directions relating to the vehicle 100. The audio sensor devices may be provided, for example. , by an omnidirectional digital microphone of audio sensor with nano-electromechanical system (NEMS for “Nano-Electromechanical Systems” 25 or micro-electromechanical system (MEMS for “MicroElectromechanical Systems”), a digital microphone triggered by sound , etc.
    Video sensor devices include associated fields of vision. In autonomous operation, the video sensor devices 30 can provide a visual blind spot detection (as for another vehicle adjacent to the vehicle 100) relative to the vehicle user, and / or a visual detection of the front periphery (as for objects outside the front view of a vehicle user, such as a pedestrian, cyclist, etc.).
    In autonomous operation, the vehicle control unit 110 can deploy the sensor devices 102 to provide readings of taxiway markings, to determine a position of vehicle 100 relative to the road to facilitate driving of the vehicle. via the selected route option 134 at Vioo speed, etc.
    The vehicle 100 may include options for operating in manual mode, autonomous mode, and / or driving assistance mode.
    When the vehicle 100 is in manual mode, the driver manually controls the vehicle systems, which may include a propulsion system, a steering system, a stability control system, a navigation system, a system of energy, and all other systems that can control various vehicle functions (such as vehicle air conditioning or entertainment functions, etc.). Vehicle 100 may also include interfaces for the driver to interact with vehicle systems, for example, one or more interactive displays, audio systems, voice recognition systems, buttons and / or dials, haptic feedback systems, or any other means for entering or leaving information.
    In autonomous mode of operation, a computer device, which can be provided by the vehicle control unit 110, or in combination with it, can be used to control one or more of the vehicle systems without direct intervention. of the vehicle user. Certain vehicles can also be equipped with a “driving assistance mode”, in which the operation of vehicle 100 can be shared between the vehicle user and a computer device.
    When the vehicle 100 is operating in an autonomous (or driving assistance) mode, the vehicle control unit 110 issues commands to the various vehicle systems to direct their operation, rather than such systems. vehicle are controlled by the vehicle user.
    As shown in Figure 1, the vehicle control unit 110 can be configured to provide wireless communication 126 through the antenna 112. Wireless communication 126 can provide access to data , as via a network to which the vehicle control unit 110 can send a request for map layer data 150 and receive, in response, map layer data 152 for road conditions and / or configurations, for data obtained by participatory production (in near real time and / or historical), as well as receiving data from and / or relating to other vehicles (as in vehicle-to-vehicle communications and / or or vehicle-to-infrastructure communications ). In this regard, the vehicle control unit 110 can operate to engage in the selected route option 134, via autonomous mission description data, for autonomous vehicle routing, which is discussed in detail below. referring to Figures 2 to 6.
    FIG. 2 illustrates a block diagram of a vehicle control unit 110, which includes a wireless communication interface 202, a processor 204, and a memory 206, which are communicatively coupled via a bus 208.
    The processor 204 in the control unit 110 can be a conventional central processing unit (CPU) or any other type of device, or multiple devices, capable of handling or processing informations. As can be appreciated, the processor 204 can be a single processing device or a plurality of processing devices. Such a processing device can be a microprocessor, a microcontroller, a digital signal processor, a microcomputer, a central processing unit, a preprogrammed network programmable by the user ("fieldprogrammable gâte array" in English), a programmable logic device , a state machine, a set of logic circuits, a set of analog circuits, a set of digital circuits, and / or any device that manipulates signals (analog and / or digital) on the basis of hard coding of the set of circuits and / or operational instructions.
    The memory and / or the memory element 206 can be a single memory device, a plurality of memory devices, and / or a set of integrated circuits of the processor 204. Such a memory device can be a memory read only memory, random access memory, volatile memory, non-volatile memory, static memory, dynamic memory, flash memory, cache memory, and / or any device that stores digital information. The memory 206 is capable of storing machine readable instructions so that the machine readable instructions can be accessed by the processor 204. The machine readable instructions may include logic or algorithm (s) ( s) written in programming languages, and generations thereof, (eg, in first generation programming languages (LIG) (1GL for “first-generation programming languages”) second generation (L2G) (2GL for “second-generation programming languages” in third generation programming languages (L3G) (3GL for “third-generation programming languages” in fourth generation programming languages (L4G) (4GL for “fourth-generation programming languages”), or in fifth generation programming languages (L5G) (5GL for “fifth-generation programming languages” in English) such as, for example, a machine language which can be executed directly by the processor 204, or an assembly language, object-oriented programming (OOP for "object-oriented 5 programming" in English), scripting languages , microcode, etc., which can be compiled or assembled into machine-readable instructions and stored in memory 206. Alternatively, machine-readable instructions can be written in a hardware description language (HDL). ”In English), 10 as a logic implemented via either a user programmable pre-broadcast network configuration (FPGA for“ field- programmable gate array ”in English) or an application-specific integrated circuit (ASIC for“ application- specific integrated circuit ”, or their equivalents. Consequently, the methods and devices described in this disclosure can be implemented in any conventional computer programming language, as preprogrammed hardware elements, or as a combination of hardware and software components.
    It should be noted that when the processor 204 includes more than one processing device, the processing devices can be located centrally (eg, directly coupled together via a wired bus structure and / or or wireless) or can be localized in a distributed fashion (eg, cloud computing via indirect coupling via a local area network and / or a wide area network). It should also be noted that when the processor 204 implements one or more of its functions via a state machine, a set of analog circuits, a set of digital circuits, and / or a set of logic circuits, the memory and / or the memory element storing the corresponding operational instructions 30 can be incorporated into, or external to, the circuit assembly comprising the state machine, the analog circuit assembly, the digital circuit assembly, and / or the set of logic circuits. It should also be noted that the memory element stores, and the processor 204 executes, hard-coded and / or operational instructions corresponding to at least some of the steps and / or functions illustrated in FIGS. 1 to 6 for performing Autonomous vehicle routing features and methods described in this talk.
    The wireless communication interface 202 governs and generally manages the input data via the vehicle network 212 on the communication path 213 and / or the wireless communication 126. The wireless communication interface 202 also handles controller unit output data such as standalone mission description data 220, and data requests, such as layer 150 data request, and also handles controller unit input data , such as destination objective data 224, autonomous vehicle current position data 226, and map layer data 152. The present disclosure is in no way limited to operation on a particular hardware arrangement and therefore features basic presented in this presentation can be substituted, deleted, supplemented, or modified for hardware arrangements ("hardware" in ang lais) and / or firmware (firmware) improved as these can develop.
    The vehicle network 212 can be communicatively coupled to receive signals from satellites of the global positioning system, such as via the antenna 112 of the vehicle control unit 110, or another such vehicle antenna ( not shown). The antenna 112 may include one or more conductive elements which interact with electromagnetic signals transmitted by satellites of the global positioning system. The received signals can be transformed into a data signal indicative of the location (for example, positions of latitude and longitude) and further indicative of the positioning of the vehicle relative to traffic data, such as current position data of autonomous vehicle 226 .
    Wireless communication 126 can be based on one or many specifications of wireless communication system. For example, wireless communication systems may operate in accordance with one or more standard specifications including, but not limited to, 3GPP ("3rd Generation Partnership Project" in English), 4GPP ("4th Generation Partnership Project" in English) ), 5GPP (“5th Generation Partnership Project” in English), LTE (“Long-Term Evolution” in English), LTE Advanced, RFID, IEEE 802.11, Bluetooth, AMPS (“Advanced Mobile Phone Services” in English), digital AMPS , GSM (“Global System for Mobile communications” in English), CDMA (“Code Division Multiple Access” in English), LMDS (“Local Multi-point Distribution Systems” in English), MMDS (“Multi-channel-Multi-point Distribution Systems "in English), IrDA, Wireless USB, Z-Wave, ZigBee, and / or variations thereof.
    The vehicle control unit 110 can be communicatively coupled to a computer via wireless communication 126 and / or another wireless communication. A server 233 can be communicatively coupled to the network cloud 218 via wireless communication 232. The server 233 can include third-party servers that are associated with applications that are running and / or executed by the control unit 110, etc.
    For example, map data layers can be executed on the vehicle control unit 110 and further include current autonomous vehicle position data 226 and destination goal data 224. In addition, such data can be presented to a vehicle user via a graphics card display of a vehicle screen to route location data to a vehicle user 100.
    The server 233 can be operated by an organization which provides the application, such as a mapping application and map application layer data including pavement information data, traffic layer data, data geolocation layer, etc. Layer data can be provided in RNDF (“Route Network Description File”) format. An RNDF file specifies, for example, accessible road segments and provides information such as waypoints, STOP sign locations, lane widths, checkpoint locations, and parking location locations. The road network has no implicit starting or ending point.
    The vehicle control unit 110 can operate to generate autonomous mission description data 220, such as an MDF file ("Mission Description File" in English) for autonomous vehicle operation. Data relating to the MDF file can function to specify control points to be reached in a mission, such as a destination indicated by destination objective data 224, such as along a selected route operation 134 (Figure 1).
    The vehicle control unit 110 operates to determine a selected routing option 134 for autonomous vehicle routing. Autonomous vehicle routing can be based on road condition data provided via traffic map layer data 152 received via wireless communication 126, based on vehicle metric data relating to other vehicles via the vehicle-to-vehicle communications and / or vehicle-to-infrastructure communication, and / or a combination thereof, which can be similarly provided via wireless communication 126, and which is discussed in detail with reference to the figures 3 to 6.
    Figure 3 illustrates a functional block diagram of the vehicle control unit 110 for providing autonomous vehicle routing.
    Generally, autonomous and / or driverless vehicles can receive praise for the efficiencies perceived in comparison with manual driving. Vehicles that are capable of communicating with each other (such as vehicle-to-vehicle and / or vehicle-to-infrastructure communications) will be able to alert other vehicles when the vehicle changes lanes or has need to slow down, which can eliminate the uncertainty and / or chaos resulting from manual driving. In addition, autonomous vehicles can avoid accidents, which are considered a major cause of slowdowns and incidents on the road. In addition, when all vehicles on a road are autonomous, much of the chaos introduced by human error and errors in judgment can be eliminated. However, until this happens, human operators introduce chaos over autonomous vehicle operation. In this regard, the autonomous vehicle routing described in the embodiments in this talk can work to identify sources of chaos on route options and can engage in a selected route option in an autonomous cooperability metric of the vehicle 100. Indeed, vehicle control unit 110 can operate to provide basic iterative actions including navigation along a selected route option 134 (Figure 1) and provide appropriate planning for flow interruptions and / or road chaos.
    The vehicle control unit 110 may include a route generation module 302 and an autonomous mission description module 314, which the memory 206 stores, and each module includes instructions which, when executed by processor 204, provide respective functionality.
    The route generation module 302 includes instructions relating to a route option generator 306 and a chaos level assessment 310. In operation, the route option generator 306 receives objective data from destination 224. The destination goal data 224 may be preprogrammed data relating to routine activities (such as shopping, work, leisure activities, etc.) that the vehicle control unit 110 can discern. In another aspect, a user can provide the destination goal data 224 via a man-machine interface, such as a touch screen device (such as that which can be presented by a vehicle head unit), via voice control (such as via a microphone providing speech-to-text control functionality), via a portable mobile device communicably coupled to a vehicle network 212, etc.
    The route option generator 306 can generate a plurality of route options, via route option data 308, based on destination goal data 224 and current vehicle position data autonomous 226. As can be appreciated, current position data of autonomous vehicle 226 can be retrieved from global positioning satellite (GPS) data or other formats of other location data devices.
    Route option data 308 can be generated based on map layer data 152, which can be provided in response to a request for map layer data 150 (Figure 2) by the control unit of vehicle 110.
    The route option data 308 can operate to indicate a level of chaos in a mixed environment of autonomous vehicles non-autonomous vehicles. As can be appreciated, the higher the level of chaos, the lower the autonomous cooperability. In other words, successful autonomous functioning (that is, reaching a destination) can be seen as a function of taking into account various levels of chaos. For example, a third party collision can cause traffic congestion; however, other factors include the fact that all lanes are now closed and that the autonomous vehicle will have the ability to change routes or simply stay on the selected route option until it becomes available . In other words, the degree to which artificial intelligence has been developed and / or matured can fluctuate between different autonomous vehicles.
    Other examples of chaos may include a vehicle breakdown, tire damage, a sudden and / or unexpected change in a position of a manually driven vehicle, speed on the road, a rock fall, etc.
    The chaos level evaluation 310 operates to receive route option data 308 in series or in parallel from the route option generator 306. For each of a plurality of route options, chaos level assessment can work to assess an associated chaos level, generate an autonomous cooperability metric based on the associated chaos level, and produce an evaluated route option 312.
    As can be appreciated, a level of chaos for a route option can be based on road condition data 309. The road condition data 309 can be based on map layer data 152, data obtained by crowd-source data in near real time 342, vehicle metric data in near real time 344, and / or historical data obtained by crowdfunding 346.
    The map layer 152 data may reflect road conditions, such as undeveloped roadways, the absence of an emergency stop strip and / or taxiway markings, etc., which have a level greater chaos than improved roads with defined traffic lanes. In addition, map layer data 152, at a refresh rate, may reflect a road construction affecting a level of chaos for a road option.
    Vehicle metric data in near real time 344 may include collaboration between various vehicles via vehicle to vehicle and / or vehicle to infrastructure communications.
    Autonomous and / or driver assistance vehicles can be configured to broadcast their vehicle metrics, such as speed and location data, in near real time. Such information can be used to assess an associated level of chaos for a route option, and / or segments thereof. For example, based on speed data obtained from other vehicles, speed profiles for the other vehicles can be generated. Chaotic or volatile speed profiles may be indicative of an unpredictable driving condition, which would create a poor autonomous cooperability metric for this route option.
    Alternatively or additionally, near real-time vehicle metric data 344 may indicate that a number and / or percentage of vehicle volume exceeding a speed limit may indicate excessive chaos and again, render a weak autonomous cooperability metric for this route option.
    In another aspect, frequent lane changes by one or more vehicles can be an indicator of a high level of chaos for a route option. In mixed or largely manual driving vehicles, frequent lane changes beyond a lane change threshold within a predefined distance (e.g., five lane changes in a quarter-mile (402,336 m)) may be considered to include a high level of chaos.
    The data obtained by participatory production in almost real time 342 can be based on GPS-based locations of road users via respective portable mobile devices (via on-board GPS devices). The general speeds of portable mobile devices indicate the flow of traffic (or traffic incidents) for at least a portion of a road. Visually, the traffic flow rate can be transmitted as map layer data 152, and for machine-to-human display purposes, presented via a vehicle display (such as a head unit display vehicle, a head-up display, and / or other vehicle screen device).
    For example, a colored layer appears above main roads and highways, with green representing normal traffic flow, yellow representing slower traffic conditions, red indicating congestion , and dark red indicating almost stopped traffic or discontinuous traffic for a roadway. The underlying data values can be used by the vehicle control unit 110 to determine chaos levels, and an autonomous cooperability metric threshold 316 can be used to determine whether an autonomous vehicle 100 can counter the level of resulting chaos.
    Historical data obtained by historical participatory production 346 can provide an indication of a level of chaos to occur and / or develop. One aspect of the 346 data may be a probability of collision for a time of day for a route option. That is, the level of chaos for a route option can be based on a time of day, a given day of the week, or a combination of these. Governmental or non-governmental sources, accessible via a server 233 (Figure 2) can collect such data. Such data can then be used to generate historical profiles for certain route options. Other information may be based on chaos resulting from ending events (such as sporting events, concerts, festivals, etc.). For example, if a golf tournament takes place on a particular date, then it can be assumed from historical data obtained through participatory production 346 that a high level of chaos results from golf carts on a road, congestion of increased traffic and / or vehicle collisions near the tournament site.
    Consequently, the chaos level evaluation 310 can include instructions which cause the processor 204 to produce the evaluated route option 312 for each of the plurality of route options.
    The autonomous mission description module 314 can include instructions, which, when executed, cause the processor 204 of the vehicle control unit 110 to independently select the route option evaluated from each. the plurality of route options which includes a favorable autonomous cooperability metric to produce a selected route option. The route option evaluated 312 includes an autonomous cooperability metric which compares favorably with the autonomous cooperation metric threshold 316, as when the autonomous cooperation metric enters the limits of threshold 316. The threshold 316 relates to the autonomous capacity of the vehicle 100, which can be supplied via vehicle control unit 100 and / or another vehicle control unit 100. The more advanced the autonomous capacity, like the artificial intelligence (AI) engine, the ability to adapt, etc., the higher the level of chaos that the vehicle control unit 110 can endure to achieve a vehicle objective, such as arriving at a destination.
    The autonomous mission description module 314 can include instructions, which, when executed, cause the processor 204 of the vehicle control unit 110 to generate autonomous mission description data 220 based on the route option selected for the transmission. The autonomous mission description data 220 can be transmitted to other modules of the vehicle 100 to provide a powertrain command to engage autonomously to a destination which is defined by the destination objective data 224. As this can also be appreciated, the function described here can be provided remotely, and transmitted to the vehicle control unit 110 for execution by the processor 204. In addition, in the case where multiple selected route options can enter the autonomous cooperability metric threshold 316, the route option can also be selected on the basis of a favorable comparison with a travel time parameter 318 and / or a travel distance parameter 320, such as the option of evaluated route 312 which may also have shorter travel time and / or distance compared to other route options. Parameters 318 and / or 320 may be based on an optimization basis by the vehicle control unit 110 (such as for optimizing fuel and / or energy resources) or may be based on user input vehicle via a man-machine interface (such as a head unit display, an application (“app” in English) of portable mobile device, etc.).
    As can be appreciated, in another aspect, the chaos level assessment 310 and the resulting assessed route option 312 can be generated by remote processing relative to the vehicle control unit 110 for reduce a processing load on the local processor of the vehicle, like that of the processor 204 in FIG. 2. Such remote processing can include cloud processing accessible via a network cloud 218 (FIG. 2), allowing storage and access to data and access to an application and / or program via the cloud network (“network cloud”) 218, freeing the processor 204 and the memory 206 (FIG. 2) from the control unit of vehicle 110. As can be appreciated, the term “cloud” is a metaphor for the Internet. In this regard, the chaos level evaluation may also be available for other vehicle control units 110 of other vehicles 100. [0078] Figure 4 illustrates an example of graphical user interface 400 representing the data under - adjacent and associated chaos levels for a plurality of route options 420, 422, 424, 426, 428 superimposed with a cartographic representation 402, which can be based on map layer data 152. As noted, chaos can be introduced into a vehicle environment by human error in driving, such as excessive speed, excessive lane changes, error in judgment, etc. Chaos can also be introduced by infrastructure conditions and / or events, such as collisions (resulting in lane closures), road construction, road deterioration (such as potholes, wavy surfaces, etc.). ), road maintenance (lane closures, congestion), and / or congestion due to an event.
    Each of the plurality of route options 420, 422, 424, 426 can be based on routing to reach a destination 412, based on destination objective data 224 (FIG. 3), and data of current autonomous vehicle position 226.
    In general, road condition data 309 (FIG. 3) can be based on cartographic layer data 152, data obtained by participatory production in near real time 342, vehicle metric data in near real time. 344, and / or historical data obtained by participatory production 346. Each of the plurality of route options 420, 422, 424, 426 may include segments shared with each other, as well as segments independent of each other . In this regard, the plurality of route options can be analyzed to form a section data set for each of the plurality of route options 420, 422, 424, 426. In addition, associated chaos levels for each respective section datasets can be weighted, as from W0 (default) to W5, from the lowest to highest chaos levels. As can be appreciated, an additional granularity can be defined with additional weighted chaos levels (such as from W0 to W09, etc.).
    For the example of Figure 4, the route option 420 includes data obtained by participatory production 342 indicating a collision, which can be weighted as an associated level of chaos W3 for a section of the data set of sections relating to the route option 420.
    The route option 424 includes historical data obtained by participatory production 346 indicating congestion due to an event, which can be weighted as an associated level of chaos W4 for a section of the section data set relating to route option 424. Based on an assessment by vehicle control unit 110, congestion due to an event may not be present. For example, when the event is a golf tournament scheduled to end at approximately 3:00 p.m., and the current time of the autonomous position 226 current position data is 1:00 p.m., vehicle 100 has two hours for " arrive before the end of the golf tournament. In this regard, the planned journey time to the event can call into question the level of chaos of the event. If this were the case, the weight for the associated level of chaos in route option 424 would be W0. In this regard, other criteria may be considered by the vehicle control unit 110 for the selection of the route option having the lowest associated level of chaos. Examples of such other criteria may include travel time criteria (the amount of time to arrive at the destination at time equal t 0 plus td) and / or travel distance criteria (the total distance traveled to arrive at the destination 412). These values can be generated by the vehicle control unit 110, such as for optimizing vehicle resources (such as fuel, battery charge, etc.), as well as arriving at a reasonable time interval. A vehicle user can also provide their preferences via a machine-to-man interface (such as a vehicle head unit display).
    The route option 426 includes vehicle metric data 344 indicating erratic traffic, which can be weighted as an associated level of chaos W5 for a section of the section data set relating to the option of route 426.
    As shown, the route options 420, 422, 426 include map layer data 152 indicating a road construction, which can be weighted as an associated level of chaos W1 for each of the section data sets relating to the options of route 420, 422, and 426; that is, each route option includes a certain level of chaos, with the exception of route option 424, which may or may not be based on the time of day.
    Consequently, the respective weighting of the level of chaos associated for the route option 420 is W3; for route option 422 is W1; for route option 424 is W3; for route option 426 is W5. As shown, the associated level of chaos relates to the highest level along the route option, based on the location and the desirability of avoiding or minimizing chaos (such as route option 422 can be used to avoid the chaos associated with “congestion due to an event” of route option 424, when present).
    Consequently, the route option with a low level of associated chaos is the route option 422 with a weighting of Wl. The route option with a high associated level of chaos is route option 426 with a weighting of W5 relative to the erratic traffic shown by the vehicle metric data 344.
    The autonomous vehicle routing can be based on a selection of one of the route options, which in the present example, can include the route options 420, 422, 424 and 426. With reference to the engine with artificial intelligence of an autonomous vehicle, different methods may include different autonomous cooperation metrics. That is, some artificial intelligence engines may be more robust than others in generally chaotic vehicle environments, or further refinements of the algorithms and / or algorithms still to be developed may produce robustness. extra in higher chaos environments. Generally, a level of instant chaos can be present with the mixture of autonomous and manually driven vehicles on roadways. The embodiments presented in this discussion provide intelligent autonomous route selection taking into account available data relating to routing options. Regarding route selection, an autonomous vehicle can base the option on the autonomous cooperability metric of the artificial intelligence engine - that is, the ability of an artificial intelligence engine to coexist and operate in different and variable vehicle environments. With a low autonomous cooperability metric, low levels of chaos may be tolerable in accomplishing the task (such as accomplishing a destination goal); in contrast, a high autonomous cooperability metric can support higher levels of chaos in the vehicle environment.
    Consequently, a route option can be selected in view of an autonomous cooperability metric threshold linked to an autonomous vehicle. As can be appreciated, the threshold may vary between different agents (i.e., different autonomous vehicle), including considerations like vehicle performance capabilities and artificial intelligence engine capabilities.
    For the example of FIG. 4, with a low autonomous cooperability metric threshold, the route option 422 can be selected in view of the level of chaos relatively low compared to the route options 420, 424 and 426 .
    On the other hand, a higher autonomous cooperability metric threshold can allow a wider route selection, like that of one or the other route option 420 (W3) and 422 (Wl). When this is the case, other criteria can be used to provide an autonomous route selection between multiple available routes, such as a journey time parameter and / or a journey distance parameter. Such parameters may be based on an optimization basis by the vehicle control unit 110 (such as for optimizing fuel and / or energy resources), or may be based on vehicle user input via a human machine interface (such as a head unit display, an application (“app” in English) of portable mobile device, etc.). Therefore, based on subsequent selection criteria, the route option 420 can be selected in view of a shorter journey distance, and depending on the details of the collision (such as delay in travel time, number of lane closings, time of collision, etc.) can also provide a shorter journey time than that which can be associated with route option 422.
    FIG. 5 illustrates an example of a graphical user interface 400 representing the selected route option 134 of the route options of FIG. 4 superimposed with a cartographic representation 402. The selected route option 134 provides a destination objective 412 relative to current autonomous vehicle position data 226. As noted, the selected route option may be based on the autonomous selection of a route option from the plurality of route options 420, 422, 424, 426 (Figure 4) which includes a favorable autonomous cooperability metric.
    Based on the route option 134, the vehicle control unit 110 of the vehicle 100 (Figure 1) can generate autonomous mission description data, which can be transmitted to engage autonomously to destination 412, which can be defined by destination objective data 224 (Figure 3) by an artificial intelligence engine of the vehicle control unit 110, by a vehicle user (via a man-machine interface , such as a head unit touch screen, portable mobile device, etc.). The autonomous mission description data 220 can be provided in an MDF format (for “Mission Description Files” in English) for autonomous vehicle operation. The data 220 can operate to specify control points to be reached in a mission, such as a destination 412 indicated by destination objective data 224, such as along a selected route operation 134.
    Figure 6 shows an example of process 600 for autonomous vehicle routing based on an assessment of chaos. In operation 602, the process generates a plurality of route options based on the destination objective data relative to current autonomous vehicle position data.
    In operation 604, each of the plurality of route options is evaluated for a level of chaos associated with operation 606, and on the basis of the level of chaos associated, the process generates a metric of autonomous cooperability. in operation 608.
    Route option data can be based on map layer data, which can be provided in response to a request for map layer data 150 (Figure 2) by a vehicle control unit 110. The data Route options can operate to indicate a level of chaos in a mixed autonomous vehicle - non-autonomous vehicle environment. As can be appreciated, the greater the level of chaos, the lower the autonomous cooperability. In other words, successful autonomous functioning (that is, reaching a destination) can be a function of taking into account various levels of chaos. For example, a third party collision can cause traffic congestion; however, other factors include that all lanes are now closed due to the collision and that the autonomous vehicle will have the ability to change routes or simply stay on the selected route option until that the scene of the collision be released. In other words, the degree to which the artificial intelligence engine has been developed and / or matured can fluctuate between different autonomous vehicles.
    Other examples of chaos may include a vehicle breakdown, tire damage, a sudden and / or unexpected change in the position of a manually driven vehicle, speed on the road, rock collapse, etc.
    When each of the plurality of route options has been evaluated and has generated an autonomous cooperability metric in operation 610, the process continues in operation 612 by autonomously selecting a route option from the plurality route options which includes a favorable autonomous cooperability metric. That is, for each of the plurality of route options, the chaos level assessment can operate to assess an associated chaos level, generate an autonomous cooperability metric based on the associated chaos level , and produce an evaluated route option.
    As can be appreciated, variable criteria can be used to select a route option. Examples may include opting for the route having a respective lower autonomous cooperability metric. Another example can be to use an autonomous cooperability metric threshold value for an autonomous vehicle. The evaluated route option 312 includes an autonomous cooperability metric which compares favorably with the autonomous cooperation metric threshold 316, as when the autonomous cooperation metric enters the limits of threshold 316. An example of such a threshold can relate to the autonomous capacity of an autonomous vehicle 100 (FIG. 1), which can be provided via the vehicle control unit 110 and / or another vehicle control unit 100. The more the autonomous capacity of the vehicle is improved, as the artificial intelligence (AI) engine, the ability to adapt, etc., the higher the level of chaos that the vehicle control unit 110 can handle to achieve the vehicle goal - this is that is, arriving at a destination.
    In operation 614, autonomous mission description data can be generated based on the route option selected in operation 612. Autonomous mission description data 220 can be transmitted to other vehicle modules 100 to provide powertrain control to autonomously engage a destination which is defined by the destination objective data.
    The autonomous mission description data can then be transmitted to operation 616 to engage autonomously towards a destination which is defined by the destination objective data. As can also be appreciated, the process 600 described in the present disclosure can be provided remotely and transmitted to the vehicle control unit 110 of the autonomous vehicle 100.
    In addition, in the case where multiple selected route options can enter the autonomous cooperability metric threshold, or have similar associated chaos levels, the route option can also be selected on the basis of '' a favorable comparison with a travel time parameter and / or a travel distance parameter. Such parameters can be based on an optimization algorithm (such as to optimize fuel and / or energy resources), or can be based on vehicle user input via a human-machine interface (such as a display head unit, an application (“app” in English) of portable mobile device, etc.).
    As a person skilled in the art can further appreciate, the term “coupled”, as it can be used in the present description, includes direct coupling and indirect coupling via another component, element, circuit, or module where, for an indirect coupling, the component, element, circuit, or intermediate module does not modify the information of a signal but can adjust its current level, voltage level, and / or power level. As one skilled in the art will also appreciate, an inferred coupling (that is, where one element is coupled to another element by inference) includes direct and indirect coupling between two elements in the same manner as "coupled".
    As one skilled in the art will further appreciate, the term "compares favorably", as it can be used in this discussion, indicates that a comparison between two elements, articles, signals, and so on, provides a desired relationship.
    As the term "module" is used in the description of the drawings, a module includes a functional block which is implemented in hardware, software, and / or firmware which performs one or more functions such as the processing of 'an input signal to produce an output signal. As used in this presentation, a module can contain sub-modules which themselves are modules.
    The above description relates to those which are currently considered to be the most practical embodiments. However, it should be understood that the description should not be limited to these embodiments but, on the contrary, is intended to cover various modifications and equivalent arrangements.
    权利要求:
    Claims (19)
    [1]
    1. Method (600) for autonomous vehicle routing, the method comprising:
    generating (602) a plurality of route options (420, 422, 424, 426) based on the destination objective data (224) relative to current autonomous vehicle position data (226);
    for each of the plurality of route options (420, 422, 424, 426):
    the evaluation (604, 606) of an associated level of chaos (Wl, W3, W4, W5); and generating (604, 608) an autonomous cooperability metric based on the associated level of chaos (Wl, W3, W4, W5);
    independently selecting (612) a route option (134) from the plurality of route options (420, 422, 424, 426) which includes a favorable autonomous cooperability metric;
    generating (614) autonomous mission description data (220) based on the route option which includes the favorable autonomous cooperability metric; and transmitting (616) the autonomous mission description data (220) to engage autonomously to a destination defined by the destination objective data (224).
    [2]
    2. Method according to claim 1, in which the favorable autonomous cooperability metric falls within the limits of the autonomous cooperability metric threshold.
    [3]
    3. Method according to claim 2, in which the favorable autonomous cooperability metric furthermore enters a travel time parameter.
    [4]
    4. The method of claim 2, wherein the favorable autonomous cooperability metric further enters respective options of the plurality of route options (420, 422, 424, 426).
    [5]
    5. Method according to claim 1, in which the generation (604, 608) of the plurality of route options (420, 422, 424, 426) further comprises:
    ranking the plurality of route options based on a first criterion and a second criterion.
    [6]
    6. The method of claim 5, wherein the first criterion includes a travel distance parameter and the second criterion includes a travel time parameter.
    [7]
    The method of claim 5, wherein the first criterion and the second criterion are provided as a user preference.
    [8]
    8. Method according to any one of claims 1 to 7, in which the associated level of chaos is based on road condition data (309) including at least one of:
    map layer data (152);
    data obtained by participatory production in near real time (342);
    near-real-time vehicle metric data (344); and historical data obtained by participatory production (346).
    [9]
    9. Method (600) for autonomous vehicle routing, the method comprising:
    generating (602) a plurality of route options (420, 422, 424, 426) based on the destination objective data (224) relative to current autonomous vehicle position data (226);
    analyzing each of the plurality of route options (420, 422, 424, 426) to form a section data set;
    for each of the plurality of route options (420, 422, 424, 426):
    evaluating (604, 606) an associated level of chaos for each of the section dataset;
    weighting the associated chaos level for each of the section dataset which includes a high chaos level to produce a plurality of weighted chaos levels corresponding to each of the section data set;
    generating (604, 608) a route chaos level for the section data set based on the weighted chaos level of each of the section data set; and generating an autonomous cooperability metric for the section dataset based on the weighted level of chaos;
    the autonomous selection of a route option from the plurality of route options which includes a favorable autonomous cooperability metric;
    generating (614) autonomous mission description data (220) based on the route option which includes the favorable autonomous cooperability metric; and transmitting (616) the autonomous mission description data (220) to engage autonomously to a destination defined by the destination objective data (224).
    [10]
    10. The method of claim 9, wherein the favorable autonomous cooperability metric falls within the limits of the autonomous cooperability metric threshold.
    [11]
    11. The method of claim 10, wherein the metric of
    5 favorable autonomous cooperability also comes within a travel time parameter.
    [12]
    12. The method as claimed in claim 10, in which the favorable autonomous cooperability metric also enters respective options from each of the plurality of route options (420, 422, 424,
    10,426).
    [13]
    13. The method of claim 9, wherein the generation of the plurality of route options further comprises:
    ranking the plurality of route options (420, 422, 424, 426) based on a first criterion and a second criterion.
    [14]
    14. The method of claim 13, wherein the first criterion includes a travel distance parameter and the second criterion includes a travel time parameter.
    15. The method of claim 13, wherein the first criterion and the second criterion are provided as a user preference.
    20
    [15]
    16. Method according to any one of claims 9 to 15, in which the associated level of chaos being based on road condition data including at least one of:
    map layer data (152);
    data obtained by participatory production in near real time (342);
    near-real-time vehicle metric data (344); and historical data obtained by participatory production (346).
    [16]
    17. Vehicle control unit (110) comprising:
    a wireless communication interface (202) for serving communication with a vehicle network;
    a processor (204) communicatively coupled to the wireless communication interface (202); and a memory (206) communicably coupled to the processor (204) and storing:
    a route generation module (302) including instructions which, when executed by the processor (204), cause the processor to:
    generating a plurality of route options (420, 422, 424, 426) on the destination goal database (224) relative to current autonomous vehicle position data (226);
    for each of the plurality of route options (420, 422, 424, 426):
    assess an associated level of chaos (Wl, W3, W4, W5); and generate an autonomous cooperability metric based on the associated level of chaos (Wl, W3, W4, W5) to produce an evaluated route option (312); and an autonomous mission description module (314) including instructions which, when executed by the processor (204), cause the processor to:
    receiving the evaluated route option (312) for each of the plurality of route options (420, 422, 424, 426);
    independently selecting the route option evaluated from each of the plurality of route options (420, 422, 424, 426) which includes a favorable autonomous cooperability metric to produce a selected route option; and generating autonomous mission description data (220) based on the route option selected for transmission to autonomously engage to a destination defined by the destination objective data (224).
    [17]
    18. Vehicle control unit according to claim 17, in which the autonomous cooperability metric falls within the limits of an autonomous cooperability metric threshold.
    [18]
    19. A vehicle control unit according to claim 18, wherein the selected route option further enters a travel time parameter.
    [19]
    20. A vehicle control unit according to any of claims 17 to 19, wherein the associated level of chaos (Wl, W3, W4, W5) being based on road condition data (309) including at least l one of:
    map layer data (152);
    data obtained by participatory production in near real time (342);
    near-real-time vehicle metric data (344); and historical data obtained by participatory production (346).
    类似技术:
    公开号 | 公开日 | 专利标题
    FR3070066A1|2019-02-15|AUTONOMOUS VEHICLE ROUTING BASED ON CHAOS EVALUATION
    US10366612B2|2019-07-30|Optimal warning distance
    EP2940545B1|2018-08-15|Mode transition for an autonomous vehicle
    US9720418B2|2017-08-01|Autonomous vehicle monitoring and control
    US20200255026A1|2020-08-13|System and method for providing precise driving recommendations based on network-assisted scanning of a surrounding environment
    US9666072B2|2017-05-30|Dynamic speed limit
    US8134478B2|2012-03-13|Data mining in a digital map database to identify community reported driving hazards along roads and enabling precautionary actions in a vehicle
    US20200374653A1|2020-11-26|Map based feedback loop for vehicle observations
    CN107436149B|2020-12-11|System and method for progressive map maintenance and communication channel selection
    US20180340790A1|2018-11-29|Individualized risk routing for human drivers
    US20200020226A1|2020-01-16|Method, apparatus, and system for estimating vulnerable road users
    US11100794B2|2021-08-24|Autonomous driving and slowdown patterns
    US20210368308A1|2021-11-25|Network-assisted scanning of a surrounding environment
    US20200209002A1|2020-07-02|Systems and methods for vehicle telemetry
    US20210303884A1|2021-09-30|Automatic positioning of 2d image sign sightings in 3d space
    US11010621B2|2021-05-18|Automatic detection and positioning of structure faces
    US20210284176A1|2021-09-16|Behavior-based vehicle alerts
    JP2022517454A|2022-03-09|Providing additional instructions for difficult maneuvers during navigation
    KR20210079237A|2021-06-29|How to provide additional commands for difficult maneuvers during navigation
    US20210223788A1|2021-07-22|System, device and method of identifying and updating the operational design domain of an autonomous vehicle
    US20210269054A1|2021-09-02|System and Method for Controlling a Vehicle Using Contextual Navigation Assistance
    US20200208998A1|2020-07-02|Systems and methods for safe route planning for a vehicle
    Byon2011|GISTMARG: GPS and GIS for traffic monitoring and route guidance
    CN113748316A|2021-12-03|System and method for vehicle telemetry
    Byon2011|Department of Civil Engineering
    同族专利:
    公开号 | 公开日
    US20190049257A1|2019-02-14|
    US10345110B2|2019-07-09|
    CN109387213B|2021-09-07|
    JP6687685B2|2020-04-28|
    JP2019056691A|2019-04-11|
    FR3070066B1|2021-06-25|
    CN109387213A|2019-02-26|
    引用文献:
    公开号 | 申请日 | 公开日 | 申请人 | 专利标题
    JP4952268B2|2007-01-24|2012-06-13|トヨタ自動車株式会社|Travel control plan generator|
    US8126642B2|2008-10-24|2012-02-28|Gray & Company, Inc.|Control and systems for autonomously driven vehicles|
    US20100106344A1|2008-10-27|2010-04-29|Edwards Dean B|Unmanned land vehicle having universal interfaces for attachments and autonomous operation capabilities and method of operation thereof|
    US8392117B2|2009-05-22|2013-03-05|Toyota Motor Engineering & Manufacturing North America, Inc.|Using topological structure for path planning in semi-structured environments|
    WO2011124271A1|2010-04-09|2011-10-13|Tomtom International B.V.|Method of generating a route|
    US8509982B2|2010-10-05|2013-08-13|Google Inc.|Zone driving|
    US20130013198A1|2011-07-08|2013-01-10|Adrain John B|Navigation System Creating A Route Based On Certain Criteria Along The Route|
    US8909474B2|2012-12-26|2014-12-09|Echostar Broadcasting Corporation|Methods and apparatus for socioeconomic routing in navigation systems|
    US8972175B2|2013-03-14|2015-03-03|Qualcomm Incorporated|Navigation using crowdsourcing data|
    US10451428B2|2013-03-15|2019-10-22|Volkswagen Aktiengesellschaft|Automatic driving route planning application|
    US9435652B2|2013-12-19|2016-09-06|Novatel Wireless, Inc.|Dynamic routing intelligent vehicle enhancement system|
    US9720418B2|2014-05-27|2017-08-01|Here Global B.V.|Autonomous vehicle monitoring and control|
    US9372089B2|2014-06-02|2016-06-21|International Business Machines Corporation|Monitoring suggested routes for deviations|
    US20150345967A1|2014-06-03|2015-12-03|Nissan North America, Inc.|Probabilistic autonomous vehicle routing and navigation|
    US9360333B2|2014-08-04|2016-06-07|Here Global B.V.|Method and apparatus calculating estimated time of arrival from multiple devices and services|
    JP6112123B2|2015-01-19|2017-04-12|トヨタ自動車株式会社|Automatic driving device|
    JP6490486B2|2015-04-21|2019-03-27|クラリオン株式会社|Route search apparatus and route search method|
    JP6380274B2|2015-07-28|2018-08-29|トヨタ自動車株式会社|Navigation device for autonomous vehicles|
    CN105549597B|2016-02-04|2018-06-26|同济大学|A kind of unmanned vehicle dynamic path planning method based on environmental uncertainty|
    US10331141B2|2016-06-30|2019-06-25|GM Global Technology Operations LLC|Systems for autonomous vehicle route selection and execution|
    US20180113450A1|2016-10-20|2018-04-26|Toyota Motor Engineering & Manufacturing North America, Inc.|Autonomous-mode traffic lane selection based on traffic lane congestion levels|US11269352B2|2017-12-15|2022-03-08|Baidu Usa Llc|System for building a vehicle-to-cloud real-time traffic map for autonomous driving vehicles |
    US10755111B2|2018-01-29|2020-08-25|Micron Technology, Inc.|Identifying suspicious entities using autonomous vehicles|
    US11009876B2|2018-03-14|2021-05-18|Micron Technology, Inc.|Systems and methods for evaluating and sharing autonomous vehicle driving style information with proximate vehicles|
    US20190287392A1|2018-03-14|2019-09-19|Micron Technology, Inc.|Systems and methods for evaluating and sharing human driving style information with proximate vehicles|
    US10997429B2|2018-04-11|2021-05-04|Micron Technology, Inc.|Determining autonomous vehicle status based on mapping of crowdsourced object data|
    US11161518B2|2018-06-15|2021-11-02|Micron Technology, Inc.|Detecting road conditions based on braking event data received from vehicles|
    CN110244725B|2019-06-13|2020-09-11|腾讯科技（深圳）有限公司|Control method and device for simulated vehicle, storage medium and electronic device|
    法律状态:
    2019-07-22| PLFP| Fee payment|Year of fee payment: 2 |
    2020-07-17| PLSC| Search report ready|Effective date: 20200717 |
    2020-07-21| PLFP| Fee payment|Year of fee payment: 3 |
    2021-07-23| PLFP| Fee payment|Year of fee payment: 4 |
    优先权:
    申请号 | 申请日 | 专利标题
    US15676033|2017-08-14|
    US15/676,033|US10345110B2|2017-08-14|2017-08-14|Autonomous vehicle routing based on chaos assessment|
    [返回顶部]