Vehicle guidance with system optimization

Abstract

Vehicle guidance with system optimization can include traversing, by a current vehicle, a vehicle transportation network by obtaining, by the current vehicle, system utility vehicle guidance data for a current portion of the vehicle transportation network and traversing, by the current vehicle, the current portion of the vehicle transportation network according to the system utility vehicle guidance data. Obtaining system utility vehicle guidance data can include obtaining vehicle operation data for a region of the vehicle transportation network, where the vehicle operation data includes current operation data for a plurality of vehicles operating in the region; operating a system utility vehicle guidance model for the region; obtaining, from the system utility vehicle guidance model, system utility vehicle guidance data for the region in response to the vehicle operation data; and outputting the system utility vehicle guidance data to the current vehicle.

Description

Technical Field

[0001] This invention relates to vehicle operation, including methods, apparatus, and non-transitory computer-readable media for performing system-optimized vehicle guidance. Background Technology

[0002] Vehicles operating within a vehicle transportation network (such as manually controlled vehicles, semi-autonomous vehicles, or autonomous vehicles) can traverse the network or a portion thereof by performing a series of discrete vehicle control operations identified based on maximizing the predicted operational utility of the respective vehicle. Summary of the Invention

[0003] This article discloses aspects, features, elements, implementations, and examples of vehicle guidance with system optimization.

[0004] One aspect of the disclosed embodiments is a method for traversing a vehicle transportation network using a vehicle guided by a system-optimized vehicle. The method includes: obtaining system utility vehicle guidance data of the current portion of the vehicle transportation network from the vehicle, and traversing the current portion of the vehicle transportation network by the vehicle based on the system utility vehicle guidance data.

[0005] Another aspect of the disclosed embodiments is a method for vehicle guidance with system optimization. The method includes: obtaining vehicle operation data for a region of a vehicle transportation network, wherein the vehicle operation data includes current operation data of a plurality of vehicles operating in the region; a system utility vehicle guidance model operating the region; obtaining system utility vehicle guidance data for the region from the system utility vehicle guidance model in response to the vehicle operation data; and outputting the system utility vehicle guidance data.

[0006] Another aspect of the disclosed embodiments is a method for vehicle guidance with system optimization. The method includes: obtaining system utility vehicle guidance data for a current portion of a vehicle transportation network from a vehicle, and traversing the current portion of the vehicle transportation network by the vehicle based on the system utility vehicle guidance data. Obtaining the system utility vehicle guidance data includes: obtaining vehicle operation data for a region of the vehicle transportation network, wherein the vehicle operation data includes current operation data of a plurality of vehicles operating in the region; a system utility vehicle guidance model operating the region; obtaining system utility vehicle guidance data for the region from the system utility vehicle guidance model in response to the vehicle operation data; and outputting the system utility vehicle guidance data.

[0007] These and other aspects, features, elements, implementations, and variations of the methods, apparatuses, processes, and algorithms disclosed herein will be described in further detail below. Attached Figure Description

[0008] The various aspects of the methods and apparatus disclosed herein will become more apparent by referring to the examples provided in the following description and accompanying figures:

[0009] Figure 1 The diagram shows examples of vehicles that can realize the aspects, features, and elements disclosed herein.

[0010] Figure 2 The diagram is an example of a vehicle transportation and communication system that can realize the aspects, features and elements disclosed herein.

[0011] Figure 3 This is a diagram of a transportation network consisting of various vehicles.

[0012] Figure 4 This is a diagram illustrating an example of an autonomous vehicle operation and management system.

[0013] Figure 5 This is a flowchart illustrating an example of vehicle guidance with system optimization according to an embodiment of the present invention. Detailed Implementation

[0014] Vehicles operating within a transportation network (such as manually controlled vehicles, semi-autonomous vehicles, or autonomous vehicles) traverse the network or a portion thereof by performing a series of discrete vehicle control operations (such as vehicle control actions or route determination). Each discrete vehicle control operation has operational costs such as risk (or conversely, safety) and travel time. These operational costs may be interrelated. For example, increasing vehicle speed may reduce operational costs associated with travel time but may increase operational costs associated with risk.

[0015] The weighted sum of operating costs associated with vehicle control operations can be identified as the operational utility of that vehicle control operation. Maximizing operational utility balances the minimization of various operating costs, such as risk (or conversely, safety) and travel time. Although this paper describes operational utility in terms of risk and travel time, other operating costs, such as fuel utilization, can also be used. The operational utility of a vehicle control operation for a vehicle performing a vehicle control operation can be identified as vehicle-specific operational utility.

[0016] Controlling a vehicle in response to its current operating parameters and current operating environment (such as being within a defined distance of the vehicle) within a vehicle transportation network aims to maximize its specific operational utility. Information used to identify vehicle-specific operational utility may omit information that could affect vehicle operation or may not be properly weighted. For example, for some vehicles, information that might affect vehicle operation (such as information related to the area's operating environment in addition to the vehicle's current operating environment) may be unavailable to the vehicle or its operator (manual or autonomous), or may be available but unused or improperly weighted. In another example, response delays—the time delay from indicating an event (or encounter) in an area that might affect vehicle operation to detecting the event or data representing the event, and then to identifying and performing vehicle control actions in response to the event—may limit the operational utility of the vehicle control actions. The difference between the predicted operational utility and the observed operational utility can be correlated with the difference between the operational information used and their relative weights.

[0017] For some vehicles, maximizing vehicle-specific operational utility may be related to suboptimal system utility. System utility balances or aggregates the operational utility of vehicles operating within a defined area of ​​the vehicle transportation network. Maximizing system utility may include using information that is unavailable, unused, or improperly weighted for maximizing vehicle-specific operational utility. Suboptimal system utility may correspond to the difference between predicted and observed vehicle-specific operational utility.

[0018] System-optimized vehicle guidance includes obtaining vehicle operation and environmental data for vehicles within a defined area of ​​the vehicle transportation network. This vehicle operation and environmental data may include data that is unavailable, unused, or improperly weighted for maximizing the utility of vehicle-specific operations on a vehicle-by-vehicle basis for each vehicle in the area. System-optimized vehicle guidance includes: operating a system utility vehicle guidance model that maximizes the system utility of the area. System-optimized vehicle guidance includes: obtaining per-vehicle system utility vehicle guidance data from the system utility vehicle guidance model for the area in response to the vehicle operation and environmental data for that area. System-optimized vehicle guidance includes: providing system utility vehicle guidance data to each participating vehicle operating in the area.

[0019] Compared to regions where participating vehicles are omitted from the list of those operating in the region, regions including participating vehicles offer improved system utility in the observed area. This is because participating vehicles acquire system utility vehicle guidance data and traverse at least a portion of the vehicle transportation network within the region based on this data. Since the operation of vehicles (such as participating vehicles) affects the operation of other vehicles (such as vehicles operating within the participating vehicle's environment, which may be non-participating vehicles), a relatively small proportion (e.g., one percent) of participating vehicles relative to non-participating vehicles can effectively maximize the system utility of the region. This can improve the observed vehicle-specific operational utility of vehicles (including both participating and non-participating vehicles). In some embodiments, the improvement in system utility of the region may be related to the proportion of participating vehicles.

[0020] Figure 1 This is a diagram illustrating an example of a vehicle that can implement the aspects, features, and elements disclosed herein. As shown, vehicle 1000 includes a chassis 1100, a powertrain 1200, a controller 1300, and wheels 1400. Although vehicle 1000 is shown as including four wheels 1400 for simplicity, one or more other propulsion devices (such as pushers or step plates) may be used. Figure 1 In this system, the lines that interconnect components such as powertrain 1200, controller 1300, and wheels 1400 indicate information such as data or control signals, power such as electricity or torque, or both information and power that can communicate between the components. For example, controller 1300 may receive power from powertrain 1200 and may communicate with powertrain 1200, wheels 1400, or both to control vehicle 1000. This may include controlling the dynamic state of vehicle (such as by accelerating or decelerating), controlling the directional state of vehicle (such as by steering), or otherwise controlling vehicle 1000.

[0021] As shown in the figure, the powertrain 1200 includes a power source 1210, a transmission 1220, a steering unit 1230, and an actuator 1240. Other components of the powertrain (such as suspension, drive shafts, wheel axles, or exhaust systems) or combinations of components may be included. Although shown separately, wheels 1400 may be included in the powertrain 1200.

[0022] Power source 1210 may include an engine, a battery, or a combination thereof. 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, 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 a prime mover to one or more wheels of wheel 1400. Power source 1210 may include a potential energy unit, such as one or more dry cell batteries (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.

[0023] The transmission 1220 can receive energy (such as kinetic energy) from the power source 1210 and can transmit that energy to the wheels 1400 to provide prime mover power. The transmission 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 the steering unit 1230 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 1220, the steering unit 1230, or any combination thereof to operate the vehicle 1000.

[0024] As shown in the figure, 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 components of the controller 1300 can be integrated into any number of individual 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, controller 1300 may include a power source such as a battery. Although shown as separate elements, positioning unit 1310, electronic communication unit 1320, processor 1330, memory 1340, user interface 1350, sensor 1360, electronic communication interface 1370, or any combination thereof may be integrated into one or more electronic units, circuits, or chips.

[0025] Processor 1330 may include any existing or subsequently developed means or combination of means capable of manipulating or processing signals or other information, including optical processors, quantum processors, molecular processors, or combinations thereof. For example, 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. Processor 1330 may be operatively coupled to positioning unit 1310, memory 1340, electronic communication interface 1370, electronic communication unit 1320, user interface 1350, sensor 1360, powertrain 1200, or any combination thereof. For example, the processor may be operatively coupled to memory 1340 via communication bus 1380.

[0026] Memory 1340 may include any tangible, non-transitory, computer-usable or computer-readable medium capable of, for example, containing, storing, communicating or transporting machine-readable instructions or any information associated therewith, for use by or in connection with processor 1330. Memory 1340 may, for example, be 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.

[0027] The communication interface 1370 can be a wireless antenna, a wired communication port, an optical communication port, or any other wired or wireless unit capable of interacting with the wired or wireless electronic communication medium 1500, as shown in the figure. Although Figure 1 A communication interface 1370 is shown that communicates via a single communication link, but the communication interface can be configured to communicate via multiple communication links. Although Figure 1 A single communication interface 1370 is shown, but the vehicle may include any number of communication interfaces.

[0028] The communication unit 1320 can be configured to send or receive signals via a wired or wireless electronic communication medium 1500 (such as via a communication interface 1370). Although in Figure 1Although not explicitly shown, communication unit 1320 can be configured to transmit, receive, or both via any wired or wireless communication medium (such as radio frequency (RF), ultraviolet (UV), visible light, optical fiber, wired lines, or combinations 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 can 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.

[0029] Positioning unit 1310 can determine geographic location information, such as the longitude, latitude, altitude, direction of travel, or speed of the vehicle 1000. For example, the positioning unit may include a Global Positioning System (GPS) unit, such as a National Marine Electronics Association (NMEA) unit with Wide Area Augmentation System (WAAS) enabled, a radio triangulation unit, or a combination thereof. Positioning unit 1310 can be used to obtain information, such as 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.

[0030] User interface 1350 may include any unit capable of human interaction, such as a virtual or physical keyboard, touchpad, display, touch display, heads-up display, virtual display, augmented reality display, haptic display, feature tracking device (such as an eye-tracking device), speaker, microphone, camera, sensor, printer, or any combination thereof. As shown, user interface 1350 may be operatively coupled to processor 1330 or to any other element of controller 1300. Although shown as a single unit, user interface 1350 may include one or more physical units. For example, user interface 1350 may include an audio interface for audio communication with a person and a touch display for vision- and touch-based communication with a person. User interface 1350 may include multiple displays, such as multiple physically separate units, multiple defined portions within a single physical unit, or combinations thereof.

[0031] Sensor 1360 may include one or more sensors (such as a sensor array) that are operable to provide information that can be used to control the vehicle. Sensor 1360 may provide information related to the current operating characteristics of the vehicle 1000. Sensor 1360 may include, for example, a speed sensor, an acceleration sensor, a steering angle sensor, a traction-related sensor, a braking-related sensor, a steering wheel position sensor, an eye-tracking sensor, a seat position sensor, or any sensor or combination of sensors that are operable to report information related to certain aspects of the current dynamic state of the vehicle 1000.

[0032] Sensor 1360 may include one or more sensors operable to obtain information relating to the physical environment surrounding vehicle 1000. For example, one or more sensors may detect road geometry and features (such as lane markings) and obstacles (such as fixed obstacles, vehicles, and pedestrians). Sensor 1360 may be or may include one or more cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of vehicle environment sensing device, or a combination of such devices, now known or subsequently developed. In some embodiments, sensor 1360 and positioning unit 1310 may be a combined unit.

[0033] Although not shown separately, vehicle 1000 may include a trajectory controller. For example, controller 1300 may include a trajectory controller. The trajectory controller is operable to obtain information describing the current state of vehicle 1000 and a planned route for vehicle 1000, and to determine and optimize the trajectory of vehicle 1000 based on that information. In some embodiments, the trajectory controller may output a signal operable to control vehicle 1000 such that 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 powertrain 1200, wheels 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 position. In some embodiments, the optimized trajectory may be one or more paths, lines, curves, or combinations thereof.

[0034] One or more of the wheels 1400 may be: a steering wheel that can pivot to a steering angle under the control of the steering unit 1230; a drive wheel that can be twisted to propel the vehicle 1000 under the control of the transmission 1220; or a steering drive wheel that can steer and propel the vehicle 1000.

[0035] although Figure 1 Not shown in the diagram, but the vehicle may include those not listed. Figure 1The units or components shown, such as housings, Bluetooth module, FM radio unit, Near Field Communication (NFC) module, Liquid Crystal Display (LCD) unit, Organic Light Emitting Diode (OLED) display unit, speaker, or any combination thereof.

[0036] Vehicle 1000 can be an autonomous vehicle that can be autonomously controlled to traverse a part of a vehicle transport network without direct human intervention. Although in Figure 1 Not shown separately, however, an autonomous vehicle may include an autonomous vehicle control unit capable of route selection, navigation, and control. The autonomous vehicle control unit may be integrated with other units of the vehicle. For example, controller 1300 may include the autonomous vehicle control unit.

[0037] The autonomous vehicle control unit can control or operate vehicle 1000 to traverse a portion of the vehicle transportation network based on current vehicle operating parameters. The autonomous vehicle control unit can control or operate 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 vehicle 1000, to a destination based on vehicle information, environmental information, vehicle transportation network data representing the transportation network, or a combination thereof, and can control or operate vehicle 1000 to traverse the transportation network based on this 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 vehicle 1000 to travel from the starting point to the destination.

[0038] Figure 2 This is a diagram illustrating an example of a vehicle transportation and communication system that can implement the aspects, features, and elements disclosed herein. The vehicle transportation and communication system 2000 may include, for example... Figure 1 One or more vehicles 2100 / 2110, such as the vehicle 1000 shown, can travel via one or more parts of a vehicle transport network 2200 and can communicate via one or more electronic communication networks 2300. Although in Figure 2 It is not explicitly stated, but vehicles may traverse areas not explicitly or fully included in the vehicle transport network (such as off-road areas).

[0039] The electronic communication network 2300 may be, for example, a multiple access system and may provide communication between the vehicle 2100 / 2110 and one or more communication devices 2400 / 2410, such as voice communication, data communication, video communication, message transmission communication, or combinations thereof. For example, the vehicle 2100 / 2110 may receive information such as information representing the vehicle transportation network 2200 from the communication device 2400 via the network 2300. In another example, the vehicle 2100 / 2110 may receive information such as information representing the vehicle transportation network 2200 from the communication device 2410 via direct wireless communication.

[0040] In some embodiments, vehicle 2100 / 2110 may communicate via a wired communication link (not shown), a wireless communication link 2310 / 2320 / 2370 / 2380 / 2385, or any combination of wired or wireless communication links. For example, as shown, vehicle 2100 / 2110 may communicate via a terrestrial wireless communication link 2310, a non-terrestrial wireless communication link 2320, or a combination thereof. The terrestrial wireless communication link 2310 may 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.

[0041] Vehicles 2100 / 2110 can communicate with infrastructure equipment. For example, Figure 2 The communication devices 2400 / 2410 shown may be infrastructure devices. Infrastructure devices may be associated with defined areas (such as lanes, road segments, consecutive groups of road segments, roads, or intersections) or defined geographical areas (such as blocks, communities, districts, counties, municipalities, states, countries, etc.) or other defined geographical areas within a transportation network. Infrastructure devices may be centralized or distributed. For example, communication device 2400 may be a centralized infrastructure device, and communication device 2410 may be a distributed infrastructure device. Vehicles 2100 / 2110 may communicate with communication device 2410 via direct communication links 2380 / 2385 or via network 2300. Direct communication links 2380 / 2385 may be wireless communication links.

[0042] Vehicles 2100 / 2110 can communicate with other vehicles 2100 / 2110. For example, a primary vehicle (HV) or main vehicle 2100 can receive one or more inter-vehicle messages (such as Basic Safety Messages (BSMs)) from a remote vehicle (RV) or target vehicle 2110 via a direct communication link 2370 or via a network 2300. For example, the remote vehicle 2110 can broadcast the message to the primary vehicle within a defined broadcast range (such as 300 meters). In some embodiments, the primary vehicle 2100 can receive the message via a third party such as a signal repeater (not shown) or other remote vehicles (not shown). Vehicles 2100 / 2110 can periodically send one or more inter-vehicle messages based on, for example, defined intervals (such as 100 milliseconds). The direct communication link 2370 can be, for example, a wireless communication link.

[0043] Messages between automated vehicles can include vehicle identification information, geospatial status information (such as longitude, latitude, or altitude), geospatial location accuracy information, kinematic status information (such as vehicle acceleration, yaw rate, speed, heading, braking system status, throttle position, and steering wheel angle), or vehicle route selection information, or vehicle operational status information (such as vehicle dimensions, headlight status, turn signal information, wiper status, transmission information, or any other information or combination of information related to changing the vehicle's gear position). For example, transmission status information can indicate whether the transmission causing the vehicle to change gears is in neutral, parked, forward, or reverse.

[0044] Vehicle 2100 can communicate with communication network 2300 via access point 2330. Access point 2330, which may include a computing device, can be configured to communicate with vehicle 2100, communication network 2300, one or more communication devices 2400 / 2410, or a combination thereof, via wired or wireless communication links 2310 / 2340. For example, access point 2330 can be a base station, base transceiver station (BTS), Node-B, enhanced Node-B (eNode-B), Home Node-B (HNode-B), wireless router, wired router, hub, repeater, switch, or any similar wired or wireless device. Although Figure 2 The interface is shown as a single unit, but the access point can include any number of interconnecting elements.

[0045] The vehicle 2100 can communicate with the communication network 2300 via satellite 2350 or other non-terrestrial communication devices. The satellite 2350, 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 / 2410, or a combination thereof, via one or more communication links 2320 / 2360. Although Figure 2 The satellite is shown as a single unit, but it can include any number of interconnecting elements.

[0046] Electronic communication network 2300 can be any type of network configured to provide voice communication, data communication, or any other type of electronic communication. For example, electronic communication 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 communication system. Electronic communication network 2300 can use communication protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Internet Protocol (IP), Real-Time Transfer Protocol (RTP), Hypertext Transfer Protocol (HTTP), or combinations thereof. Although... Figure 2 While shown as a single unit, the electronic communication network can include any number of interconnecting elements. The communication device 2400 / 2410 can communicate, for example, via communication link 2390.

[0047] Vehicle 2100 can identify a portion of or conditions of the vehicle transportation network 2200. For example, vehicle 2100 may include one or more onboard sensors 2105 (such as...). Figure 1 The sensor 1360 shown, etc., may include one or more on-board sensors 2105 such as speed sensors, wheel speed sensors, cameras, gyroscopes, optical sensors, laser sensors, radar sensors, acoustic sensors, or any other sensor or device or combination thereof capable of determining or identifying a portion or condition of the vehicle transportation network 2200. Sensor data may include lane line data, remote vehicle location data, or both.

[0048] Vehicle 2100 may use information communicated via network 2300 (such as information representing vehicle transport network 2200, information identified by one or more on-board sensors 2105, or a combination thereof) to traverse one or more portions of one or more vehicle transport networks 2200.

[0049] Although for the sake of simplicity, Figure 2The diagram shows two vehicles 2100 and 2110, a vehicle transportation network 2200, an electronic communication network 2300, and two communication devices 2400 / 2410, but any number of vehicles, networks, or computing devices can be used. The vehicle transportation and communication system 2000 may include devices not shown in the diagram. Figure 2 The device, unit, or element shown. Although vehicle 2100 is shown as a single unit, the vehicle may include any number of interconnecting elements.

[0050] Although the vehicle 2100 is shown 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 / 2410 via a direct communication link such as a Bluetooth communication link.

[0051] In some embodiments, vehicle 2100 / 2210 may be associated with entity 2500 / 2510 (such as the driver, operator, or owner of the vehicle). In some embodiments, entity 2500 / 2510 associated with vehicle 2100 / 2110 may be associated with one or more personal electronic devices 2502 / 2504 / 2512 / 2514 (such as smartphone 2502 / 2512 or computer 2504 / 2514). In some embodiments, personal electronic devices 2502 / 2504 / 2512 / 2514 may communicate with the corresponding vehicle 2100 / 2110 via direct or indirect communication links. Although in Figure 2 One entity 2500 / 2510 is shown as associated with a vehicle 2100 / 2110, but any number of vehicles can be associated with an entity and any number of entities can be associated with a vehicle.

[0052] Figure 3 This is a diagram of a portion of a vehicle transportation network according to the present invention. The vehicle transportation network 3000 may include one or more unnavigable areas 3100 (such as buildings, etc.), one or more partially navigable areas (such as parking areas 3200, etc.), one or more navigable areas (such as roads 3300 / 3400, etc.), or combinations thereof. In some embodiments, autonomous vehicles (such as...) Figure 1 The vehicle shown is 1000. Figure 2 One of the vehicles shown in the diagram 2100 / 2110, a semi-autonomous vehicle, or any other vehicle capable of autonomous driving may traverse one or more sections of the vehicle transport network 3000.

[0053] The transportation network 3000 may include one or more interchanges 3210 between one or more navigable or partially navigable areas 3200 / 3300 / 3400. For example, Figure 3 A 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 parking spaces 3220.

[0054] A portion of the transportation network 3000 (such as roads 3300 / 3400, etc.) may include one or more lanes 3320 / 3340 / 3360 / 3420 / 3440, and may be connected with... Figure 3 The arrow indicates one or more directions of travel.

[0055] Transportation networks or parts thereof (such as) Figure 3 A portion of the vehicle transportation network 3000 shown can be represented as vehicle transportation network data. For example, vehicle transportation network data can be represented as a hierarchy of elements (such as markup language elements that can be stored in a database or file). For simplicity, the accompanying figures depict vehicle transportation network data representing portions of the vehicle transportation network as diagrams or maps; however, vehicle transportation network data can be represented in any computer-usable format capable of representing the vehicle transportation network or a portion thereof. Vehicle transportation network data may include vehicle transportation network control information, such as driving direction information, speed limit information, toll information, gradient information (such as inclination or angle information), road surface material information, aesthetic information, defined hazard information, or combinations thereof.

[0056] Vehicle transportation networks can be associated with, or may include, pedestrian transportation networks. For example, Figure 3 This includes a portion 3600 of a pedestrian transport network, which may be a pedestrian walkway. Although in Figure 3 Although not shown separately, pedestrian navigable areas (such as pedestrian crossings) may correspond to navigable areas or parts of navigable areas in a vehicle transportation network.

[0057] A portion or combination of portions of a vehicle transportation network can be identified as points of interest or destinations. For example, vehicle transportation network data can identify buildings (such as unnavigable area 3100) and adjacent partially navigable parking areas 3200 as points of interest, vehicles can identify these points of interest as destinations, and vehicles can travel from their origin to their destination by traversing the vehicle transportation network. Although parking areas 3200 are associated with unnavigable area 3100... Figure 3 The destination may be shown as adjacent to the non-navigable area 3100, but the destination may include, for example, a building and a parking area that is not physically or geographically adjacent to the building.

[0058] Identifying a destination can include identifying the location of the destination, which can be a discrete, uniquely identifiable geographic location. For example, a transportation network can include a defined location for the destination, such as a street address, postal address, transportation network address, GPS address, or a combination thereof.

[0059] A destination can be associated with one or more entrances (such as...) Figure 3 The entry point shown (e.g., 3500) is associated with this. Vehicle transportation network data can include defined entry point location information, such as information identifying the geographic location of the entry point associated with the destination.

[0060] The destination can be connected to one or more docking points (such as...) Figure 3 This is associated with docking point 3700, etc. Docking point 3700 can be a designated or undesignated location or area near the destination, where the autonomous vehicle can stop, dock, or park, thereby enabling docking operations (such as passenger loading or unloading).

[0061] Transportation network data can include docking point information, such as information identifying one or more geographic locations associated with a destination. Although in Figure 3 Although not shown separately, docking location information can identify the type of docking operation associated with docking location 3700. For example, a destination may be associated with a first docking location for passenger loading and a second docking location for passenger unloading. Although autonomous vehicles may park at docking locations, the docking location associated with a destination may be independent of and different from the parking area associated with the destination.

[0062] Figure 4 This is a diagram illustrating 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 can operate on autonomous vehicles (such as...) Figure 1 The vehicle shown is 1000. Figure 2 This can be implemented in one of the vehicles shown, such as the 2100 / 2110, a semi-autonomous vehicle, or any other vehicle that achieves autonomous driving.

[0063] like Figure 4As shown, the autonomous vehicle operation management system 4000 includes an autonomous vehicle operation management controller 4100 (AVOMC), an operation environment monitor 4200, and a scenario-specific operation control evaluation module 4300.

[0064] Autonomous vehicles can traverse a vehicle transport network or a portion thereof, which may include traversing different vehicle operating scenarios. Different vehicle operating scenarios can include any clearly identifiable set of operating conditions that may affect the operation of the autonomous vehicle within its defined spatiotemporal area or operating environment. For example, different vehicle operating scenarios may be based on the number or base of roads, road segments, or lanes that the autonomous vehicle can traverse within a defined spatiotemporal distance. In another example, different vehicle operating scenarios may be based on one or more traffic control devices that may affect the operation of the autonomous vehicle within its defined spatiotemporal area or operating environment. In another example, different vehicle operating scenarios may be based on one or more identifiable rules, regulations, or laws that may affect the operation of the autonomous vehicle within its defined spatiotemporal area or operating environment. In yet another example, different vehicle operating scenarios may be based on one or more identifiable external objects that may affect the operation of the autonomous vehicle within its defined spatiotemporal area or operating environment.

[0065] For simplicity, this article may refer to vehicle operation scenario types or classes to describe similar vehicle operation scenarios. A vehicle operation scenario type or class can refer to a scenario definition pattern or set of definition patterns. 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 transportation network that includes one or more pedestrians, or is within the defined proximity of one or more pedestrians, such as where the pedestrian is crossing or approaching the autonomous vehicle's intended path; a lane-changing scenario may include an autonomous vehicle crossing a portion of a vehicle transportation network by changing lanes; a lane-merging scenario may include an autonomous vehicle crossing a portion of a vehicle transportation network by merging from a first lane to the merged lane; and an obstacle-crossing scenario may include an autonomous vehicle crossing a portion of a vehicle transportation network by passing through an obstacle or barrier. Although this article describes pedestrian vehicle operation scenarios, intersection vehicle operation scenarios, lane-changing vehicle operation scenarios, lane-merging vehicle operation scenarios, and obstacle-crossing vehicle operation scenarios, any other vehicle operation scenario or vehicle operation scenario type may be used.

[0066] The AVOMC 4100 or other unit of an autonomous vehicle can control the autonomous vehicle to traverse a vehicle transportation network or a portion thereof. Controlling the autonomous vehicle to traverse a 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 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 actions.

[0067] The AVOMC 4100 can receive, identify, or otherwise access operating environment data representing the operating environment of an autonomous vehicle or one or more aspects thereof. The operating environment of an autonomous vehicle may include a clearly identifiable set of operating conditions that may affect the operation of the autonomous vehicle within its defined spatiotemporal region, within the defined spatiotemporal region of its identified route, or a combination thereof. For example, operating conditions that may affect the operation of the autonomous vehicle can be identified based on sensor data, vehicle transport network data, route data, or any other data or combination of data representing the defined or determined operating environment of the vehicle. Operating conditions that may affect the operation of an autonomous vehicle may include roads, road sections, or lanes that the autonomous vehicle may traverse; traffic control devices that may affect the operation of the autonomous vehicle; identifiable rules, regulations, or laws that may affect the operation of the autonomous vehicle; identifiable external objects that may affect the operation of the autonomous vehicle; the operational status of the autonomous vehicle; the operational status of one or more passengers on the autonomous vehicle; the operational status of cargo on the autonomous vehicle; or any other identifiable conditions, status, or event that may affect the operation of the autonomous vehicle.

[0068] Operating environment data may include vehicle information for autonomous vehicles, such as information indicating the geospatial location of the autonomous vehicle, information that associates the geospatial location of the autonomous vehicle with information representing the vehicle's transportation network, the autonomous vehicle's route, the autonomous vehicle's speed, the autonomous vehicle's acceleration status, the autonomous vehicle's passenger information, or any other information related to the autonomous vehicle or its operation.

[0069] Operating environment data may include information representing a vehicle transportation network that is close to the identified route of the autonomous vehicle (such as within a defined spatial distance (such as 300 meters) of a portion of the vehicle transportation network along the identified route), and this information may include information indicating the geometry of one or more aspects of the vehicle transportation network, information indicating the conditions of the vehicle transportation network (such as road conditions), or any combination thereof.

[0070] Operating environment data may include information representing a vehicle transportation network near the autonomous vehicle (such as within a defined spatial distance of the autonomous vehicle, such as 300 meters), and this information may include information indicating the geometry of one or more aspects of the vehicle transportation network, information indicating the conditions of the vehicle transportation network (such as road conditions), or any combination thereof.

[0071] Operating environment data may include information representing external objects within the operating environment of an autonomous vehicle, such as information representing pedestrians, non-human animals, non-motorized transport devices such as bicycles or skateboards, motorized transport devices such as remote-controlled vehicles, or any other external objects or entities that may affect the operation of the autonomous vehicle.

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

[0073] Although this article describes operation scenarios for pedestrian vehicles, intersection vehicles, lane-changing vehicles, lane-merging vehicles, and obstacle-crossing vehicles, any other vehicle operation scenario can also be used.

[0074] Autonomous vehicles can simultaneously traverse multiple different vehicle operation scenarios within an operating environment. The Autonomous Vehicle Operation Management System 4000 can operate or control autonomous vehicles to traverse different vehicle operation scenarios under defined constraints (such as safety constraints, legal constraints, physical constraints, user acceptability constraints, or any other constraints or combinations thereof that may be defined or derived for the operation of the autonomous vehicle).

[0075] The AVOMC 4100 can monitor the operating environment of an autonomous vehicle or aspects thereof. Monitoring the operating environment of an autonomous vehicle can include identifying and tracking external objects, identifying different vehicle operating scenarios, or combinations of these actions. For example, the AVOMC 4100 can identify and track external objects within the operating environment of the autonomous vehicle. Identifying and tracking external objects can include: identifying the spatiotemporal location of each external object (which may be relative to the spatiotemporal location of the autonomous vehicle), and identifying one or more expected paths for each external object (which may include identifying the speed, trajectory, or both of the external object). For simplicity and clarity, the descriptions of locations, expected locations, paths, and expected paths herein may omit explicit indications of geospatial and temporal components; however, unless explicitly stated herein or otherwise clearly apparent from the context, locations, expected locations, paths, and expected paths described herein may include geospatial components, temporal components, or both. Monitoring the operating environment of an autonomous vehicle can include using operating environment data received from the operating environment monitor 4200. The AVOMC 4100 can monitor, update, or both monitor and update the operating environment data.

[0076] The operating environment monitor 4200 may include an unknown scene monitor, a scene-specific monitor, or a combination thereof.

[0077] An unknowable scene monitor (such as obstruction monitor 4210) can monitor the operating environment of an autonomous vehicle, generate operating environment data representing aspects of the autonomous vehicle's operating environment, and output the operating environment data to one or more scene-specific monitors, AVOMC 4100, or a combination thereof.

[0078] Scene-specific monitors (such as pedestrian monitor 4220, intersection monitor 4230, lane change monitor 4240, lane merging monitor 4250, or obstacle ahead monitor 4260) can monitor the operating environment of the autonomous vehicle, generate scene-specific operating environment data representing aspects of the autonomous vehicle's operating environment, and output the operating environment data to one or more scene-specific operation control evaluation modules 4300, AVOMC 4100, or combinations thereof. For example, pedestrian monitor 4220 can be an operating environment monitor for monitoring pedestrians, intersection monitor 4230 can be an operating environment monitor for monitoring intersections, lane change monitor 4240 can be an operating environment monitor for monitoring lane changes, lane merging monitor 4250 can be an operating environment monitor for lane merging, and obstacle ahead monitor 4260 can be an operating environment monitor for monitoring obstacles ahead. 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.

[0079] 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 transport network data, vehicle transport network geometry data, route data, or combinations thereof). For example, the pedestrian monitor 4220 can receive or otherwise access information such as sensor data that can indicate, correspond to, or otherwise associate with one or more pedestrians in the operating environment of the autonomous vehicle. The operating environment monitor 4200 can associate operating environment data or a portion thereof with the operating environment or an aspect thereof, such as with external objects (such as pedestrians, remote vehicles, etc.) or aspects of the vehicle transport network geometry.

[0080] The operating environment monitor 4200 can generate or otherwise identify information representing one or more aspects of the operating environment (such as aspects having external objects (such as pedestrians, remote vehicles, etc.) or vehicle transport network geometry), which may include filtering, extracting, or otherwise processing the operating environment data. The operating environment monitor 4200 can, for example, store information representing one or more aspects of the operating environment in the memory of the autonomous vehicle accessible by the AVOMC 4100 (such as...). Figure 1The operating environment monitor 4200 can output or allow the AVOMC 4100 to access information representing one or more aspects of the operating environment, such as information stored in the memory 1340 (as shown), the AVOMC 4100, or a combination of these actions. The operating environment monitor 4200 can output operating environment data to one or more components (such as the AVOMC 4100) of the autonomous vehicle operation management system 4000. Although in Figure 4 Not shown, but scene-specific operating environment monitors 4220, 4230, 4240, 4250, and 4260 can output operating environment data to unknown scene operating environment monitors (such as obstruction monitor 4210).

[0081] Pedestrian monitor 4220 can correlate, associate, or otherwise process operational environment data to identify, track, or predict the movement of one or more pedestrians. For example, pedestrian monitor 4220 can receive information (such as sensor data) from one or more sensors that corresponds to one or more pedestrians. Pedestrian monitor 4220 can associate sensor data with one or more identified pedestrians. This may include identifying the direction of travel, path (such as a predicted path), current or predicted rate, current or predicted acceleration rate, or a combination thereof for one or more of the identified pedestrians. Pedestrian monitor 4220 can output the identified, associated, or generated pedestrian information to or make it accessible to AVOMC 4100.

[0082] The intersection monitor 4230 can correlate, associate, or otherwise process operational environment data to identify, track, or predict the actions of one or more remote vehicles in the operational environment of an autonomous vehicle, identify intersections or aspects thereof in the operational environment of an autonomous vehicle, identify the geometry of a vehicle transport network, or combinations of these actions. For example, the intersection monitor 4230 can receive information (such as sensor data) from one or more sensors, which may correspond to: one or more remote vehicles in the autonomous vehicle's operating environment, an intersection in the autonomous vehicle's operating environment or one or more aspects thereof, the vehicle's transport network geometry, or a combination thereof. The intersection monitor 4230 can associate the sensor data with one or more identified remote vehicles in the autonomous vehicle's operating environment, an intersection in the autonomous vehicle's operating environment or one or more aspects thereof, the vehicle's transport network geometry, or a combination thereof. This may include being able to identify the current or expected direction of travel, path (such as expected path), current or expected speed, current or expected acceleration rate, or a combination thereof for one or more of the identified remote vehicles. The intersection monitor 4230 can output the identified, associated, or generated intersection information to or make it accessible to the AVOMC 4100.

[0083] The lane change monitor 4240 can correlate, associate, or otherwise process operational environment data to identify, track, or predict the actions of one or more remote vehicles in the operational environment of the autonomous vehicle corresponding to the lane change operation in geospatial space (such as information indicating a slow or stationary remote vehicle along the expected path of the autonomous vehicle), identify one or more aspects of the operational environment of the autonomous vehicle (such as the vehicle transport network geometry in the operational environment of the autonomous vehicle), or combinations of these actions. For example, lane change monitor 4240 may receive information (such as sensor data) from one or more sensors, which may correspond to: one or more remote vehicles in the geographic operating environment of an autonomous vehicle corresponding to a lane change operation, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof. Lane change monitor 4240 may associate sensor data with one or more identified remote vehicles in the geographic operating environment of an autonomous vehicle corresponding to a lane change operation, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof. This may include identifying the current or expected direction of travel, path (such as expected path), current or expected speed, current or expected acceleration rate, or a combination thereof for one or more of the identified remote vehicles. Lane change monitor 4240 may output the identified, associated, or generated lane change information to or make it accessible to AVOMC 4100.

[0084] The lane merging monitor 4250 can correlate, associate, or otherwise process operational environment data to identify, track, or predict the actions of one or more remote vehicles in the operational environment of an autonomous vehicle corresponding to a lane merging operation in geospatial space, identify one or more aspects of the operational environment of the autonomous vehicle (such as the vehicle transport network geometry in the operational environment of the autonomous vehicle), or combinations of these actions. For example, the lane change monitor 4250 can receive information (such as sensor data) from one or more sensors, which may correspond to: one or more remote vehicles in the geographic operating environment of the autonomous vehicle corresponding to the lane change operation, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof. The lane change monitor 4250 can associate the sensor data with one or more identified remote vehicles in the geographic operating environment of the autonomous vehicle corresponding to the lane change operation, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof. This may include being able to identify the current or expected direction of travel, path (such as expected path), current or expected speed, current or expected acceleration rate, or a combination thereof for one or more of the identified remote vehicles. The lane change monitor 4250 can output the identified, associated, or generated lane change information to or make it accessible to the AVOMC 4100.

[0085] The Forward Obstacle Monitor 4260 can correlate, correlate, or otherwise process operational environment data to identify one or more aspects of the autonomous vehicle's operational environment corresponding to forward obstacle maneuvering in geospatial space. For example, the Forward Obstacle Monitor 4260 can identify the vehicle transport network geometry in the autonomous vehicle's operational environment; the Forward Obstacle Monitor 4260 can identify one or more obstacles or hindrances in the autonomous vehicle's operational environment (such as slow-moving or stationary remote vehicles along the autonomous vehicle's intended path or its identified route); and the Forward Obstacle Monitor 4260 can identify, track, or predict the movement of one or more remote vehicles in the autonomous vehicle's operational environment. The Forward Obstacle Monitor 4250 can receive information (such as sensor data) from one or more sensors, which may correspond to: one or more remote vehicles in the operating environment of an autonomous vehicle corresponding to forward obstacle passage in geospatial space, one or more aspects of the operating environment of an autonomous vehicle in the operating environment of an autonomous vehicle, or a combination thereof. The Forward Obstacle Monitor 4250 can associate the sensor data with one or more identified remote vehicles in the operating environment of an autonomous vehicle corresponding to forward obstacle passage in geospatial space, one or more aspects of the operating environment of an autonomous vehicle, or a combination thereof. This may include being able to identify the current or expected direction of travel, path (such as expected path), current or expected speed, current or expected acceleration rate, or a combination thereof for one or more of the identified remote vehicles. The Forward Obstacle Monitor 4250 can output the identified, associated, or generated forward obstacle information to or make it accessible to the AVOMC 4100.

[0086] Obstruction monitor 4210 can receive operational environment data representing the operating environment or aspects thereof of an autonomous vehicle. Obstruction monitor 4210 can determine individual availability probabilities or corresponding obstruction probabilities for one or more portions of a vehicle transportation network (such as a portion of the vehicle transportation network near the autonomous vehicle), wherein the one or more portions may include portions of the vehicle transportation network corresponding to the autonomous vehicle's intended path (such as an intended path identified based on the autonomous vehicle's current route). Availability probabilities or corresponding obstruction probabilities can indicate the probability or likelihood that the autonomous vehicle can safely (e.g., without obstruction from external objects such as remote vehicles or pedestrians) traverse a portion of the vehicle transportation network or a spatial location within the vehicle transportation network. Obstruction monitor 4210 can continuously or periodically determine or update availability probabilities. Obstruction monitor 4210 can communicate availability probabilities or corresponding obstruction probabilities to AVOMC 4100.

[0087] The AVOMC 4100 can identify one or more different vehicle operation scenarios based on one or more aspects of the operating environment represented by operating environment data. For example, the AVOMC 4100 can identify different vehicle operation scenarios in response to the identification or based on operating environment data indicated by one or more operating environment monitors 4200. Different vehicle operation scenarios can be identified based on route data, sensor data, or a combination thereof. For example, the AVOMC 4100 can identify one or more different vehicle operation scenarios corresponding to an identified route of the vehicle (such as based on map data corresponding to the identified route). Multiple different vehicle operation scenarios can be identified based on one or more aspects of the operating environment represented by operating environment data. For example, operating environment data may include information indicating a pedestrian approaching an intersection along the expected path of the autonomous vehicle, and the AVOMC 4100 can identify a pedestrian vehicle operation scenario, an intersection vehicle operation scenario, or both.

[0088] AVOMC 4100 can instantiate one or more instances of scenario-specific operation control evaluation modules 4300 based on one or more aspects of the operating environment represented by operation environment data. Scenario-specific operation control evaluation modules 4300 may include scenario-specific operation control evaluation modules (SSOCEMs), such as pedestrian SSOCEM 4310, intersection SSOCEM 4320, lane changing SSOCEM 4330, lane merging SSOCEM 4340, obstacle crossing SSOCEM 4350, or combinations thereof. SSOCEM 4360 is shown using dashed lines to indicate that the autonomous vehicle operation management system 4000 may include any number of SSOCEMs 4300. For example, AVOMC 4100 can instantiate instances of SSOCEM 4300 in response to the identification of 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 operation environment data. For example, the operating environment data can indicate two pedestrians in the operating environment of the autonomous vehicle, and the AVOMC 4100 can 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.

[0089] The AVOMC 4100 can, for example, transmit, send, or otherwise make operational environment data or one or more aspects thereof available to another unit of the autonomous vehicle (such as a blockage monitor 4210 or one or more instances of SSOCEM 4300) by storing operational environment data or one or more aspects thereof in shared memory. For example, the AVOMC 4100 can communicate availability probabilities or corresponding blockage probabilities received from the blockage monitor 4210 to the various instantiated instances of SSOCEM 4300. The AVOMC 4100 can store operational environment data or one or more aspects thereof, such as storing it in the autonomous vehicle's memory (e.g., in shared memory). Figure 1 The memory shown is 1340, etc.

[0090] Controlling an autonomous vehicle to traverse a vehicle transportation network can 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 based on one or more of the candidate vehicle control actions; or a combination of these actions. For example, the AVOMC 4100 can receive one or more candidate vehicle control actions from various instances of the SSOCEM 4300. The AVOMC 4100 can identify vehicle control actions from the candidate vehicle control actions and control the vehicle, or it can provide the identified vehicle control actions to another vehicle control unit to traverse the vehicle transportation network based on the vehicle control actions.

[0091] Vehicle control actions can instruct vehicle control operations or maneuvers, such as controlling the motion state of the vehicle (e.g., by accelerating, decelerating, or stopping the vehicle), controlling the directional state of the vehicle (e.g., by turning or stopping the vehicle), or any other vehicle operation or combination of vehicle operations that can be performed by an autonomous vehicle in conjunction with traversing a part of a vehicle transport network.

[0092] For example, a "stop" vehicle control action may include controlling a vehicle to cross a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to stop the vehicle or otherwise control the vehicle to become or remain stationary; a "give way" vehicle control action may include controlling a vehicle to cross a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to decelerate the vehicle or otherwise control the vehicle to move at a speed within a defined threshold or range, wherein the defined threshold or range may be below or within a defined statutory speed limit; a "heading adjustment" vehicle control action may include controlling a vehicle to cross a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to change the vehicle's orientation relative to an obstruction, an external object, or both within a defined right-of-way parameter; and a "accelerate" vehicle control action may also be included. Braking actions may include controlling a vehicle to traverse a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to accelerate at a defined rate or at a rate within a defined range; decelerating vehicle control actions may include controlling a vehicle to decelerate at a defined rate or at a rate within a defined range by controlling a motion control unit, a trajectory control unit, or a combination of control units to maintain current operating parameters by controlling a vehicle to traverse a vehicle transport network or a portion thereof; and forward vehicle control actions may include controlling a vehicle to traverse a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to maintain current operating parameters (such as by maintaining current speed, current path or route, or current lane orientation); and forward vehicle control actions may include controlling a vehicle to traverse a vehicle transport network or a portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to initiate or resume a previously identified set of operating parameters. Although some vehicle control actions are described herein, other vehicle control actions may also be used.

[0093] Vehicle control actions 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, speed information, acceleration rate, or a combination thereof as a performance metric, or may explicitly or implicitly indicate that a currently or previously identified path, speed, acceleration rate, or a combination thereof can be maintained. Vehicle control actions may be composite vehicle control actions, which may include a sequence, combination, or both of vehicle control actions. For example, a "heading adjustment" 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 "heading adjustment" vehicle control action includes controlling the autonomous vehicle to slowly move forward a short distance (such as a few inches or a foot).

[0094] The AVOMC 4100 can uninstantiate instances of the SSOCEM 4300. For example, the AVOMC 4100 can identify different sets of operating conditions indicating different vehicle operation scenarios for autonomous vehicles, instantiate instances of the SSOCEM 4300 for different vehicle operation scenarios, monitor the operating conditions, and then determine the probability that one or more operating conditions have expired or have a probability below a defined threshold affecting the operation of the autonomous vehicle. The AVOMC 4100 can then uninstantiate instances of the SSOCEM 4300.

[0095] AVOMC 4100 can instantiate and deinstantiate instances of SSOCEM 4300 based on one or more vehicle operation management control metrics (such as intrinsicity metrics, urgency metrics, utility metrics, acceptability metrics, or combinations thereof). Intrinsicity metrics can indicate or represent, or be based on, spatial, temporal, or spatiotemporal distance or proximity, which can be the expected distance or proximity of a vehicle traversing the vehicle transport network from its current location to the portion of the vehicle transport network corresponding to the corresponding identified vehicle operation scenario. Urgency metrics can indicate or represent, or be based on, a measure of the spatial, temporal, or spatiotemporal distance that can be used to control the vehicle's traversal of the vehicle transport network corresponding to the corresponding identified vehicle operation scenario. Utility metrics can indicate or represent, or be based on, the expected value of instantiating an instance of SSOCEM 4300 corresponding to the corresponding identified vehicle operation scenario. Acceptability metrics can be safety metrics (such as metrics indicating collision avoidance), vehicle transport network control compliance metrics (such as metrics indicating compliance with vehicle transport network rules and regulations), physical capability metrics (such as metrics indicating the vehicle's maximum braking capacity), and user-defined metrics (such as user preferences). Other metrics or combinations of metrics can be used. Vehicle operation management control metrics can indicate defined rates, ranges, or limits. For example, acceptability metrics can indicate defined target deceleration rates, defined deceleration rate ranges, or defined maximum deceleration rates.

[0096] SSOCEM 4300 can include one or more models of various vehicle operation scenarios. The Autonomous Vehicle Operation Management System 4000 can include any number of SSOCEM 4300s, each including a model of a different vehicle operation scenario. SSOCEM 4300 can include one or more models from one or more model types. For example, SSOCEM 4300 can include partially observable Markov Decision Process (POMDP) ​​models, Markov Decision Process (MDP) models, classical programming models, partially observable stochastic game (POSG) models, distributed partially observable Markov Decision Process (Dec-POMDP) ​​models, reinforcement learning (RL) models, artificial neural network models, or any other model corresponding to a different vehicle operation scenario. Different types of models can have their own characteristics in terms of accuracy and resource utilization. For example, a POMDP model used to define a scenario may have higher accuracy and higher resource utilization than an MDP model used to define a scenario. Models included in SSOCEM 4300 can be sorted in a hierarchical manner, or based on accuracy. For example, a specified model (such as the most accurate model included in SSOCEM 4300) can be identified as the master model in SSOCEM 4300, and other models included in SSOCEM 4300 can be identified as slave models.

[0097] In the examples, one or more of the SSOCEM 4300 models may include a POMDP model, which can be a single-agent model and a decision framework for reasoning in partially observable stochastic environments. The POMDP model can model different vehicle operation scenarios, which may include modeling uncertainty using a set of states, actions (A), observations (Ω), state transition probabilities (T), conditional observation probabilities (O), a reward function (R), or combinations thereof within the model domain. The POMDP model can be defined or described as a tuple.<S,A,Ω,T,O,R> .

[0098] A state(s) from a state set(S) can represent different conditions of various defined aspects of the autonomous vehicle's operating environment (such as external objects and traffic control devices) that may probabilistically affect the operation of the autonomous vehicle at discrete time locations within the model domain. A corresponding state set(S) can be defined for each different vehicle operation scenario. Each state (state space) from the state set(S) can include one or more defined state factors. Although this paper describes some examples of state factors for some models, models including any model described herein 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 this paper describes some examples of state factor values ​​for some state factors, state factors including any state factor described herein can include any number or cardinality of values.

[0099] An action (a) from the action set (A) can indicate the available vehicle control actions at each state in the state set (S). The corresponding action set can be defined for different vehicle operation scenarios. Each action (action space) from the action set (A) can include one or more defined action factors. Although this paper describes some examples of action factors for some models, models including any model described herein 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 this paper describes some examples of action factor values ​​for some action factors, action factors including any action factor described herein can include any number or cardinality of values.

[0100] An observation (ω) from an observation set (Ω) can indicate available, observable, measurable, or determinable data for each state from a state set (S). The observation set can be defined for different vehicle operation scenarios. Each observation (observation space) from the observation set (Ω) can include one or more defined observation factors. Although this document describes some examples of observation factors for certain models, models including any model described herein 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 this document describes some examples of observation factor values ​​for certain observation factors, observation factors including any observation factor described herein can include any number or cardinality of values.

[0101] The state transition probabilities from the state transition probability set (T) can probabilistically represent changes in the autonomous vehicle's operating environment (e.g., represented by the state set (S)) in response to actions of the autonomous vehicle (e.g., represented by the action set (A)). This can be expressed as T: S×A×S→[0, 1], which represents the mapping of the probabilities of each state s (s∈S) from the state set S and an action a (a∈A) from the action set A to a subsequent state s' (s'∈S) from the state set. The corresponding state transition probability set (T) can be defined for different vehicle operating scenarios. Although this paper describes some examples of state transition probabilities for some models, models including any model described herein can include any number or cardinality of state transition probabilities. For example, combinations of states, actions, and subsequent states can be associated with corresponding state transition probabilities.

[0102] Conditional observation probabilities from a set of conditional observation probabilities (O) can represent the probability of making a corresponding observation (Ω) based on the autonomous vehicle's operating environment (e.g., a set of states (S)) in response to an action of the autonomous vehicle (e.g., represented by a set of actions (A)). This can be expressed as O: A × S × Ω → [0, 1]. This represents an observation function that maps each state s (s∈S) from the state set S and an action a (a∈A) from the action set A to the corresponding probability of observing an observation ω (ω∈Ω). The appropriate set of conditional observation probabilities (O) can be defined for different vehicle operating scenarios. Although this paper describes some examples of state-conditional observation probabilities for some models, models including any model described herein can include any number or cardinality of conditional observation probabilities. For example, combinations of actions, subsequent states, and observations can be associated with corresponding conditional observation probabilities.

[0103] The reward function (R) determines the corresponding positive or negative (cost) value that can be accumulated for each combination of states and actions. It can represent the expected value of an autonomous vehicle traversing the vehicle transportation network from a corresponding state corresponding to the corresponding vehicle control action to a subsequent state. This reward function can be expressed as R: This can represent the mapping of each state s (s∈S) from the state set S and an action a (a∈A) from the action set A to the expected immediate reward at the corresponding subsequent state s' (s'∈S) from the state set.

[0104] For simplicity, examples of the model values ​​(such as state factor values ​​or observation factor values) described in this paper 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 time can have values ​​from the set {short, long}; the value “short” can represent a discrete value such as time distance that is within or less than a defined threshold (such as three seconds), and the value “long” can represent a discrete value such as time distance that is at least (such as equal to or greater than) a defined threshold. Defined thresholds for individual categorical values ​​can be defined relative to associated factors. For example, a defined threshold for the set {short, long} of time factors can be associated with a relative spatial location factor value, and another defined threshold for the set {short, long} of time factors can be associated with another relative spatial location factor value. Although categorical representations of factor values ​​are described in this paper, other representations or combinations of representations can also be used. For example, the set of time state factor values ​​could be {short (representing values ​​less than three seconds), 4, 5, 6, long (representing values ​​at least 7 seconds)}.

[0105] In some embodiments (such as embodiments implementing the POMDP model), modeling the autonomous vehicle operation control scenario may include modeling obstructions. For example, the operational environment data may include information corresponding to one or more obstructions (such as sensor obstructions) in the autonomous vehicle's operational environment, such that the operational environment data may omit information representing one or more obstructed external objects in the autonomous vehicle's operational environment. For example, an obstruction may be an external object (such as a traffic sign, building, tree, identified external object, etc.), or any other operational condition or combination of operational conditions that can obstruct one or more other operational conditions (such as external objects) from the autonomous vehicle at a defined spatiotemporal location. In some embodiments, the operational environment monitor 4200 may identify obstructions, identify or determine the probability that an external object is obstructed or hidden by the identified obstruction, and may include obstructed vehicle probability information in the operational environment data output to the AVOMC 4100, and the AVOMC 4100 may communicate the obstructed vehicle probability information to each SSOCEM 4300.

[0106] The Autonomous Vehicle Operation Management System 4000 can include any number or combination of models of various types. For example, pedestrian SSOCEM 4310, intersection SSOCEM 4320, lane changing SSOCEM 4330, lane merging SSOCEM 4340, and obstacle crossing 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.

[0107] Instantiating an SSOCEM 4300 instance can include identifying a model from SSOCEM 4300 and instantiating an instance of the identified model. For example, SSOCEM 4300 can include a primary model and secondary models for different vehicle operation scenarios, and instantiating SSOCEM 4300 can include identifying the primary model as the current model and instantiating an instance of the primary model. Instantiating a model can include determining whether a solution or strategy is available for that model. Instantiating a model can include determining whether the available solutions or strategies for the model are partially solved or converged and solved. Instantiating SSOCEM 4300 can include instantiating an instance of a solution or strategy for the identified model of SSOCEM 4300.

[0108] Solving models such as the POMDP model can involve determining a policy or solution that can be a function that maximizes a cumulative reward, which can be obtained by evaluating tuples that define the model (such as...).<S,A,Ω,T,O,R> The strategy or solution can be determined based on possible combinations of elements such as (e.g., ...). It can identify or output reward-maximizing or optimal candidate vehicle control actions based on identified belief state data, which may include belief states b (b∈B) from a belief state set B, which may be a probability distribution over state (S). The identified belief state data (which may be probabilistic) can indicate current state data (such as the current state value set or the probability of the current state value set of the corresponding model) and may correspond to a corresponding relative time and place. For example, solving an MDP model may include identifying states from a state set (S), identifying actions from an action set (A), and determining subsequent or successor states from the state set (S) after simulating actions affected by state transition probabilities. Each state can be associated with a corresponding utility value, and solving an MDP model may include determining the corresponding utility value corresponding to each possible combination of state, action, and subsequent state. The utility value of a subsequent state can be identified as the largest identified utility value affected by a reward or penalty, which may be a discounted reward or penalty. A policy can indicate the action corresponding to the maximum utility value of the given 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 each state and are influenced by the observation probabilities corresponding to the observations that generated each state. Therefore, solving an SSOCEM model involves evaluating possible state-action-state transitions based on each action and observation, and updating each belief state (e.g., using Bayesian rules).

[0109] In the example, the initial belief state (b0∈B) can be identified as the current belief state (b∈B), an action can be taken (a∈A), an observation can be made (ω∈Ω), and the current belief state (b∈B) can be updated to identify the updated current belief state (b'∈B), where a normalization constant η=Pr(ω|b,s) can be used. -1 The following represents the updated current belief state:

[0110]

[0111] At each increment (such as at each time step), an action (a∈A) can be selected based on the current belief state (b∈B). The policy π: B→A can represent the mapping from the belief state (b∈B) to the action (a∈A). The value function V... π : The cumulative reward for each belief state (b∈B) can be represented and anticipated. The optimal policy π* maximizes the anticipated cumulative reward by maximizing the expected future reward based on the current belief state (b∈B) according to the actions of the optimal policy. Other POMDP solutions can be used.

[0112] although Figure 4 Not shown, but an autonomous vehicle may include an autonomous vehicle actuation control system or multiple autonomous vehicle actuation control systems. The autonomous vehicle actuation control system can receive vehicle control actions (such as vehicle control actions from the autonomous vehicle operation management system 4000) and can control one or more motion units of the autonomous vehicle (such as steering actuators, accelerators, braking systems, or combinations thereof) to perform vehicle control actions. The autonomous vehicle actuation control system may include one or more actuation models (such as POMDP or other automatic control models) based on the identified vehicle control actions and the autonomous vehicle's operating environment, and can determine low-level vehicle actuation control parameters (such as force magnitude or steering angle) based on the actuation model.

[0113] Figure 5 This is a flowchart illustrating an example of a vehicle guidance system 5000 with system optimization according to an embodiment of the present invention. The vehicle guidance system 5000 with system optimization can be used in, for example... Figure 1 The vehicle shown is 1000 or Figure 2 This is implemented or partially implemented in one of the vehicle vehicles 2100 / 2110 shown. In some embodiments, the vehicle vehicle may be an autonomous vehicle, a semi-autonomous vehicle, or any other vehicle vehicle that achieves autonomous driving. For example, the autonomous vehicle vehicle may implement an autonomous vehicle operation management system (such as... Figure 4 The autonomous vehicle operation management system 4000 shown is an example. In some embodiments, the vehicle may omit autonomous driving, or may be in an operation mode that omits autonomous driving. Aspects of the system-optimized vehicle guidance 5000 can be implemented in infrastructure devices (such as...) Figure 2 It is implemented in one or more of the communication devices 2400 / 2410 shown.

[0114] like Figure 5 As shown, the vehicle guidance 5000 with system optimization includes: obtaining system utility vehicle guidance data at 5100, and traversing a portion of the vehicle transportation network at 5110 based on the system utility vehicle guidance data.

[0115] Obtaining system utility vehicle guidance data at 5100 includes: obtaining vehicle operation data for the region at 5200, operating the system utility vehicle guidance model for the region at 5210, generating system utility vehicle guidance data at 5220, and outputting system utility vehicle guidance data at 5230.

[0116] In some embodiments, a vehicle, such as the current vehicle, can implement or solve a system utility vehicle guidance model, and obtaining system utility vehicle guidance data at 5100 may include: obtaining vehicle operation data for the region via the current vehicle at 5200, operating the system utility vehicle guidance model for the region via the current vehicle at 5210, generating system utility vehicle guidance data via the current vehicle at 5220, and outputting system utility vehicle guidance data via the current vehicle at 5230. Outputting system utility vehicle guidance data via the current vehicle at 5230 may include: outputting system utility vehicle guidance data from a unit of the implementation or operating system utility vehicle guidance model of the current vehicle to another unit or component of the current vehicle. In some embodiments, outputting system utility vehicle guidance data via the current vehicle at 5230 may include: such as via an electronic communication link (such as...) Figure 2 The wireless communication links shown (one or more of 2310 / 2320 / 2370 / 2380 / 2385, etc.) output system utility vehicle guidance data to one or more external devices (such as one or more remote vehicles, one or more infrastructure devices, or combinations thereof) via the current vehicle.

[0117] In some embodiments, remote vehicles (such as Figure 2 The remote vehicle 2110 shown can implement or solve the system utility vehicle guidance model, and at 5100, obtaining system utility vehicle guidance data for the current vehicle can include: such as via electronic communication links (e.g., Figure 2The system utility vehicle guidance data is obtained from the remote vehicle via one or more of the wireless communication links 2310 / 2320 / 2370 / 2380 / 2385 shown. For example, the current vehicle may automatically receive the system utility vehicle guidance data from the remote vehicle, such as via a monitored communication port at the current vehicle, or by sending a request for the system utility vehicle guidance data from the current vehicle to the remote vehicle, and in response to the request, the current vehicle receives the system utility vehicle guidance data from the remote vehicle. In an embodiment where system utility vehicle guidance data is obtained at 5100 for the current vehicle, including obtaining system utility vehicle guidance data from a remote vehicle, the remote vehicle may implement or perform: obtaining vehicle operation data for the region at 5200, operating the system utility vehicle guidance model for the region at 5210, generating system utility vehicle guidance data at 5220, and outputting system utility vehicle guidance data at 5230. Although in Figure 5 While not explicitly stated, it can be performed by a remote vehicle in response to a request for system utility vehicle boot data, in response to a defined event, or periodically by one or more of the following: obtaining vehicle operation data for the region at 5200, operating the system utility vehicle boot model for the region at 5210, generating system utility vehicle boot data at 5220, and outputting system utility vehicle boot data at 5230. Although in Figure 5 It is not explicitly stated, but the current vehicle can generate and send one or more requests for system utility vehicle boot data in response to defined events or periodically.

[0118] In some embodiments, the infrastructure may be a centralized infrastructure device or a distributed infrastructure device (such as...) Figure 2 The communication device shown (such as one of 2400 / 2410) can realize or solve the system utility vehicle guidance model, and at 5100, obtaining system utility vehicle guidance data for the current vehicle can include, for example, via electronic communication links (such as...). Figure 2The wireless communication links shown (one or more of 2310 / 2320 / 2370 / 2380 / 2385, etc.) obtain system utility vehicle guidance data from the infrastructure device. For example, the current vehicle can automatically receive system utility vehicle guidance data from the infrastructure device, such as via a monitored communication port at the current vehicle, or it can send a request for system utility vehicle guidance data from the current vehicle to the infrastructure device, and in response to the request, the current vehicle receives system utility vehicle guidance data from the infrastructure device. In the embodiment where obtaining system utility vehicle guidance data for the current vehicle at 5100 includes obtaining system utility vehicle guidance data from the infrastructure device, the infrastructure device or a combination of infrastructure devices can implement or perform: obtaining vehicle operation data for the area at 5200, operating the system utility vehicle guidance model for the area at 5210, generating system utility vehicle guidance data at 5220, and outputting system utility vehicle guidance data at 5230. Although in Figure 5 Not shown separately, but can be performed by the infrastructure device in response to receiving a request for system utility vehicle guidance data, in response to a defined event, or periodically performing one or more of the following: obtaining vehicle operation data for the area at 5200, operating the system utility vehicle guidance model for the area at 5210, generating system utility vehicle guidance data at 5220, and outputting system utility vehicle guidance data at 5230. Although in Figure 5 It is not explicitly stated, but the current vehicle can generate and send one or more requests for system utility vehicle boot data in response to defined events or periodically.

[0119] In some embodiments, a centralized infrastructure device (such as a server) in the region implements (such as solving) a system utility vehicle guidance model for the region. The centralized infrastructure device may be physically located in, near, or at any distance from the region.

[0120] In some embodiments, distributed infrastructure devices (such as edge servers) in the region implement (such as solving) a system utility vehicle bootstrapping model for the region. The distributed infrastructure devices may be physically located in or near the region.

[0121] Obtaining vehicle operation data for the area at point 5200 includes obtaining vehicle transportation network data representing the vehicle transportation network for the area. For example, vehicle transportation network data may include stop-lines, traffic light (or meter) locations, toll booths, yield points, mandatory lane-changing locations, lane-split locations, or any other data describing the area of ​​the vehicle transportation network that can be represented by vehicle transportation network data.

[0122] Obtaining vehicle operation data for the area at point 5200 includes obtaining vehicle operation data (current operation data) of vehicles operating in the area. This vehicle operation data may include data reported by individual vehicles in the area. It may also include data generated by one or more vehicle-external sensors (such as sensors on infrastructure devices) within the area. The vehicle operation data for a specific vehicle in the area may include location data (such as road identifiers, road segment identifiers, lane identifiers, etc.) or any other data indicating the vehicle's location within the vehicle transportation network. The vehicle operation data for a specific vehicle may indicate its heading. It may indicate its speed data. It may indicate its current route, destination, or both. Vehicle operation data for a given vehicle may include non-operational data for that vehicle, such as vehicle type data, data indicating the type of car or truck, or data indicating the brand, model, model year, or any other data describing the vehicle. Participating vehicles may omit sending vehicle operation data (except for vehicle operation data identifying currently valid opt-in data). Vehicle operation data may be obtained using one or more sensors (such as infrastructure sensors, vehicle-mounted sensors, or combinations thereof). For example, infrastructure sensors may include pressure sensors, cameras, lidar sensors, radar sensors, or any other type of infrastructure sensor. The vehicle may report (e.g., by sending or otherwise making available) sensor data from the vehicle-mounted sensors.

[0123] As described herein, a participating vehicle is a vehicle (such as the current vehicle) identified as participating in traversing at least a portion of the area of ​​the vehicle transport network based on system utility vehicle guidance data obtained from the system utility vehicle guidance model of the area. For example, at a certain time and place, the system utility vehicle guidance data may indicate a defined target speed, the participating vehicle may be an autonomous vehicle, and the autonomous vehicle may traverse the area of ​​the vehicle transport network at or reasonably close to the defined target speed, or the defined target speed may be displayed to the vehicle's occupants or driver.

[0124] A non-participating vehicle is a vehicle that is identified as traversing at least a portion of the vehicle transport network in the absence of, or without reference to, system utility vehicle guidance data obtained from the system utility vehicle guidance model of the region, or without consistency with the system utility vehicle guidance data.

[0125] At 5210, the system utility vehicle bootstrapping model for that region is operated. The system utility vehicle bootstrapping model includes generating or regenerating the system utility vehicle bootstrapping model using vehicle operation data for that region. In some embodiments, generating the system utility vehicle bootstrapping model may include: obtaining a previously generated system utility vehicle bootstrapping model, and generating (regenerating) the system utility vehicle bootstrapping model based on the previously generated system utility vehicle bootstrapping model using vehicle operation data for that region. In some embodiments, the model may be generated or regenerated and solved based on vehicle or system operation data obtained prior to the current vehicle operation (such as previous observation data, previous action data, or combinations thereof) or their aggregations (such as state transition probabilities (T), conditional observation probabilities (O), or statistical approximations of both), and the generation strategy may omit the use of the current vehicle operation data for that region obtained at 5200, or a portion thereof. In some embodiments, generating or regenerating the system utility vehicle bootstrapping model may include obtaining and using a previously generated system utility vehicle bootstrapping model for that region. In some embodiments, the vehicle operation data of the region obtained before obtaining the vehicle operation data of the region at 5200 can be used to generate the model, and the vehicle operation data of the region obtained at 5200 can be used to regenerate the model.

[0126] At point 5210, the operating system utility vehicle guidance model includes solving (such as optimal solution, approximate solution, or partial solution) the system utility vehicle guidance model to obtain strategies, such as system utility vehicle guidance strategies. This strategy can be expressed as pi(S)→A, such that pi(S)=[a1,a2,…,a…]. k], wherein the vehicle operation data of the region indicates that the region includes (k) participating vehicles, and (a i This indicates the action identified for the i-th participating vehicle. In some embodiments, obtaining a system utility vehicle guidance strategy may include: obtaining a previously generated system utility vehicle guidance strategy corresponding to the system utility vehicle guidance model operating in the region at 5210.

[0127] A system utility vehicle guidance model is a stochastic model of the system operation aspects of a region within a vehicle transportation network. For example, a system utility vehicle guidance model for a region of a vehicle transportation network can be a Markov Decision Process (MDP) model, a Stochastic Shortest Path (SSP) model, a Partially Observable Markov Decision Process (POMDP) ​​model, a Markov Game (MG) model, a Partially Observable Markov Game (POMG) model, or a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) ​​model. Different regions can be associated with, or modeled by, various system utility vehicle guidance models. A region of a vehicle transportation network can be a lane, a segment, a contiguous group of segments, a road or intersection, or a defined geographic area (such as a block, community, district, county, municipality, state, country, or other defined geographic area). Regions can be defined specifically (e.g., manually). In some embodiments, regions can be non-overlapping. In some embodiments, two or more regions can overlap. The various system utility vehicle guidance models in overlapping areas can be operated simultaneously or substantially simultaneously. In some embodiments, participating vehicles operating in the portion of the vehicle transportation network corresponding to the overlapping area can identify (e.g., select) communication devices, areas, or corresponding system utility vehicle guidance models from candidates such as overlapping areas, for example, based on location, route, or a combination thereof. In some embodiments, an overlapping area or its associated communication device can be a region of vehicles operating in the overlapping portion of the area. In some embodiments, one or more overlapping areas can communicate, for example, according to one or more area coordination rules, to identify models, strategies, or system utility vehicle guidance data from area-specific candidates.

[0128] In some embodiments, a particular rule-based system may be used to implement the system utility vehicle guidance model. This rule-based system may include, for example, a function such as f(n, c) = s, which maps the cardinality or count of the vehicle set (v) in the region and the cardinality or count of the participating vehicle set (c) to a speed (s) that can be expressed as the distance traveled per unit time (e.g., miles or kilometers).

[0129] In some embodiments, the model can be solved as a Markov game or a similar game-theoretic structure. This yields relevant equilibria, Nash equilibria, or stationary Markov perfect equilibria, where the stationary Markov perfect equilibria ensures the action that maximizes utility even if other (such as non-participating vehicles) choose strategies different from those calculated from the equilibrium.

[0130] As defined in the system utility vehicle guidance model, states(s) from a state set(S) can represent different conditions of various defined aspects of a region (such as vehicle operation). A corresponding state set(S) is defined. Each state (state space) from the state set(S) can include one or more defined state factors. For example, the system utility vehicle guidance model can include stochastic state factors (S = × i S i The random state factor indicates location data (such as lane identifiers in road segments) within the area on a vehicle-by-vehicle basis. The granularity or specificity of the random state factor can correspond to the granularity or detail of the available vehicle transportation network data. For example, vehicle transportation network data may be relatively low-resolution data describing roads but omitting lane data, and the random state factor may accordingly indicate road locations while omitting lane data; or vehicle transportation network data may include relatively high-resolution data describing roads and lanes, and the random state factor may accordingly indicate the road and lane locations of the respective vehicles. The random state factor for a given vehicle may include heading data. In some embodiments, the random state factor for a given vehicle may indicate other data about the vehicle, such as observed rate, vehicle brand, model, year, type (e.g., car or truck), or any other data describing the vehicle or its operation.

[0131] The system utility vehicle guidance model includes actions (a) from the action set (A) that can instruct available vehicle control actions or route guidance at each state in the state set (S). Each action (action space) from the action set (A) can include one or more defined action factors. For example, action (A = × j A j Actions can be provided (such as being transmitted to or otherwise made available) to each participating vehicle(j) to indicate target vehicle control actions, target speeds, target lanes, or any other potentially target aspect of vehicle operation. Actions can be indicated on a vehicle-by-vehicle basis for participating vehicles. In some embodiments, the action space may include non-transferable target actions for non-participating vehicles.

[0132] The state transition probabilities from the state transition probability set (T) can probabilistically represent the vehicle (i) in S. i Proceed to S after the current state. i The probability of subsequent states in a region can be based on the density of vehicles in the region. The density of vehicles in a region can be a function of the number or cardinality of vehicles operating in that region and the size of that region (e.g., in terms of traversable space). The state transition probability models how state factors change (for a single step) based on action factors. For example, the states S of two vehicles a and b. a and S b It can be indicated that S is on the road a In S b After that, the actions of vehicle a (A) a It can indicate a target speed of 65 mph, and the movement of vehicle b (A) b () can indicate a target speed of 45 mph, and the transition probability (T) will be described as S a Cannot move more than S b Therefore, the state factor S at subsequent time steps or time locations... a 'and S b The state transition will reflect this coercion. The state transition probability (T) can describe or map how vehicles (including participating and non-participating vehicles) behave based on the system utility of participating vehicles and vehicle guidance data. In some embodiments, the state transition probability (T) can be a probability matrix. In some embodiments, the state transition probability (T) can be a model generated from Monte Carlo simulations.

[0133] The system utility vehicle guidance model includes a reward function (R) that determines the corresponding positive or negative (cost) value that can be accumulated for each combination of states and actions. The reward represents the time spent traveling along a lane. In some embodiments, the time spent traveling along a lane may indicate an average value (such as a historical average), the time span of a vehicle traversing a road segment, or a defined sequence thereof. In some embodiments, the time spent traveling along a lane may indicate the distance traversed on a road segment, or a defined sequence thereof, divided by the corresponding speed limit or average vehicle speed. The time spent traveling along a lane may be identified in units of vehicles, or it may be an aggregate value (such as an average value) of vehicles operating in that area.

[0134] For example, the system utility vehicle-guided model could be an MDP model, and the reward could be a weighted sum of vehicle speeds. In another example, the system utility vehicle-guided model could be an MG model, and the reward could be in vehicle units. The reward is a negative value corresponding to the time spent on the lane, which could be the lane length (e.g., in miles) divided by the vehicle speed (e.g., in miles per hour), thus indicating the time spent traversing the lane (e.g., in hours).

[0135] At point 5220, system utility vehicle guidance data is generated via the system utility vehicle guidance model. Generating system utility vehicle guidance data includes generating corresponding messages or signals for each participating vehicle in the region. Generating messages for the corresponding participating vehicles includes indicative actions identified by the system utility vehicle guidance model at point 5210 for the respective participating vehicle. Although described as actions, the indications of actions in the system utility vehicle guidance data can be indications of control guidance actions, which can be suggested actions or suggested target operating parameters (such as target speed).

[0136] In the example, a region of the vehicle transportation network can be an intersection within the vehicle transportation network, which can be in a relatively low spatial range relative to other regions described herein. For example, the region of the vehicle transportation network corresponding to an intersection in the vehicle transportation network can include a defined geospatial distance, such as less than or equal to a quarter kilometer around the intersection. The system utility vehicle guidance model (system utility intersection guidance model) for the region can optimize the throughput of vehicles crossing the intersection. Risk can be minimized (safety maximized). For example, the system utility vehicle guidance strategy for the system utility intersection guidance model of the region of the vehicle transportation network corresponding to an intersection in the vehicle transportation network can obtain or generate system utility vehicle guidance data, which indicates one or more vehicle control actions corresponding to the right-of-way priority of the intersection, one or more vehicle control actions corresponding to the speed of the corresponding vehicle approaching or crossing the intersection, or both.

[0137] Compared to a scenario where no vehicle is a participating vehicle, guiding the operation of one or more participating vehicles across an intersection area based on system utility vehicle guidance data can improve the system utility of vehicles operating in the intersection area. For example, a system utility vehicle guidance model may be more complex than a vehicle-specific operation model, which may correspond to higher accuracy in the system utility vehicle guidance model. Non-participating vehicles may operate according to a model that maximizes the utility of vehicle-specific operations or may operate via manual control, which may omit vehicle operation data (such as data indicating the uncertainty of delays of one or more other vehicles operating in the area) due to unavailability, which may correspond to lower system utility relative to the system utility vehicle guidance model. In some embodiments, the state transition probability (T) of the system utility vehicle guidance model may include: representing vehicle operations as deviations from or different from previous vehicle operations with right-of-way priorities, such as based on aggregation (such as statistical averages), which may be omitted or unavailable from the model that maximizes the utility of vehicle-specific operations.

[0138] The system utility intersection guidance model can be implemented by current vehicles, remote vehicles, distributed infrastructure units located in or near the area, or centralized infrastructure units.

[0139] System utility intersection guidance models can include per-vehicle state factors. For example, a per-vehicle lane state factor indicates the lane, segment, or road corresponding to the vehicle's location in the vehicle transport network; this lane state factor can be represented in the system utility intersection guidance model as follows: Lane status factors can indicate the identifier of a lane, segment, or road. This identifier can be unique within a region or vehicle transportation network, or it can have semantic meaning, such as road name, lane number, and distance along the road from a defined point.

[0140] Although the description per vehicle state factor per vehicle state factor is about lane state data, in some implementations, this factor may include other data. For example, it may include time data, such as time data indicating the time span a vehicle has been at a location. In some implementations, it may include speed or rate data. In some implementations, it may include acceleration data, such as lateral acceleration, longitudinal acceleration, or both. In some implementations, it may include relative aggregated control data. For example, relative aggregated control data may be obtained using a machine learning classifier and a defined set of previous vehicle control data for the corresponding vehicle. The defined set of previous vehicle control data may be, for example, vehicle control data for a defined time span (such as one minute) and may include vehicle data such as speed data, rate data, acceleration data, or combinations thereof (which may include lateral and longitudinal data). The relative aggregated control data may indicate a probabilistic classification or measure of the vehicle's operation corresponding to input vehicle control data, which may be associated with corresponding target control data.

[0141] A system utility intersection guidance model may include one or more state factors, which may be included in the corresponding model as aggregate state factors or as per-vehicle state factors. For example, it can be represented as S s The aggregation rate or rate state factor can indicate an aggregation measure of vehicle speeds within a region, such as the average or median speed of vehicles within the region. In another example, it can be represented as... The per-vehicle speed or rate state factor can indicate the reported or observed speed of the corresponding vehicle. Increasing the spatial extent of the state factor or other factors in the system utility vehicle guidance model (e.g., from aggregate factors to per-vehicle factors) can increase the accuracy, computational complexity, or both of solving the system utility vehicle guidance model. The uncertainty associated with reported vehicle operation data (such as speed data) can be different from (e.g., can be less than) the uncertainty associated with observed vehicle operation data. As used herein, the term “reported” with respect to data refers to data identified by the data subject (e.g., vehicle sensors that identify the speed of a vehicle). As used herein, the term “observed” with respect to data refers to data identified by a party other than the data subject (e.g., vehicle sensors that identify the state of a traffic control device or the speed of another vehicle) or by infrastructure device sensors that identify the speed of a vehicle.

[0142] The system utility intersection guidance model may include a right-of-way priority state factor, which indicates the right-of-way priority of vehicles in the area. This right-of-way priority state factor can be represented as S. o In some embodiments, right-of-way priority may indicate the vehicle having the current right-of-way priority. In some embodiments, right-of-way priority may indicate the relative position or order of the various vehicles with respect to the right-of-way priority.

[0143] For a region representing a vehicle transportation network at an intersection, the state factors of the system utility intersection guidance model can include a per-vehicle lane state factor, a convergent speed factor, and a convergent priority factor, which can be represented as:

[0144] In another example, for a region representing a vehicle transportation network at an intersection, the state factors of the system utility intersection guidance model can include a per-vehicle lane state factor, a per-vehicle speed factor, and an aggregation priority factor, which can be represented as:

[0145] The system utility intersection guidance model can include vehicle control guidance actions such as "stop", "advance", and "proceed" vehicle control guidance actions.

[0146] The "Stop" control guidance action can instruct the initiation of a "Stop" vehicle control action as described herein. For manually controlled vehicles, the "Stop" control guidance action can be presented to occupants such as the vehicle's driver. For autonomous vehicles or vehicles operating autonomously, the autonomous vehicle can initiate a "Stop" vehicle control action in response to receiving system utility vehicle guidance data including the "Stop" control guidance action.

[0147] "Moving" control guidance actions can instruct the guidance of "moving" vehicle control actions as described herein. For manually controlled vehicles, "moving" control guidance actions can be presented to occupants such as the vehicle's driver. For autonomous vehicles or vehicles that operate autonomously, the autonomous vehicle can perform "moving" vehicle control actions in response to receiving system utility vehicle guidance data, including "moving" control guidance actions.

[0148] "Forward" control guidance actions can instruct the guidance of "forward" vehicle control actions as described herein. For manually controlled vehicles, "forward" control guidance actions can be presented to occupants such as the vehicle's driver. For autonomous vehicles or vehicles that operate autonomously, the autonomous vehicle can perform "forward" vehicle control actions in response to receiving system utility vehicle guidance data including "forward" control guidance actions.

[0149] The system utility intersection guidance model may include a reward function (R), which may be a piecewise function. The vehicle (i) may have priority. And the reward is zero (0). Positive rewards (such as 1) can be used. In other cases, the reward is the observed speed per vehicle. This penalizes vehicles that violate right-of-way priority by crossing an intersection in proportion to their speed. A fixed negative reward or cost (such as -1) can be used.

[0150] In the example, the region of the vehicle transportation network may include geographically relevant roads or portions thereof within the vehicle transportation network, and this region may be in a relatively high spatial range relative to other regions described herein. The system utility vehicle guidance model (system utility route guidance model) for this region can be implemented by a centralized infrastructure device.

[0151] The system utility routing guidance model may include per-vehicle state factors. For example, a per-vehicle lane state factor indicates the lane, segment, or road corresponding to the vehicle's location in the vehicle transportation network; this lane state factor can be represented in the system utility routing guidance model as follows: Lane status factors can indicate the identifier of a lane, segment, or road. This identifier can be unique within a region or vehicle transportation network, or it can have semantic meaning, such as road name, lane number, and distance along the road from a defined point.

[0152] The system utility routing guidance model may include a per-vehicle density state factor indicating the local density of vehicles in the corresponding current vehicle's operating environment (such as within 50 meters of the current vehicle), which can be expressed as...

[0153] The system utility routing guidance model may include a per-vehicle speed or rate state factor, which can be expressed as: This speed or rate state factor indicates the reported or observed speed of the corresponding vehicle.

[0154] For a region of a vehicle transportation network represented by a system utility route selection guidance model, the state factors of the system utility route selection guidance model can include a lane state factor per vehicle, a speed factor per vehicle, and a vehicle density factor per vehicle, which can be expressed as:

[0155] The system utility routing guidance model may include guidance actions that can instruct the speed of each vehicle. Each vehicle control guidance action can indicate the target speed of the corresponding vehicle. In some embodiments, the action space may include a target lane guidance action for each vehicle. It can indicate the target lane for the corresponding vehicle. In some embodiments, the action space may include target route guidance actions for each vehicle. It can indicate the target route for the corresponding vehicle. The target route can indicate the route from the location of the corresponding vehicle to the target destination of the corresponding vehicle, as indicated in the vehicle operation data of the area obtained for the corresponding vehicle at 5200.

[0156] The system utility route selection guidance model may include a reward function (R) that reflects the average time taken by vehicles to traverse the area. This average time can be a negative sum of the differences between the lane or road length per vehicle and the observed speed per vehicle, which can be expressed as... Where i ranges from 1 to k, and can be averaged by dividing by k, where k may, for example, indicate a defined target average speed. In some embodiments, the reward function may be the maximum time taken for vehicles operating in the area to traverse between them. In some embodiments, the reward function for two or more vehicles simultaneously in a road segment or intersection may be negative 1, and for vehicles in a road segment or intersection where no other vehicles are operating positively, the reward function may be zero.

[0157] In the example, a region of the vehicle transportation network can be a continuous sequence of roads or road segments within the vehicle transportation network, and this region can be located in an intermediate spatial range relative to other regions described herein. The system utility vehicle-guided model (system utility flow-guided model) of the region (flow-guided region) can be implemented by a distributed infrastructure device or a centralized infrastructure device.

[0158] In flow guidance zones (where the set of vehicles operating in the zone omits participating vehicles), vehicle control is based on vehicle-specific operational utility as understood by a human driver or determined by the vehicle's autonomous processing. For example, vehicles operating in low-vehicle-density sections of the zone may accelerate or change lanes to minimize inter-vehicle distances (e.g., approaching or being at a relative minimum safe operating distance), thereby maximizing vehicle density in the corresponding sections of the zone and correspondingly reducing vehicle density in following vehicles or other sections of the zone. For a vehicle, low vehicle density may indicate that the relative distance between the vehicle and another vehicle immediately ahead in the current lane is greater than the minimum safe operating distance. Delays in response to changes in the operating environment (response delay) may reduce operational utility as a function of vehicle density. Thus, the current operational utility of a vehicle is at least partially inversely related to the density of vehicles operating in the current vehicle's operating environment. Furthermore, the base number or count of vehicles operating in the portion of the region with a relatively high vehicle density and thus relatively low operational utility is relatively high, while the base number or count of vehicles operating in the portion of the region with a relatively low vehicle density (corresponding to the relatively high operational utility of that portion) is relatively low, making the system (e.g., average) operational utility of that region suboptimal. As reflected in suboptimal system utility, although the predicted per-vehicle operational utility is maximized, the operations of other vehicles that also maximize the corresponding per-vehicle operational utility affect the operation of the current vehicle, thus reducing the observed per-vehicle operational utility. This example can be referred to as elastic congestion. Although described with reference to elastic congestion, other vehicle operations optimized for per-vehicle operational utility may be associated with suboptimal system utility.

[0159] For example, multiple vehicles in the low-vehicle-density segment of the area can operate independently (e.g., by acceleration) to minimize the distance between vehicles to a minimum safe operating distance, thus forming a high-density vehicle group in the high-vehicle-density segment of the area. The first vehicle in the high-density group can decelerate by braking, and the distance between the first vehicle and a second vehicle immediately following it in the direction of travel may decrease due to factors such as the response delay of the second vehicle. The reduced distance between the first and second vehicles may be less than the minimum safe operating distance. The second vehicle may decelerate due to the response delay. Because the distance between the first and second vehicles is less than the minimum safe operating distance, uncertainties, or other factors, the second vehicle may decelerate faster than the first vehicle (response amplification). Other vehicles in the high-density group (further behind in the direction of travel) may have a similar cascading increase in response delay and deceleration rate. It may reduce the average or other aggregate measures and speeds of vehicles in high-density clusters, and may increase the risk per vehicle, thereby reducing the operational utility of the high-density segment of vehicles.

[0160] In a flow guidance area (where vehicles operating in the area include one or more participating vehicles, and the area may include non-participating vehicles), participating vehicles may operate at a speed identified based on system utility vehicle guidance data or in a lane identified based on system utility vehicle guidance data, wherein the system utility vehicle guidance data can be identified to optimize system operational utility in the area. For example, a vehicle may receive or otherwise access system utility vehicle guidance data output at 5230, which may indicate a target speed less than or equal to the speed of the vehicle immediately ahead of it in the current lane. The target speed indicated by the system utility vehicle guidance data may differ from the target speed identified based on per-vehicle operational utility. Operating participating vehicles according to system utility vehicle guidance data can reduce the effects of resilient congestion and increase system operational utility.

[0161] For example, multiple vehicles may be operating within an area of ​​a vehicle transport network. Some non-participating vehicles may operate to minimize inter-vehicle distance, subject to the minimum safe operating distance between these non-participating vehicles and vehicles traveling in the direction of travel. Participating vehicles operating based on system utility vehicle guidance data may operate to maintain or increase the inter-vehicle distance relative to vehicles traveling in the direction of travel. Because participating vehicles operating based on system utility vehicle guidance data omit minimizing inter-vehicle distance, the number of vehicles forming high-density clusters may be reduced. The inter-vehicle distance between the leading non-participating vehicle and the following participating vehicle may be relatively large. The leading non-participating vehicle can decelerate by braking, and the distance between the leading non-participating vehicle and the following participating vehicle may decrease due to factors such as response delays of the following participating vehicle. Due to the relatively large inter-vehicle distance before deceleration, the reduced inter-vehicle distance between the leading non-participating vehicle and the following participating vehicle can exceed the minimum safe operating distance. The second vehicle may decelerate due to response delay. Because the inter-vehicle distance between the leading non-participating vehicle and the following participating vehicle is greater than the minimum safe operating distance, the following participating vehicle can decelerate at a rate substantially similar to that of the leading non-participating vehicle. Response amplification can be reduced or avoided. The extent of any cascading response amplification can be reduced, per-vehicle risk can be maintained, and the reduction in average or other aggregate measures of vehicle speed can be minimized, thereby maintaining or increasing the relative system operational utility in that region.

[0162] The system utility flow guidance model can include per-vehicle state factors. For example, a per-vehicle lane state factor indicates the lane, segment, or road corresponding to the vehicle's location in the vehicle transportation network; this lane state factor can be represented in the system utility vehicle guidance model as follows: Lane status factors can indicate the identifier of a lane, segment, or road. This identifier can be unique within a region or vehicle transportation network, or it can have semantic meaning, such as road name, lane number, and distance along the road from a defined point.

[0163] The system utility flow-guided model may include one or more aggregated state factors for the region. For example, the aggregated vehicle density state factor indicates the density of vehicles in the region, and this aggregated vehicle density state factor can be expressed as (S dThe density of vehicles in the area can be a function of the number, count, or cardinality of vehicles operating in the area (including participating and non-participating vehicles), and can be expressed as an aggregate value (such as average or median) of vehicles per unit distance (such as per mile or per kilometer) of the road (per square meter). In some embodiments, the aggregated vehicle density state factor can represent an aggregate value (such as average or median) of the distance between vehicles.

[0164] A system utility flow-guided model may include one or more state factors, which may be included in the corresponding model as aggregated state factors or as per-vehicle state factors. For example, an aggregated velocity or rate state factor, which may be represented as (Ss), may indicate an aggregate measure of vehicle vehicular ...

[0165] For a region of a vehicle transportation network represented by a system utility flow-guided model, the state factors of the system utility flow-guided model can include a per-vehicle lane state factor, an aggregated observation speed factor, and an aggregated vehicle density factor, and can be expressed as:

[0166] The system utility flow guidance model may include per-vehicle control guidance actions, which may indicate the target speed of the corresponding vehicle.

[0167] The system utility flow-guided model can include a reward function (R), which can be a negative sum of the differences between the observed speed of the vehicle and the target speed indicated by the action, and can be represented as sum(S_observed_speeds[i]-A_speed[i]), where i is from 1 to k. The system utility flow-guided model can be optimized to minimize the difference between the target speed and the observed speed.

[0168] System utility vehicle guidance data is output at 5230. The system utility vehicle guidance data, or a portion thereof, may be transmitted to or otherwise made available to participating vehicles in the region. For example, infrastructure installations may use any communication link (including a combination of communication links or dedicated short-range communications) as described herein to transmit system utility vehicle guidance data to the various participating vehicles in the region. In some embodiments (such as embodiments where the current participating vehicles implement the system utility vehicle guidance model), the transmission of system utility vehicle guidance data to other participating vehicles may be omitted.

[0169] The system utility vehicle guidance data output at 5230 for the corresponding participating vehicle can indicate the vehicle operation data for the region obtained at 5200, and the per-vehicle control guidance action generated at 5220 based on the system utility vehicle guidance model operating at 5210. In some embodiments, the system utility vehicle guidance data output at 5230 for the corresponding participating vehicle can indicate the system utility vehicle guidance strategy obtained at 5210, the vehicle operation data for the region obtained at 5200, or a portion thereof, or a combination thereof.

[0170] At 5110, a vehicle traverses a portion of the vehicle transportation network in the area based on system utility vehicle guidance data. For example, a vehicle may obtain (such as by receiving or otherwise accessing) system utility vehicle guidance data output at 5230, and may traverse a portion of the vehicle transportation network at 5110 based on system utility vehicle guidance data.

[0171] In some embodiments, traversing a portion of the vehicle transportation network based on system utility vehicle guidance data at 5110 includes outputting a representation of at least a portion of the system utility vehicle guidance data to present to the occupants of the vehicle (the current vehicle). For example, the system utility vehicle guidance data may indicate a target speed, and traversing a portion of the vehicle transportation network based on the system utility vehicle guidance data may include outputting a representation of the target speed to present to the driver of the vehicle by highlighting the target speed on the vehicle's speedometer. Other representations of the system utility vehicle guidance data may be used, such as visual representations, audio representations, tactile representations, or combinations thereof.

[0172] In some embodiments, traversing a portion of the vehicle transportation network at 5110 based on system utility vehicle guidance data includes: performing autonomous driving based on system utility vehicle guidance data (such as in response to receiving system utility vehicle guidance data, etc.) from the master control vehicle (current vehicle). For example, the system utility vehicle guidance data may indicate a target speed, and the autonomous vehicle may accelerate or decelerate to traverse a portion of the vehicle transportation network at or near the target speed.

[0173] In some embodiments, traversing a portion of a vehicle transportation network at 5110 based on system utility vehicle guidance data includes: outputting a representation of at least a portion of the system utility vehicle guidance data to present to the occupants of the vehicle, and controlling the vehicle autonomously based on the system utility vehicle guidance data (such as in response to receiving system utility vehicle guidance data). For example, the system utility vehicle guidance data may indicate a target speed, and the autonomous vehicle may accelerate or decelerate to traverse a portion of the vehicle transportation network at or near the target speed, and may output a representation of the system utility vehicle guidance data as an indication of the reason or explanation for traversing a portion of the vehicle transportation network at the target speed.

[0174] In some embodiments, participating vehicles may receive system utility vehicle guidance data from two or more overlapping areas, and traversing a portion of the vehicle transportation network at 5110 based on the system utility vehicle guidance data includes: for each corresponding system utility vehicle guidance data, outputting a representation of at least a portion of the system utility vehicle guidance data to be presented to the occupants of the vehicle (the current vehicle), wherein selected (or chosen) system utility vehicle guidance data can be identified in response to input (such as user input indicating system utility vehicle guidance data). In some embodiments, a vehicle may autonomously traverse a portion of the vehicle transportation network based on selected system utility vehicle guidance data.

[0175] Although the system utility vehicle-guided model described in this paper addresses aspects of the state space, action space, transition probabilities, and reward function, other aspects can be implemented. For example, the model's state space may include other state factors. In another example, the model may include other aspects such as the observation set (Ω) and the conditional observation probability set (O).

[0176] As used herein, the terms “computer” or “computing device” include any unit or combination of units disclosed herein capable of performing any method or any or more parts thereof.

[0177] As used herein, the term "processor" refers to one or more processors, such as 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 application processors, one or more application-specific integrated circuits, one or more dedicated standard products; one or more field-programmable gate arrays, any other type or combination of integrated circuits, one or more state machines, or any combination thereof.

[0178] As used herein, the term "memory" refers to any computer-usable or computer-readable medium or device that can tangibly contain, store, communicate, or transport any signals or information that can be used by or associated with any processor. For example, a memory can be one or more read-only memories (ROMs), one or more random access memories (RAMs), one or more registers, 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.

[0179] As used herein, the term "instructions" can include indications or expressions for performing any of the methods disclosed herein or any one or more of any portion thereof, and can be implemented in hardware, software, or any combination thereof. For example, instructions can be implemented as information (such as a computer program) stored in memory, which can be executed by a processor to perform any of the various methods, algorithms, aspects, or combinations thereof described herein. In some embodiments, instructions or portions thereof can be implemented as dedicated processors or circuitry, which can include dedicated hardware for performing any of the methods, algorithms, aspects, or combinations thereof described herein. In some implementations, portions of instructions can be distributed across a single device or multiple processors across multiple devices that can communicate directly or across networks (such as local area networks, wide area networks, the Internet, or combinations thereof).

[0180] As used herein, the terms “example,” “implementation,” “aspect,” “feature,” or “element” indicate that they are used as examples, instances, or illustrations. Unless expressly indicated, any example, embodiment, implementation, aspect, feature, or element is independent of various other examples, embodiments, implementations, aspects, features, or elements, and may be used in combination with any other example, embodiment, implementation, aspect, feature, or element.

[0181] As used herein, the terms “determine” and “identify” or any variation thereof include using one or more of the devices shown and described herein to select, identify, calculate, locate, receive, determine, establish, obtain or otherwise identify or determine in any way.

[0182] As used herein, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or.” That is, unless otherwise specified or explicitly stated from the context, “X includes A or B” is intended to indicate any natural inclusive arrangement. That is, “X includes A or B” is satisfied in any of the foregoing cases if X includes A; X includes B; or X includes both A and B. Additionally, unless otherwise specified or explicitly stated from the context to refer to the singular form, the articles “a” and “an” as used in this application and the appended claims should generally be understood to mean “one or more.”

[0183] Furthermore, for the sake of simplicity, although the accompanying drawings and descriptions may include a sequence or series of steps or stages, the elements of the methods disclosed herein may occur in various orders or in parallel. Additionally, the elements of the methods disclosed herein may occur together with other elements not explicitly presented and described herein. Moreover, it is not necessary to implement the method according to the invention with all the elements of the method described herein. Although aspects, features, and elements are described herein in specific combinations, each aspect, feature, or element may be used independently, or in various combinations with other aspects, features, and elements, or in various combinations without other aspects, features, and elements.

[0184] To facilitate a clear understanding of the invention, the foregoing aspects, examples, and implementations have been described, but the invention is not restrictive. In contrast, the invention covers various modifications and equivalent arrangements included within the scope of the appended claims, which should be interpreted in the broadest possible sense to encompass all such modifications and equivalent structures permitted by law.

Claims

1. A method for traversing a vehicle transport network, the method comprising: The current vehicle traverses a vehicle transportation network, wherein traversing the vehicle transportation network includes: The system utility vehicle guidance data for the current portion of the vehicle transportation network is obtained from an instance of a system utility vehicle guidance strategy generated by solving a system utility vehicle guidance model, which is used to maximize the system utility of multiple vehicles operating within the region of the vehicle transportation network that includes the current portion; and The current vehicle traverses the current portion of the vehicle transportation network based on the system utility vehicle guidance data.

2. The method according to claim 1, wherein, The current portion of traversing the vehicle transportation network based on the system utility vehicle guidance data includes: The system outputs a representation of the vehicle guidance data to be presented to the occupants of the current vehicle.

3. The method according to claim 1, wherein, The current portion of traversing the vehicle transportation network based on the system utility vehicle guidance data includes: The system uses vehicle guidance data to control the current vehicle for autonomous driving.

4. The method according to claim 1, wherein, The system utility vehicle guidance data indicates at least one of the following: The target speed used by the current vehicle to traverse the current portion of the vehicle transportation network; The target lane used by the current vehicle to traverse the current portion of the vehicle transportation network; The target route taken by the current vehicle from its current location through the current portion of the vehicle transportation network to its target destination; as well as The target right-of-way priority used by the current vehicle to cross the intersection in the vehicle transportation network, wherein the current portion of the vehicle transportation network includes the intersection.

5. The method according to claim 1, wherein, Obtaining the system utility vehicle guidance data includes: The system utility vehicle guidance data is obtained from an external device by the current vehicle.

6. The method according to claim 5, wherein, The external device is a remote transport vehicle; The external device is a centralized infrastructure device; or The external device is a distributed infrastructure device.

7. The method according to claim 1, wherein, The system utility vehicle guidance model is a stochastic model.

8. The method according to claim 7, wherein, The stochastic model is: Markov decision process model; Random shortest path model; Partially observable Markov decision process models; Markov game model; Partially observable Markov game models; or Distributed partially observable Markov decision process models.

9. The method according to claim 7, wherein, Obtaining the system utility vehicle guidance data includes: The random model is operated by the current vehicle.

10. A method for traversing a vehicle transport network, comprising: Obtain vehicle operation data for a region of the vehicle transportation network, wherein the vehicle operation data includes current operation data of multiple vehicles operating in the region; A system utility vehicle guidance model for operating the region, the system utility vehicle guidance model being used to maximize the system utility of multiple vehicles operating within the region; In response to the vehicle operation data, system utility vehicle guidance data for the region is obtained from the system utility vehicle guidance model; and Output the system utility vehicle guidance data.

11. The method according to claim 10, wherein, Obtaining system utility vehicle guidance data for the region includes obtaining per-vehicle system utility vehicle guidance data for participating vehicles in the region.

12. The method according to claim 10, wherein, Obtaining system utility vehicle boot data includes: obtaining the system utility vehicle boot data such that the system utility vehicle boot data includes at least one of the following: The target speed at which a vehicle traverses a portion of the vehicle transport network; The target lane used by the vehicle to traverse the portion of the vehicle transportation network; The target route taken by the vehicle from its current location through the portion of the vehicle transportation network to its target destination; and The target right-of-way priority used by a vehicle to cross an intersection in the vehicle transportation network, wherein the portion of the vehicle transportation network includes the intersection.

13. The method according to claim 10, wherein, The operation of the system utility vehicle guidance model is carried out through the following: Vehicles; Centralized infrastructure facilities; or Distributed infrastructure devices.

14. The method of claim 10, wherein, The system utility vehicle guidance model is: Markov decision process model; Random shortest path model; Partially observable Markov decision process models; Markov game model; Partially observable Markov game models; or Distributed partially observable Markov decision process models.

15. The method according to claim 10, wherein, The operational system utility vehicle guidance model includes: The vehicle operation data is used to generate the system utility vehicle guidance model; and Solve the system utility vehicle guidance model to obtain the system utility vehicle guidance strategy.

16. The method according to claim 15, wherein, Obtaining the system utility vehicle guidance data includes: The system utility vehicle bootstrapping strategy is used to generate the system utility vehicle bootstrapping data.

17. A method for traversing a vehicle transport network, the method comprising: The current vehicle traverses a vehicle transportation network, wherein traversing the vehicle transportation network includes: Obtaining system utility vehicle guidance data for the current portion of the vehicle transportation network from the current vehicle, wherein obtaining the system utility vehicle guidance data includes: Obtain vehicle operation data for a region of the vehicle transportation network, wherein the vehicle operation data includes current operation data of multiple vehicles operating in the region. In response to the vehicle operation data, a system utility vehicle guidance model is operated for the region, the system utility vehicle guidance model being used to maximize the system utility of multiple vehicles operating within the region, and The system utility vehicle guidance data for the region is obtained from the strategy generated by the system utility vehicle guidance model; and The current vehicle traverses the current portion of the vehicle transportation network based on the system utility vehicle guidance data.

18. The method according to claim 17, wherein, The current portion of traversing the vehicle transportation network based on the system utility vehicle guidance data includes: The system outputs a representation of the vehicle guidance data to be presented to the occupants of the current vehicle.

19. The method of claim 17, wherein, The current portion of traversing the vehicle transportation network based on the system utility vehicle guidance data includes: The system uses vehicle guidance data to control the current vehicle for autonomous driving.

20. The method of claim 17, wherein, The system utility vehicle guidance data indicates at least one of the following: The target speed used by the current vehicle to traverse the current portion of the vehicle transportation network; The target lane used by the current vehicle to traverse the current portion of the vehicle transportation network; The target route taken by the current vehicle from its current location through the current portion of the vehicle transportation network to its target destination; as well as The target right-of-way priority used by the current vehicle to cross the intersection in the vehicle transportation network, wherein the current portion of the vehicle transportation network includes the intersection.

Images