Centralized shared autonomous vehicle operations management

Abstract

A centralized shared scenario-specific operation control management, which includes: receiving shared scenario-specific operation control management input data from an autonomous vehicle at a centralized shared scenario-specific operation control management device; verifying the shared scenario-specific operation control management input data; identifying current different vehicle operation scenarios based on the shared scenario-specific operation control management input data; generating shared scenario-specific operation control management output data based on the current different vehicle operation scenarios; and sending the shared scenario-specific operation control management output data.

Description

Technical Field

[0001] The present invention relates to autonomous vehicle operation management and autonomous driving. Background Art

[0002] Autonomous vehicles may traverse a vehicle transportation network, which may include encountering different vehicle operating scenarios. Autonomous vehicles may use strategies or solutions based on models of current different vehicle operating scenarios to traverse the current different vehicle operating scenarios. Autonomous vehicles may have limited resources for identifying different vehicle operating scenarios and generating or optimizing corresponding strategies. Therefore, systems, methods, and apparatus for centralized shared scenario-specific operational control management may be advantageous. Summary of the Invention

[0003] Disclosed herein are aspects, features, elements, implementations, and embodiments of centralized shared scenario-specific operational control management.

[0004] An aspect of the disclosed embodiment is a method for centralized shared scenario-specific operational control management. The method includes: receiving shared scenario-specific operational control management input data from an autonomous vehicle at a centralized shared scenario-specific operational control management device; validating the shared scenario-specific operational control management input data; identifying a current different vehicle operational scenario based on the shared scenario-specific operational control management input data; generating shared scenario-specific operational control management output data based on the current different vehicle operational scenario; and transmitting the shared scenario-specific operational control management output data.

[0005] Another aspect of the disclosed embodiment is an apparatus comprising: a non-transitory computer-readable medium; and a processor configured to execute instructions stored on the non-transitory computer-readable medium to implement a method for centralized shared scenario-specific operation control management. The method comprises: receiving shared scenario-specific operation control management input data from an autonomous vehicle at a centralized shared scenario-specific operation control management device; validating the shared scenario-specific operation control management input data; identifying a current different vehicle operation scenario based on the shared scenario-specific operation control management input data; generating shared scenario-specific operation control management output data based on the current different vehicle operation scenario; and transmitting the shared scenario-specific operation control management output data.

[0006] Another aspect of the disclosed embodiment is a non-transitory computer-readable storage medium comprising executable instructions that, when executed by a processor, facilitate a method for centralized shared scenario-specific operational control management. The method comprises: receiving shared scenario-specific operational control management input data from an autonomous vehicle at a centralized shared scenario-specific operational control management device; validating the shared scenario-specific operational control management input data; identifying a current different vehicle operational scenario based on the shared scenario-specific operational control management input data; generating shared scenario-specific operational control management output data based on the current different vehicle operational scenario; and transmitting the shared scenario-specific operational control management output data.

[0007] Variations on these and other aspects, features, elements, implementations, and embodiments of the methods, apparatus, processes, and algorithms disclosed herein are described in further detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Various aspects of the methods and apparatus disclosed herein will become more apparent by reference to the examples provided in the following description and accompanying drawings, in which:

[0009] Figure 1 is a diagram of an example of a vehicle in which the aspects, features, and elements disclosed herein may be implemented;

[0010] Figure 2 is a diagram of an example of a portion of a vehicle transportation and communication system in which aspects, features, and elements disclosed herein may be implemented;

[0011] Figure 3 is a diagram of a portion of a vehicle transportation network according to the present invention;

[0012] Figure 4 is a diagram of an example of an autonomous vehicle operations management system according to an embodiment of the present invention;

[0013] Figure 5 is a flow chart of an example of autonomous vehicle operations management according to an embodiment of the present invention;

[0014] Figure 6 is a flow diagram of an example of autonomous vehicle operations management utilizing shared scenario-specific operational control management data communications according to an embodiment of the present invention.

[0015] Figure 7 is a diagram of an example of a centralized shared scenario-specific operation control management apparatus that can implement aspects, features, and elements disclosed herein.

[0016] Figure 8 is a flow chart of an example of centralized shared scenario-specific operation control management according to an embodiment of the present invention.

[0017] Figure 9 is a flow chart of an example of policy data validation according to an embodiment of the present invention.

[0018] Figure 10 is a flow chart of an example of empirical data validation according to an embodiment of the present invention. DETAILED DESCRIPTION

[0019] Vehicles, such as autonomous vehicles or semi-autonomous vehicles, may traverse the vehicle transportation network. Traversing the vehicle transportation network may include traversing one or more different vehicle operating scenarios, such as pedestrian scenarios, intersection scenarios, lane change scenarios, or any other vehicle operating scenario or combination of vehicle operating scenarios.

[0020] The autonomous vehicle may navigate through the current different vehicle operating scenarios based on strategies or solutions based on corresponding models of the different vehicle operating scenarios, such as partially observable Markov decision process (POMDP) ​​models. The autonomous vehicle may have limited resource availability for identifying the corresponding different vehicle operating scenarios and solving the corresponding models for the different vehicle operating scenarios. The autonomous vehicle may electronically communicate with an external centralized shared scenario-specific operational control management device to identify the different vehicle operating scenarios and corresponding strategy data for the corresponding models for the different vehicle operating scenarios.

[0021] The centralized shared scenario-specific operation control management device can maintain vehicle data and vehicle transportation network data including different vehicle operation scenario data, wherein the different vehicle operation scenario data may include data defining or describing various different vehicle operation scenarios, experience data generated by the corresponding vehicles passing through the corresponding different vehicle operation scenarios, model data for modeling the corresponding different vehicle operation scenarios, strategy data including strategies or solutions of the corresponding models, or any other data or data combination that can be used for centralized shared scenario-specific operation control management.

[0022] The centralized shared scenario-specific operational control management device can receive experience data, policy data, or both generated by vehicles traversing the vehicle transportation network and can integrate the received data with previously stored shared scenario-specific operational control management data, which can include processing the data to validate and compress the data. The centralized shared scenario-specific operational control management device can distribute the policy data to the respective autonomous vehicles for use when traversing the respective different vehicle operational scenarios. The centralized shared scenario-specific operational control management device can distribute the experience data to the respective autonomous vehicles that have available resources to generate the corresponding policy data.

[0023] Although described herein with reference to autonomous vehicles, the methods and apparatus described herein can be implemented in any vehicle capable of autonomous or semi-autonomous operation. Although described herein with reference to a vehicle transportation network, the methods and apparatus described herein can include autonomous vehicles operating in any area in which a vehicle can navigate.

[0024] Figure 1 1 is a diagram of an example of a vehicle that may implement aspects, features, and elements disclosed herein. As shown, vehicle 1000 includes chassis 1100, powertrain 1200, controller 1300, and wheels 1400. Although vehicle 1000 is shown as including four wheels 1400 for simplicity, any other propulsion means such as a pusher or treads may be used. Figure 1 1000, which may include accelerating, decelerating, steering, or otherwise controlling the vehicle 1000.

[0025] As shown, powertrain 1200 includes a power source 1210, a transmission unit 1220, a steering unit 1230, and an actuator 1240. Any other components or combinations of components of the powertrain, such as a suspension, a drive shaft, an axle, or an exhaust system, may be included. Although shown separately, wheel 1400 may be included in powertrain 1200.

[0026] The power source 1210 may include an engine, a battery, or a combination thereof. The power source 1210 may be any device or combination of devices operable to provide energy such as electrical energy, thermal energy, or kinetic energy. For example, the power source 1210 may include an engine such as an internal combustion engine, an electric motor, or a combination of an internal combustion engine and an electric motor, and may be operable to provide kinetic energy as motive force to one or more of the wheels 1400. The power source 1210 may include a potential energy unit, for example: one or more dry cells such as nickel-cadmium (NiCd) batteries, nickel-zinc (NiZn) batteries, nickel-metal hydride (NiMH) batteries, lithium-ion (Li-ion) batteries, etc.; solar cells; fuel cells; or any other device capable of providing energy.

[0027] The transmission unit 1220 can receive energy, such as kinetic energy, from the power source 1210 and can transmit the energy to the wheels 1400 to provide motive force. The transmission unit 1220 can be controlled by the controller 1300, the actuator 1240, or both. The steering unit 1230 can be controlled by the controller 1300, the actuator 1240, or both and can control the wheels 1400 to steer the vehicle. The actuator 1240 can receive signals from the controller 1300 and can actuate or control the power source 1210, the transmission unit 1220, the steering unit 1230, or any combination thereof to operate the vehicle 1000.

[0028] As shown, the controller 1300 may include a positioning unit 1310, an electronic communication unit 1320, a processor 1330, a memory 1340, a user interface 1350, a sensor 1360, an electronic communication interface 1370, or any combination thereof. Although shown as a single unit, any one or more elements of the controller 1300 may be integrated into any number of separate physical units. For example, the user interface 1350 and the processor 1330 may be integrated into a first physical unit, and the memory 1340 may be integrated into a second physical unit. Although in Figure 1 Although not shown, the controller 1300 may include a power source such as a battery, etc. Although shown as separate elements, the positioning unit 1310, the electronic communication unit 1320, the processor 1330, the memory 1340, the user interface 1350, the sensor 1360, the electronic communication interface 1370, or any combination thereof may be integrated into one or more electronic units, circuits, or chips.

[0029] The processor 1330 may include any existing or subsequently developed device or combination of devices capable of manipulating or processing signals or other information, including optical processors, quantum processors, molecular processors, or combinations thereof. For example, the processor 1330 may include one or more dedicated processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more microcontrollers, one or more integrated circuits, one or more application-specific integrated circuits, one or more field programmable gate arrays, one or more programmable logic arrays, one or more programmable logic controllers, one or more state machines, or any combination thereof. The processor 1330 may be operably coupled to the positioning unit 1310, the memory 1340, the electronic communication interface 1370, the electronic communication unit 1320, the user interface 1350, the sensor 1360, the powertrain 1200, or any combination thereof. For example, the processor may be operably coupled to the memory 1340 via a communication bus 1380.

[0030] The memory 1340 may include any tangible, non-transitory computer-usable or computer-readable medium that, for example, is capable of containing, storing, communicating, or transporting machine-readable instructions or any information associated therewith for use by or in conjunction with the processor 1330. The memory 1340 may be, for example, one or more solid-state drives, one or more memory cards, one or more removable media, one or more read-only memories, one or more random-access memories, one or more disks (including hard disks, floppy disks, optical disks, magnetic cards, or optical cards), or any type of non-transitory medium suitable for storing electronic information, or any combination thereof.

[0031] The communication interface 1370 may be a wireless antenna (as shown), a wired communication port, an optical communication port, or any other wired or wireless means capable of interfacing with a wired or wireless electronic communication medium 1500. Figure 1 The communication interface 1370 is shown communicating via a single communication link, but the communication interface can be configured to communicate via multiple communication links. Figure 1 A single communication interface 1370 is shown, but the vehicle may include any number of communication interfaces.

[0032] The communication unit 1320 may be configured to send or receive signals via a wired or wireless electronic communication medium 1500, such as via the communication interface 1370. Figure 1 Although not explicitly shown, the communication unit 1320 may be configured to transmit, receive, or both via any wired or wireless communication medium, such as radio frequency (RF), ultraviolet light (UV), visible light, fiber optics, wireline, or a combination thereof. Figure 1 A single communication unit 1320 and a single communication interface 1370 are shown, but any number of communication units and any number of communication interfaces may be used. In some embodiments, the communication unit 1320 may include a dedicated short range communication (DSRC) unit, an on-board unit (OBU), or a combination thereof.

[0033] The positioning unit 1310 can determine geographic location information of the vehicle 1000, such as longitude, latitude, altitude, direction of travel, or speed. For example, the positioning unit can include a global positioning system (GPS) unit, a National Marine Electronics Association (NMEA) unit such as a Wide Area Augmentation System (WAAS) enabled unit, a radio triangulation unit, or a combination thereof. The positioning unit 1310 can be used to obtain information representing, for example, the current heading of the vehicle 1000, the current position of the vehicle 1000 in two or three dimensions, the current angular orientation of the vehicle 1000, or a combination thereof.

[0034] User interface 1350 can comprise any unit that can interact with people, such as virtual or physical keyboard, touch pad, display, touch display, head-up display, virtual display, augmented reality display, tactile display, feature tracking device such as eye tracking device, loud speaker, microphone, camera, sensor, printer or its any combination.As shown in the figure, user interface 1350 can be operably coupled with processor 1330 or with any other element of controller 1300.Although being shown as single unit, user interface 1350 can comprise one or more physical units.For example, user interface 1350 comprises the audio interface for carrying out audio communication with people and the touch display for carrying out the communication based on vision and touch with people.User interface 1350 can comprise multiple displays, such as multiple physically separated units, multiple definition parts or its combination in single physical unit.

[0035] Sensors 1360 may include one or more sensors (such as a sensor array) operable to provide information that can be used to control the vehicle. Sensors 1360 may provide information related to the current operating characteristics of the vehicle 1000. Sensors 1360 may include, for example, a velocity sensor, an acceleration sensor, a steering angle sensor, a traction-related sensor, a brake-related sensor, a steering wheel position sensor, an eye-tracking sensor, a sitting position sensor, or any sensor or combination of sensors operable to report information related to certain aspects of the current dynamic condition of the vehicle 1000.

[0036] Sensors 1360 may include one or more sensors operable to obtain information related to the physical environment surrounding vehicle 1000. For example, one or more sensors may detect road geometry and features (such as lane markings, etc.) and obstacles (such as fixed obstacles, vehicles, and pedestrians, etc.). Sensors 1360 may be or include one or more cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of vehicle-mounted environmental sensing device or combination of devices, now known or subsequently developed. In some embodiments, sensors 1360 and positioning unit 1310 may be a combined unit.

[0037] Although not shown separately, the vehicle 1000 may include a trajectory controller. For example, the controller 1300 may include a trajectory controller. The trajectory controller may be operable to obtain information describing the current state of the vehicle 1000 and the route planned for the vehicle 1000, and determine and optimize the trajectory of the vehicle 1000 based on this information. In some embodiments, the trajectory controller may output a signal that is operable to control the vehicle 1000 so that the vehicle 1000 follows the trajectory determined by the trajectory controller. For example, the output of the trajectory controller may be an optimized trajectory that may be supplied to the powertrain 1200, the wheel 1400, or both. In some embodiments, the optimized trajectory may be a control input such as a set of steering angles, where each steering angle corresponds to a point in time or a position. In some embodiments, the optimized trajectory may be one or more paths, lines, curves, or a combination thereof.

[0038] One or more of the wheels 1400 may be: a steering wheel that can be pivoted to a steering angle under the control of the steering unit 1230; a propulsion wheel that can be twisted under the control of the sending unit 1220 to propel the vehicle 1000; or a steering propulsion wheel that can steer and propel the vehicle 1000.

[0039] although Figure 1 Not shown, but the vehicle may include Figure 1 Units or components not shown, such as housing, Bluetooth module, a frequency modulation (FM) radio unit, a near field communication (NFC) module, a liquid crystal display (LCD) display unit, an organic light emitting diode (OLED) display unit, a speaker, or any combination thereof.

[0040] Vehicle 1000 may be an autonomous vehicle that is autonomously controlled to traverse a portion of a vehicle transportation network without direct human intervention. Figure 1 Although not shown separately, the autonomous vehicle may include an autonomous vehicle control unit that can perform autonomous vehicle route planning, navigation, and control. The autonomous vehicle control unit may be integrated with other units of the vehicle. For example, controller 1300 may include an autonomous vehicle control unit.

[0041] The autonomous vehicle control unit can control or operate the vehicle 1000 to traverse a portion of the vehicle transport network based on current vehicle operating parameters. The autonomous vehicle control unit can control or operate the vehicle 1000 to perform defined operations or maneuvers, such as parking the vehicle. The autonomous vehicle control unit can generate a travel route from a starting point (such as the current location of the vehicle 1000) to a destination based on vehicle information, environmental information, vehicle transport network data representing the vehicle transport network, or a combination thereof, and can control or operate the vehicle 1000 to traverse the vehicle transport network based on the route. For example, the autonomous vehicle control unit can output the travel route to a trajectory controller, and the trajectory controller can use the generated route to operate the vehicle 1000 to travel from the starting point to the destination.

[0042] Figure 2 is a diagram of an example of a portion of a vehicle transportation and communication system that may implement aspects, features, and elements disclosed herein. The vehicle transportation and communication system 2000 may include one or more vehicles 2100 / 2110 (such as Figure 1 The vehicle 1000 shown in FIG. 1 may travel via one or more portions of one or more vehicle transportation networks 2200 and may communicate via one or more electronic communication networks 2300. Figure 2 It is not explicitly shown, but the vehicle may traverse areas that are not explicitly or fully included in the vehicle transportation network (such as off-road areas, etc.).

[0043] The electronic communication network 2300 may be, for example, a multiple access system and may provide communications such as voice communications, data communications, video communications, messaging communications, or combinations thereof between the vehicles 2100 / 2110 and one or more communication devices 2400. For example, the vehicle 2100 / 2110 may receive information such as information indicating the vehicle transportation network 2200 from the communication device 2400 via the network 2300.

[0044] In some embodiments, the vehicle 2100 / 2110 can communicate via a wired communication link (not shown), a wireless communication link 2310 / 2320 / 2370, or a combination of any number of wired or wireless communication links. For example, as shown, the vehicle 2100 / 2110 can communicate via a terrestrial wireless communication link 2310, via a non-terrestrial wireless communication link 2320, or via a combination thereof. The terrestrial wireless communication link 2310 can include an Ethernet link, a serial link, a Bluetooth link, an infrared (IR) link, an ultraviolet (UV) link, or any link capable of providing electronic communication.

[0045] The vehicle 2100 / 2110 can communicate with another vehicle 2100 / 2110. For example, the host or subject vehicle (HV) 2100 can receive one or more automated inter-vehicle messages, such as basic safety messages (BSMs), from the remote or target vehicle (RV) 2110 via a direct communication link 2370 or via the network 2300. For example, the remote vehicle 2110 can broadcast the message to host vehicles within a defined broadcast range, such as 300 meters. In some embodiments, the host vehicle 2100 can receive the message via a third party, such as a signal repeater (not shown) or another remote vehicle (not shown). The vehicle 2100 / 2110 can periodically send one or more automated inter-vehicle messages, for example, based on a defined interval, such as 100 milliseconds.

[0046] Automated inter-vehicle messages may include: vehicle identification information; geospatial status information, such as longitude, latitude, or altitude information; geospatial positioning accuracy information; kinematic status information, such as vehicle acceleration information, yaw rate information, velocity information, etc.; vehicle heading information; brake system status information; throttle information; steering wheel angle information or vehicle course information; or vehicle operating status information, such as vehicle dimensions, headlight status information, turn signal information, wiper status data, transmission information, or any other information or combination of information related to the status of the transmitting vehicle. For example, the transmission status information may indicate whether the transmitting vehicle is in neutral, parked, forward, or reverse.

[0047] The vehicle 2100 can communicate with the communication network 2300 via an access point 2330. The access point 2330, which may include a computing device, can be configured to communicate with the vehicle 2100, the communication network 2300, one or more communication devices 2400, or a combination thereof via a wired or wireless communication link 2310 / 2340. For example, the access point 2330 can be a base station, a base transceiver station (BTS), a node B, an enhanced node B (eNode-B), a home node B (HNode-B), a wireless router, a wired router, a hub, a repeater, a switch, or any similar wired or wireless device. Although in Figure 2 Although shown as a single unit, an access point may include any number of interconnected elements.

[0048] Vehicle 2100 may communicate with communication network 2300 via satellite 2350 or other non-terrestrial communication means. Satellite 2350, which may include a computing device, may be configured to communicate with vehicle 2100, communication network 2300, one or more communication devices 2400, or a combination thereof via one or more communication links 2320 / 2360. Figure 2 Although shown as a single unit, a satellite may comprise any number of interconnected elements.

[0049] The electronic communications network 2300 may be any type of network configured to provide voice, data, or any other type of electronic communications. For example, the electronic communications network 2300 may include a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a mobile or cellular telephone network, the Internet, or any other electronic communications system. The electronic communications network 2300 may use a communications protocol such as the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), the Internet Protocol (IP), the Real-time Transport Protocol (RTP), the Hypertext Transfer Protocol (HTTP), or a combination thereof. Although in Figure 2 Although shown as a single unit, the electronic communications network may include any number of interconnected elements.

[0050] The vehicle 2100 can identify a portion or condition of the vehicle transportation network 2200. For example, the vehicle 2100 can include one or more onboard sensors 2105 (such as Figure 1 The one or more onboard sensors 2105 may include a rate sensor, a wheel speed sensor, a camera, a gyroscope, an optical sensor, a laser sensor, a radar sensor, an acoustic sensor, or any other sensor or device or combination thereof capable of determining or identifying a portion or condition of the vehicle transportation network 2200. The sensor data may include lane data, remote vehicle position data, or both.

[0051] Vehicles 2100 may traverse one or more portions of one or more vehicle transportation networks 2200 using information communicated via network 2300, such as information representative of vehicle transportation network 2200, information identified by one or more onboard sensors 2105, or a combination thereof.

[0052] Although for simplicity, Figure 2 Two vehicles 2100, 2110, a vehicle transport network 2200, an electronic communications network 2300, and a communications device 2400 are shown, but any number of vehicles, networks, or computing devices may be used. The vehicle transport and communications system 2000 may include Figure 2Although vehicle 2100 is shown as a single unit, the vehicle may include any number of interconnected elements.

[0053] Although the vehicle 2100 is shown as communicating with the communication device 2400 via the network 2300, the vehicle 2100 can communicate with the communication device 2400 via any number of direct or indirect communication links. For example, the vehicle 2100 can communicate with the communication device 2400 via a direct communication link, such as a Bluetooth communication link.

[0054] In some embodiments, the vehicle 2100 / 2210 may be associated with an entity 2500 / 2510, such as a driver, operator, or owner of the vehicle. In some embodiments, the entity 2500 / 2510 associated with the vehicle 2100 / 2110 may be associated with one or more personal electronic devices 2502 / 2504 / 2512 / 2514, such as a smartphone 2502 / 2512 or a computer 2504 / 2514. In some embodiments, the personal electronic devices 2502 / 2504 / 2512 / 2514 may communicate with the respective vehicle 2100 / 2110 via a direct or indirect communication link. Although in Figure 2 One entity 2500 / 2510 is shown as being associated with one vehicle 2100 / 2110, but any number of vehicles may be associated with an entity, and any number of entities may be associated with a vehicle.

[0055] Figure 3 is a diagram of a portion of a vehicle transportation network according to the present invention. Vehicle transportation network 3000 may include one or more non-navigable areas 3100 such as buildings, one or more partially navigable areas such as parking areas 3200, one or more navigable areas such as roads 3300 / 3400, or a combination thereof. In some embodiments, autonomous vehicles (such as Figure 1 The vehicle 1000 shown, Figure 2 One of the vehicles 2100 / 2110 shown, a semi-autonomous vehicle, or any other vehicle that enables autonomous driving, etc.) can traverse one or more portions of the vehicle transportation network 3000.

[0056] The vehicle transportation network 3000 may include one or more intersections 3210 between one or more navigable or partially navigable areas 3200 / 3300 / 3400. For example, Figure 3The portion of the vehicle transportation network 3000 shown includes an intersection 3210 between a parking area 3200 and a road 3400. The parking area 3200 may include a parking space 3220.

[0057] A portion of the vehicle transportation network 3000, such as a road 3300 / 3400, etc., may include one or more lanes 3320 / 3340 / 3360 / 3420 / 3440 and may be connected to a vehicle. Figure 3 is associated with one or more directions of travel indicated by the arrows in .

[0058] A vehicle transport network or a portion thereof (such as Figure 3 The vehicle transportation network data may be represented as a portion of the vehicle transportation network 3000 shown, for example. For example, the vehicle transportation network data may be represented as a hierarchy of elements, such as markup language elements, that may be stored in a database or file. For simplicity, the figures herein depict vehicle transportation network data representing a portion of a vehicle transportation network as a graph or map; however, the vehicle transportation network data may be represented in any computer-usable form capable of representing the vehicle transportation network or a portion thereof. The vehicle transportation network data may include vehicle transportation network control information, such as direction of travel information, rate limit information, toll information, grade information (such as incline or angle information), surface material information, aesthetic information, defined hazard information, or a combination thereof.

[0059] The vehicle transport network may be associated with or include a pedestrian transport network. For example, Figure 3 A portion 3600 of the pedestrian transport network may be included, which may be a pedestrian walkway. Figure 3 Not separately shown, but pedestrian navigable areas, such as crosswalks, may correspond to navigable areas or portions of navigable areas of the vehicle transportation network.

[0060] A portion or combination of portions of the vehicle transportation network may be identified as a point of interest or a destination. For example, the vehicle transportation network data may identify a building such as the non-navigable area 3100 and the adjacent partially navigable parking area 3200 as a point of interest, and the vehicle may identify the point of interest as a destination, and the vehicle may travel from the origin to the destination by traversing the vehicle transportation network. Figure 3 The docking area 3200 associated with the non-navigable area 3100 is shown as being adjacent to the non-navigable area 3100, but a destination may include, for example, a building and a docking area that is not physically or geographically adjacent to the building.

[0061] Identifying the destination may include identifying a location of the destination, which may be a discrete, uniquely identifiable geographic location. For example, the vehicle transportation network may include a defined location of the destination, such as a street address, postal address, vehicle transportation network address, GPS address, or a combination thereof.

[0062] A destination can be associated with one or more portals such as Figure 3 The vehicle transportation network data may include defined entry location information, such as information identifying the geographic location of the entry associated with the destination.

[0063] A destination can be associated with one or more docking locations such as Figure 3 Docking location 3700, etc., may be associated with a designated or undesignated location or area proximate to a destination where an autonomous vehicle may stop, park, or dock so that docking operations, such as passenger loading or unloading, may occur.

[0064] The vehicle transportation network data may include docking location information, such as information identifying the geographic location of one or more docking locations 3700 associated with a destination. Figure 3 Although not separately shown in the figure, the docking location information can identify the type of docking operation associated with the docking location 3700. For example, the destination can be associated with a first docking location for passenger loading and a second docking location for passenger unloading. Although the autonomous vehicle can be docked at the docking location, the docking location associated with the destination can be independent and different from the docking area associated with the destination.

[0065] Figure 4 FIG. 4 is a diagram of an example of an autonomous vehicle operation management system 4000 according to an embodiment of the present invention. The autonomous vehicle operation management system 4000 may be configured to manage an autonomous vehicle (such as a Figure 1 The vehicle 1000 shown, Figure 2 The system may be implemented in one of the vehicles 2100 / 2110 shown, a semi-autonomous vehicle, or any other vehicle that implements autonomous driving, etc.

[0066] An autonomous vehicle may traverse a vehicle transportation network or a portion thereof, which may include traversing different vehicle operating scenarios. Different vehicle operating scenarios may include any distinct set of identifiable operating conditions within a defined spatiotemporal region or operating environment of an autonomous vehicle that may affect the operation of the autonomous vehicle. For example, different vehicle operating scenarios may be based on the number or cardinality of roads, road segments, or lanes that an autonomous vehicle may traverse within a defined spatiotemporal distance. In another example, different vehicle operating scenarios may be based on one or more traffic control devices within a defined spatiotemporal region or operating environment of an autonomous vehicle that may affect the operation of an autonomous vehicle. In another example, different vehicle operating scenarios may be based on one or more identifiable rules, regulations, or laws within a defined spatiotemporal region or operating environment of an autonomous vehicle that may affect the operation of an autonomous vehicle. In another example, different vehicle operating scenarios may be based on one or more identifiable external objects within a defined spatiotemporal region or operating environment of an autonomous vehicle that may affect the operation of an autonomous vehicle.

[0067] For simplicity and clarity, similar vehicle operating scenarios may be described herein with reference to vehicle operating scenario types or categories. A type or category of vehicle operating scenario may refer to a defined pattern or set of defined patterns of a scenario. For example, an intersection scenario may include an autonomous vehicle crossing an intersection; a pedestrian scenario may include an autonomous vehicle crossing a portion of a vehicle transport network that includes or is within a defined proximity of one or more pedestrians, such as where a pedestrian is crossing or approaching the intended path of the autonomous vehicle; a lane change scenario may include an autonomous vehicle crossing a portion of the vehicle transport network by changing lanes; a merge scenario may include an autonomous vehicle crossing a portion of the vehicle transport network by merging from a first lane into a merging lane; a through an obstruction scenario may include an autonomous vehicle crossing a portion of the vehicle transport network by passing through an obstacle or obstruction. Although pedestrian vehicle operating scenarios, intersection vehicle operating scenarios, lane change vehicle operating scenarios, merge vehicle operating scenarios, and through an obstruction vehicle operating scenarios are described herein, any other vehicle operating scenario or vehicle operating scenario type may be used.

[0068] like Figure 4 As shown, the autonomous vehicle operation management system 4000 includes an autonomous vehicle operation management controller 4100 (AVOMC), an operation environment monitor 4200 and an operation control evaluation module 4300.

[0069] The AVOMC 4100 or another unit of an autonomous vehicle may control the autonomous vehicle to traverse a vehicle transportation network or a portion thereof. Controlling the autonomous vehicle to traverse the vehicle transportation network may include monitoring the autonomous vehicle's operating environment, identifying or detecting different vehicle operating scenarios, identifying candidate vehicle control actions based on the different vehicle operating scenarios, controlling the autonomous vehicle to traverse a portion of the vehicle transportation network based on one or more candidate vehicle control actions, or a combination of these operations.

[0070] The AVOMC 4100 may receive, identify, or otherwise access operating environment data representing an operating environment of an autonomous vehicle, or one or more aspects thereof. The operating environment of an autonomous vehicle may include a distinct set of identifiable operating conditions within a defined spatiotemporal region of the autonomous vehicle, within a defined spatiotemporal region of an identified route of the autonomous vehicle, or a combination thereof that may affect the operation of the autonomous vehicle. For example, operating conditions that may affect the operation of the autonomous vehicle may be identified based on sensor data, vehicle transportation network data, route data, or any other data or combination of data representing a defined or determined operating environment of the vehicle.

[0071] The operating environment data may include vehicle information for the autonomous vehicle, such as information indicating the geospatial location of the autonomous vehicle, information correlating the geospatial location of the autonomous vehicle with information representing the vehicle transportation network, the route of the autonomous vehicle, the velocity of the autonomous vehicle, the acceleration state of the autonomous vehicle, passenger information of the autonomous vehicle, or any other information related to the autonomous vehicle or the operation of the autonomous vehicle. The operating environment data may include information representing the vehicle transportation network proximate to the identified route of the autonomous vehicle, such as within a defined spatial distance (such as 300 meters, etc.) of a portion of the vehicle transportation network along the identified route, which information may include information indicating the geometry of one or more aspects of the vehicle transportation network, information indicating the condition of the vehicle transportation network (such as surface condition, etc.), or any combination thereof. The operating environment data may include information representing a vehicle transportation network in proximity to the autonomous vehicle (such as within a defined spatial distance of the autonomous vehicle (such as 300 meters, etc.)), which may include information indicating the geometry of one or more aspects of the vehicle transportation network, information indicating the condition of the vehicle transportation network (such as surface conditions, etc.), or any combination thereof. The operating environment data may include information representing external objects within the operating environment of the autonomous vehicle, such as information representing pedestrians, non-human animals, non-motorized transportation devices such as bicycles or skateboards, motorized transportation devices such as tele-vehicles, or any other external objects or entities that may affect the operation of the autonomous vehicle.

[0072] Various aspects of the autonomous vehicle's operating environment can be represented within different corresponding vehicle operating scenarios. For example, the relative orientation, trajectory, and expected path of external objects can be represented within different corresponding vehicle operating scenarios. In another example, the relative geometry of the vehicle transportation network can be represented within different corresponding vehicle operating scenarios.

[0073] As an example, a first different vehicle operation scenario may correspond to a pedestrian crossing a road at a crosswalk, and the relative orientation and intended path of the pedestrian (such as crossing from left to right or from right to left, etc.) may be represented within the first different vehicle operation scenario. A second different vehicle operation scenario may correspond to a pedestrian crossing a road without following traffic rules, and the relative orientation and intended path of the pedestrian (such as crossing from left to right or from right to left, etc.) may be represented within the second different vehicle operation scenario.

[0074] The autonomous vehicle may traverse a plurality of different vehicle operating scenarios within the operating environment, which may be aspects of a composite vehicle operating scenario. The autonomous vehicle operations management system 4000 may operate or control the autonomous vehicle to traverse the different vehicle operating scenarios subject to defined constraints, such as safety constraints, legal constraints, physical constraints, user acceptability constraints, or any other constraints or combinations of constraints that may be defined or derived for the operation of the autonomous vehicle.

[0075] The AVOMC 4100 may monitor the autonomous vehicle's operating environment or defined aspects thereof. Monitoring the autonomous vehicle's operating environment may include identifying and tracking external objects, identifying different vehicle operating scenarios, or a combination of these operations. For example, the AVOMC 4100 may utilize the autonomous vehicle's operating environment to identify and track external objects. Identifying and tracking external objects may include identifying the respective external object's possible spatiotemporal location relative to the autonomous vehicle, identifying one or more expected paths of the respective external object, which may include identifying the external object's velocity, trajectory, or both. For simplicity and clarity, descriptions herein of positions, expected positions, paths, expected paths, etc. may omit explicit indication that the respective positions and paths refer to both geospatial and temporal components; however, unless explicitly indicated herein or clear from the context, positions, expected positions, paths, expected paths, etc. described herein may include geospatial components, temporal components, or both. Monitoring the autonomous vehicle's operating environment may include using operating environment data received from the operating environment monitor 4200.

[0076] Operating environment monitors 4200 may include scenario-independent monitors, scenario-specific monitors, or a combination thereof. Scenario-independent monitors, such as obstruction monitor 4210, may monitor the autonomous vehicle's operating environment, generate operating environment data representing aspects of the autonomous vehicle's operating environment, and output the operating environment data to one or more scenario-specific monitors, AVOMC 4100, or a combination thereof. Scenario-specific monitors, such as pedestrian monitor 4220, intersection monitor 4230, lane change monitor 4240, merge monitor 4250, or forward obstruction monitor 4260, may monitor the autonomous vehicle's operating environment, generate operating environment data representing scenario-specific aspects of the autonomous vehicle's operating environment, and output the operating environment data to one or more scenario-specific operational control evaluation modules 4300, AVOMC 4100, or a combination thereof. For example, pedestrian monitor 4220 may be an operating environment monitor for monitoring pedestrians, intersection monitor 4230 may be an operating environment monitor for monitoring intersections, lane change monitor 4240 may be an operating environment monitor for monitoring lane changes, merge monitor 4250 may be an operating environment monitor for monitoring merges, and forward obstacle monitor 4260 may be an operating environment monitor for monitoring forward obstacles. The operating environment monitor 4270 is shown using dashed lines to indicate that the autonomous vehicle operation management system 4000 may include any number of operating environment monitors 4200.

[0077] The operating environment monitor 4200 can receive or otherwise access operating environment data, such as operating environment data generated or captured by one or more sensors of the autonomous vehicle, vehicle transportation network data, vehicle transportation network geometry data, route data, or a combination thereof. For example, the pedestrian monitor 4220 can receive or otherwise access information, such as sensor data, that can indicate or correspond to one or more pedestrians in the operating environment of the autonomous vehicle, or can be otherwise associated with one or more pedestrians in the operating environment of the autonomous vehicle. The operating environment monitor 4200 can associate the operating environment data, or a portion thereof, with the operating environment or an aspect thereof, such as with an external object, such as a pedestrian, a remote vehicle, or an aspect of the vehicle transportation network geometry.

[0078] The operating environment monitor 4200 may generate or otherwise identify information representing one or more aspects of the operating environment (such as external objects such as pedestrians, remote vehicles, or an aspect of the vehicle transportation network geometry), which may include filtering, extracting, or otherwise processing the operating environment data. The operating environment monitor 4200 may generate or otherwise identify information representing one or more aspects of the operating environment, such as external objects such as pedestrians, remote vehicles, or an aspect of the vehicle transportation network geometry, ... Figure 1 The operating environment monitor 4200 may output the operating environment data to one or more components of the autonomous vehicle operations management system 4000 (such as the AVOMC 4100). Although Figure 4 Not shown, but the scenario-specific operating environment monitors 4220 , 4230 , 4240 , 4250 , 4260 may output operating environment data to a scenario-independent operating environment monitor such as the blocking monitor 4210 .

[0079] The pedestrian monitor 4220 may correlate, associate, or otherwise process the operating environment data to identify, track, or predict the movements of one or more pedestrians. For example, the pedestrian monitor 4220 may receive information, such as sensor data, from one or more sensors that may correspond to one or more pedestrians, the pedestrian monitor 4220 may associate the sensor data with the identified one or more pedestrians (which may include identifying a direction of travel, such as an expected path, a current or expected speed, a current or expected acceleration rate, or a combination thereof, of the corresponding identified one or more pedestrians), and the pedestrian monitor 4220 may output the identified, associated, or generated pedestrian information to or for access by the AVOMC 4100.

[0080] The intersection monitor 4230 can correlate, associate, or otherwise process the operating environment data to identify, track, or predict the actions of one or more remote vehicles in the operating environment of the autonomous vehicle, identify intersections or aspects thereof in the operating environment of the autonomous vehicle, identify vehicle transportation network geometry, or a combination of these operations. For example, the intersection monitor 4230 may receive information such as sensor data from one or more sensors that may correspond to one or more remote vehicles in the autonomous vehicle's operating environment, intersections or one or more aspects thereof in the autonomous vehicle's operating environment, autonomous vehicle transport network geometry, or a combination thereof, and the intersection monitor 4230 may associate the sensor data with one or more remote vehicles identified in the autonomous vehicle's operating environment, intersections or one or more aspects thereof in the autonomous vehicle's operating environment, autonomous vehicle transport network geometry, or a combination thereof (which may include identifying a current or expected direction of travel of the corresponding identified one or more remote vehicles, a path such as an expected path, a current or expected speed, a current or expected acceleration rate, or a combination thereof), and the intersection monitor 4230 may output the identified, associated, or generated intersection information to the AVOMC 4100 or for access by the AVOMC 4100.

[0081] The lane change monitor 4240 can correlate, associate, or otherwise process operating environment data (such as information indicative of slow or stationary remote vehicles along the intended path of the autonomous vehicle) to identify, track, or predict the actions of one or more remote vehicles in the operating environment of the autonomous vehicle, identify one or more aspects of the operating environment of the autonomous vehicle that geospatially correspond to the lane change maneuver (such as the geometry of the vehicle transportation network in the operating environment of the autonomous vehicle), or a combination thereof. For example, the lane change monitor 4240 may receive information such as sensor data from one or more sensors that may correspond to one or more remote vehicles in the operating environment of the autonomous vehicle that geospatially corresponds to the lane change operation, one or more aspects of the operating environment of the autonomous vehicle in the operating environment of the autonomous vehicle, or a combination thereof, and the lane change monitor 4240 may associate the sensor data with the one or more remote vehicles identified in the operating environment of the autonomous vehicle that geospatially corresponds to the lane change operation, one or more aspects of the operating environment of the autonomous vehicle, or a combination thereof (which may include identifying the current or expected direction of travel of the corresponding identified one or more remote vehicles, a path such as an expected path, a current or expected speed, a current or expected acceleration rate, or a combination thereof), and the lane change monitor 4240 may output the identified, associated, or generated lane change information to the AVOMC 4100 or for access by the AVOMC 4100.

[0082] The merge monitor 4250 can correlate, associate, or otherwise process the operating environment data to identify, track, or predict the actions of one or more remote vehicles in the operating environment of the autonomous vehicle, identify one or more aspects of the operating environment of the autonomous vehicle that correspond geospatially to the merged operation (such as the geometry of the vehicle transportation network in the operating environment of the autonomous vehicle, etc.), or a combination thereof. For example, the merge monitor 4250 may receive information such as sensor data from one or more sensors that may correspond to one or more remote vehicles in the operating environment of the autonomous vehicle that geospatially corresponds to the merge operation, one or more aspects of the operating environment of the autonomous vehicle in the operating environment of the autonomous vehicle, or a combination thereof, and the merge monitor 4250 may associate the sensor data with the one or more remote vehicles identified in the operating environment of the autonomous vehicle that geospatially corresponds to the merge operation, one or more aspects of the operating environment of the autonomous vehicle, or a combination thereof (which may include identifying the current or expected direction of travel of the corresponding identified one or more remote vehicles, a path such as an expected path, a current or expected speed, a current or expected acceleration rate, or a combination thereof), and the merge monitor 4250 may output the identified, associated, or generated merge information to the AVOMC 4100 or for access by the AVOMC 4100.

[0083] The forward obstruction monitor 4260 can correlate, associate, or otherwise process the operating environment data to identify one or more aspects of the autonomous vehicle's operating environment that geospatially correspond to the proceeding past an obstruction operation. For example, the forward obstruction monitor 4260 can identify the vehicle transportation network geometry in the autonomous vehicle's operating environment; the forward obstruction monitor 4260 can identify one or more obstructions or obstacles in the autonomous vehicle's operating environment (such as slow or stationary remote vehicles along the autonomous vehicle's intended path or along an identified route for the autonomous vehicle); and the forward obstruction monitor 4260 can identify, track, or predict the movements of one or more remote vehicles in the autonomous vehicle's operating environment. The forward obstruction monitor 4260 may receive information such as sensor data from one or more sensors that may correspond to one or more remote vehicles in an operating environment that geospatially corresponds to an autonomous vehicle operating past an obstruction, one or more aspects of an autonomous vehicle's operating environment in an operating environment, or a combination thereof, and the forward obstruction monitor 4260 may associate the sensor data with one or more remote vehicles identified in an operating environment that geospatially corresponds to an autonomous vehicle operating past an obstruction, one or more aspects of an autonomous vehicle's operating environment, or a combination thereof (which may include identifying a current or expected direction of travel, a path such as an expected path, a current or expected speed, a current or expected acceleration rate, or a combination thereof, of the corresponding identified one or more remote vehicles, and the forward obstruction monitor 4260 may output the identified, associated, or generated forward obstruction information to or for access by the AVOMC 4100.

[0084] The congestion monitor 4210 may receive operating environment data representing an operating environment of the autonomous vehicle or an aspect thereof. The congestion monitor 4210 may determine a corresponding availability probability or a corresponding blocking probability for one or more portions of the vehicle transportation network (such as a portion of the vehicle transportation network proximate to the autonomous vehicle), which may include a portion of the vehicle transportation network corresponding to an expected path of the autonomous vehicle (such as an expected path identified based on the current route of the autonomous vehicle). The availability probability or the corresponding blocking probability may indicate the probability or likelihood that the autonomous vehicle can safely traverse a portion or spatial location in the vehicle transportation network (such as without being obstructed by external objects such as remote vehicles or pedestrians). The congestion monitor 4210 may determine or update the availability probability continuously or periodically. The congestion monitor 4210 may communicate the availability probability or the corresponding blocking probability to the AVOMC 4100.

[0085] AVOMC 4100 may identify one or more different vehicle operating scenarios based on one or more aspects of the operating environment represented by the operating environment data. For example, AVOMC 4100 may identify different vehicle operating scenarios in response to identifying operating environment data indicated by one or more operating environment monitors 4200 or based on operating environment data indicated by one or more operating environment monitors 4200. Different vehicle operating scenarios may be identified based on route data, sensor data, or a combination thereof. For example, AVOMC 4100 may identify one or more different vehicle operating scenarios corresponding to the identified route in response to identifying a route of the vehicle, such as based on map data corresponding to the identified route. Multiple different vehicle operating scenarios may be identified based on one or more aspects of the operating environment represented by the operating environment data. For example, the operating environment data may include information indicating a pedestrian approaching an intersection along the intended path of the autonomous vehicle, and AVOMC 4100 may identify a pedestrian vehicle operating scenario, an intersection vehicle operating scenario, or both.

[0086] AVOMC 4100 can instantiate corresponding instances of one or more operational control evaluation modules 4300 based on one or more aspects of the operating environment represented by the operating environment data. The operational control evaluation modules 4300 can include scenario-specific operational control evaluation modules (SSOCEMs), such as a pedestrian SSOCEM 4310, an intersection SSOCEM 4320, a lane change SSOCEM 4330, a merge SSOCEM 4340, a pass-through SSOCEM 4350, or combinations thereof. SSOCEM 4360 is shown with dashed lines to indicate that the autonomous vehicle operation management system 4000 can include any number of SSOCEMs 4300. For example, AVOMC 4100 can instantiate instances of SSOCEM 4300 in response to identifying different vehicle operation scenarios. AVOMC 4100 can instantiate multiple instances of one or more SSOCEMs 4300 based on one or more aspects of the operating environment represented by the operating environment data. For example, the operating environment data may indicate two pedestrians in the operating environment of the autonomous vehicle, and the AVOMC 4100 may instantiate a corresponding instance of the Pedestrian SSOCEM 4310 for each pedestrian based on one or more aspects of the operating environment represented by the operating environment data.

[0087] The AVOMC 4100 may transmit the operating environment data or one or more aspects thereof to another unit of the autonomous vehicle (such as the congestion monitor 4210, or one or more instances of the SSOCEM 4300). For example, the AVOMC 4100 may communicate the availability probability or the corresponding congestion probability received from the congestion monitor 4210 to a corresponding instantiation of the SSOCEM 4300. The AVOMC 4100 may store the operating environment data or one or more aspects thereof in a memory such as a memory of the autonomous vehicle (such as a memory). Figure 1 In the memory 1340 shown, etc.

[0088] Controlling an autonomous vehicle to traverse the vehicle transportation network may include identifying candidate vehicle control actions based on different vehicle operating scenarios, controlling the autonomous vehicle to traverse a portion of the vehicle transportation network according to one or more candidate vehicle control actions, or a combination thereof. For example, the AVOMC 4100 may receive one or more candidate vehicle control actions from a corresponding instance of the SSOCEM 4300. The AVOMC 4100 may identify a vehicle control action from the candidate vehicle control actions and may control the vehicle according to the vehicle control action, or may provide the identified vehicle control action to another vehicle control unit to traverse the vehicle transportation network.

[0089] The vehicle control action may indicate a vehicle control operation or maneuver, such as accelerating, decelerating, turning, stopping, or any other vehicle operation or combination of vehicle operations that an autonomous vehicle may perform while traversing a portion of a vehicle transportation network. For example, a "forward" vehicle control action may include slowly jogging forward a short distance (such as a few inches or a foot); an "accelerate" vehicle control action may include accelerating at a defined acceleration rate or an acceleration rate within a defined range; a "decelerate" vehicle control action may include decelerating at a defined deceleration rate or a deceleration rate within a defined range; a "maintain" vehicle control action may include maintaining current operating parameters, such as by maintaining a current speed, a current path or route, or a current lane orientation; and a "continue" vehicle control action may include starting or resuming a previously identified set of operating parameters. Although some vehicle control actions are described herein, other vehicle control actions may also be used.

[0090] A vehicle control action may include one or more performance metrics. For example, a "stop" vehicle control action may include a deceleration rate as a performance metric. In another example, a "forward" vehicle control action may explicitly indicate route or path information, velocity information, acceleration rate, or a combination thereof as a performance metric, or may explicitly or implicitly indicate that a current or previously identified path, velocity, acceleration rate, or a combination thereof may be maintained. A vehicle control action may be a compound vehicle control action, which may include a sequence, combination, or both of vehicle control actions. For example, a "forward" vehicle control action may indicate a "stop" vehicle control action, a subsequent "accelerate" vehicle control action associated with a defined acceleration rate, and a subsequent "stop" vehicle control action associated with a defined deceleration rate, such that controlling the autonomous vehicle according to the "forward" vehicle control action includes controlling the autonomous vehicle to slowly incline forward a short distance (such as a few inches or a foot, etc.).

[0091] AVOMC 4100 may de-instantiate an instance of SSOCEM 4300. For example, AVOMC 4100 may identify different sets of operating conditions as indicative of different vehicle operating scenarios for an autonomous vehicle, instantiate instances of SSOCEM 4300 for the different vehicle operating scenarios, monitor the operating conditions, and then determine that one or more operating conditions have expired or have a probability of impacting operation of the autonomous vehicle below a defined threshold, and AVOMC 4100 may de-instantiate an instance of SSOCEM 4300.

[0092] The AVOMC 4100 can instantiate and de-instantiate instances of the SSOCEM 4300 based on one or more vehicle operations management control metrics, such as an intrinsicness metric, an urgency metric, a utility metric, an acceptability metric, or a combination thereof. The intrinsicness metric can indicate, represent, or be based on the spatial, temporal, or spatiotemporal distance or proximity (which can be an expected distance or proximity) for a vehicle to traverse the vehicle transportation network from its current location to the portion of the vehicle transportation network corresponding to the corresponding identified vehicle operation scenario. The urgency metric can indicate, represent, or be based on a measure of the spatial, temporal, or spatiotemporal distance that can be used to control the vehicle to traverse the portion of the vehicle transportation network corresponding to the corresponding identified vehicle operation scenario. The utility metric can indicate, represent, or be based on an expected value for instantiating an instance of the SSOCEM 4300 corresponding to the corresponding identified vehicle operation scenario. The acceptability metric can be a safety metric such as a metric indicating collision avoidance, a vehicle transportation network control compliance metric such as a metric indicating compliance with vehicle transportation network rules and regulations, a physical capability metric such as a metric indicating the maximum braking capability of the vehicle, or a user-defined metric such as a user preference. Other metrics or combinations of metrics can be used. The vehicle operation management control metric can indicate a defined rate, range, or limit. For example, the acceptability metric can indicate a defined target deceleration rate, a defined deceleration rate range, or a defined maximum deceleration rate.

[0093] SSOCEM 4300 may include one or more models corresponding to different vehicle operation scenarios. Autonomous vehicle operation management system 4000 may include any number of SSOCEMs 4300, each including a model corresponding to a different vehicle operation scenario. SSOCEM 4300 may include one or more models from one or more types of models. For example, SSOCEM 4300 may include a partially observable Markov decision process (POMDP) ​​model, a Markov decision process (MDP) model, a classical planning model, a partially observable stochastic game (POSG) model, a decentralized partially observable Markov decision process (Dec-POMDP) ​​model, a reinforcement learning (RL) model, an artificial neural network model, or any other model for different vehicle operation scenarios. Each different type of model may have corresponding characteristics with respect to accuracy and resource utilization. For example, a scenario-defining POMDP model may have greater accuracy and greater resource utilization than a scenario-defining MDP model. The models included in SSOCEM 4300 may be ranked, for example, in a hierarchical order based on accuracy. For example, a designated model, such as the most accurate model included in the SSOCEM 4300, may be identified as a primary model of the SSOCEM 4300, and other models included in the SSOCEM 4300 may be identified as secondary models.

[0094] In an example, one or more SSOCEM 4300 may include a POMDP model, which may be a single agent model. The POMDP model may model different vehicle operation scenarios, which may include modeling uncertainty using a state set (S), an action set (A), an observation set (Ω), a state transition probability set (T), a conditional observation probability set (O), a reward function (R), or a combination thereof. The POMDP model may be defined or described as a tuple<S,A,Ω,T,O,R> .

[0095] The states in the state set (S) can represent different conditions of corresponding defined aspects of the operating environment of the autonomous vehicle (such as external objects and traffic control devices, etc.), which may probabilistically affect the operation of the autonomous vehicle at discrete time locations. A corresponding state set (S) can be defined for each different vehicle operating scenario. Each state (state space) in the state set (S) can include one or more defined state factors. Although some examples of state factors for some models are described here, the models including any model described here can include any number or cardinality of state factors. Each state factor can represent a defined aspect of the corresponding scenario and can have a corresponding set of defined values. Although some examples of state factor values ​​for some state factors are described here, the state factors including any state factors described here can include any number or cardinality of values.

[0096] The actions in the action set (A) can indicate available vehicle control actions in each state in the state set (S). Corresponding action sets can be defined for different vehicle operating scenarios. Each action (action space) in the action set (A) can include one or more defined action factors. Although some examples of action factors for some models are described here, the models including any model described here can include any number or cardinality of action factors. Each action factor can represent an available vehicle control action and can have a corresponding set of defined values. Although some examples of action factor values ​​for some action factors are described here, the action factors including any action factors described here can include any number or cardinality of values.

[0097] The observations in the observation set (Ω) can indicate available observable, measurable or determinable data for each state in the state set (S). A corresponding observation set can be defined for each different vehicle operating scenario. Each observation (observation space) in the observation set (Ω) can include one or more defined observation factors. Although some examples of observation factors for some models are described here, the models including any models described here can include any number or cardinality of observation factors. Each observation factor can represent an available observation and can have a corresponding set of defined values. Although some examples of observation factor values ​​for some observation factors are described here, the observation factors including any observation factors described here can include any number or cardinality of values.

[0098] The state transition probabilities in the state transition probability set (T) can probabilistically represent changes in the operating environment of the autonomous vehicle (as represented by the state set (S)) in response to the actions of the autonomous vehicle (as represented by the action set (A)), which can be expressed as T: S×A×S→[0,1]. A corresponding state transition probability set (T) can be defined for each different vehicle operation scenario. Although some examples of state transition probabilities for some models are described herein, models including any of the models described herein can include any number or cardinality of state transition probabilities. For example, each combination of a state, an action, and a subsequent state can be associated with a corresponding state transition probability.

[0099] The conditional observation probabilities in the conditional observation probability set (O) can represent the probability of making a corresponding observation (Ω) in response to the action of the autonomous vehicle (as represented by the action set (A)) and based on the operating environment of the autonomous vehicle (as represented by the state set (S)), which can be expressed as O:A×S×Ω→[0,1]. A corresponding conditional observation probability set (O) can be defined for each different vehicle operation scenario. Although some examples of state conditional observation probabilities of some models are described here, models including any model described herein can include any number or cardinality of conditional observation probabilities. For example, each combination of action, subsequent state, and observation can be associated with a corresponding conditional observation probability.

[0100] The reward function (R) may determine the corresponding positive or negative (cost) value that may be accumulated for each combination of state and action, which may represent the expected value of the autonomous vehicle moving from the corresponding state through the vehicle transportation network to the subsequent state according to the corresponding vehicle control action, which may be expressed as

[0101] For simplicity and clarity, examples of model values ​​(such as state factor values ​​or observation factor values) described herein include categorical representations, such as {start, target} or {short, long}. Categorical values ​​can represent defined discrete values, which can be relative values. For example, a state factor representing a temporal aspect can have values ​​from the set {short, long}; the value "short" can represent a discrete value, such as a temporal distance, that is within or less than a defined threshold (such as 3 seconds), while the value "long" can represent a discrete value, such as a temporal distance, that is at least (such as equal to or greater than) a defined threshold. Defined thresholds for corresponding categorical values ​​can be defined relative to related factors. For example, a defined threshold for the temporal factor set {short, long} can be associated with a relative spatial position factor value, and another defined threshold for the temporal factor set {short, long} can be associated with another relative spatial position factor value. Although categorical representations of factor values ​​are described herein, other representations or combinations of representations can be used. For example, a temporal state factor value set can be {short (representing values ​​less than 3 seconds), 4, 5, 6, long (representing values ​​at least 7 seconds)}.

[0102] In some embodiments (such as those implementing the POMDP model), modeling the autonomous vehicle operational control scenario can include modeling occluders. For example, the operational environment data can include information corresponding to one or more occluders (such as sensor occluders) in the autonomous vehicle's operational environment, such that the operational environment data can omit information representing one or more obscured external objects in the autonomous vehicle's operational environment. For example, an occluder can be an external object such as a traffic sign, a building, a tree, or the like, an identified external object, or any other operational condition or combination of operational conditions that can obscure one or more other operational conditions, such as an external object, relative to the autonomous vehicle at a defined spatiotemporal location. In some embodiments, the operational environment monitor 4200 can identify occluders, can identify or determine a probability that an external object is obscured or hidden by the identified occluder, and can include the vehicle obscuration probability information in the operational environment data output to the AVOMC 4100 and communicated by the AVOMC 4100 to the corresponding SSOCEM 4300.

[0103] Autonomous vehicle operation management system 4000 can include any number of model types or combinations of model types. For example, pedestrian SSOCEM 4310, intersection SSOCEM 4320, lane change SSOCEM 4330, merge SSOCEM 4340, and obstacle passing SSOCEM 4350 can be POMDP models. In another example, pedestrian SSOCEM 4310 can be an MDP model, and intersection SSOCEM 4320 can be a POMDP model. AVOMC 4100 can instantiate any number of SSOCEM 4300 instances based on operational environment data.

[0104] Instantiating an instance of SSOCEM 4300 may include identifying a model from SSOCEM 4300 and instantiating an instance of the identified model. For example, SSOCEM 4300 may include a primary model and secondary models for respective different vehicle operation scenarios, and instantiating SSOCEM 4300 may include identifying the primary model as the current model and instantiating an instance of the primary model. Instantiating a model may include determining whether a solution or strategy is available for the model. Instantiating a model may include determining whether available solutions or strategies for the model are partially solved or converged and solved. Instantiating SSOCEM 4300 may include instantiating an instance of the solution or strategy of the identified model of SSOCEM 4300.

[0105] Solving a model such as a POMDP model may include determining a strategy or solution that can be used to define a model by evaluating a tuple such as<S,A,Ω,T,O,R> ) is a function that maximizes the cumulative reward determined by the possible combinations of elements of a model. A strategy or solution can identify or output a reward-maximizing or optimal candidate vehicle control action based on the identified belief state data. The identified belief state data (which may be probabilistic) can indicate current state data (such as the current state value set of the corresponding model or the probability of the current state value set) and can correspond to the corresponding relative time position. For example, solving the MDP model may include identifying a state from a state set (S), identifying an action from an action set (A), and determining a subsequent or successor state from the state set (S) after simulating the action subject to the state transition probability. Each state can be associated with a corresponding utility value, and solving the MDP model may include determining the corresponding utility value corresponding to each possible combination of state, action, and subsequent state. The utility value of the subsequent state can be identified as the maximum identified utility value subject to a reward or penalty (which may be a discounted reward or penalty). The strategy can indicate the action corresponding to the maximum utility value of the corresponding state. Solving a POMDP model can be similar to solving an MDP model, except that it is based on belief states, which represent the probabilities of the corresponding states and are subject to the observation probabilities corresponding to the observations that generated the corresponding states. Thus, solving an SSOCEM model involves evaluating possible state-action-state transitions based on the corresponding actions and observations, such as using Bayes' rule, and updating the corresponding belief states.

[0106] In some implementations, a model such as an MDP model or a POMDP model can reduce resource utilization associated with solving the corresponding model by evaluating the states, belief states, or both modeled therein to identify computations corresponding to the corresponding states, belief states, or both that can be omitted, and omitting the identified computations. This can include obtaining or maintaining a measure of current quality, such as upper and lower bounds on the utility of the corresponding states, belief states, or both. In some implementations, solving the model can include parallel processing, such as using multiple processor cores or using multiple processors, where the multiple processors can include a graphics processing unit (GPU). In some implementations, solving the model can include obtaining an approximation of the model, which can improve the efficiency of solving the model.

[0107] Figure 5 is a flow chart of an example of autonomous vehicle operation management 5000 according to an embodiment of the present invention. Autonomous vehicle operation management 5000 may be performed on an autonomous vehicle such as Figure 1 The vehicle 1000 shown, Figure 22100 / 2110, a semi-autonomous vehicle, or any other vehicle that implements autonomous driving, etc. For example, an autonomous vehicle may implement an autonomous vehicle operations management system (such as Figure 4 The autonomous vehicle operation management system 4000 shown, etc.)

[0108] like Figure 5 As shown, autonomous vehicle operations management 5000 includes implementing or operating an autonomous vehicle operations management system (including one or more modules or components of an autonomous vehicle operations management system), which may include: operating an autonomous vehicle operations management controller (AVOMC) 5100 (such as Figure 4 AVOMC 4100 shown, etc.); operating operating environment monitor 5200 (such as Figure 4 One or more operating environment monitors 4300 shown, etc.); and an operating scenario specific operating control evaluation module instance (SSOCEM instance) 5300 (such as Figure 4 SSOCEM 4300 example shown, etc.).

[0109] The AVOMC 5100 may monitor the autonomous vehicle's operating environment, or defined aspects thereof, at 5110 to identify the autonomous vehicle's operating environment, or an aspect thereof. For example, the operating environment monitor 5200 may monitor scenario-specific aspects of the operating environment and may send operating environment data representing the operating environment to the AVOMC 5100. Monitoring the autonomous vehicle's operating environment may include identifying and tracking external objects at 5110, identifying different vehicle operating scenarios at 5120, or a combination thereof. For example, the AVOMC 5100, the operating environment monitor 5200, or both may identify the operating environment data based on sensor data, vehicle data, route data, vehicle transportation network data, previously identified operating environment data, or any other available data or combination of data describing one or more aspects of the operating environment.

[0110] Identifying the operating environment may include identifying operating environment data representing the operating environment or one or more aspects thereof. The operating environment data may include vehicle information of the autonomous vehicle, information representing a vehicle transportation network or one or more aspects thereof, proximity to the autonomous vehicle, information representing external objects within the operating environment of the autonomous vehicle along or near a route identified for the autonomous vehicle or one or more aspects thereof, or a combination thereof. The sensor information may be processed sensor information, such as processed sensor information from a sensor information processing unit of the autonomous vehicle, where the sensor information processing unit may receive sensor information from sensors of the autonomous vehicle and may generate processed sensor information based on the sensor information.

[0111] Identifying operating environment data may include obtaining data from sensors of the autonomous vehicle, such as Figure 1 The sensor 1360 shown or Figure 2 The onboard sensors 2105 shown, etc.) receive information indicative of one or more aspects of the operating environment. The sensors of the autonomous vehicle or another unit may store the sensor information in a memory of the autonomous vehicle (such as Figure 1 The AVOMC 5100 reads the sensor information from the memory 1340, etc. shown in the figure.

[0112] Identifying the operating environment data may include identifying information indicative of one or more aspects of the operating environment from the vehicle transportation network data. For example, the AVOMC 5100 may read or otherwise receive vehicle transportation network data indicating that the autonomous vehicle is approaching an intersection, or otherwise describing the geometry or configuration of the vehicle transportation network in proximity to the autonomous vehicle (such as within 300 meters of the autonomous vehicle).

[0113] Identifying the operating environment data at 5110 may include identifying information indicative of one or more aspects of the operating environment from a remote vehicle or other remote device located external to the autonomous vehicle. For example, the autonomous vehicle may receive a remote vehicle message from the remote vehicle via a wireless electronic communication link, the remote vehicle message including remote vehicle information indicative of remote vehicle geospatial state information of the remote vehicle, remote vehicle kinematic state information of the remote vehicle, or both.

[0114] Identifying the operating environment data may include identifying information indicative of one or more aspects of the operating environment from route data representing an identified route of the autonomous vehicle. For example, the AVOMC 5100 may read or otherwise receive vehicle transportation network data representing an identified route of the autonomous vehicle (such as a route identified in response to user input, etc.).

[0115] AVOMC 5100 and operating environment monitor 5200 may communicate to identify operating environment information as indicated by 5110, 5112, and 5210. Alternatively or in addition, operating environment monitor 5200 may receive operating environment data from another component of the autonomous vehicle (such as from a sensor of the autonomous vehicle or from another operating environment monitor 5200), or operating environment monitor 5200 may read operating environment data from a memory of the autonomous vehicle.

[0116] The AVOMC 5100 may detect or identify one or more different vehicle operating scenarios at 5120 , such as based on one or more aspects of the operating environment represented by the operating environment data identified at 5110 .

[0117] AVOMC 5100 may instantiate SSOCEM instance 5300 based on one or more aspects of the operating environment represented by the operating environment data at 5130, such as in response to identifying different vehicle operating scenarios at 5120. Figure 5 5100, the AVOMC 5100 may instantiate multiple SSOCEM instances 5300 based on one or more aspects of the operating environment represented by the operating environment data identified at 5110, each SSOCEM instance 5300 corresponding to a respective different vehicle operating scenario detected at 5120, or a combination of a different external object identified at 5110 and a respective different vehicle operating scenario detected at 5120. Instantiating the SSOCEM instance 5300 at 5130 may include sending the operating environment data representing the operating environment of the autonomous vehicle to the SSOCEM instance 5300 as indicated at 5132. The SSOCEM instance 5300 may receive the operating environment data representing the operating environment of the autonomous vehicle or one or more aspects thereof at 5310. Instantiating the SSOCEM instance 5300 at 5130 may include identifying models (such as a primary model or a secondary model, etc.) for different vehicle operating scenarios, instantiating instances of the models, identifying solutions or strategies corresponding to the models, instantiating instances of the solutions or strategies, or a combination of these operations.

[0118] The operating environment monitor 5200 may include a blocking monitor such as Figure 4The congestion monitor 4210 shown, etc.) can determine a corresponding probability of availability (POA) or a corresponding probability of congestion at 5220 for one or more portions of the vehicle transportation network (such as a portion of the vehicle transportation network that is proximate to the autonomous vehicle), which can include a portion of the vehicle transportation network corresponding to an expected path of the autonomous vehicle (such as an expected path identified based on the current route of the autonomous vehicle). The congestion monitor can send the available probability identified at 5220 to the SSOCEM instance 5300 at 5222. Alternatively or in addition, the congestion monitor can store the available probability identified at 5220 in a memory of the autonomous vehicle. Although not in Figure 5 5220 , but in addition to or in lieu of sending the available probabilities to the SSOCEM instance 5300 , the congestion monitor may also send the available probabilities identified at 5220 to the AVOMC 5100 at 5222 . The SSOCEM instance 5300 may receive the available probabilities at 5320 .

[0119] The SSOCEM instance 5300 may generate or identify candidate vehicle control actions at 5330. For example, the SSOCEM instance 5300 may generate or identify candidate vehicle control actions at 5330 in response to receiving the operating environment data at 5310, receiving the available probability data at 5320, or both. For example, an instance of a solution or strategy instantiated at 5310 for a model of different vehicle operating scenarios may output candidate vehicle control actions based on the operating environment data, the available probability data, or both. The SSOCEM instance 5300 may send the candidate vehicle control actions identified at 5330 to the AVOMC 5100 at 5332. Alternatively or in addition, the SSOCEM instance 5300 may store the candidate vehicle control actions identified at 5330 in a memory of the autonomous vehicle.

[0120] The AVOMC 5100 may receive the candidate vehicle control action at 5140. For example, the AVOMC 5100 may receive the candidate vehicle control action at 5140 from the SSOCEM instance 5300. Alternatively or additionally, the AVOMC 5100 may read the candidate vehicle control action from a memory of the autonomous vehicle.

[0121] The AVOMC 5100 may approve or otherwise identify the candidate vehicle control action as a vehicle control action for controlling the autonomous vehicle through the vehicle transportation network at 5150. Approving the candidate vehicle control action at 5150 may include determining whether to traverse a portion of the vehicle transportation network based on the candidate vehicle control action.

[0122] The AVOMC 5100 may control the autonomous vehicle at 5160 based on the vehicle control action identified at 5150 or may provide the identified vehicle control action to another vehicle control unit to cause the autonomous vehicle to traverse the vehicle transportation network or a portion thereof.

[0123] The AVOMC 5100 may identify the operating environment of the autonomous vehicle, or an aspect thereof, at 5170. Identifying the operating environment of the autonomous vehicle, or an aspect thereof, at 5170 may be similar to identifying the operating environment of the autonomous vehicle at 5110 and may include updating previously identified operating environment data.

[0124] AVOMC 5100 may determine or detect whether different vehicle operating scenarios have been resolved or not resolved at 5180. For example, as described above, AVOMC 5100 may continuously or periodically receive operating environment information. AVOMC 5100 may evaluate the operating environment data to determine whether different vehicle operating scenarios have been resolved.

[0125] The AVOMC 5100 may determine at 5180 that a different vehicle operating scenario corresponding to the SSOCEM instance 5300 is unresolved, the AVOMC 5100 may send the operating environment data identified at 5170 to the SSOCEM instance 5300 as indicated at 5185, and de-instantiating the SSOCEM instance 5300 at 5180 may be omitted or different.

[0126] The AVOMC 5100 may determine at 5180 that different vehicle operation scenarios have been resolved, and may de-instantiate at 5190 the SSOCEM instances 5300 corresponding to the different vehicle operation scenarios determined to have been resolved at 5180. For example, the AVOMC 5100 may identify at 5120 different sets of operating conditions that form different vehicle operation scenarios for the autonomous vehicle, may determine at 5180 that one or more operating conditions have expired or have a probability of affecting the operation of the autonomous vehicle below a defined threshold, and may de-instantiate the corresponding SSOCEM 5300 instances.

[0127] Despite Figure 5Not explicitly shown, but the AVOMC 5100 can continuously or periodically repeatedly identify or update the operating environment data at 5170, determine whether the different vehicle operating scenarios are resolved at 5180, and send the operating environment data identified at 5170 to the SSOCEM instance 5300 as indicated at 5185 in response to determining at 5180 that the different vehicle operating scenarios are not resolved, until determining at 5180 whether the different vehicle operating scenarios are resolved includes determining that the different vehicle operating scenarios are resolved.

[0128] Figure 6 is a flow chart illustrating an example of autonomous vehicle operation management using shared scenario-specific operation control management data communication 6000 according to an embodiment of the present invention. Autonomous vehicle operation management using shared scenario-specific operation control management data communication 6000 may be performed on autonomous vehicles such as Figure 1 The vehicle 1000 shown, Figure 2 2100 / 2110, a semi-autonomous vehicle, or any other vehicle that implements autonomous driving, etc. For example, an autonomous vehicle may implement an autonomous vehicle operations management system (such as Figure 4 Specific operational control management data communication 6000 according to an embodiment of the present invention. Autonomous vehicle operation management using shared scenario-specific operational control management data communication 6000 can be used in conjunction with other autonomous vehicle operation management systems except as described herein or otherwise clear from the context. Figure 5 The same as shown is the autonomous vehicle operation management 5000.

[0129] like Figure 6 As shown, autonomous vehicle operations management utilizing shared scenario specific operations control management data communications 6000 includes the autonomous vehicle implementing or operating an autonomous vehicle operations management system 6100 (including one or more modules or components of the autonomous vehicle operations management system), which may include: operating an AVOMC 6200 (such as Figure 4 AVOMC 4100 or Figure 5 AVOMC 5100 shown, etc.); operating an operating environment monitor (not shown); and operating an SSOCEM instance 6300 (such as Figure 4 SSOCEM 4300 example shown, etc.).

[0130] The AVOMC 6200 may communicate shared scenario-specific operation control management data with the external shared scenario-specific operation control management system 6400. Communicating the shared scenario-specific operation control management data with the external shared scenario-specific operation control management system 6400 may include: transmitting or sending the shared scenario-specific operation control management data or a portion thereof to the external shared scenario-specific operation control management system 6400; receiving the shared scenario-specific operation control management data or a portion thereof from the external shared scenario-specific operation control management system 6400; or a combination of transmitting or sending a corresponding portion of the shared scenario-specific operation control management data to the external shared scenario-specific operation control management system 6400 and receiving a corresponding portion of the shared scenario-specific operation control management data from the external shared scenario-specific operation control management system 6400.

[0131] The autonomous vehicle operation management system 6100 may operate in an inactive or stationary mode, such as when parked or charging, etc. Operating in an inactive mode may include communicating shared scenario-specific operation control management data with an external shared scenario-specific operation control management system 6400 as indicated at 6202 .

[0132] Communicating shared scenario-specific operation control management data with the external shared scenario-specific operation control management system 6400 in an inactive mode as indicated by 6202 may include the AVOMC 6200 receiving shared scenario-specific operation control management data from the external shared scenario-specific operation control management system 6400. The shared scenario-specific operation control management data may include solution or strategy data, experience data, or both for one or more different vehicle operation scenarios. The AVOMC 6200 may receive the shared scenario-specific operation control management data as a push notification based on a system update or based on a vehicle transportation network information update, etc.

[0133] Communicating shared scenario-specific operational control management data with the external shared scenario-specific operational control management system 6400 in an inactive mode as indicated at 6202 may include the AVOMC 6200 receiving a request for shared scenario-specific operational control management data from the external shared scenario-specific operational control management system 6400, the shared scenario-specific operational control management data may include solutions or strategy data, experience data, or both for one or more identified different vehicle operational scenarios. The request may include information identifying the different vehicle operational scenarios.

[0134] Communicating shared scenario-specific operational control management data with the external shared scenario-specific operational control management system 6400 in an inactive mode, as indicated at 6202, may include the AVOMC 6200 transmitting or sending shared scenario-specific operational control management data to the external shared scenario-specific operational control management system 6400, the shared scenario-specific operational control management data including recently generated (e.g., not previously sent) solution or strategy data, experience data, or both for one or more different vehicle operating scenarios. The AVOMC 6200 may send the shared scenario-specific operational control management data automatically (e.g., periodically, in response to an event, or both). For example, the AVOMC 6200 may send the shared scenario-specific operational control management data for different vehicle operating scenarios to the external shared scenario-specific operational control management system 6400 in response to receiving a request for the shared scenario-specific operational control management data for different vehicle operating scenarios from the external shared scenario-specific operational control management system 6400. In another example, the AVOMC 6200 may transmit the most recently generated shared scenario specific operation control management data to the external shared scenario specific operation control management system 6400 while charging.

[0135] The autonomous vehicle operation management system 6100 can operate in an active mode, such as in response to powering on, starting up, or receiving information indicating a current destination (such as in response to user input). Operating in the active mode can include monitoring the autonomous vehicle's operating environment at 6210, detecting different vehicle operation scenarios at 6220, communicating with an external shared scenario-specific operation control management system 6400 at 6230, instantiating an SSOCEM instance 6300 at 6240, traversing a vehicle transportation network at 6250, identifying the autonomous vehicle's operating environment at 6260, determining whether different vehicle operation scenarios are resolved at 6270, de-instantiating the SSOCEM instance 6300 at 6280, and communicating with the external shared scenario-specific operation control management system 6400 at 6290.

[0136] The AVOMC 6200 can monitor the operating environment of the autonomous vehicle, or defined aspects thereof, at 6210 to identify the operating environment of the autonomous vehicle, or an aspect thereof. For example, an operating environment monitor can monitor scenario-specific aspects of the operating environment and can send operating environment data representing the operating environment to the AVOMC 6200. Identifying the operating environment data can include identifying information indicative of one or more aspects of the operating environment from route data representing an identified route of the autonomous vehicle. For example, the AVOMC 6200 can read or otherwise receive vehicle transportation network data representing an identified route of the autonomous vehicle (such as a route identified in response to user input, etc.).

[0137] In another example, the AVOMC 6200 may receive information indicating a current destination, such as in response to a user input, and may send the information indicating the current destination to the external shared scenario-specific operation control management system 6400 as indicated at 6212. In some implementations, the AVOMC 6200 may receive information indicating a route from the current location of the autonomous vehicle to the destination from the external shared scenario-specific operation control management system 6400 as indicated at 6212.

[0138] In another example, the AVOMC 6200 may receive information indicating a current destination, such as in response to user input, the AVOMC 6200 may determine a route from the current location of the autonomous vehicle to the destination, and may send the information indicating the route to the external shared scenario-specific operation control management system 6400 as indicated by 6212.

[0139] The AVOMC 6200 may detect or identify one or more different vehicle operating scenarios at 6220. For example, the AVOMC 6200 may detect or identify one or more different vehicle operating scenarios at 6220 based on one or more aspects of the operating environment represented by the operating environment data identified at 6210. The AVOMC 6200 may send information indicating the different vehicle operating scenarios to the external shared scenario-specific operational control management system 6400 as indicated at 6222.

[0140] In another example, the AVOMC 6200 may receive information indicating different vehicle operating scenarios from the external shared scenario-specific operational control management system 6400 as indicated at 6222 .

[0141] Communicating shared scenario-specific operation control management data with an external shared scenario-specific operation control management system 6400 at 6230 may include transmitting or sending the shared scenario-specific operation control management data or a part thereof (such as a shared scenario-specific operation control management planning data part, etc.) to the external shared scenario-specific operation control management system 6400 at 6230.

[0142] Sending the shared scenario-specific operational control management plan data portion to the external shared scenario-specific operational control management system 6400 may include sending a shared scenario-specific operational control management plan data request to the external shared scenario-specific operational control management system 6400. The shared scenario-specific operational control management plan data request may indicate a request for shared scenario-specific operational control management plan data (such as policy data, experience data, or a combination thereof) corresponding to one or more different vehicle operational scenarios identified at 6220. The autonomous vehicle operation management system 6100 may send the shared scenario-specific operational control management plan data request at other times, such as shown at 6202, or in response to receiving input, such as user input, to initiate the request.

[0143] Experience, history, or experience data may include state data, belief data, action data, observation data, or any combination thereof generated, identified, or determined based on operating the autonomous vehicle. Experience data may include temporal information, such as temporal information that identifies the experience data as a time series.

[0144] Communicating the shared scenario-specific operational control management data with the external shared scenario-specific operational control management system 6400 at 6230 can include transmitting or sending a portion of the shared scenario-specific operational control management data to the external shared scenario-specific operational control management system 6400, the shared scenario-specific operational control management data portion including solution or strategy data, experience data, or both corresponding to different vehicle operational scenarios. For example, the autonomous vehicle operations management system 6100 can identify previously generated solutions or strategies, previously generated experience data, or both corresponding to the different vehicle operational scenarios identified at 6220, and the autonomous vehicle operations management system 6100 can send the portion of the shared scenario-specific operational control management data including the previously generated data to the external shared scenario-specific operational control management system 6400 at 6230.

[0145] The shared scenario-specific operational control management data portion may include privacy-protected data. For example, the shared scenario-specific operational control management data portion may include empirical data such as belief data, action data, and vehicle operational scenario type data, and may omit user or vehicle identification data. In some implementations, geospatial data, temporal data, or both may be included in the shared scenario-specific operational control management data portion.

[0146] Communicating shared scenario-specific operation control management data with the external shared scenario-specific operation control management system 6400 at 6230 may include receiving the shared scenario-specific operation control management data or a portion thereof (such as a received shared scenario-specific operation control management data portion) from the external shared scenario-specific operation control management system 6400. For example, the autonomous vehicle operation management system 6100 may receive the received shared scenario-specific operation control management data portion as a response to a request to send shared scenario-specific operation control management planning data, or the autonomous vehicle operation management system 6100 may receive the received shared scenario-specific operation control management data portion as a push notification, which may correspond to an autonomous vehicle system update or a vehicle transportation network data distribution.

[0147] Communicating shared scenario specific operation control management data with the external shared scenario specific operation control management system 6400 at 6230 may include receiving a received shared scenario specific operation control management data request portion from the external shared scenario specific operation control management system 6400. The received shared scenario specific operation control management data request may indicate different vehicle operation scenarios, and a request for solution or strategy data, experience data, or both corresponding to the identified different vehicle operation scenarios. The received shared scenario specific operation control management data request may be received in response to transmitting or sending the shared scenario specific operation control management data to the external shared scenario specific operation control management system 6400 at 6230. Although Figure 6 Not explicitly shown, but the received shared scenario-specific operational control management data request can be received by the autonomous vehicle operation management system 6100 independently of detecting the defined vehicle operation scenario at 6220.

[0148] Receiving shared scenario-specific operation control management data from the external shared scenario-specific operation control management system 6400 may include determining whether a portion of the received shared scenario-specific operation control management data includes malicious data. Determining whether the received portion of the shared scenario-specific operation control management data includes malicious data may include determining a probability that the received portion of the shared scenario-specific operation control management data includes malicious data, and determining whether the probability that the received portion of the shared scenario-specific operation control management data includes malicious data exceeds a defined security threshold.

[0149] The received shared scenario-specific operational control management data portion may include a solution or strategy for the model of the different vehicle operational scenarios identified at 6220, and determining whether the received shared scenario-specific operational control management data portion includes malicious data may include validating the solution or strategy.

[0150] Verifying a solution or strategy may include evaluating the data indicated in the solution or strategy based on relevant defined metrics. For example, a solution or strategy may include a utility value associated with a corresponding belief state, and verifying the solution or strategy may include determining whether the utility value is within a corresponding defined range (such as whether it is greater than or equal to a defined minimum threshold and less than or equal to a defined maximum threshold) for the corresponding belief state. In another example, a solution or strategy may include action data (such as an index or unique identifier associated with an available action), and verifying the solution or strategy may include determining whether the action data is valid. For example, a model may include three available actions (which may have action index values ​​0, 1, and 2, respectively), and action data with action index values ​​0, 1, and 2 in the solution or strategy may be identified as valid action data, and action data with action index values ​​other than 0, 1, and 2 in the solution or strategy may be identified as invalid. In another example, a solution or strategy may include state data (such as an index or unique identifier associated with an available state), and verifying the solution or strategy may include determining whether the state data is valid, which may be similar to verifying the action data. In another example, a solution or policy may include belief state data (such as an index or unique identifier associated with an available belief state, etc.), and verifying the solution or policy may include determining whether the belief state data is valid, which may be similar to verifying the action data. In another example, a solution or policy may include observation data (such as an index or unique identifier associated with an available observation, etc.), and verifying the solution or policy may include determining whether the observation data is valid, which may be similar to verifying the action data.

[0151] The solution or strategy may include belief data, and verifying the solution or strategy may include verifying the belief data. For example, the received belief data may be verified by determining corresponding calculated belief data based on the state transition probabilities and observation probabilities corresponding to the received belief data. Received belief data that differs from the calculated belief data may be identified as invalid or malicious data.

[0152] Verifying a solution or policy may include determining whether the policy indicates an action corresponding to a corresponding belief state with a corresponding penalty or negative reward exceeding a defined threshold. A policy indicating an action with a penalty exceeding the relevant defined threshold may be identified as invalid or malicious data.

[0153] Validating a solution or policy may include evaluating the policy based on one or more defined conditions. The defined conditions may explicitly identify a state or belief state and may indicate one or more invalid actions associated with the identified state or belief state. For example, the defined conditions may indicate that the state data indicates that an obstacle is blocking the path of the autonomous vehicle and may indicate an acceleration action as an invalid action. A policy indicating an action identified as an invalid action under the defined conditions may be identified as invalid or malicious data.

[0154] Validating a solution or strategy may include evaluating the strategy based on one or more spatial constraints. For example, a belief state indicated in the strategy may correspond to a first relative spatial position of the vehicle and corresponding operating conditions (such as trajectory and velocity information of the vehicle), and a subsequent belief state indicated in the strategy may correspond to a second relative spatial position of the vehicle, and evaluating the strategy based on the spatial constraints may include determining whether a difference between the first spatial position and the second spatial position exceeds a threshold (such as a maximum motion value), where the threshold may be determined based on the corresponding operating conditions and actions.

[0155] Verifying a solution or policy may include identifying a difference between the solution or policy and another solution or policy. For example, the autonomous vehicle operation management system 6100 may receive solutions or policies for POMDP models for different vehicle operation scenarios, the autonomous vehicle operation management system 6100 may identify solutions or policies for MDP models for different vehicle operation scenarios (this may include identifying previously generated solutions or policies or generating solutions or policies), and verifying the solution or policy for the POMDP model may include determining a ratio of actions from the solution or policy for the MDP model to equivalent actions from the solution or policy for the POMDP model (a comparison ratio), wherein the corresponding actions are related based on a correspondence between corresponding states in the MDP model and collapsed belief states in the POMDP model. Solutions or policies having a comparison ratio within a defined threshold (such as equal to or less than a defined threshold, etc.) may be identified as valid solutions or policies, and solutions or policies having a comparison ratio exceeding a defined threshold (such as greater than a defined threshold, etc.) may be identified as invalid policies.

[0156] Validating the solution or strategy may include generating simulated empirical data based on the strategy and validating the empirical data.

[0157] The received shared scenario-specific operation control management data portion may include scenario-specific operation control management experience data, and determining whether the received shared scenario-specific operation control management data portion includes malicious data may include verifying the scenario-specific operation control management experience data.

[0158] Validating the scenario-specific operational control management experience data may include time validation. The time validation may include: identifying an operational state and a corresponding time location from the scenario-specific operational control management experience data; identifying a vehicle control action associated with a transition from the identified operational state to a subsequent operational state from the scenario-specific operational control management experience data; identifying a time location associated with the subsequent operational state from the scenario-specific operational control management experience data; determining a difference between a first time location and a second time location; and determining whether the difference between the first time location and the second time location is within a defined time transition range associated with transitioning from the first operational state to the subsequent operational state according to the identified vehicle control action. A time difference that is outside the defined time transition range (such as less than a minimum value of the defined time transition range or greater than a maximum value of the defined time transition range) may be identified as indicating malicious data. A time difference that is within the defined time transition range (such as greater than or equal to a minimum value of the defined time transition range and less than or equal to a maximum value of the defined time transition range) may be identified as indicating the omission or absence of malicious data.

[0159] In response to determining that the received shared scenario-specific operation control management data portion includes malicious data (such as in response to determining that the probability that the received shared scenario-specific operation control management data portion includes malicious data exceeds a defined security threshold), the AVOMC 6200 may omit using the received shared scenario-specific operation control management data portion. For example, the AVOMC 6200 may store the received shared scenario-specific operation control management data portion and an indication that the received shared scenario-specific operation control management data portion includes malicious data, or the AVOMC 6200 may delete the received shared scenario-specific operation control management data portion.

[0160] The AVOMC 6200 may instantiate an SSOCEM instance 6300 at 6240 based on one or more aspects of the operating environment represented by the operating environment data, such as in response to identifying different vehicle operating scenarios at 6220 .

[0161] Instantiating the SSOCEM instance 6300 at 6240 may include identifying solutions or strategies for the model of the different vehicle operating scenarios identified at 6220 .

[0162] Identifying a solution or strategy for the model of the different vehicle operating scenario identified at 6220 may include determining whether the received portion of shared scenario-specific operational control management data includes a solution or strategy corresponding to the model of the different vehicle operating scenario identified at 6220. For example, in response to determining that a probability that the received portion of shared scenario-specific operational control management data includes malicious data is within a defined security threshold, identifying a solution for the scenario-specific operational control evaluation model may include determining whether the received portion of shared scenario-specific operational control management data includes a solution or strategy corresponding to the model of the different vehicle operating scenario identified at 6220. The received solution or strategy may be identified as corresponding to the model of the different vehicle operating scenario identified at 6220 based on a type or classification of the corresponding model. For example, the received shared scenario-specific operational control management data portion may include a solution or policy for a POMDP model for a four-way stop intersection scenario, the different vehicle operating scenario identified at 6220 may be a four-way stop intersection scenario, and the solution or policy included in the received shared scenario-specific operational control management data portion may be identified as corresponding to the different vehicle operating scenario identified at 6220. The solution or policy included in the received shared scenario-specific operational control management data portion may be a solution or policy generated based on a vehicle operating scenario that is different in geospatially, temporally, or both from the different vehicle operating scenario identified at 6220. In some embodiments, other data may be used to correlate the different vehicle operating scenario identified at 6220 with the solution or policy indicated in the received shared scenario-specific operational control management data portion (such as geographic data, temporal data, or both).

[0163] The received shared scenario-specific operational control management data portion may include solutions or strategies corresponding to models of different vehicle operational scenarios identified at 6220, and instantiating the SSOCEM instance 6300 at 6240 may include identifying the solution or strategy indicated in the received shared scenario-specific operational control management data portion as a solution or strategy for the scenario-specific operational control evaluation model identified at 6220, and instantiating an instance of the solution or strategy for the scenario-specific operational control evaluation model identified at 6220.

[0164] Identifying a solution or strategy for the model of the different vehicle operating scenarios identified at 6220 may include determining whether the received portion of shared scenario-specific operational control management data includes empirical data corresponding to the model of the different vehicle operating scenarios identified at 6220. For example, in response to determining that a probability that the received portion of shared scenario-specific operational control management data includes malicious data is within a defined security threshold, identifying a solution for the scenario-specific operational control evaluation model may include determining whether the received portion of shared scenario-specific operational control management data includes empirical data corresponding to the model of the different vehicle operating scenarios identified at 6220.

[0165] Instantiating the SSOCEM instance 6300 at 6240 may include generating a solution or strategy for the scenario-specific operational control evaluation model identified at 6220. For example, the AVOMC 6200 may identify available resources (such as time, etc.) for generating a solution or strategy for the scenario-specific operational control evaluation model identified at 6220, and the AVOMC 6200 may instantiate the SSOCEM instance 6300 at 6240 such that instantiating the SSOCEM instance 6300 at 6240 includes generating a solution or strategy for the scenario-specific operational control evaluation model identified at 6220.

[0166] For example, the received shared scenario-specific operational control management data portion may include experience data corresponding to models of different vehicle operational scenarios identified at 6220, and instantiating the SSOCEM instance 6300 at 6240 may include: using the experience data included in the received shared scenario-specific operational control management data portion to generate a solution or strategy for the scenario-specific operational control evaluation model identified at 6220; and instantiating an instance of the generated solution or strategy for the scenario-specific operational control evaluation model identified at 6220. Generating the solution or strategy using the experience data included in the received shared scenario-specific operational control management data portion may include determining that a previously solved or partially solved solution or strategy is not available at the autonomous vehicle. Generating the solution or strategy using the experience data included in the received shared scenario-specific operational control management data portion may include determining that a previously solved or partially solved solution or strategy is available at the autonomous vehicle, and generating the solution or strategy using the previously solved or partially solved solution or strategy and the experience data included in the received shared scenario-specific operational control management data portion. Generating a solution or strategy using the experience data included in the received shared scenario-specific operational control management data portion may include identifying previously generated or received experience data available at the autonomous vehicle and generating a solution or strategy using the previously generated or received experience data and the experience data included in the received shared scenario-specific operational control management data portion.

[0167] The autonomous vehicle operation management system 6100 can transmit or send shared scenario-specific operation control management data to the external shared scenario-specific operation control management system 6400 at 6310, which shared scenario-specific operation control management data may include recently generated (such as not previously sent) solution or strategy data.

[0168] In some implementations, the AVOMC 6200 may instantiate the SSOCEM instance 6300 to generate a corresponding solution or policy, such as in response to receiving a request for a solution or policy or an instruction to generate a solution or policy from an external shared scenario-specific operation control management system 6400.

[0169] In some implementations, the AVOMC 6200 may suspend or de-instantiate the SSOCEM instance 6300 in response to obtaining a solution or strategy for a corresponding different vehicle operation scenario. For example, the AVOMC 6200 may instantiate the SSOCEM instance 6300 to generate the corresponding solution or strategy in response to receiving a request for a solution or strategy or an instruction to generate a solution or strategy from the external shared scenario-specific operation control management system 6400, and may suspend or de-instantiate the SSOCEM instance 6300 in response to obtaining a solution or strategy for the corresponding different vehicle operation scenario. In another example, the AVOMC 6200 may suspend or de-instantiate the SSOCEM instance 6300 in response to determining that the difference between the current position of the autonomous vehicle and the position associated with the different vehicle operation scenario exceeds a defined threshold. The AVOMC 6200 may resume or re-instantiate the SSOCEM instance 6300 in response to determining that the difference between the current position of the autonomous vehicle and the position associated with the different vehicle operation scenario is within the defined threshold.

[0170] The SSOCEM instance 6300 may generate or identify candidate vehicle control actions at 6310. The SSOCEM instance 6300 may send the candidate vehicle control actions identified at 6310 to the AVOMC 6200.

[0171] The AVOMC 6200 may identify a candidate vehicle control action as a vehicle control action for traversing the vehicle transportation network and may control the autonomous vehicle at 6250 based on the identified vehicle control action or provide the identified vehicle control action to another vehicle control unit of the autonomous vehicle to control the autonomous vehicle traversing the vehicle transportation network or a portion thereof. Traversing the vehicle transportation network or a portion thereof at 6250 may include generating experience data (such as recent experience data, etc.) corresponding to a corresponding strategy of the SSOCEM instance 6300.

[0172] AVOMC 6200 may identify the autonomous vehicle's operating environment, or an aspect thereof, at 6260. Identifying the autonomous vehicle's operating environment, or an aspect thereof, at 6260 may be similar to identifying the autonomous vehicle's operating environment at 6210 and may include updating previously identified operating environment data. AVOMC 6200 may determine or detect whether different vehicle operating scenarios have been resolved or unresolved at 6270. For example, as described above, AVOMC 6200 may continuously or periodically receive operating environment information. AVOMC 6200 may evaluate the operating environment data to determine whether different vehicle operating scenarios have been resolved. If AVOMC 6200 determines at 6270 that the different vehicle operating scenario corresponding to SSOCEM instance 6300 is unresolved, AVOMC 6200 may send the operating environment data identified at 6260 to SSOCEM instance 6300 as indicated, and de-instantiating SSOCEM instance 6300 at 6280 may be omitted or different. The AVOMC 6200 may determine at 6270 that the different vehicle operation scenarios have been resolved, and may de-instantiate at 6280 the SSOCEM instance 6300 corresponding to the different vehicle operation scenarios determined to be resolved at 6270 .

[0173] The autonomous vehicle operation management system 6100 can transmit or send shared scenario-specific operation control management data to the external shared scenario-specific operation control management system 6400 at 6290, and the shared scenario-specific operation control management data may include recently generated (such as previously not sent) experience data generated at 6250.

[0174] Figure 7 1 is a diagram of an example of a computing and communication device such as a centralized shared scenario-specific operation control management device that can implement aspects, features, and elements disclosed herein. As shown in the figure, a computing and communication device 7000 (such as Figure 47000, a plurality of components of the computing and communication device 7000 are shown in the figure. The computing and communication device 7000 is ...

[0175] Power source 7100 may include an external power source interface, a power scavenger, a power receiver, a potential energy unit, or a combination thereof. Power source 7100 may be the same as power source 1210 except as indicated herein or otherwise clear from the context. Power source 7100 may be any device or combination of devices operable to provide energy, such as electrical energy.

[0176] The processor 7300 may include any device or combination of devices now known or later developed that can manipulate or process signals or other information, including optical processors, quantum processors, molecular processors, or combinations thereof. The processor 7300 may be used with other processors except as indicated herein or otherwise clear from the context. Figure 1 The processor 7300 is the same as the processor 1330 shown. The processor 7300 can be operably coupled to the power source 7100, the memory 7400, the electronic communication unit 7200, the user interface 7500, the sensor 7600, the communication bus 7700, or any combination thereof. For example, the processor can be operably coupled to the memory 7400 via the communication bus 7700.

[0177] Memory 7400 may include any tangible, non-transitory computer-usable or computer-readable medium that is capable of, for example, containing, storing, communicating, or transmitting machine-readable instructions or any information associated therewith for use by or in conjunction with processor 7300. Memory 7400 may be used in conjunction with other than as indicated herein or otherwise clear from the context. Figure 1 The memory 1340 shown is the same.

[0178] The communication unit 7200 can be used with other devices except as indicated herein or otherwise clear from the context. Figure 1The communication unit 7200 may include a communication interface 7210. The communication unit 7200 may send or receive signals via a wired or wireless electronic communication medium 7800, such as via the communication interface 7210. Figure 7 Although not explicitly shown, the communication unit 7200 may be configured to transmit, receive, or both via any wired or wireless communication medium, such as radio frequency (RF), ultraviolet light (UV), visible light, optical fiber, wireline, or a combination thereof. Figure 7 A single communication unit 7200 and a single communication interface 7210 are shown, but any number of communication units and any number of communication interfaces may be used.

[0179] The communication interface 7210 may be a wireless antenna (as shown), a wired communication port, an optical communication port, or any other wired or wireless means capable of interfacing with the wired or wireless electronic communication medium 7800. The communication interface 7210 may be connected to other devices except as indicated herein or otherwise clear from the context. Figure 1 The electronic communication interface 1370 shown is the same. Figure 7 The communication interface 7210 is shown communicating via a single communication link, but may be configured to communicate via multiple communication links.

[0180] The user interface 7500 may include any unit capable of interacting with a person, such as a virtual or physical keyboard, a touchpad, a display, a touch display, a head-up display, a virtual display, an augmented reality display, a tactile display, a feature tracking device such as an eye tracking device, a speaker, a microphone, a camera, a sensor, a printer, or any combination thereof. The user interface 7500 may be used with other than those indicated herein or otherwise clear from the context. Figure 1 The user interface 1350 shown is the same.

[0181] Sensor 7600 may be used with other than as indicated herein or otherwise clear from the context. Figure 1 The sensors 1360 shown are identical.

[0182] although Figure 7 Not shown, but the computing and communication device 7000 may include Figure 7 Units or components not shown, such as housing, Bluetooth module, a frequency modulation (FM) radio unit, a near field communication (NFC) module, a liquid crystal display (LCD) display unit, an organic light emitting diode (OLED) display unit, a speaker, or any combination thereof, etc.

[0183] Figure 88000 is a flow chart of an example of a centralized shared scenario-specific operation control management system 8000 according to an embodiment of the present invention. Figure 7 The computing and communication device 7000 shown or Figure 2 For example, the computing and communication device implementing the shared scenario specific operation control management 8000 may be a centralized shared scenario specific operation control management device that may be used in conjunction with other devices except as described herein or otherwise apparent from the context. Figure 6 The illustrated external shared scenario specific operation control management system 6400 is the same. The centralized shared scenario specific operation control management apparatus may implement an artificial intelligence unit for shared scenario specific operation control management.

[0184] Shared scenario specific operational control management 8000 may include communication with autonomous vehicles such as Figure 1 The vehicle 1000 shown, Figure 2 2100 / 2110 shown in the vehicle 2100 / 2110) and the like, which may be used in conjunction with one or more external devices for shared context-specific operation control management data communications except as described herein or otherwise clear from the context. Figure 6 The shared scenario-specific operation control management data communications shown at 6202, 6212, 6222, 6230, 6310 and 6290 are the same.

[0185] like Figure 8 As shown, shared scenario specific operation control management 8000 includes: receiving shared scenario specific operation control management (SSSOCM) input data at 8100; validating the shared scenario specific operation control management input data at 8200; identifying the current different vehicle operation scenarios at 8300; generating shared scenario specific operation control management output data at 8400; and sending the shared scenario specific operation control management output data or a portion thereof at 8500.

[0186] The centralized shared scenario-specific operation control management device can maintain shared scenario-specific operation control management data. For example, the centralized shared scenario-specific operation control management device can write or store the shared scenario-specific operation control management data to a data storage unit, structure, or device (such as a database of the centralized shared scenario-specific operation control management device, etc.), and can read or otherwise access the shared scenario-specific operation control management data from the data storage unit. The shared scenario-specific operation control management data may include: different vehicle operation scenario data, such as different vehicle operation scenario definition data, etc.; model data, which can be associated with corresponding different vehicle operation scenario data; strategy data, which can be associated with corresponding model data; experience data, which can be associated with corresponding strategy data; or any other shared scenario-specific operation control management data.

[0187] Shared scenario-specific operational control management input data may be received at 8100. For example, the shared scenario-specific operational control management input data may be received by a centralized shared scenario-specific operational control management device via electronic communication from one or more external devices, such as autonomous vehicles. Receiving the shared scenario-specific operational control management input data may include identifying the external device from which the shared scenario-specific operational control management input data was received as a current vehicle, a current device, or a current autonomous vehicle.

[0188] The received shared scenario-specific operational control management input data may include policy data, experience data, policy availability data, experience availability data, route data, origin data, destination data, different vehicle operational scenario data, vehicle configuration data, vehicle operational status data, or any other data or data combination that can be used for shared scenario-specific operational control management.

[0189] Strategy data may include strategies or solutions for different vehicle operation scenarios. Experience, history, or experience data may include state data, belief data, action data, observation data, or any combination thereof generated, identified, or determined based on operating the autonomous vehicle. Experience data may include temporal information, such as temporal information identifying the experience data as a time series. Strategy availability data may include an indication that strategies for different vehicle operation scenarios are available at the autonomous vehicle. Experience availability data may indicate that experience data for different vehicle operation scenarios is available at the autonomous vehicle. Route data may indicate a route for the vehicle to travel from an origin through a vehicle transportation network to a destination. Origin data may indicate a geospatial location in the vehicle transportation network (such as the current geospatial location of the autonomous vehicle) and may include temporal data. Destination data may indicate a target geospatial location in the vehicle transportation network and may include temporal data (such as a target arrival time). Different vehicle operation scenario data may indicate one or more different vehicle operation scenarios identified by the autonomous vehicle, such as different vehicle operation scenarios along the route. The vehicle configuration data may, for example, indicate sensor capability information of the autonomous vehicle. The vehicle operational state data may indicate the current state of the autonomous vehicle, such as launch state, acceleration state, directional control state, or power source state.

[0190] For example, the centralized shared scenario-specific operation control management device may receive shared scenario-specific operation control management input data (including experience data, strategy data, or a combination thereof), such as periodically, in response to an event, or in response to a request from the centralized shared scenario-specific operation control management device. In another example, the centralized shared scenario-specific operation control management device may receive shared scenario-specific operation control management input data indicating a request for shared scenario-specific operation control management data, such as strategy data for one or more different vehicle operation scenarios.

[0191] The shared scenario-specific operational control management input data received at 8100 may be validated at 8200. Validating the shared scenario-specific operational control management input data may include determining whether the shared scenario-specific operational control management input data received at 8100 includes malicious data. Determining whether the shared scenario-specific operational control management input data includes malicious data may include determining a probability that the shared scenario-specific operational control management input data includes malicious data, and determining whether the probability that the shared scenario-specific operational control management input data includes malicious data exceeds a defined security threshold.

[0192] For example, sharing scenario-specific operational control management input data may include policy data, and validating the shared scenario-specific operational control management input data may include validating the policy data. Figure 9 An example of verifying policy data is shown in FIG. In another example, the shared scenario-specific operation control management input data may include experience data, and verifying the shared scenario-specific operation control management input data may include verifying the experience data. Figure 10 An example of verification experience data is shown in .

[0193] At 8300, a current different vehicle operating scenario can be identified. The current different vehicle operating scenario can be identified based on shared scenario-specific operational control management input data. For example, the shared scenario-specific operational control management input data can include a different vehicle operating scenario identifier indicating the current different vehicle operating scenario. In another example, the shared scenario-specific operational control management input data can include policy data, empirical data, or both, and the current different vehicle operating scenario can be identified based on the policy data, the empirical data, or a combination thereof.

[0194] The shared scenario-specific operational control management input data received at 8100 may include state data (such as vehicle state data, vehicle operating environment state data, or a combination thereof), and identifying the current different vehicle operating scenario at 8300 may include identifying the current different vehicle operating scenario based on the state data, which operation may be different from that described herein or otherwise clear from the context, such as Figure 5 The detection scene is the same as indicated at 5120 in .

[0195] Shared scenario-specific operational control management input data may include origin data and destination data, and identifying the current different vehicle operational scenarios at 8300 may include generating route data indicating one or more routes for a source autonomous vehicle to travel from a origin indicated by the origin data through the vehicle transportation network to a destination indicated by the destination data.

[0196] For example, the centralized shared scenario-specific operation control management device may determine that the shared scenario-specific operation control management input data includes a starting point identifier and a destination identifier. The starting point identifier may indicate a starting point location (such as a geographic location, etc.) in the vehicle transportation network. The destination identifier may indicate a destination location (such as a geographic location, etc.) in the vehicle transportation network. The centralized shared scenario-specific operation control management device may determine that the shared scenario-specific operation control management input data omits a route, and identifying the current different vehicle operation scenarios at 8300 may include generating a current route for a vehicle (which may be an autonomous vehicle) from the starting point location through the vehicle transportation network to the destination location.

[0197] The shared scenario-specific operational control management input data may include temporal location data associated with an origin location, and generating the route may include generating the route based on a vehicle departing the origin location according to the corresponding temporal location. The shared scenario-specific operational control management input data may include temporal location data associated with a destination location, and generating the route may include generating the route such that an expected arrival of the vehicle at the destination location corresponds to the corresponding temporal location.

[0198] The shared scenario-specific operational control management input data may include route data, or the route data may be generated based on the scenario-specific operational control input data, and identifying the current different vehicle operating scenarios at 8300 may include identifying one or more different vehicle operating scenarios based on the route data. For example, the centralized shared scenario-specific operational control management device may determine that the shared scenario-specific operational control management input data includes a route, and the route may be identified as the current route.

[0199] Identifying different current vehicle operating scenarios at 8300 may include identifying different current vehicle operating scenarios based on the current route. For example, the centralized shared scenario-specific operation control management device may evaluate vehicle transportation network map data to identify different vehicle operating scenarios along the route.

[0200] In some embodiments, the shared scenario-specific operational control management input data may include different vehicle operating scenario data indicating one or more different vehicle operating scenarios identified by the autonomous vehicle, and the centralized shared scenario-specific operational control management device may evaluate the vehicle transportation network map data to verify the different vehicle operating scenarios identified by the autonomous vehicle, which may include identifying one or more different vehicle operating scenarios along the route other than the different vehicle operating scenarios identified by the autonomous vehicle.

[0201] Although shown sequentially, validating input data at 8200 and identifying the current different vehicle operating scenarios at 8300 may overlap or may be combined.

[0202] Identifying the current different vehicle operating scenarios at 8300 may include determining whether the shared scenario-specific operational control management input data indicates a policy override. For example, the shared scenario-specific operational control management input data may include an indication of a policy override for policies for different vehicle operating scenarios, and the centralized shared scenario-specific operational control management device may determine that the shared scenario-specific operational control management input data may include an indication of a policy override for policies for different vehicle operating scenarios.

[0203] The policy override may indicate that the source vehicle previously traversed a different vehicle operating scenario by performing a vehicle control action different from the vehicle control action indicated by the different vehicle operating scenario indicated by the policy override. For simplicity and clarity, the different vehicle operating scenario indicated by the policy override may be referred to herein as the source scenario, and the policy for the source scenario may be referred to as the source policy.

[0204] The centralized shared scenario-specific operation control management device can determine the scenario branch metrics of the source scenario. For example, the centralized shared scenario-specific operation control management device can read or otherwise access one or more scenario branch metrics of each corresponding different vehicle operation scenario. Accessing the scenario branch metrics of the corresponding different vehicle operation scenarios can include generating the scenario branch metrics of the corresponding different vehicle operation scenarios based on previously identified experience data associated with the corresponding different vehicle operation scenarios. The scenario branch metrics can include a cardinality of previously received policy coverage indications for the corresponding different vehicle operation scenarios, corresponding recent information, or corresponding frequency information, etc. The centralized shared scenario-specific operation control management device can include the policy coverage data indicated in the shared scenario-specific operation control management input data in the scenario branch metrics of the current different vehicle operation scenarios.

[0205] The centralized shared scenario-specific operation control management device may determine whether the scenario branching metric is within the scenario branching threshold. For example, the centralized shared scenario-specific operation control management device may determine whether the cardinality of policy coverage for different vehicle operation scenarios exceeds (such as is greater than) a defined cardinality of policy coverage indicated by the scenario branching threshold.

[0206] The centralized shared scenario-specific operation control management device can determine that the scenario branch metric is within the scenario branch threshold (such as less than or equal to the scenario branch threshold), and can identify the source scenario as the current different vehicle operation scenario.

[0207] In another example, the centralized shared scenario-specific operation control management device may determine that the scenario branch metric exceeds (such as is greater than) a scenario branch threshold, and may identify the current different vehicle operation scenarios based on the source scenario.

[0208] Identifying the current different vehicle operating scenarios based on the source scenario can include identifying branching factors, such as an aspect of the source scenario associated with the policy coverage or an operating condition associated with the policy coverage. For example, the centralized shared scenario-specific operation control management device can determine that the cardinality of policy coverage within a defined time period (such as a high traffic time period, such as a peak period, etc.) exceeds the scenario branching threshold. In another example, the centralized shared scenario-specific operation control management device can determine that the cardinality of policy coverage for instances of the source scenario at a defined geospatial location exceeds the scenario branching threshold. In another example, the centralized shared scenario-specific operation control management device can determine that the cardinality of policy coverage associated with defined weather conditions exceeds the scenario branching threshold. Other branching factors or combinations of branching factors can be used. In an example, the centralized shared scenario-specific operation control management device can compare the experience data associated with the policy coverage with other experience data associated with the same source policy to identify state data, belief state data, or both, and identify branching factors that are similar in the policy coverage experience data, similar in other experience data, and dissimilar between the policy coverage experience data and other experience data.

[0209] Identifying the current different vehicle operation scenarios based on the source scenario may include: generating the current different vehicle operation scenarios by branching, copying or cloning the source scenario, and modifying the current different vehicle operation scenarios based on the branching factor, so that the different vehicle operation scenarios corresponding to the source scenario and omitting the branching factor can be identified as the source scenario, and the different vehicle operation scenarios corresponding to the source scenario and including the branching factor can be identified as the current different vehicle operation scenarios. The centralized shared scenario-specific operation control management device may store or otherwise maintain the current, branched different vehicle operation scenarios separately from the source different vehicle operation scenarios. Generating the branched different vehicle operation scenarios may include copying the experience data associated with the source scenario, the model data associated with the source scenario, or both. The probabilities of the models of the source scenario (such as state transition probabilities and observation probabilities, etc.) may be different from the probabilities of the corresponding models of the branch scenarios.

[0210] Shared scenario specific operational control management output data or a portion thereof may be generated at 8400. Although Figure 8In the figure, generating shared scenario specific operation control management output data at 8400 is shown as occurring after receiving shared scenario specific operation control management input data at 8100, but generating shared scenario specific operation control management output data at 8400 or a portion thereof may occur before receiving shared scenario specific operation control management input data at 8100, after receiving shared scenario specific operation control management input data at 8100, or both.

[0211] The centralized shared scenario-specific operation control management device can generate shared scenario-specific operation control management output data or a portion thereof at 8400. For example, the centralized shared scenario-specific operation control management device can distribute shared scenario-specific operation control management data (such as policy data, model data, experience data, or any other data that can be used for shared scenario-specific operation control management) periodically or in response to an event. In another example, the centralized shared scenario-specific operation control management device can respond to a request for policy data by including the requested policy data in the shared scenario-specific operation control management output data. In another example, the centralized shared scenario-specific operation control management device can include a request to generate policy data for the current different vehicle operation scenarios in the shared scenario-specific operation control management output data.

[0212] Generating shared scenario-specific operation control management output data at 8400 may include determining that a current strategy for the current different vehicle operation scenario is available and including the current strategy in the shared scenario-specific operation control management output data. Generating shared scenario-specific operation control management output data at 8400 may include determining whether current experience data for the current different vehicle operation scenario is available. For example, the centralized shared scenario-specific operation control management device may read or otherwise access an information storage unit associated with the current different vehicle operation scenario to determine whether the current experience data is available. The centralized shared scenario-specific operation control management device may determine that the current experience data for the current different vehicle operation scenario is available and may include the current experience data for the current different vehicle operation scenario in the shared scenario-specific operation control management output data.

[0213] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include associating the current vehicle identified at 8100 with the current, different vehicle operating scenario identified at 8300, such as by storing, recording, or otherwise maintaining information indicating the association between the current vehicle and the current, different vehicle operating scenario. The information indicating the association between the current vehicle and the current, different vehicle operating scenario may include temporal information, such as information indicating a temporal validity period of the association.

[0214] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include identifying other vehicles (such as autonomous vehicles, etc.) currently associated with the current different vehicle operational scenario, which may include the current vehicle, such as by reading or otherwise accessing previously stored information indicating a corresponding association between the other vehicles and the current different vehicle operational scenario, which may include determining that the association information is valid in time (such as not expired, etc.). Identifying the autonomous vehicles associated with the current different vehicle operational scenario may include identifying the autonomous vehicles based on one or more grouping or clustering criteria (such as temporal proximity, spatial proximity, or a combination thereof, etc.).

[0215] For example, the centralized shared scenario-specific operation control management device may receive shared scenario-specific operation control management input data from a first autonomous vehicle indicating the route of the first autonomous vehicle. The centralized shared scenario-specific operation control management device may identify different vehicle operation scenarios along the route of the first autonomous vehicle. The centralized shared scenario-specific operation control management device may receive shared scenario-specific operation control management input data from a second autonomous vehicle indicating the route of the second autonomous vehicle. The route of the first autonomous vehicle may geographically overlap with the route of the second autonomous vehicle, or the route of the first autonomous vehicle may be geographically different from the route of the second autonomous vehicle. The centralized shared scenario-specific operation control management device may identify different vehicle operation scenarios for the second autonomous vehicle based on the route of the second autonomous vehicle. One or more different vehicle operation scenarios identified for the first autonomous vehicle based on the route of the first autonomous vehicle can correspond to corresponding different vehicle operation scenarios in the different vehicle operation scenarios identified for the second autonomous vehicle based on the route of the second autonomous vehicle, and the centralized shared scenario-specific operation control management device can identify the first autonomous vehicle and the second autonomous vehicle as autonomous vehicles associated with the corresponding different vehicle operation scenarios.

[0216] Generating the shared scenario-specific operation control management output data or a portion thereof at 8400 may include determining whether the current policy for the current different vehicle operation scenario is available. For example, the centralized shared scenario-specific operation control management device may read or otherwise access an information storage unit associated with the current different vehicle operation scenario to determine whether the current policy is available. Determining whether the current policy is available may include determining whether the policy for the current different vehicle operation scenario previously identified by the centralized shared scenario-specific operation control management device has expired or has not been optimized. For example, the centralized shared scenario-specific operation control management device may determine that the time position corresponding to the generation of the previously identified policy is before the time position corresponding to the received experience data for the current different vehicle operation scenario, and may determine that the previously identified policy has expired.

[0217] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include determining an expected complexity metric for generating the current policy. For example, the centralized shared scenario-specific operational control management device may determine that the current policy for the current different vehicle operational scenario is not available and may determine an expected complexity metric for generating the current policy. The expected complexity metric may indicate an expected amount of resources (such as processor resources, time resources, or a combination thereof) required to generate the policy for the current different vehicle operational scenario. The expected complexity metric may be determined, for example, based on the type of model for the current different vehicle operational scenario.

[0218] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include determining whether sufficient available resources for generating the current strategy are available at the current vehicle or at one or more other vehicles associated with the current different-vehicle operational scenario. For example, the centralized shared scenario-specific operational control management device may identify resources for generating the current strategy based on an expected complexity metric and may identify resources available at the corresponding vehicle based on the identified resource availability information. The available resources may include communication bandwidth, data storage resources, processing resources, time resources (such as the temporal distance between the corresponding vehicle and the current different-vehicle operational scenario), or any other resources that may be used to generate the strategy.

[0219] Despite Figure 8Not shown separately, the shared scenario-specific operation control management 8000 may include generating shared scenario-specific operation control management output data or a portion thereof indicating a request for resource availability information and sending it to one or more vehicles (such as the current vehicle and other vehicles associated with the current different vehicle operation scenario, etc.), and receiving shared scenario-specific operation control management input data indicating current resource availability information of the corresponding vehicle from one or more vehicles (such as the current vehicle and other vehicles associated with the current different vehicle operation scenario, etc.).

[0220] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include identifying a target autonomous vehicle with sufficient available resources and including in the shared scenario-specific operational control management output data a request for the target autonomous vehicle to generate the current strategy. For example, the process may include identifying the target autonomous vehicle such that resource utilization is evenly distributed across the vehicles. In another example, a vehicle with sufficient available resources and a minimum proximity to the current different vehicle operational scenario may be identified as the target autonomous vehicle.

[0221] In some embodiments, a centralized shared scenario-specific operational control management device may receive temporally overlapping route planning information from multiple vehicles. The centralized shared scenario-specific operational control management device may determine commonalities, such as commonalities between different vehicle operational scenarios. The centralized shared scenario-specific operational control management device may identify corresponding target autonomous vehicles for generating corresponding strategies for the multiple different vehicle operational scenarios and may include corresponding requests to generate the corresponding strategies in the shared scenario-specific operational control management output data.

[0222] Generating the shared scenario-specific operational control management output data, or a portion thereof, at 8400 may include determining that a target autonomous vehicle with sufficient available resources is unavailable, and the centralized shared scenario-specific operational control management apparatus may generate a current policy. In some embodiments, the centralized shared scenario-specific operational control management apparatus may omit identifying available resources and may generate a current policy.

[0223] Generate Current Policy Except as described herein or otherwise clear from the context may be used with Figure 6The strategy generation shown is the same. Generating the current strategy may include identifying a definition model (such as a POMDP model, etc.) for the current different vehicle operation scenarios. For example, generating the current strategy may include identifying previously received or obtained experience data (such as experience data previously received from one or more autonomous vehicles, etc.) for the current different vehicle operation scenarios, and solving the model based on the previously obtained experience data. The centralized shared scenario-specific operation control management device can identify previously identified strategies or solutions for the definition model of the current different vehicle operation scenarios, can identify subsequently generated experience data generated using the identified strategy, and can generate the current strategy or solution (reinforcement or model learning) by updating the previously identified strategy or solution based on the subsequently generated experience data. Generating the current strategy may include performing function approximation (which may include identifying groupings of belief states) and performing belief point compression (which may map the belief set to a smaller belief set).

[0224] In some embodiments, a centralized shared scenario-specific operational control management device may identify multiple external devices, such as autonomous vehicles, as a cluster and may include a request in the shared scenario-specific operational control management output data for the cluster to generate a current policy. The request may indicate the respective belief point data for the respective vehicles.

[0225] The shared scenario-specific operational control management output data generated at 8400 may include privacy-protected data and may omit unprotected data.

[0226] The shared scenario-specific operational control management output data, or a portion thereof, may be sent at 8500. For example, the shared scenario-specific operational control management output data may be output, sent, transmitted, or otherwise communicated from a centralized shared scenario-specific operational control management device to an external device, such as an autonomous vehicle, via a wired or wireless electronic communication medium.

[0227] The centralized shared scenario-specific operational control management device may generate shared scenario-specific operational control management output data at 8400 and may transmit, send, or otherwise electronically communicate the shared scenario-specific operational control management output data, or a portion thereof, to one or more autonomous vehicles at 8500. For example, the centralized shared scenario-specific operational control management device may include a request to generate a current policy in the shared scenario-specific operational control management output data, and sending the shared scenario-specific operational control management output data may include sending the shared scenario-specific operational control management output data, or a portion thereof, to the target vehicle identified at 8400.

[0228] In another example, the shared scenario-specific operation control management input data received at 8100 may include a request from the current autonomous vehicle for policy data for the current different vehicle operation scenarios, the centralized shared scenario-specific operation control management device may identify available policy data for the current different vehicle operation scenarios at 8300, the centralized shared scenario-specific operation control management device may include the policy data for the current different vehicle operation scenarios in the shared scenario-specific operation control management output data at 8400, and the centralized shared scenario-specific operation control management device may output, transmit, send or otherwise electronically communicate the shared scenario-specific operation control management output data or a portion thereof to the source autonomous vehicle at 8500.

[0229] In an example, shared scenario-specific operational control management 8000 may include the autonomous vehicle generating shared scenario-specific operational control management output data or a portion thereof at 8400 (including experience data previously generated by the autonomous vehicle, such as unreported data, etc.), and sending the shared scenario-specific operational control management output data or a portion thereof to a centralized shared scenario-specific operational control management device at 8500.

[0230] For example, an autonomous vehicle may generate and transmit shared scenario-specific operational control management output data, or a portion thereof, after traversing corresponding different vehicle operating scenarios, or an autonomous vehicle may generate and transmit output periodically or in response to an event (such as in an inactive or stationary mode, such as when parked or charging, etc.). The shared scenario-specific operational control management output data, or a portion thereof, generated by the autonomous vehicle at 8400 and transmitted at 8500 and received by the centralized shared scenario-specific operational control management device at 8100 as shared scenario-specific operational control management input data may include experience data associated with multiple different vehicle operating scenarios, respectively. For example, a first portion of the experience data may be associated with a first different vehicle operating scenario, and a second portion of the experience data may be associated with a second different vehicle operating scenario. The portions of the experience data may be validated and processed as shown at 8200 and 8300, and the corresponding processed experience data for the portions of the input experience data may be distributed as shown at 8400 and 8500.

[0231] The data sent by the autonomous vehicle at 8500 may be received by the centralized shared scenario-specific operational control management device at 8100 as shared scenario-specific operational control management input data. The centralized shared scenario-specific operational control management device may validate the shared scenario-specific operational control management input data at 8200. Validating the experience data at 8200 may include identifying different vehicle operational scenarios corresponding to the experience data at 8300. Validating the shared scenario-specific operational control management input data may include integrating the experience data. For example, the centralized shared scenario-specific operational control management device may generate processed experience data that integrates the input experience data.

[0232] The centralized shared scenario-specific operation control management device can distribute the processed experience data to one or more vehicles, which can include generating shared scenario-specific operation control management output data or a portion thereof (including the processed experience data) at 8400, and sending the shared scenario-specific operation control management output data or a portion thereof to one or more vehicles at 8500.

[0233] In an example, a centralized shared scenario-specific operational control management device may receive shared scenario-specific operational control management input data at 8100 that indicates a previously unidentified different vehicle operational scenario for a portion of a vehicle transportation network. In some embodiments, the shared scenario-specific operational control management input data may explicitly indicate that the shared scenario-specific operational control management input data includes a previously unidentified different vehicle operational scenario for a portion of the vehicle transportation network. For example, the centralized shared scenario-specific operational control management device may receive the shared scenario-specific operational control management input data from an external infrastructure device or system, and the shared scenario-specific operational control management input data may indicate a change in the vehicle transportation network (which may be a permanent or temporary change, and may be a planned or unplanned change). In response to receiving shared scenario-specific operational control management input data indicating a previously unidentified different vehicle operating scenario, the centralized shared scenario-specific operational control management apparatus may validate the shared scenario-specific operational control management input data at 8200, identify the different vehicle operating scenario at 8300, obtain a policy for the different vehicle operating scenario at 8400, identify target vehicles for distributing the policy and the different vehicle operating scenario data at 8400, and transmit the policy data, the different vehicle operating scenario data, or both to the target vehicles at 8500. In some implementations, the centralized shared scenario-specific operational control management apparatus may prioritize transmission to some vehicles, such as vehicles having current operating conditions or routes that include a previously unidentified different vehicle operating scenario or have a probability exceeding a defined threshold of including a previously unidentified different vehicle operating scenario.

[0234] In another example, the centralized shared scenario-specific operational control management device may generate different vehicle operating scenarios by branching at 8300. In response to generating different vehicle operating scenarios by branching at 8300, the centralized shared scenario-specific operational control management device may obtain a policy for the branched different vehicle operating scenarios at 8400, identify target vehicles for distributing the policy and the different vehicle operating scenario data at 8400, and transmit the policy data, the branched different vehicle operating scenario data, or both to the target vehicles at 8500. In some implementations, the centralized shared scenario-specific operational control management device may prioritize transmission to some vehicles, such as vehicles having current operating conditions or routes that include the branched different vehicle operating scenarios or having a probability of including the branched different vehicle operating scenarios exceeding a defined threshold.

[0235] Despite Figure 8Not shown separately, but the current autonomous vehicle can receive shared scenario-specific operation control management input data from the source autonomous vehicle at 8100, and the shared scenario-specific operation control management input data can include requests for strategies for different vehicle operation scenarios, the current autonomous vehicle can verify the shared scenario-specific operation control management input data at 8200, the current autonomous vehicle can identify the different vehicle operation scenarios indicated in the shared scenario-specific operation control management input data as the current different vehicle operation scenarios at 8300, the current autonomous vehicle can identify available strategies for different vehicle operation scenarios, the current autonomous vehicle can generate shared scenario-specific operation control management output data or a portion thereof (including available strategies), and the current autonomous vehicle can send the shared scenario-specific operation control management output data or a portion thereof to the source autonomous vehicle at 8500.

[0236] Despite Figure 8 Although not separately shown in the figure, the current autonomous vehicle can identify the current different vehicle operating scenario, the current autonomous vehicle can identify one or more approaching autonomous vehicles that are close to the current different vehicle operating scenario, the current autonomous vehicle can generate shared scenario-specific operational control management output data or a portion thereof (including a request for a strategy for the current different vehicle operating scenario) at 8400, and the current autonomous vehicle can send the shared scenario-specific operational control management output data or a portion thereof to the one or more approaching autonomous vehicles at 8500. In response, the current autonomous vehicle can receive shared scenario-specific operational control management input data (including a strategy for the current different vehicle operating scenario) from the one or more approaching autonomous vehicles at 8100, the current autonomous vehicle can verify the shared scenario-specific operational control management input data at 8200, and the current autonomous vehicle can use the received strategy to traverse the current different vehicle operating scenario.

[0237] Figure 9 9000 is a flowchart of an example of policy data verification according to an embodiment of the present invention. The policy data verification 9000 can be performed in a centralized shared scenario-specific operation control management device (such as Figure 7 The computing and communication device 7000 shown or Figure 2 For example, Figure 8 The verification shown at 8200 in may include policy data verification 9000. Figure 9 The illustrated policy data validation 9000 may be used with other Figure 6 The verification solution or strategy is the same as shown in 6230.

[0238] like Figure 9 As shown, policy data validation 9000 includes determining at 9100 the shared scenario specific operational control management input data (such as Figure 8 Whether the received shared scenario-specific operational control management input data (e.g., the received shared scenario-specific operational control management input data as shown at 8100 in FIG. 1 ) includes policy data. For example, determining whether the shared scenario-specific operational control management input data includes policy data at 9100 may include identifying a solution or policy for a defined model of different vehicle operational scenarios from the policy data from the shared scenario-specific operational control management input data.

[0239] The shared scenario-specific operation control management input data may include policy data (such as solutions or policies for defined models for current different vehicle operation scenarios, etc.), and the centralized shared scenario-specific operation control management device may determine that the shared scenario-specific operation control management input data includes policy data, and the centralized shared scenario-specific operation control management device may verify the policy data at 9200.

[0240] Validating the policy data at 9200 may include determining whether the policy data is valid or invalid. Validating the policy data at 9200 may include evaluating the data indicated in the solution or policy based on relevant defined metrics. For example, the solution or policy may include a utility value associated with a corresponding belief state, and validating the solution or policy may include determining whether the utility value is within a corresponding defined range (such as greater than or equal to a defined minimum threshold and less than or equal to a defined maximum threshold, etc.) for the corresponding belief state.

[0241] In another example, the solution or strategy identified at 9100 may include action data (such as an index or unique identifier associated with an available action), and verifying the solution or strategy may include determining whether the action data is valid. For example, a model may include three available actions (which may have action index values ​​of 0, 1, and 2, respectively), action data in the solution or strategy with action index values ​​of 0, 1, and 2 may be identified as valid action data, and action data in the solution or strategy with action index values ​​other than 0, 1, and 2 may be identified as invalid.

[0242] In another example, the solution or strategy identified at 9100 may include state data (such as an index or unique identifier associated with an available state), and verifying the solution or strategy may include determining whether the state data is valid, which may be similar to verifying the action data. In another example, the solution or strategy may include belief state data (such as an index or unique identifier associated with an available belief state), and verifying the solution or strategy may include determining whether the belief state data is valid, which may be similar to verifying the action data. In another example, the solution or strategy may include observation data (such as an index or unique identifier associated with an available observation), and verifying the solution or strategy may include determining whether the observation data is valid, which may be similar to verifying the action data.

[0243] The solution or strategy identified at 9100 may include belief data (received belief data), and verifying the solution or strategy may include verifying the belief data. For example, the received belief data may be verified by determining corresponding calculated belief data based on the state transition probabilities and observation probabilities corresponding to the received belief data. Received belief data that differs from the calculated belief data may be identified as invalid or malicious data.

[0244] Verifying the solution or policy identified at 9100 at 9200 may include determining whether the policy indicates an action corresponding to the corresponding belief state with a corresponding penalty or negative reward exceeding a defined threshold. A policy indicating an action with a penalty exceeding the relevant defined threshold may be identified as invalid or malicious data.

[0245] Verifying the solution or strategy identified at 9100 at 9200 may include evaluating the strategy based on one or more defined conditions. The defined conditions may specifically identify a state or belief state and may indicate one or more invalid actions associated with the identified state or belief state. For example, the defined conditions may indicate that the state data indicates that an obstacle is blocking the path of the autonomous vehicle and may indicate that an acceleration action is an invalid action. A strategy that indicates an action identified as an invalid action under the defined conditions may be identified as invalid or malicious data.

[0246] Verifying, at 9200, the solution or strategy identified at 9100 may include evaluating the strategy based on one or more spatial constraints. For example, a belief state indicated in the strategy may correspond to a first relative spatial position of the vehicle and corresponding operating conditions (such as trajectory and velocity information of the vehicle), and a subsequent belief state indicated in the strategy may correspond to a second relative spatial position of the vehicle, and evaluating the strategy based on the spatial constraints may include determining whether a difference between the first spatial position and the second spatial position exceeds a threshold (such as a maximum motion value), where the threshold may be determined based on the corresponding operating conditions and actions.

[0247] Verifying the solution or strategy identified at 9100 at 9200 may include identifying a difference between the solution or strategy and another solution or strategy. For example, the centralized shared scenario-specific operation control management device may receive solutions or strategies for POMDP models of different vehicle operation scenarios, the centralized shared scenario-specific operation control management device may identify solutions or strategies for MDP models of different vehicle operation scenarios (this may include identifying previously generated solutions or strategies or generating solutions or strategies), and verifying the solution or strategy for the POMDP model may include determining a ratio of actions from the solution or strategy for the MDP model to equivalent actions from the solution or strategy for the POMDP model (a comparison ratio), wherein the corresponding actions are related based on a correspondence between corresponding states in the MDP model and collapsed belief states in the POMDP model. Solutions or strategies with a comparison ratio within a defined threshold (such as equal to or less than the defined threshold) may be identified as valid solutions or strategies, and solutions or strategies with a comparison ratio exceeding the defined threshold (such as greater than the defined threshold) may be identified as invalid strategies.

[0248] Verifying the solution or strategy may include generating simulated experience data based on the strategy, and verifying the simulated experience data.

[0249] The centralized shared scenario-specific operation control management device may determine that the policy data is invalid and may ignore, delete, discard, isolate, mark, or otherwise omit the policy data from use in shared scenario-specific operation control management.

[0250] The centralized shared scenario-specific operation control management device can determine that the policy data or the corresponding policy is valid, and can combine the policy with the current different vehicle operation scenarios (such as Figure 8 Associated with the current different vehicle operation scenarios identified at 8300, etc.).

[0251] Figure 1010000 is a flowchart of an example of experience data verification according to an embodiment of the present invention. The experience data verification 10000 can be performed in a centralized shared scene specific operation control management device (such as Figure 7 The computing and communication device 7000 shown or Figure 2 For example, Figure 8 The verification shown at 8200 in can include empirical data verification 10000. Figure 10 The empirical data shown verify that 10000 can be used with Figure 6 The verification scenario specific operation control management experience data is the same as shown in 6230.

[0252] like Figure 10 As shown, empirical data verification 10000 includes determining at 10100 shared scenario specific operational control management input data (such as Figure 8 Whether the shared scenario specific operation control management input data received as shown at 8100 in the example includes experience data, such as different vehicle operation scenarios from the current one (such as Figure 8 Current experience data associated with the current different vehicle operation scenarios identified at 8300, etc.

[0253] For example, the shared scenario-specific operation control management input data may include experience data associated with the current different vehicle operation scenarios, the centralized shared scenario-specific operation control management device may determine that the shared scenario-specific operation control management input data includes experience data, the centralized shared scenario-specific operation control management device may identify the experience data as the received experience data at 10100, and the centralized shared scenario-specific operation control management device may verify the experience data at 10200.

[0254] Verifying the experience data at 10200 may include determining whether the experience data is valid or invalid (malicious). Verifying the received experience data identified at 10100 at 10200 may include time verification. The time verification may include: identifying an operating state and a corresponding time location from the scenario-specific operational control management experience data; identifying a vehicle control action associated with a transition from the identified operating state to a subsequent operating state from the scenario-specific operational control management experience data; identifying a time location associated with the subsequent operating state from the scenario-specific operational control management experience data; determining a difference between a first time location and a second time location; and determining whether the difference between the first time location and the second time location is within a defined time transition range associated with transitioning from the first operating state to the subsequent operating state according to the identified vehicle control action. A time difference outside the defined time transition range (such as less than a minimum value of the defined time transition range or greater than a maximum value of the defined time transition range) may be identified as indicating malicious data. A time difference within the defined time transition range (such as greater than or equal to a minimum value of the defined time transition range and less than or equal to a maximum value of the defined time transition range) may be identified as indicating the omission or absence of malicious data.

[0255] The centralized shared scenario-specific operation control management device may determine that the experience data is invalid and may ignore, delete, discard, isolate, mark or otherwise omit the experience data from use in shared scenario-specific operation control management.

[0256] The centralized shared scenario-specific operational control management device may determine that the experience data is valid and may integrate or otherwise retain the experience data at 10300. Integrating the experience data may include integrating the current or received experience data with previously integrated experience data associated with the current different vehicle operational scenario.

[0257] Integrating current experience data into previously integrated experience data associated with a current different vehicle operating scenario may include identifying similar experience data from the previously integrated experience data based on determined similarities with the current experience data, and generating an updated experience data set associated with the current different vehicle operating scenario based on the similar experience data and the current experience data.

[0258] Generating the updated experience data set may include pruning experience data for the current different vehicle operation scenario. For example, similar experience data for the current different vehicle operation scenario (including the current experience data) may have a cardinality exceeding a defined pruning threshold, and pruning the experience data may include deleting or removing a portion of the similar experience data from the experience data associated with the current different vehicle operation scenario.

[0259] Despite Figure 8 Although not separately shown in the figures, the centralized shared scenario-specific operation control management device can periodically or in response to an event other than receiving the experience data and delete the experience data associated with one or more different vehicle operation scenarios. In some embodiments, deleting the experience data in response to receiving the experience data can be omitted.

[0260] Generating the updated experience data set may include merging the current experience data with similar experience data. Merging the current experience data with similar experience data may include determining an average value (such as an average probability value) of the experience data and storing the average value.

[0261] Despite Figure 8 Although not separately shown in the figures, the centralized shared scenario-specific operation control management device can periodically or in response to an event other than receiving the experience data and merge the experience data associated with one or more different vehicle operation scenarios. In some embodiments, merging the experience data in response to receiving the experience data can be omitted.

[0262] As used herein, the term "computer" or "computing device" includes any unit or combination of units capable of performing any method disclosed herein or any portion thereof.

[0263] As used herein, the term "processor" refers to one or more processors, such as one or more special-purpose processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more application processors, one or more application-specific integrated circuits, one or more application-specific standard products; one or more field programmable gate arrays, any other type of integrated circuit or combination thereof, one or more state machines, or any combination thereof.

[0264] As used herein, the term "memory" refers to any computer-usable or computer-readable medium or device that can tangibly contain, store, communicate, or transmit any signal or information that can be used by or in conjunction with any processor. For example, the memory can be one or more read-only memories (ROMs), one or more random access memories (RAMs), one or more registers, a low-power double data rate (LPDDR) memory, one or more cache memories, one or more semiconductor memory devices, one or more magnetic media, one or more optical media, one or more magneto-optical media, or any combination thereof.

[0265] As used herein, the term "instructions" may include instructions or representations for performing any method disclosed herein, or any portion thereof, and may be implemented in hardware, software, or any combination thereof. For example, instructions may be implemented as information, such as a computer program, stored in a memory, which may be executed by a processor to perform any of the corresponding methods, algorithms, aspects, or combinations thereof as described herein. In some embodiments, instructions, or a portion thereof, may be implemented as a dedicated processor or circuit, which may include dedicated hardware for performing any of the methods, algorithms, aspects, or combinations thereof as described herein. In some implementations, a portion of the instructions may be distributed across multiple processors on a single device, on multiple devices that may communicate directly or across a network, such as a local area network, a wide area network, the Internet, or a combination thereof.

[0266] As used herein, the terms "example," "embodiment," "implementation," "aspect," "feature," or "element" indicate serving as an example, instance, or illustration. Unless expressly indicated otherwise, any example, embodiment, implementation, aspect, feature, or element is independent of each other and can be used in combination with any other example, embodiment, implementation, aspect, feature, or element.

[0267] As used herein, the terms "determine" and "identify" or any variations thereof include selecting, ascertaining, calculating, searching, receiving, determining, establishing, obtaining, or otherwise identifying or determining in any manner using one or more of the devices shown and described herein.

[0268] As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless specified otherwise or clear from the context, "X includes A or B" is intended to indicate any of the natural inclusive permutations. That is, if X includes A; X includes B; or X includes both A and B, then "X includes A or B" is satisfied in any of the foregoing cases. Additionally, the articles "a" and "an" as used in this application and the appended claims should generally be construed to mean "one or more" unless specified otherwise or clear from the context to be directed to the singular.

[0269] In addition, for simplicity of explanation, although the figure here and description can comprise the sequence or a series of steps or the stage of step or stage, the element of method disclosed here can occur in different orders or simultaneously.In addition, the element of method disclosed here can occur with other elements that are not clearly presented and described here.In addition, all elements of method described here may not be needed to realize method according to the present invention.Although aspect, feature and element have been described here with particular combination, each aspect, feature or element can be used separately, or can use with the various combination that has or does not have other aspects, feature and element.

[0270] The above aspects, examples and implementations have been described to facilitate the understanding that the present invention is not restrictive. On the contrary, the present invention covers various modifications and equivalent arrangements included within the scope of the appended claims, which scope should be given the broadest interpretation to include all such modifications and equivalent structures allowed by law.

Claims

1. A method for centralized shared scenario-specific operation control management, the method comprising: The centralized shared scene specific operation control management device performs centralized shared scene specific operation control management, wherein the centralized shared scene specific operation control management includes: receiving shared scenario-specific operational control management input data from the autonomous vehicle; Verifying the shared scenario specific operation control management input data; identifying a current different vehicle operating scenario based on the shared scenario-specific operational control management input data; generating shared scenario-specific operational control management output data based on the current different vehicle operational scenarios; and Sending the shared scenario specific operation control management output data; The step of generating the shared scenario specific operation control management output data includes: In response to determining that a current strategy for the current different vehicle operation scenario is available, including the current strategy in the shared scenario-specific operation control management output data, wherein generating the shared scenario-specific operation control management output data comprises: including the autonomous vehicle in a plurality of autonomous vehicles, wherein a respective host vehicle in the plurality of autonomous vehicles is currently associated with the current different vehicle operating scenario; and In response to determining that a current strategy for a defined model of the current different vehicle operating scenario is unusable: determining an expected complexity metric for generating the current policy based on the defined model; In response to determining that a target autonomous vehicle of the plurality of autonomous vehicles having sufficient available resources based on the expected complexity metric is available, including a request to generate the current strategy in the shared scenario-specific operational control management output data; and The current strategy is generated in response to a determination that a target autonomous vehicle of the plurality of autonomous vehicles having sufficient available resources based on the expected complexity metric is unavailable.

2. The method according to claim 1, wherein Identifying the current different vehicle operation scenarios includes: generating a route for the autonomous vehicle from a starting location in a vehicle transportation network, through the vehicle transportation network, to a destination location in the vehicle transportation network, in response to a determination that the shared scenario-specific operational control management input data omits a route and includes an origin identifier and a destination identifier, wherein the origin identifier indicates the origin location, and wherein the destination identifier indicates the destination location; In response to determining that the shared scenario-specific operation control management input data includes a route, identifying the route as a current route; and The current different vehicle operating scenarios are identified based on the current route, such that traversal of the route by the autonomous vehicle includes traversal of the current different vehicle operating scenarios.

3. The method according to claim 1, wherein Generating the shared scenario specific operation control management output data includes: previously received experience data identifying said current different vehicle operating scenarios; and The previously received experience data is included in the shared scenario-specific operational control management output data.

4. The method according to claim 1, wherein Sending the shared scenario specific operation control management output data includes: In response to including the request to generate the current policy in the shared scenario-specific operational control management output data, the shared scenario-specific operational control management output data is sent to the target autonomous vehicle.

5. The method according to claim 1, wherein Verifying the shared scenario specific operation control management input data includes: In response to determining that the shared scenario-specific operation control management input data includes the strategy of the current different vehicle operation scenarios: validating the policy; and In response to determining that the strategy is effective, the strategy is associated with the current different vehicle operation scenarios.

6. The method according to claim 1, wherein Verifying the shared scenario specific operation control management input data includes: In response to determining that the shared scenario-specific operational control management input data includes current experience data associated with the current different vehicle operational scenario: verifying the current empirical data; and In response to determining that the current experience data is valid, the current experience data is integrated into an experience data set associated with the current different vehicle operation scenarios.

7. The method according to claim 6, wherein: Integrating the current experience data into an experience data set associated with the current different vehicle operating scenarios includes: identifying similar experience data from the experience data set based on the determined similarity to the current experience data; and An updated experience data set associated with the current different vehicle operating scenario is generated based on the similar experience data and the current experience data.

8. The method according to claim 7, wherein: Generating the updated experience dataset includes pruning the experience dataset.

9. The method according to claim 7, wherein: Generating the updated experience data set includes merging the current experience data with the similar experience data.

10. The method according to claim 1, wherein Identifying the current different vehicle operation scenarios includes: In response to determining that the shared scenario-specific operational control management input data indicates a policy override of policies for different vehicle operational scenarios: determining scenario branch metrics for the different vehicle operation scenarios; In response to determining that the scenario branch metric is within a scenario branch threshold, identifying the different vehicle operating scenario as the current different vehicle operating scenario; and In response to determining that the scenario branch metric exceeds a scenario branch threshold, the current different vehicle operating scenario is identified based on the different vehicle operating scenario.

11. The method according to claim 1, wherein Generating the shared scenario specific operation control management output data includes: In response to determining that current experience data for the current different vehicle operation scenario is available, the current experience data is included in the shared scenario-specific operation control management output data.

12. A device for centralized shared scenario-specific operation control management, comprising: non-transitory computer-readable media; as well as A processor configured to execute instructions stored on the non-transitory computer-readable medium to implement the method according to claim 1.

13. A non-transitory computer-readable storage medium comprising executable instructions that, when executed by a processor, facilitate performing the method of claim 1.

Images