Vehicle Guidance with Systematic Optimization

Abstract

Vehicle guidance with systematic optimization includes obtaining, by a current vehicle, systematic utility vehicle guidance data for a current portion of the vehicle network, and navigating, by the current vehicle, the vehicle network by navigating, by the current vehicle, the current portion of the vehicle network according to the systematic utility vehicle guidance data. Obtaining the systematic utility vehicle guidance data may include obtaining vehicle operation data for a region of the vehicle network, the vehicle operation data including current operation data for a plurality of vehicles operating within the region, operating a systematic utility vehicle guidance model for the region, obtaining systematic utility vehicle guidance data for the region from the systematic utility vehicle guidance model in response to the vehicle operation data, and outputting the systematic utility vehicle guidance data to the current vehicle.

Description

[Technical Field]

[0001] The present disclosure relates to vehicle operations, including methods, apparatus, and non-transitory computer-readable media for performing vehicle guidance with systematic optimization. [Background technology]

[0002] Vehicles, such as manually controlled vehicles, semi-autonomously controlled vehicles, or autonomous vehicles, operating within a vehicle traffic network may navigate the vehicle traffic network or portions thereof by executing a sequence of individual vehicle control actions identified based on maximizing predicted operational utility for each vehicle. Summary of the Invention

[0003] Disclosed herein are aspects, features, elements, implementations and embodiments of vehicle guidance with systematic optimization.

[0004] One aspect of the disclosed embodiments is a method for use in navigating a vehicle network by a vehicle using vehicle guidance with systematic optimization, the method including obtaining, by the vehicle, systematic utility vehicle guidance data for a current portion of the vehicle network, and navigating, by the vehicle, the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data.

[0005] Another aspect of the disclosed embodiments is a method for vehicle guidance with systematic optimization, the method including obtaining vehicle operation data for a region of a vehicle traffic network, the vehicle operation data including current operation data for a plurality of vehicles operating in the region, operating a systematic utility vehicle guidance model for the region, obtaining systematic utility vehicle guidance data for the region from the systematic utility vehicle guidance model in response to the vehicle operation data, and outputting the systematic utility vehicle guidance data.

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

[0007] These and other aspects, features, elements, implementations and embodiment variations of the methods, apparatus, procedures and algorithms disclosed herein are described in further detail below.

[0008] Various aspects of the methods and apparatus disclosed herein will become more apparent with reference to the examples provided in the following description and drawings. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 illustrates an example of a vehicle in which aspects, features, and elements disclosed herein may be implemented.

[0010] [Figure 2] FIG. 1 is an example diagram of a portion of a vehicle traffic and communication system in which aspects, features, and elements disclosed herein may be implemented.

[0011] [Figure 3] FIG. 1 is a diagram of a portion of a vehicle traffic network.

[0012] [Figure 4] FIG. 1 is a diagram of an example autonomous vehicle operation management system.

[0013] [Figure 5] FIG. 1 is a flow diagram illustrating an example of vehicle guidance with systematic optimization according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0014] A vehicle operating within a vehicle network, such as a manually controlled vehicle, a semi-autonomously controlled vehicle, or an autonomous vehicle, may navigate the vehicle network or a portion thereof by performing a series of individual vehicle control actions, such as vehicle control actions or route decisions. Each vehicle control action has an operational cost, such as risk (or conversely, safety) and travel time. The operational costs may be interrelated. For example, a vehicle control action that increases speed may decrease operational costs associated with travel time and increase operational costs associated with risk.

[0015] A weighted sum of the operational costs associated with the vehicle control action may be identified as the operational utility for the vehicle control action. Maximizing operational utility balances minimizing each operational cost, such as risk (or conversely, safety) and travel time. Although operational utility is described here in terms of risk and travel time, other operational costs, such as fuel utilization, may also be used. The operational utility of the vehicle control action for the vehicle performing the vehicle control action may be identified as a vehicle-specific operational utility.

[0016] Vehicles operating within a vehicular traffic network are controlled according to the vehicle's current operating parameters and the vehicle's current operating environment, such as within a defined distance of the vehicle, to maximize vehicle-specific operational utility. The information used to identify vehicle-specific operational utility may omit or incorrectly weight some information that may affect vehicle operation. For example, for some vehicles, some information that may affect vehicle operation, such as information about the operating environment of areas other than the vehicle's current operating environment, may be unavailable to a manual or autonomous vehicle or vehicle operator, or may be available but not utilized or inappropriately weighted. In another example, a time delay between an event or occurrence in an area that may affect vehicle operation and the detection of the event, or a response delay indicating data representing the event, may limit the operational utility of a vehicle control action through the identification of a vehicle control action in response to the event and the execution of that vehicle control action. The difference between predicted and observed operational utility may correspond to differences in the operational information utilized and its relative weighting.

[0017] For some vehicles, maximizing vehicle-specific operational utility may correlate with suboptimal system utility. System utility balances or aggregates operational utility for vehicles operating within a defined region of the vehicular traffic network. Maximizing system utility may involve 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] Vehicle guidance with systematic optimization includes obtaining vehicle behavior and environmental data for vehicles within a defined region of a vehicular traffic network. The vehicle behavior and environmental data may include some data that is unavailable, unused, or improperly weighted for maximizing vehicle-specific operational utility performed on a vehicle-by-vehicle basis for each vehicle within the region. Vehicle guidance with systematic optimization includes operating a systematic utility vehicle guidance model that maximizes systematic utility for the region. Vehicle guidance with systematic optimization includes obtaining systematic utility vehicle guidance data for each vehicle from the systematic utility vehicle guidance model for the region that is responsive to the vehicle behavior data and environmental data for the region. Vehicle guidance with systematic optimization includes providing the systematic utility vehicle guidance data to each participating vehicle operating within the region.

[0019] A region including participating vehicles that obtain systematic utility vehicle guidance data and operate within the region traversing at least a portion of the vehicle traffic network within the region according to the systematic utility vehicle guidance data has an improved systematic utility for the observed region compared to a region that excludes the participating vehicles. Because the behavior of vehicles, such as participating vehicles, affects the behavior of other vehicles, such as vehicles that may be non-participating vehicles, in the participating vehicles' operating environment, a relatively small proportion of participating vehicles, such as 1%, relative to non-participating vehicles, may effectively maximize the systematic utility for the region, which may improve the observed vehicle-specific operating utility of vehicles, including participating and non-participating vehicles. In some embodiments, the improvement in systematic utility for a region may be correlated with the proportion of participating vehicles.

[0020] FIG. 1 illustrates an example of a vehicle in which aspects, features, and elements disclosed herein may be implemented. As illustrated, vehicle 1000 includes a chassis 1100, a powertrain 1200, a controller 1300, and wheels 1400. For simplicity, vehicle 1000 is shown as including four wheels 1400, but any other propulsion device, such as propellers or treads, may be used. In FIG. 1, lines interconnecting elements such as powertrain 1200, controller 1300, and wheels 1400 indicate that information, such as data or control signals, force, such as power or torque, or both information and power, may be transmitted between the elements. For example, controller 1300 may receive power from powertrain 1200 and communicate with powertrain 1200, wheels 1400, or both, to control vehicle 1000, including controlling the vehicle's motion state, such as by accelerating or decelerating, controlling the vehicle's directional state, such as by steering, or otherwise controlling vehicle 1000.

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

[0022] The power source 1210 may include an engine, a battery, or a combination thereof. The power source 1210 may be any device or combination of devices that operate to provide energy, such as electrical energy, thermal energy, or kinetic energy. For example, the power source 1210 may include an engine, such as an internal combustion engine, an electric motor, or a combination of an internal combustion engine and an electric motor, and may operate to provide kinetic energy as motive power to one or more wheels 1210. The power source 1210 may include a potential energy device, such as one or more dry batteries, such as nickel-cadmium (NiCd), nickel-zinc (NiZn), nickel-metal hydride (NiMH), lithium-ion (Li-ion), etc., a solar cell, a fuel cell, or any other device capable of providing energy.

[0023] The transmission 1220 may receive energy, such as kinetic energy, from the power source 1210 and may send the energy to the wheels 1400 to provide motive power. The transmission 1220 may be controlled by the controller 1300, the actuator 1240, or both. The steering device 1230 may be controlled by the controller 1300, the actuator 1240, or both and may control the wheels 1400 to steer the vehicle. The actuator 1240 may receive signals from the controller 1300 and may operate or control the power source 1210, the transmission 1220, the steering device 1230, or any combination thereof to operate the vehicle 1000.

[0024] As shown, the controller 1300 may include a positioning device 1310, an electronic communication device 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 device, any one or more elements of the controller 1300 may be incorporated into any number of separate physical devices. For example, the user interface 1350 and the processor 1330 may be incorporated into a first physical device, and the memory 1340 may be incorporated into a second physical device. Although not shown in FIG. 1 , the controller 1300 may include a power source 1210, such as a battery. Although shown as separate elements, the positioning device 1310, the electronic communication device 1320, the processor 1330, the memory 1340, the user interface 1350, the sensor 1360, the electronic communication interface 1370, or any combination thereof may be incorporated into one or more electronic devices, circuits, or chips.

[0025] The processor 1330 may include any device or combination of devices now known or later developed that can manipulate or process signals or other information, including an optical processor, a quantum processor, a molecular processor, or a combination thereof. For example, the processor 1330 may include one or more special purpose processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more microcontrollers, one or more integrated circuits, one or more application-specific integrated circuits, one or more field programmable gate arrays, one or more programmable logic arrays, one or more programmable logic controllers, one or more state machines, or any combination thereof. The processor 1330 may be operatively coupled to the positioning device 1310, the memory 1340, the electronic communication interface 1370, the electronic communication device 1320, the user interface 1350, the sensor 1360, the powertrain 1200, or any combination thereof. For example, the processor may be operatively coupled to the memory 1340 via a communication bus 1380.

[0026] Memory 1340 may include any tangible, non-transitory computer-usable or computer-readable medium capable of, for example, holding, storing, transmitting, or carrying machine-readable instructions, or any information associated therewith, for use by or in connection with processor 1330. Memory 1340 may be, for example, one or more solid-state drives, one or more memory cards, one or more removable media, one or more read-only memories, one or more random access memories, one or more disks including hard disks, floppy disks, optical disks, magnetic or optical cards, or any type of non-transitory medium suitable for storing electronic information, or any combination thereof.

[0027] Communication interface 1370 may be a wireless antenna as shown, a wired communication port, an optical communication port, or any other wired or wireless device capable of interfacing with wired or wireless electronic communication medium 1500. While Figure 1 shows communication interface 1370 communicating over a single communication link, the communication interface may be configured to communicate over multiple communication links. Although Figure 1 shows a single communication interface 1370, the vehicle may include any number of communication interfaces.

[0028] The communication device 1320 may be configured to transmit or receive signals over a wired or wireless electronic communication medium 1500, such as via a communication interface 1370. Although not explicitly shown in FIG. 1 , the communication device 1320 may be configured to transmit, receive, or both over any wired or wireless communication medium, such as radio frequency (RF), ultraviolet (UV), visible light, optical fiber, wired line, or a combination thereof. While FIG. 1 depicts a single communication device 1320 and a single communication interface 1370, any number of communication devices and any number of communication interfaces may be used. In some embodiments, the communication device 1320 may include a dedicated short range communication (DSRC) device, an on-board unit (OBU), or a combination thereof.

[0029] The positioning device 1310 may determine geographic information such as the longitude, latitude, altitude, heading, or speed of the vehicle 1000. For example, the positioning device may include a Global Positioning System (GPS) device, such as a Wide Area Augmentation System (WAAS)-enabled National Marine-Electronics Association (NMEA) device, a radiotriangulation device, or a combination thereof. The positioning device 1310 may be used to obtain information representing, for example, the current heading of the vehicle 1000, the current location of the vehicle 1000 in two or three dimensions, the current angular heading of the vehicle 1000, or a combination thereof.

[0030] The user interface 1350 may include any device capable of interfacing with a person, such as a virtual or physical keypad, touchpad, display, touch display, heads-up display, virtual display, augmented reality display, tactile display, feature tracking device such as an eye-tracking device, speaker, microphone, video camera, sensor, printer, or any combination thereof. The user interface 1350 may be operatively coupled to the processor 1330 as shown or to any other element of the controller 1300. Although shown as a single device, the user interface 1350 may include one or more physical devices. For example, the user interface 1350 may include an audio interface for audio communication with the person and a touch display for visual and touch-based communication with the person. The user interface 1350 may include multiple displays, such as multiple physically separate devices, multiple defined portions of a single physical device, or a combination thereof.

[0031] Sensors 1360 may include one or more sensors, such as an array of sensors, operable to provide information that can be used to control the vehicle. Sensors 1360 may provide information regarding current operating characteristics of vehicle 1000. Sensors 1360 may include, for example, speed sensors, acceleration sensors, steering angle sensors, traction-related sensors, brake-related sensors, steering wheel position sensors, eye-tracking sensors, seating position sensors, or any sensor or combination of sensors operable to report information regarding some aspect of the current dynamic situation of vehicle 1000.

[0032] Sensors 1360 may include one or more sensors operable to obtain information about the physical environment surrounding vehicle 1000. For example, one or more sensors may detect road features and shapes, such as lanes, and obstacles, such as fixed obstacles, vehicles, and pedestrians. Sensors 1360 may be or include one or more video cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of on-board environmental sensing device or combination of devices, whether known or later developed. In some embodiments, sensors 1360 and positioning device 1310 may be a combined device.

[0033] Although not separately shown, vehicle 1000 may include a trajectory controller. For example, controller 1300 may include the trajectory controller. The trajectory controller may be operable to obtain information describing the current state of vehicle 1000 and a planned route for vehicle 1000, and to determine and optimize a trajectory for vehicle 1000 based on this information. In some embodiments, the trajectory controller may output signals operable to control vehicle 1000 so 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 provided 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 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 steered wheels that can be pivoted to a steering angle under the control of the steering device 1230, propelled wheels that can be given torque to propel the vehicle 1000 under the control of the transmission 1220, or steered and propelled wheels that can both steer and propel the vehicle 1000.

[0035] Although not shown in FIG. 1, the vehicle may include devices or elements not shown in FIG. 1, such as an enclosure, a Bluetooth® module, a frequency modulation (FM) radio device, a near field communication (NFC) module, a liquid crystal display (LCD) display device, an organic light emitting diode (OLED) display device, a speaker, or any combination thereof.

[0036] Vehicle 1000 may be an autonomous vehicle that is autonomously controlled without direct human intervention to travel through a portion of a transportation network. Although not separately shown in FIG. 1 , the autonomous vehicle may include an autonomous vehicle controller that may perform routing, navigation, and control of the autonomous vehicle. The autonomous vehicle controller may be integrated with another device in the vehicle. For example, controller 1300 may include the autonomous vehicle controller.

[0037] The autonomous vehicle controller may control or operate the vehicle 1000 to travel through a portion of a vehicle traffic network according to current vehicle operating parameters. The autonomous vehicle controller may control or operate the vehicle 1000 to perform a defined action or maneuver, such as parking the vehicle. The autonomous vehicle controller may generate a travel route from a start point, such as the current location of the vehicle 1000, to a destination based on vehicle information, environmental information, vehicle traffic network data representing the vehicle traffic network, or a combination thereof, and may control or operate the vehicle 1000 to travel through the vehicle traffic network according to the route. For example, the autonomous vehicle controller may output the travel route to a trajectory controller, and the trajectory controller may operate the vehicle 1000 to travel from the start point to the destination using the generated route.

[0038] Figure 2 is an example diagram of a portion of a vehicle traffic and communication system in which aspects, features, and elements disclosed herein may be implemented. The vehicle traffic and communication system 2000 may include one or more vehicles 2100 / 2110, such as vehicle 1000 shown in Figure 1, which may travel in one or more portions of one or more vehicle traffic networks 2200 and may communicate via one or more electronic communication networks 2300. Although not explicitly shown in Figure 2, the vehicles may travel in areas not explicitly or entirely included in the vehicle traffic network, such as off-road areas.

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

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

[0041] Vehicles 2100 / 2110 may communicate with infrastructure devices. For example, communication devices 2400 / 2410 shown in FIG. 2 may be infrastructure devices. The infrastructure devices may be associated with a defined area of ​​a vehicular traffic network, such as a lane, a road segment, a contiguous group of road segments, a road, or an intersection, or with a defined geographic area, such as a block, a neighborhood, a district, a county, a municipality, a state, a country, or another defined geographic area. The infrastructure devices may be centralized infrastructure devices or distributed infrastructure devices. 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 link 2380 / 2385 or network 2300. Direct communication link 2380 / 2385 may be a wireless communication link.

[0042] A vehicle 2100 / 2110 may communicate with another vehicle 2100 / 2110. For example, a host or target vehicle (HV) 2100 may receive one or more autonomous vehicle-to-vehicle messages, such as a basic safety message (BSM), from a remote or target vehicle (RV) 2110 via a direct communication link 2370 or via a network 2300. For example, a remote vehicle 2110 may broadcast a message to a host vehicle within a defined broadcast range, such as 300 meters. In some embodiments, the host vehicle 2100 may receive the message via a third party, such as a signal repeater (not shown) or another remote vehicle (not shown). The vehicle 2100 / 2110 may transmit one or more autonomous vehicle-to-vehicle messages periodically based on a defined interval, such as every 100 milliseconds. The direct communication link 2370 may be, for example, a wireless communication link.

[0043] The automatic vehicle-to-vehicle message may include vehicle identification information, geospatial state information such as longitude, latitude, or altitude information, geospatial position accuracy information, motion state information such as vehicle acceleration information, yaw rate information, speed information, vehicle heading information, braking system state information, throttle information, steering angle information, or vehicle path information, or vehicle operating state information such as vehicle size information, headlight state information, turn signal information, wiper state information, transmission information, or any other information or combination of information related to the transmitting vehicle state. For example, transmission state information may indicate whether the transmitting vehicle's transmission is in neutral, park, forward, or reverse.

[0044] Vehicle 2100 may communicate with communication network 2300 via access point 2330. Access point 2330, which may include a computing device, may be configured to communicate with vehicle 2100, communication network 2300, one or more communication devices 2400 / 2410, or combinations thereof, via wireless or wired communication links 2310 / 2340. For example, access point 2330 may 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, relay, switch, or any similar wired or wireless device. Although shown as a single device in FIG. 2, the access point may include any number of interconnecting elements.

[0045] Vehicle 2100 may communicate with communication network 2300 via satellite 2350 or other non-terrestrial communication device. Satellite 2350, which may include a computing device, may be configured to communicate with vehicle 2100, communication network 2300, one or more communication devices 2400 / 2410, or combinations thereof, via one or more communication links 2320 / 2360. Although shown as a single device in FIG. 2, a satellite may include any number of interconnecting elements.

[0046] The electronic communications network 2300 may be any type of network configured to provide voice, data, or any other type of electronic communications. For example, the electronic communications network 2300 may include a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a mobile or cellular telephone network, the Internet, or any other electronic communications system. The electronic communications network 2300 may use communications protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Internet Protocol (IP), Real-Time Transport Protocol (RTP), Hypertext Transport Protocol (HTTP), or combinations thereof. Although shown as a single device in FIG. 2 , the electronic communications network may include any number of interconnected elements. The communications devices 2400 / 2410 may communicate via communications links 2390, etc.

[0047] The vehicle 2100 may identify a portion or state of the vehicle network 2200. For example, the vehicle 2100 may include one or more on-board sensors 2105, such as the sensors 1360 shown in FIG. 1 , which may include a speed sensor, a wheel speed sensor, a camera, a gyroscope, an optical sensor, a laser sensor, a radar sensor, an acoustic sensor, or any other sensor or device, or combination thereof, capable of determining or identifying a portion or state of the vehicle network 2200. The sensor data may include lane data, remote vehicle position data, or both.

[0048] Vehicle 2100 may travel through one or more portions of one or more vehicle traffic networks 2200 using information communicated via network 2300, such as information representative of traffic network 2200, one or more on-board sensors 2105, or a combination thereof.

[0049] For simplicity, Figure 2 shows two vehicles 2100, 2110, one vehicle traffic network 2200, one electronic communications network 2300, and two communications devices 2400 / 2410, although any number of networks or computer devices may be used. Vehicle traffic and communications system 2000 may include devices, units, or elements not shown in Figure 2. While vehicle 2100 is shown as a single device, the vehicle may include any number of interconnected elements.

[0050] Although vehicle 2100 is shown communicating with communication device 2400 via network 2300, vehicle 2100 may communicate with communication device 2400 via any number of direct or indirect communication links. For example, vehicle 2100 may communicate with communication device 2400 / 2410 via a direct communication link, such as a Bluetooth® communication link.

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

[0052] 3 is a diagram of a portion of a vehicular traffic network according to the present disclosure. Vehicular traffic network 3000 may include one or more non-passable areas 3100, such as buildings, one or more partially passable areas, such as parking areas 3200, one or more passable areas, such as roads 3300 / 3400, or combinations thereof. In some embodiments, an autonomous vehicle, such as vehicle 1000 shown in FIG. 1, one of vehicles 2100 / 2110 shown in FIG. 2, a semi-autonomous vehicle, or any other vehicle implementing autonomy, may travel through one or more portions of vehicular traffic network 3000.

[0053] Vehicle network 3000 may include one or more interchanges between one or more passable or partially passable areas 3200 / 3300 / 3400. For example, the portion of vehicle network 3000 shown in Figure 3 includes interchange 3210 between parking area 3200 and road 3400. Parking area 3200 may include parking lot 3220.

[0054] A portion of the vehicular traffic network 3000, such as a road 3300 / 3400, may include one or more lanes 3320 / 3340 / 3360 / 3420 / 3440 and may be associated with one or more directions of travel, as indicated by arrows in FIG.

[0055] A vehicle network or a portion thereof, such as the portion of vehicle network 3000 shown in FIG. 3 , may be represented as vehicle network information. For example, vehicle network data may be represented as a hierarchy of elements, such as markup language elements, which may be stored in a database or file. For simplicity, the figures herein show vehicle network data representing a portion of a vehicle network as a diagram or map. However, vehicle network data may be represented in any computer-usable format capable of representing a vehicle network or a portion thereof. Vehicle network data may include heading information, speed limit information, toll booth information, gradient information, such as slope or angle information, surface material information, aesthetic information, defined hazard information, or a combination thereof.

[0056] A vehicular traffic network may be associated with or include a pedestrian traffic network. For example, Figure 3 includes a portion 3600 of a pedestrian traffic network, which may be a pedestrian walkway. Although not separately shown in Figure 3, pedestrian access areas, such as pedestrian crosswalks, may correspond to access areas or partial access areas of the vehicular traffic network.

[0057] A portion or combination of portions of a vehicle network may be identified as a particular location or destination. For example, vehicle network data may identify a building, such as a restricted area 3100 and an adjacent partially accessible parking area 3200, as a particular location, a vehicle may identify the particular location as a destination, and the vehicle may travel from the origin to the destination by traveling through the vehicle network. While parking area 3200 associated with restricted area 3100 is shown in FIG. 3 as adjacent to restricted area 3100, a destination may include, for example, buildings and parking areas that are not physically or geospatially adjacent to the building.

[0058] Identifying the destination may include identifying a location for the destination, which may be a distinct, uniquely identifiable geographic location. For example, a vehicle network may include a defined location, such as a street address, a physical address, a vehicle network address, a GPS address, or a combination thereof, for the destination.

[0059] A destination may be associated with one or more entrances, such as entrance 3500 shown in Figure 3. The vehicle network data may include defined entrance location information, such as information identifying the geographic location of the entrance associated with the destination.

[0060] A destination may be associated with one or more docking locations, such as docking location 3700 shown in Figure 3. Docking location 3700 may be a designated or undesignated location or area proximate to the destination where an autonomous vehicle may stop, rest, or park to perform docking operations such as loading and unloading passengers.

[0061] The vehicle network data may include docking location information, such as information identifying the geographic locations of one or more docking locations 3700 associated with a destination. Although not separately shown in FIG. 3 , the docking location information may identify a type of docking operation associated with the docking location 3700. For example, a destination may be associated with a first docking location for picking up passengers and a second docking location for dropping off passengers. While an autonomous vehicle may park at a docking location, the docking location associated with the destination may be independent and different from the parking area associated with the destination.

[0062] 4 is a diagram of an example autonomous vehicle operation management system 4000 according to an embodiment of the present disclosure. The autonomous vehicle operation management system 4000 may be implemented in an autonomous vehicle, such as the vehicle 1000 shown in FIG. 1, the vehicle 2100 / 2110 shown in FIG. 2, a semi-autonomous vehicle, or any other vehicle that implements autonomous driving.

[0063] As shown in FIG. 4 , 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] An autonomous vehicle may travel through a vehicle traffic network or a portion thereof, which may include traveling through a distinct vehicle operating scenario. A distinct vehicle operating scenario may include any clearly identifiable set of operating conditions that may affect the operation of the autonomous vehicle within a defined spatiotemporal area or operating environment of the autonomous vehicle. For example, a distinct vehicle operating scenario may be based on the number or density of roads, road segments, or lanes that the autonomous vehicle may travel within a defined spatiotemporal distance. In another example, a distinct vehicle operating scenario may be based on one or more traffic control devices that may affect the operation of the autonomous vehicle within the defined spatiotemporal area or operating environment of the autonomous vehicle. In another example, a distinct vehicle operating scenario may be based on one or more identifiable rules, regulations, or laws that may affect the operation of the autonomous vehicle within the defined spatiotemporal area or operating environment of the autonomous vehicle. In another example, a distinct vehicle operating scenario may be based on one or more identifiable external objects that may affect the operation of the autonomous vehicle within the defined spatiotemporal area or operating environment of the autonomous vehicle.

[0065] For brevity and clarity, similar vehicle operation scenarios may be described herein with reference to types or classes of vehicle operation scenarios. A type or class of vehicle operation scenario may refer to a defined pattern or set of defined patterns of scenarios. For example, an intersection scenario may include an autonomous vehicle traveling through an intersection, and a pedestrian scenario may include an autonomous vehicle traveling through a portion of a vehicular network that includes one or more pedestrians or is within a defined proximity of a pedestrian, such as a pedestrian crossing or approaching the autonomous vehicle's predicted path. A lane change scenario may include an autonomous vehicle traveling through a portion of a vehicular network by changing lanes. A merge scenario may include an autonomous vehicle traveling through a portion of a vehicular network by merging from a first lane into a merging lane. An obstacle traversal scenario may include an autonomous vehicle traveling through a portion of a vehicular network by negotiating an obstruction or obstacle. Although a pedestrian vehicle movement scenario, an intersection vehicle movement scenario, a lane change vehicle movement scenario, a merging vehicle movement scenario, and an obstacle traversal vehicle movement scenario are described herein, any other vehicle movement scenario or type of vehicle movement scenario may be used.

[0066] The AVOMC4100 or another device in the autonomous vehicle may control the autonomous vehicle to traverse the vehicular network or a portion thereof. Controlling the autonomous vehicle to traverse the vehicular network may include monitoring an operating environment for the autonomous vehicle, identifying or detecting distinct vehicle operation scenarios, identifying candidate vehicle control actions based on the distinct vehicle operation scenarios, and controlling the autonomous vehicle to traverse the portion of the vehicular network in accordance with one or more candidate vehicle control actions or a combination thereof.

[0067] The AVOMC4100 may receive, identify, or otherwise access operating environment data describing an operating environment for 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 a defined spatiotemporal area of ​​the autonomous vehicle, within a defined spatiotemporal area of ​​a route identified for the autonomous vehicle, or a combination thereof. For example, operating conditions that may affect the operation of an autonomous vehicle may be identified based on sensor data, vehicle traffic network data, route data, or any other data or combination of data that represents an operating environment defined or determined for the vehicle. Operating conditions that may affect the operation of an autonomous vehicle may include roads, road segments, or lanes that the autonomous vehicle may travel, 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 operating state of the autonomous vehicle, the operating state of one or more passengers in the autonomous vehicle, the operating state of cargo in the autonomous vehicle, or other identifiable conditions, states, or events that may affect the operation of the autonomous vehicle.

[0068] The operating environment data may include vehicle information related to the autonomous vehicle, such as information indicating the geospatial location of the autonomous vehicle, information correlating the geospatial location of the autonomous vehicle with information describing the vehicle traffic network, the path of the autonomous vehicle, the speed of the autonomous vehicle, the acceleration state of the autonomous vehicle, passenger information for the autonomous vehicle, or any other information related to the autonomous vehicle or the operation of the autonomous vehicle.

[0069] The operating environment data may include information describing a vehicle network proximate to the identified route for the autonomous vehicle, such as within a defined spatial distance of the autonomous vehicle, such as 300 meters, of a portion of the vehicle network along the identified route, which may include information indicative of the shape of one or more aspects of the vehicle network, information indicative of conditions such as surface conditions of the vehicle network, or any combination thereof.

[0070] The operating environment data may include information describing a vehicle network in proximity to the autonomous vehicle, such as within a defined spatial distance of the autonomous vehicle, such as 300 meters, which may include information indicative of the shape of one or more aspects of the vehicle network, information indicative of conditions such as the surface condition of the vehicle network, or any combination thereof.

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

[0072] Aspects of the operating environment of the autonomous vehicle may be represented in each individual vehicle operation scenario. For example, relative heading, trajectory, predicted path, or external objects may be represented in each individual vehicle operation scenario. In another example, the relative shape of a vehicular traffic network may be represented in each individual vehicle operation scenario.

[0073] Although a pedestrian vehicle operation scenario, an intersection vehicle operation scenario, a lane change vehicle operation scenario, a merging vehicle operation scenario, and an obstacle traversal vehicle operation scenario are described herein, any other vehicle operation scenario may be used.

[0074] The autonomous vehicle may simultaneously traverse multiple distinct vehicle operation scenarios within the operating environment. The autonomous vehicle operation management system 4000 may operate or control the autonomous vehicle to traverse the distinct vehicle operation scenarios subject to defined constraints, such as safety constraints, legal constraints, physical constraints, user acceptance constraints, or any other constraint or combination of constraints that may be defined or generated for the operation of the autonomous vehicle.

[0075] The AVOMC 4100 may monitor the autonomous vehicle's operating environment or defined aspects thereof. Monitoring the autonomous vehicle's operating environment may include identifying and tracking external objects, identifying individual vehicle operation scenarios, or a combination thereof. For example, the AVOMC 4100 may identify and track external objects in the autonomous vehicle's operating environment. Identifying and tracking external objects may include identifying a spatiotemporal position of each external object relative to the autonomous vehicle, and identifying one or more predicted paths for each external object, which may include identifying a speed, trajectory, or both for the external object. For the sake of brevity and clarity, references herein to location, predicted location, route, predicted path, and the like may omit explicit indications that the corresponding location and path refer to geospatial and temporal components. However, unless expressly indicated herein or unambiguously clear from the context, references herein to location, predicted location, route, predicted path, and the like may include a geospatial component, a temporal component, or both. Monitoring the operating environment of the autonomous vehicle may include using operating environment data received from the operating environment monitor 4200. The AVOMC 4100 may monitor, update, or both the operating environment data.

[0076] The operating environment monitor 4200 may include a scenario-independent monitor, a scenario-specific monitor, or a combination thereof.

[0077] A scenario-independent monitor, such as block monitor 4210, may monitor the operating environment of the autonomous vehicle, generate operating environment data that represents aspects of the operating environment of the autonomous vehicle, and output the operating environment data to one or more scenario-specific monitors, AVOMC 4100, or a combination thereof.

[0078] Scenario-specific monitors, such as pedestrian monitor 4220, intersection monitor 4230, lane change monitor 4240, merge monitor 4250, or forward obstacle monitor 4260, may monitor the autonomous vehicle's operating environment, generate operating environment data representing scenario-specific aspects of the autonomous vehicle's operating environment, and output the operating environment data to one or more scenario-specific motion control evaluation modules 4300, AVOMC 4100, or a combination thereof. For example, pedestrian monitor 4220 may be an operating environment monitor for monitoring pedestrians, intersection monitor 4230 may be an operating environment monitor for monitoring intersections, lane change monitor 4240 may be an operating environment monitor for monitoring lane changes, merge monitor 4250 may be an operating environment monitor for merging, and forward obstacle monitor 4260 may be an operating environment monitor for monitoring forward obstacles. Operating environment monitor 4270 is shown using dashed lines to indicate that autonomous vehicle operation management system 4000 can include any number of operating environment monitors 4200.

[0079] The operating environment monitor 4200 may 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 network data, vehicle network geometry data, route data, or a combination thereof. For example, the pedestrian monitor 4220 may receive or otherwise access information, such as sensor information, that may be indicative of, correspond to, or otherwise associated with one or more pedestrians in the operating environment of the autonomous vehicle. The operating environment monitor 4200 may associate the operating environment data, or portions thereof, with the operating environment, or aspects thereof, for example, with pedestrians, external objects such as remote vehicles, or aspects of the geometry of the vehicle network.

[0080] The operating environment monitor 4200 may generate or identify information representing one or more aspects of the operating environment, such as due to external objects such as pedestrians, remote vehicles, or aspects of the geometry of the vehicle traffic network, which may include filtering, abstracting, or other processing of the operating environment data. The operating environment monitor 4200 may output the one or more aspects of the operating environment to or for access by the AVOMC 4100, for example, by storing the information representing the one or more aspects of the operating environment in a memory of the autonomous vehicle accessible by the AVOMC 4100, such as memory 1340 shown in FIG. 1, by sending the information representing the one or more aspects of the operating environment to the AVOMC 4100, or a combination thereof. The operating environment monitor 4200 may output the operating environment data to one or more elements of the autonomous vehicle operation management system 4000, such as the AVOMC 4100. Although not shown in FIG. 4, the scenario-specific operating environment monitors 4220, 4230, 4240, 4250, and 4260 may output operating environment data to a scenario-independent operating environment monitor, such as block monitor 4210.

[0081] The pedestrian monitor 4220 may correlate, associate, or otherwise process operating environment data to identify, track, or predict the actions of one or more pedestrians. For example, the pedestrian monitor 4220 may receive information, such as sensor data, from one or more sensors, which may correspond to one or more pedestrians, the pedestrian monitor 4220 may associate the sensor data with one or more identified pedestrians, which may include identifying a heading, a path, such as a predicted path, a current or predicted speed, a current or predicted acceleration, or a combination thereof, for each of the one or more identified pedestrians, and the pedestrian monitor 4220 may output the identified, associated, or generated pedestrian information to or for access by the AVOMC 4100.

[0082] The intersection monitor 4230 may correlate, associate, or otherwise process operating environment data to identify, track, or predict the actions of one or more remote vehicles in the autonomous vehicle's operating environment, identify intersections or aspects thereof in the autonomous vehicle's operating environment, identify the shape of a vehicular traffic network, or any combination thereof. For example, the intersection monitor 4310 may 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 or one or more aspects thereof in the autonomous vehicle's operating environment, a vehicle traffic network geometry, or a combination thereof; the intersection monitor 4310 may associate the sensor data with one or more identified remote vehicles in the autonomous vehicle's operating environment, an intersection or one or more aspects thereof in the autonomous vehicle's operating environment, a vehicle traffic network geometry, or a combination thereof, which may include identifying a current or predicted heading, a path such as a predicted route, a current or predicted speed, a current or predicted acceleration, or a combination thereof, for each of the one or more identified remote vehicles; and the intersection monitor 4230 may output the identified, associated, or generated intersection information to or for access by the AVOMC 4100.

[0083] Lane change monitor 4240 may correlate, associate, or otherwise process operating environment data to identify, track, or predict the actions of one or more remote vehicles in the operating environment of the autonomous vehicle, such as information indicating slow or stationary remote vehicles along the autonomous vehicle's predicted path that correspond geospatially to lane change actions, identify one or more aspects of the operating environment of the autonomous vehicle, such as the shape of the vehicular traffic network in the operating environment of the autonomous vehicle, or a combination thereof. For example, the lane change monitor 4240 may receive information, such as sensor data, from one or more sensors, which may correspond geospatially to the lane change operation, to one or more remote vehicles in the autonomous vehicle's operating environment, to one or more aspects of the autonomous vehicle's operating environment in the autonomous vehicle's operating environment, or a combination thereof; the operating environment monitor 4240 for monitoring lane changes may associate the sensor information with an intersection in the autonomous vehicle's operating environment or one or more identified remote vehicles therein, to one or more aspects of the autonomous vehicle's operating environment, or a combination thereof, which may correspond geospatially to the lane change operation, which may include identifying a current or predicted heading, a path such as a predicted path, a current or predicted speed, a current or predicted acceleration, or a combination thereof, for each of the one or more identified remote vehicles; and the lane change monitor 4240 may output the identified, associated, or generated lane change information to or for access by the AVOMC 4100.

[0084] The merge monitor 4250 may correlate, associate, or otherwise process operating environment data to geospatially respond to merging operations, identify, track, or predict the actions of one or more remote vehicles in the autonomous vehicle's operating environment, identify one or more aspects of the autonomous vehicle's operating environment, such as the shape of the vehicle traffic network in the autonomous vehicle's operating environment, or a combination thereof. For example, the merge monitor 4250 may receive information, such as sensor data, from one or more sensors, which may correspond geospatially to the merge operation, to one or more remote vehicles in the autonomous vehicle's operating environment, to one or more aspects of the autonomous vehicle's operating environment in the autonomous vehicle's operating environment, or a combination thereof; the operating environment monitor 4250 for monitoring the merge may associate the sensor information with an intersection in the autonomous vehicle's operating environment or one or more identified remote vehicles therein, to one or more aspects of the autonomous vehicle's operating environment, or a combination thereof, which may correspond geospatially to the merge operation, which may include identifying a current or predicted heading, a path such as a predicted route, a current or predicted speed, a current or predicted acceleration, or a combination thereof, for each of the one or more identified remote vehicles; and the merge monitor 4250 may output the identified, associated, or generated merge information to or for access by the AVOMC 4100.

[0085] The forward obstacle monitor 4260 may correlate, associate, or otherwise process operating environment data to identify one or more aspects of the autonomous vehicle's operating environment that geospatially correspond to the autonomous vehicle's forward obstacle traversal behavior. For example, the forward obstacle monitor 4260 may identify the shape of the vehicular traffic network in the autonomous vehicle's operating environment. The forward obstacle monitor 4260 may identify one or more obstructions or obstacles in the autonomous vehicle's operating environment, such as a slow-moving or stationary remote vehicle along the autonomous vehicle's predicted path or along the autonomous vehicle's identified route. The forward obstacle monitor 4260 may also identify, track, or predict the actions of one or more remote vehicles in the autonomous vehicle's operating environment. For example, the forward obstacle monitor 4250 may receive information, such as sensor data, from one or more sensors, which may correspond geospatially to the obstacle traversal operation, to one or more remote vehicles in the autonomous vehicle's operating environment, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof; the forward obstacle monitor 4250 for monitoring obstacle traversal may associate the sensor information with an intersection in the autonomous vehicle's operating environment or one or more identified remote vehicles thereof, one or more aspects of the autonomous vehicle's operating environment, or a combination thereof, which may correspond geospatially to the obstacle traversal operation, which may include identifying a current or predicted heading, a path such as a predicted path, a current or predicted speed, a current or predicted acceleration, or a combination thereof, for each of the one or more identified remote vehicles; and the forward obstacle monitor 4250 may output the identified, associated, or generated forward obstacle information to or for access by the AVOMC 4100.

[0086] The block monitor 4210 may receive operating environment data describing the operating environment or aspects thereof for the autonomous vehicle. The block monitor 4210 may determine respective availability probabilities or corresponding blocking possibilities for one or more portions of the vehicular network, such as portions of the vehicular network proximate to the autonomous vehicle, which may include portions of the vehicular network corresponding to a predicted path of the autonomous vehicle, such as a predicted path identified based on the autonomous vehicle's current path. The availability probabilities or corresponding blocking possibilities may indicate the probability or likelihood that the autonomous vehicle can safely navigate a portion of the network or a spatial location therein, e.g., without being obstructed by external objects, such as remote vehicles or pedestrians. The block monitor 4210 may determine or update the availability probabilities continuously or periodically. The block monitor 4210 may communicate the availability probabilities or corresponding blocking possibilities to the AVOMC 4100.

[0087] The AVOMC 4100 may identify one or more individual vehicle operation scenarios based on one or more aspects of the operating environment represented by the operating environment data. For example, the AVOMC 4100 may identify an individual vehicle operation scenario based on or in response to identifying operating environment data indicated by one or more operating environment monitors 4200. The individual vehicle operation scenario may be identified based on path data, sensor data, or a combination thereof. For example, in response to identifying a route, the AVOMC 4100 may identify one or more individual vehicle operation scenarios corresponding to the identified route for the vehicle based on map data corresponding to the identified route, etc. Multiple individual vehicle operation scenarios may be identified based on one or more aspects of the operating environment represented by the operating environment data. For example, the operating environment data may include information representing a pedestrian approaching an intersection along a predicted path for the autonomous vehicle, and the AVOMC 4100 may identify a pedestrian vehicle operation scenario, an intersection vehicle operation scenario, or both.

[0088] The AVOMC 4100 may instantiate each instance of one or more scenario-specific motion control evaluation modules 4300 based on one or more aspects of the operating environment represented by the operating environment data. The scenario-specific motion control evaluation modules 4300 may include a scenario-specific motion control evaluation module (SSOCEM), such as a pedestrian SSOCEM 4310, an intersection SSOCEM 4320, a lane change SSOCEM 4330, a merging SSOCEM 4340, an obstacle passage SSOCEM 4350, or a combination thereof. The SSOCEM 4360 is depicted using dashed lines to indicate that the autonomous vehicle motion management system 4000 may include any number of SSOCEMs 4300. For example, the AVOMC 4100 may instantiate an instance of the SSOCEM 4300 in response to identifying a distinct vehicle operation scenario. The AVOMC 4100 may instantiate multiple instances of one or more AVOMCs 4300 based on one or more aspects of the operating environment represented by the operating environment data. For example, the operating environment data may indicate two pedestrians in the operating environment of the autonomous vehicle, and the AVOMC4100 may instantiate each instance of the pedestrian SSOCEM4310 for each pedestrian based on one or more aspects of the operating environment represented by the operating environment data.

[0089] The AVOMC 4100 may transmit, send, or otherwise make available, such as by storing in shared memory, the operating environment data or one or more aspects thereof to another device in the autonomous vehicle, such as the block monitor 4210, or one or more instances of the SSOCEM 4300. For example, the AVOMC 4100 may communicate the availability probability received from the block monitor 4210, or the corresponding block probability, to each instantiated instance of the SSOCEM 4300. The AVOMC 4100 may store the operating environment data or one or more aspects thereof, such as in a memory in the autonomous vehicle, such as memory 1340 shown in FIG. 1 .

[0090] Controlling the autonomous vehicle to traverse the vehicular network may include identifying candidate vehicle control actions based on the individual vehicle operation scenarios and controlling the autonomous vehicle to traverse the portion of the vehicular network according to one or more of the candidate vehicle control actions or a combination thereof. For example, the AVOMC 4100 may receive one or more candidate vehicle control actions from each instance of the SSOCEM 4300. The AVOMC 4100 may identify a vehicle control action from the candidate vehicle control actions and control the vehicle to traverse the vehicular network according to the vehicle control action, or may provide the identified vehicle control action to another vehicle controller.

[0091] A vehicle control action may refer to a vehicle control action or maneuver, such as controlling the vehicle's motion state by accelerating, decelerating, or stopping the vehicle, controlling the vehicle's directional state by steering or turning the vehicle, or any other vehicle operation or combination of vehicle operations, that may be performed by an autonomous vehicle in conjunction with navigating a portion of a vehicle traffic network.

[0092] For example, a "stop" vehicle control action may include controlling a vehicle to traverse a vehicular network or portion thereof by controlling a motion control unit, a track control unit, or a combination of control units to stop the vehicle or otherwise control the vehicle to become or remain stationary. A "yield / stop" vehicle control action may include controlling a vehicle to traverse a vehicular network or portion thereof by controlling a motion control unit, a track control unit, or a combination of control units to slow the vehicle or otherwise control the vehicle to travel at a speed within a defined threshold or range, which may be below or equal to a defined legal speed limit. A "direction adjustment" vehicle control action may include controlling a vehicle to traverse a vehicular network or portion thereof by controlling a motion control unit, a track control unit, or a combination of control units to change the direction of the vehicle relative to an occlusion, an external object, or both within defined right-of-way boundary parameters. An "accelerate" vehicle control action may include controlling a vehicle to traverse a vehicular network or portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to accelerate at a defined acceleration rate or within a defined range of acceleration rates. A "deceler" vehicle control action may include controlling a vehicle to traverse a vehicular network or portion thereof by controlling a motion control unit, a trajectory control unit, or a combination of control units to decelerate at a defined deceleration rate or within a defined range of deceleration rates. A "maintain" vehicle control action may include controlling a vehicle to traverse a vehicular network or 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 a current speed, a current path or route, or a current lane direction.A "go" vehicle control action may include controlling a vehicle to traverse a vehicle network or 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 several vehicle control actions are described herein, other vehicle control actions may be used.

[0093] A vehicle control action may include one or more performance metrics. For example, a “stop” vehicle control action may include deceleration as a performance metric. In another example, a “go” vehicle control action may explicitly indicate route or road information, speed information, acceleration, or a combination thereof as a performance metric, or may explicitly or implicitly indicate that a current or past identified route, speed, acceleration, or combination thereof may be maintained. A vehicle control action may be a composite vehicle control action, which may include a sequence, combination, or both of vehicle control actions. For example, a “direction adjustment” vehicle control action may indicate a “stop” vehicle control action, a subsequent “accelerate” vehicle control action associated with a defined acceleration, and a subsequent “stop” vehicle control action associated with a defined deceleration, whereby control of the autonomous vehicle following the “direction adjustment” vehicle control action includes controlling the autonomous vehicle to slowly move forward a short distance, such as a few inches or feet.

[0094] The AVOMC 4100 may de-instantiate an instance of the SSOCEM 4300. For example, the AVOMC 4100 may identify a distinct set of operating conditions to indicate a distinct vehicle operation scenario for the autonomous vehicle, instantiate an instance of the SSOCEM module 4300 for the distinct vehicle operation scenario, monitor the operating conditions, and then determine that one or more operating conditions have expired or have a potential to affect operation of the autonomous vehicle below a defined threshold, and the AVOMC 4100 may de-instantiate the instance of the SSOCEM 4300.

[0095] The AVOMC4100 may instantiate and de-instantiate an instance of the SSOCEM4300 based on one or more vehicle operation management control metrics, such as an urgent metric, an urgency metric, a utility metric, an acceptability metric, or a combination thereof. The urgent metric may indicate, represent, or be based on a spatial, temporal, or spatio-temporal distance or proximity for a vehicle to traverse the vehicle network from the vehicle's current location to a portion of the vehicle network corresponding to each identified vehicle operation scenario. The urgency metric may indicate, represent, or be based on a measure of spatial, temporal, or spatio-temporal distance available for controlling a vehicle to traverse the portion of the vehicle network corresponding to each identified vehicle operation scenario. The utility metric may indicate, represent, or be based on a predicted value of instantiating an instance of the SSOCEM4300 corresponding to each identified vehicle operation scenario. The acceptability metric may be, for example, a safety metric such as a metric indicating collision avoidance, a vehicle traffic network control compliance metric such as a metric indicating compliance with vehicle traffic network rules and regulations, a physical performance metric such as a metric indicating a vehicle's maximum braking capability, a user-defined metric such as a user preference, etc. Other metrics or combinations of metrics may also be used. The vehicle operation management control metric may indicate a defined rate, range, or limit. For example, the acceptability metric may indicate a defined target deceleration rate, a defined range of deceleration rates, or a defined maximum deceleration rate.

[0096] The SSOCEM 4300 may include one or more models for each individual vehicle operation scenario. The autonomous vehicle operation management system 4000 may include any number of SSOCEMs 4300, each including a model for each individual vehicle operation scenario. The SSOCEM 4300 may include one or more models from one or more types of models. For example, the SSOCEM 4300 may include a partially observable Markov decision process (POMDP) ​​model, a Markov decision process (MDP) model, a classical planning model, a partially observable stochastic game (POSG) model, a distributed partially observable Markov decision process (Dec-POMDP) ​​model, a reinforcement learning (RL) model, an artificial neural network model, or any other model for each individual vehicle operation scenario. Each different type of model may have different characteristics with respect to accuracy and resource usage. For example, a POMDP model for a defined scenario may have higher accuracy and resource usage than an MDP model for the defined scenario. The models included in the SSOCEM 4300 may be ordered, for example, hierarchically, based on accuracy, etc. For example, a designated model, such as the most accurate model included in SSOCEM4300, may be identified as the primary model for SSOCEM4300, and other models included in SSOCEM4300 may be identified as secondary models.

[0097] In one example, one or more of the SSOCEMs 4300 may include a POMDP model, which is a single-agent model and may be a decision-making framework for reasoning in partially observable probabilistic environments. The POMDP model may model individual vehicle operation scenarios, including modeling uncertainty, using a set of states, a set of actions (A), a set of observations (Ω), a set of state transition probabilities (T), a set of conditional observation probabilities (O), a reward function (R), or a combination thereof within the model's domain. The POMDP model may be a tuple<S,A,Ω、T,O,R> It may be defined or described as:

[0098] A state(s) from a set of states (S) may represent a distinct state of a defined aspect of the autonomous vehicle's operating environment, such as external objects and traffic control devices, that may probabilistically affect the autonomous vehicle's behavior at discrete time locations within the model's domain. Each set of states (S) may be defined for each distinct vehicle operation scenario. Each state (state space) from the set of states (S) may include one or more defined state factors. While several examples of state factors for some models are described herein, a model, including any model described herein, may include any number or cardinality of state factors. Each state factor may represent a defined aspect of each scenario and may have a defined set of values. While several examples of state factor values ​​for some state factors are described herein, a state factor, including any state factor described herein, may include any number or cardinality of values.

[0099] One action (a) from a set of actions (A) may represent a vehicle control action available in each state in the set of states (S). Each set of actions may be defined for each distinct vehicle operation scenario. Each action from the set of actions (A) (action space) may include one or more defined action factors. While some examples of action factors for some models are described herein, a model, including any model described herein, may include any number or cardinality of action factors. Each action factor may represent an available vehicle control action and may have a defined set of respective values. Although some examples of action factor values ​​for some action factors are described herein, an action factor, including any action factor described herein, may include any number or cardinality of values.

[0100] An observation (ω) from a set of observations (Ω) may represent available observable, measurable, or determinable data for each state from a set of states (S). Each set of observations may be defined for each distinct vehicle operation scenario. Each observation (observation space) from the set of observations (Ω) may include one or more defined observation factors. While several examples of observation factors for some models are described herein, a model, including any model described herein, may include any number or cardinality of observation factors. Each observation factor may represent available observations and may have a defined set of values. Although several examples of observation factor values ​​for some observation factors are described herein, an observation factor, including any observation factor described herein, may include any number or cardinality of values.

[0101] A state transition probability from a set of state transition probabilities (T) may probabilistically represent a change to an autonomous vehicle's operating environment, represented by a set of states (S), in response to an autonomous vehicle action, represented by a set of actions (A), which may be expressed as T: S × A × S → [0, 1]. This may represent a mapping of each state s (s∈S) from the set of states S and each action a (a∈A) from the set of actions A to a respective probability of transitioning from the set of states (s'∈S) to a subsequent state s'. Each set of state transition probabilities (T) may be defined for each distinct vehicle operation scenario. While several examples of state transition probabilities for some models are described herein, models, including any of the models described herein, may include any number or cardinality of state transition probabilities. For example, each combination of a state, action, and subsequent state may be associated with a respective state transition probability.

[0102] A conditional observation probability from a set (O) of conditional observation probabilities may represent the probability of making each observation (Ω) based on the operating environment of the autonomous vehicle, represented by a set (S) of states, depending on an action of the autonomous vehicle, represented by a set (A) of actions, which may be represented as O:A×S×Ω→[0, 1]. This may represent an observation function that maps each state s (s∈S) from the set of states S and each action a (a∈A) from the set of actions A to a respective probability ω (ω∈Ω) of observing the observation. Each set (O) of conditional observation probabilities may be defined for each distinct vehicle operation scenario. While several examples of conditional observation probabilities for some models are described herein, models, including any of the models described herein, may include any number or cardinality of conditional observation probabilities. For example, each combination of an action, subsequent state, and observation may be associated with a respective conditional observation probability.

[0103] The reward function (R) may determine the respective positive or negative (cost) value that can be obtained for each combination of state and action, which may represent the predicted value of the autonomous vehicle traversing the vehicle network from the corresponding state to a subsequent state according to the corresponding vehicle control action, which may be

number

[0104] For brevity and clarity, examples of model values, such as state factor values ​​or observation factor values, described herein include categorical representations such as {start, goal} or {short, long}. The categorical values ​​may represent defined discrete values ​​or relative values. For example, a state factor representing a temporal aspect may have a value from the set {short, long}, where a value "short" may represent a discrete value, such as a time distance within or less than a defined threshold, such as 3 seconds, and a value "long" may represent a discrete value, such as a time distance at least equal to or exceeding a defined threshold. The defined thresholds for each categorical value may be defined relative to the associated factor. For example, a defined threshold for the set {short, long} for the time factor may be associated with a relative spatial location factor value, and another defined threshold for the set {short, long} for the time factor may be associated with another relative spatial location factor value. Although categorical representations of factor values ​​are described herein, other representations or combinations of representations may be used. For example, the set of time state factor values ​​may be {short (representing values ​​less than 3 seconds), 4, 5, 6, long (representing values ​​of at least 7 seconds)}.

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

[0106] The autonomous vehicle operation management system 4000 may include any number or combination of model types. For example, the pedestrian SSOCEM 4310, intersection SSOCEM 4320, lane change SSOCEM 4330, merging SSOCEM 4340, and obstacle passage SSOCEM 4350 may be POMDP models. In another example, the pedestrian SSOCEM 4310 may be an MDP model, and the intersection SSOCEM 4320 may be a POMDP model. The AVOMC 4100 may instantiate any number of instances of the SSOCEM 4300 based on the operating environment data.

[0107] Instantiating an SSOCEM 4300 instance may include identifying a model from the SSOCEM 4300 and instantiating an instance of the identified model. For example, the SSOCEM 4300 may include a primary model and a secondary model for each distinct vehicle operation scenario, and instantiating the SSOCEM 4300 may include identifying the primary model as the current model and instantiating an instance of the primary model. Instantiating a model may include determining whether a solution or policy is available for the model. Instantiating a model may include determining whether the available solution or policy for the model is partially solved or convergently solved. Instantiating the SSOCEM 4300 may include instantiating an instance of a solution or policy for the model identified for the SSOCEM 4300.

[0108] Solving a model such as a POMDP model defines the model<S,A,Ω、T,O,R> The policy or solution may include determining a policy or solution, which may be a function that maximizes a cumulative reward, which may be determined by evaluating possible combinations of elements of a tuple such as (a) β ... The effectiveness value of the subsequent state may be identified as the maximum effectiveness value identified, subject to a reward or penalty, which may be a discounted reward or penalty. The policy may indicate an action corresponding to the maximum effectiveness value for each state. Solving a POMDP model may be similar to solving an MDP model, except that the confidence state is based on an observation probability, which represents a probability for each state and corresponds to the generation of an observation for each state. Thus, solving an SSOCEM model involves evaluating possible state-action-state transitions and updating each confidence state based on each action and observation, such as using Bayes' rule.

[0109] In one example, we identify an initial belief state (b0∈β) as the current belief state (b∈β), perform an action (a∈α), observe an observation (ω∈Ω), update the current belief state (b∈β), and identify the updated current belief state (b'∈β) by applying a normalization constant η=Pr(ω|b,s) as follows: -1 It may be represented using [Formula 1]

number

[0110] At each increment, such as each time step, an action (a∈α) may be selected based on the current belief state (b∈β). A policy π:B→A may represent a mapping of belief states (b∈β) to actions (a∈α). A value function

number

[0111] Although not shown in FIG. 4 , the autonomous vehicle may include an autonomous vehicle actuation control system or multiple autonomous vehicle actuation control systems. The autonomous vehicle actuation control system may receive vehicle control actions from an autonomous vehicle motion management system 4000 or the like and may control one or more kinematic units of the autonomous vehicle, such as a steering actuator, an accelerator, a braking system, or a combination thereof, to execute the vehicle control actions. The autonomous vehicle actuation control system may include one or more actuation models, such as a POMDP or other automatic control model of vehicle response based on the identified vehicle control actions and the autonomous vehicle's operating environment, and may determine low-level vehicle actuation control parameters, such as the amount of force or degree of steering, based on the actuation models.

[0112] FIG. 5 is a flow diagram illustrating an example of vehicle guidance with systematic optimization 5000 according to an embodiment of the present disclosure. Vehicle guidance with systematic optimization 5000 may be implemented or partially implemented in a vehicle, such as vehicle 1000 shown in FIG. 1 or any of vehicles 2100 / 2110 shown in FIG. 2. In some embodiments, the vehicle may be an autonomous vehicle, a semi-autonomous vehicle, or any other vehicle that implements autonomous navigation. For example, the autonomous vehicle may implement an autonomous vehicle operation management system, such as autonomous vehicle operation management system 4000 shown in FIG. 4. In some embodiments, the vehicle may omit implementing autonomy or may be in an operational mode in which autonomy is omitted. Aspects of vehicle guidance with systematic optimization 5000 may be implemented in infrastructure devices, such as one or more of communication devices 2400 / 2410 shown in FIG. 2.

[0113] As shown in FIG. 5, vehicle guidance with systematic optimization 5000 includes obtaining systematic utility vehicle guidance data in step 5100 and navigating a portion of a vehicle network according to the systematic utility vehicle guidance data in step 5110.

[0114] Obtaining systematic utility vehicle guidance data in step 5100 includes obtaining vehicle operation data for the region in step 5200, operating a systematic utility vehicle guidance model for the region in step 5210, generating systematic utility vehicle guidance data in step 5220, and outputting the systematic utility vehicle guidance data in step 5230.

[0115] In some embodiments, a vehicle, such as the current vehicle, may implement or solve a systematic utility vehicle guidance model, and obtaining systematic utility vehicle guidance data in step 5100 may include obtaining vehicle operation data for the region by the current vehicle in step 5200, operating a systematic utility vehicle guidance model for the region by the current vehicle in step 5210, generating systematic utility vehicle guidance data by the current vehicle in step 5220, and outputting the systematic utility vehicle guidance data by the current vehicle in step 5230. Outputting the systematic utility vehicle guidance data by the current vehicle in step 5230 may include outputting the systematic utility vehicle guidance data from a unit of the current vehicle that implements or operates the systematic utility vehicle guidance model to another unit or component of the current vehicle. In some embodiments, outputting the systematic utility vehicle guidance data by the current vehicle in step 5230 may include outputting the systematic utility vehicle guidance data by the current vehicle to one or more external devices, such as one or more remote vehicles, one or more infrastructure devices, or a combination thereof, via an electronic communication link, such as one or more of the wireless communication links 2310 / 2320 / 2370 / 2380 / 2385 shown in FIG. 2 .

[0116] In some embodiments, a remote vehicle, such as remote vehicle 2110 shown in FIG. 2, may implement or solve a systematic utility vehicle guidance model, and obtaining the systematic utility vehicle guidance data for the current vehicle in step 5100 may include obtaining the systematic utility vehicle guidance data from the remote vehicle, such as via an electronic communications link, such as one or more of wireless communications links 2310 / 2320 / 2370 / 2380 / 2385 shown in FIG. 2. For example, the current vehicle may automatically receive the systematic utility vehicle guidance data from the remote vehicle via a monitored communications port of the current vehicle, or may receive the systematic utility vehicle guidance data by sending a request for systematic utility vehicle guidance data from the current vehicle to the remote vehicle and receiving the systematic utility vehicle guidance data from the current vehicle from the remote vehicle in response to the request. In embodiments in which obtaining systematic utility vehicle guidance data for the current vehicle in step 5100 includes obtaining systematic utility vehicle guidance data from a remote vehicle, the remote vehicle may implement or perform obtaining vehicle operation data for the region in step 5200, operating a systematic utility vehicle guidance model for the region in step 5210, generating systematic utility vehicle guidance data in step 5220, and outputting the systematic utility vehicle guidance data in step 5230. Although not explicitly shown in FIG. 5 , one or more of obtaining vehicle operation data for the region in step 5200, operating a systematic utility vehicle guidance model for the region in step 5210, generating systematic utility vehicle guidance data in step 5220, and outputting the systematic utility vehicle guidance data in step 5230 may be performed by the remote vehicle in response to receiving a request for systematic utility vehicle guidance data, in response to a defined event, or periodically. Although not explicitly shown in FIG. 5, the current vehicle may generate and transmit one or more requests for systematic utility vehicle guidance data in response to defined events or periodically.

[0117] In some embodiments, an infrastructure device, which may be a centralized infrastructure device or a distributed infrastructure device, such as one of the communication devices 2400 / 2410 shown in FIG. 2, may implement or solve the systematic utility vehicle guidance model, and obtaining the systematic utility vehicle guidance data for the current vehicle in step 5100 may include obtaining the systematic utility vehicle guidance data from the infrastructure device, such as via an electronic communications link, such as one or more of the wireless communications links 2310 / 2320 / 2370 / 2380 / 2385 shown in FIG. 2. For example, the current vehicle may automatically receive the systematic utility vehicle guidance data from the infrastructure device via a monitored communications port of the current vehicle, or may send a request for systematic utility vehicle guidance data from the current vehicle to the infrastructure device and receive systematic utility vehicle guidance data by the current vehicle from the infrastructure device in response to the request. In embodiments in which obtaining systematic utility vehicle guidance data for the current vehicle in step 5100 includes obtaining systematic utility vehicle guidance data from an infrastructure device, the infrastructure device or a combination of multiple infrastructure devices may implement or perform obtaining vehicle operation data for the region in step 5200, operating a systematic utility vehicle guidance model for the region in step 5210, generating systematic utility vehicle guidance data in step 5220, and outputting the systematic utility vehicle guidance data in step 5230. Although not separately shown in FIG. 5 , one or more of obtaining vehicle operation data for the region in step 5200, operating a systematic utility vehicle guidance model for the region in step 5210, generating systematic utility vehicle guidance data in step 5220, and outputting the systematic utility vehicle guidance data in step 5230 may be performed by the infrastructure device in response to receiving a request for systematic utility vehicle guidance data, in response to a defined event, or periodically. Although not explicitly shown in FIG. 5, the current vehicle may generate and transmit one or more requests for systematic utility vehicle guidance data in response to defined events or periodically.

[0118] In some embodiments, a centralized infrastructure device for a region, such as a server, implements, for example, solving a systematic utility vehicle guidance model for the region. The centralized infrastructure device may be physically located within the region, near the region, or any distance from the region.

[0119] In some embodiments, a distributed infrastructure device for the region (such as an edge server) implements, for example, solving the systemic utility vehicle guidance model for the region. The distributed infrastructure device may be physically located within or adjacent to the region.

[0120] Obtaining vehicle operation data for the region in step 5200 includes obtaining vehicle network data representing the vehicle network for the region. For example, the vehicle network data may include stop lines, traffic signal (or meter) locations, toll booths, yields, forced merge locations, lane split locations, or other data describing the region of the vehicle network that may be represented by the vehicle network data.

[0121] Obtaining vehicle operation data for the region in step 5200 includes obtaining vehicle operation data (current operation data) for vehicles operating within the region. The vehicle operation data for the region may include data reported from each vehicle in the region. The vehicle operation data for the region may include data generated by one or more off-vehicle sensors, such as sensors of infrastructure devices in the region. The vehicle operation data for each vehicle in the region may include location data indicating the vehicle's location in the vehicle network, such as a road identifier, road segment identifier, lane identifier, or other data indicating the vehicle's location in the vehicle network. The vehicle operation data for each vehicle may indicate the heading of each vehicle. The vehicle operation data for each vehicle may indicate speed data for each vehicle. The vehicle operation data for each vehicle may indicate the current route, destination, or both for each vehicle. The vehicle operation data for each vehicle may include vehicle model data, such as data indicating the make of a car or truck, or inoperational data for each vehicle, such as data indicating the make, model, model year, or other data describing each vehicle. Participating vehicles may omit transmitting vehicle operational data other than that for which current valid opt-in data is identified. The vehicle operational data may be obtained using one or more sensors, such as infrastructure sensors, on-board sensors, or a combination thereof. For example, infrastructure sensors may include pressure sensors, cameras, lidar sensors, radar sensors, or any other type of infrastructure sensor. Vehicles may report, transmit, or otherwise make available, sensor data from on-board sensors.

[0122] A participating vehicle, as described herein, is a vehicle, e.g., a current vehicle, that is identified as participating in traversing at least a portion of a region of the vehicle network according to systematic utility vehicle guidance data obtained from a systematic utility vehicle guidance model for that region. For example, at a time location, the systematic 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 region of the vehicle network at or reasonably close to the defined target speed, or the defined target speed may be displayed to a primary occupant or driver of the vehicle.

[0123] A non-participating vehicle is a vehicle identified as traveling through at least a portion of a region of the vehicle traffic network for which no systematic utility vehicle guidance data exists, does not reference, or is inconsistent with systematic utility vehicle guidance data obtained from a systematic utility vehicle guidance model for that region.

[0124] A systematic utility vehicle guidance model for the region is operated in step 5210. Operating the systematic utility vehicle guidance model includes generating or regenerating a systematic utility vehicle guidance model using vehicle operation data for the region. In some embodiments, generating a systematic utility vehicle guidance model may include obtaining a previously generated systematic utility vehicle guidance model and generating (regenerating) a systematic utility vehicle guidance model based on the previously generated systematic utility vehicle guidance model using vehicle operation data for the region. In some embodiments, the model is generated or regenerated and solved based on vehicle or system operation data obtained before the current vehicle operation, such as previous observation data, previous action data, or a combination thereof, or an aggregation thereof, such as a statistical approximation of state transition probabilities (T), conditional observation probabilities (O), or both, and generating the policy may omit use of the current vehicle operation data for the region obtained in step 5200, or a portion thereof. In some embodiments, generating or regenerating a systematic utility vehicle guidance model may include obtaining and using a previously generated systematic utility vehicle guidance model for the region. In some embodiments, the model may be generated using vehicle operation data for the area obtained before obtaining vehicle operation data for that area in step 5200, and regenerated using vehicle operation data for the area obtained in step 5200.

[0125] Manipulating the systematic utility vehicle guidance model in step 5210 may include optimally solving, approximately solving, or partially solving the systematic utility vehicle guidance model to obtain a policy, such as a systematic utility vehicle guidance policy, which may be expressed as pi(S)=[a1, a2, ..., a k ], where the vehicle operation data for the region indicates that the region contains (k) participating vehicles, and (a i) indicates the action identified for the i-th participating vehicle. In some embodiments, obtaining a systematic utility vehicle guidance policy may include obtaining a previously generated systematic utility vehicle guidance policy that corresponds to the systematic utility vehicle guidance model for the region operated on in step 5210.

[0126] A systematic utility vehicle guidance model is a probabilistic model of system behavior for a region of a vehicular network. For example, the systematic utility vehicle guidance model for a region of a vehicular network may 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 distributed partially observable Markov decision process (Dec-POMDP) ​​model. Individual regions may be associated with or modeled by a respective systematic utility vehicle guidance model. A region of a vehicular network may be a defined geographic region such as a lane, a road segment, a group of consecutive road segments, a road, an intersection, or a block, a neighborhood, a district, a county, a municipality, a state, a country, or other defined geographic region. Regions may be defined ad hoc, such as manually. In some embodiments, regions may be non-overlapping. In some embodiments, two or more regions may overlap. Respective systematic utility vehicle guidance models for overlapping regions may be operated simultaneously or substantially simultaneously. In some embodiments, participating vehicles operating in portions of the vehicular network corresponding to the overlapping regions may identify, e.g., select, a communication device, region, or corresponding systematic utility vehicle guidance model from candidates, e.g., the overlapping regions, based on location, route, or a combination thereof. In some embodiments, the overlapping regions, or their associated communication devices, may be regions for vehicles operating in the overlapping portions of the regions. In some embodiments, one or more overlapping regions may communicate to identify models, policies, or systematic utility vehicle guidance data from among region-specific candidates, e.g., according to one or more region coordination rules.

[0127] In some embodiments, the systematic utility vehicle guidance model may be implemented using an ad-hoc rule-based system, which may include, for example, a function such as f(n,c)=s that maps the cardinality or count of a set of vehicles (v) in a region and the cardinality or count of a set of participating vehicles (c) to a speed (s), which may be expressed, for example, in distance traveled per unit time, such as miles or kilometers, per hour.

[0128] In some embodiments, the model can be solved as a Markov game or similar game-theoretic structure to obtain a correlated equilibrium, a Nash equilibrium, or a stationary Markov perfect equilibrium, which guarantees utility-maximizing action even if other vehicles, such as non-participating vehicles, choose policies different from those computed from the equilibrium.

[0129] As defined by the systematic utility vehicle guidance model, a state(s) from a set of states(S) may represent a distinct condition of each defined aspect, such as vehicle behavior for that region. Each set of states(S) is defined. Each state (state space) from the set of states(S) may include one or more defined state factors. For example, the systematic utility vehicle guidance model may define, for each vehicle, a probability state factor (S=× ) that indicates location data within the region, such as lane identifiers within a road segment. i S i ). The granularity or specificity of the probabilistic state factors may correspond to the granularity or detail of the available vehicle network data. For example, the vehicle network data may be relatively low-resolution data describing roads but omitting lane data, and the probabilistic state factors may correspondingly indicate road locations but omit lane data, or the vehicle network data may include relatively high-resolution data describing roads and lanes, and the probabilistic state factors may correspondingly indicate road and lane locations for each vehicle. The probabilistic state factors for each vehicle may include heading data. In some embodiments, the probabilistic state factors for each vehicle may indicate other data about the vehicle, such as observed speed, vehicle make, model, year, make (e.g., car or truck), or other data describing the vehicle or its operation.

[0130] A systematic utility vehicle guidance model may include an action (a) from a set of actions (A) to indicate vehicle control actions or route guidance available at each state in a set of states (S). Each action from the set of actions (A) (action space) may include one or more defined action factors. For example, an action (A) = × j A j ) may be provided to be transmitted or otherwise made available to each participating vehicle (j) to indicate a target vehicle control action, a target speed, a target lane, or other targetable aspect of vehicle behavior. Actions may be indicated on a vehicle-by-vehicle basis for participating vehicles. In some embodiments, the action space may include unreachable target actions for non-participating vehicles.

[0131] The state transition probability from the set of state transition probabilities (T) is i Then, the current state is displayed. i The probability of progressing to a subsequent state may be expressed probabilistically, which may be based on the density of vehicles in the region. The density of vehicles in the region may be a function of the number or concentration of vehicles operating in the region and the size of the region, for example, in terms of traversable space. State transition probabilities model how state factors change (at each step) based on action factors. For example, given two vehicles a and b in state S a and S b is S a On the road b indicates that vehicle a is late, and the action of vehicle a (A a ) indicates a target speed of 65 mph, and vehicle b's action (A b ) indicates a target speed of 45 mph, and the transition probability (T) is S a S b Therefore, the state factor S at the subsequent time step or time position a ' and S bThe state transitions in ' reflect this implementation. The state transition probabilities (T) may describe or map how vehicles, including participating and non-participating vehicles, may behave based on the systematic utility vehicle guidance data of the participating vehicles. In some embodiments, the state transition probabilities (T) may be a matrix of probabilities. In some embodiments, the state transition probabilities (T) may be a model generated from a Monte Carlo simulation.

[0132] The systematic utility vehicle guidance model includes a reward function (R), which determines the respective positive or negative (cost) value that can occur for each combination of state and action. The reward represents lane navigation time. In some embodiments, lane navigation time may represent an average, such as a historical average, a time span for a vehicle to traverse a road segment, or a defined sequence thereof. In some embodiments, lane navigation time may represent a traveled distance of a road segment, or a defined sequence thereof, divided by the corresponding speed limit, or an average vehicle speed. Lane navigation time may be identified for each vehicle or may be an aggregated value, such as an average for vehicles operating in the area.

[0133] For example, the systematic utility vehicle guidance model may be an MDP model and the reward may be a weighted sum of vehicles. In another example, the systematic utility vehicle guidance model may be an MG and the reward may be per vehicle. The reward is a negative value corresponding to the time spent on the lane, which may be the length of the lane, such as in miles, divided by the vehicle speed, such as in miles / hour, to indicate the time to travel the lane, such as in hours.

[0134] The systematic utility vehicle guidance data is generated by the systematic utility vehicle guidance model in step 5220. Generating the systematic utility vehicle guidance data includes generating a respective message or signal for each participating vehicle in the region. Generating a message for each participating vehicle includes indicating in the message an action identified by the systematic utility vehicle guidance model for each participating vehicle in step 5210. Although described as an action, the indication of an action in the systematic utility vehicle guidance data may be an indication of a control guidance action, which may be a proposed action or a proposed target operating parameter such as a target speed.

[0135] In one example, a region of a vehicular network may be an intersection within the vehicular network, which may have a relatively low spatial extent compared to other regions described herein. For example, a region of the vehicular network corresponding to an intersection within the vehicular network may include a defined geospatial distance of, for example, ¼ of a kilometer around the intersection. A systematic utility vehicle guidance model (systematic utility intersection guidance model) for the region may optimize the throughput of vehicles traversing the intersection. Risk may be minimized (safety may be maximized). For example, a systematic utility vehicle guidance policy for a systematic utility intersection guidance model for a region of the vehicular network corresponding to an intersection within the vehicular network may obtain or generate systematic utility vehicle guidance data indicating one or more vehicle control actions corresponding to right-of-way priorities for the intersection, one or more vehicle control actions corresponding to the speed of each vehicle approaching or traversing the intersection, or both.

[0136] Operation of one or more participating vehicles traversing the intersection area according to the systematic utility vehicle guidance data may improve the systematic utility of vehicles operating within the intersection area compared to the absence of the participating vehicles. For example, the systematic utility vehicle guidance model may be more complex than the vehicle-specific operation model and may correspond to greater accuracy of the systematic utility vehicle guidance model. Non-participating vehicles may operate the vehicle-specific operation utility maximization model or may operate via manual control, which may omit vehicle operation data, such as data indicating uncertainty in the delays of one or more other vehicles operating within the area, due to unavailability or other reasons, which may correspond to lower systematic utility vehicles compared to the systematic utility vehicle guidance model. In some embodiments, the state transition probabilities (T) of the systematic utility vehicle guidance model may include representing vehicle operations based on an aggregation, such as a statistical average, of previous vehicle operations that deviate from or differ from right-of-way priority, which may be omitted or unavailable from the vehicle-specific operation utility maximization model.

[0137] The systematic utility vehicle intersection guidance model may be implemented by the current vehicle, remote vehicles, distributed infrastructure devices located in or near the region, or centralized infrastructure devices.

[0138] The systematic utility vehicular intersection guidance model may include per-vehicle state factors. For example, per-vehicle lane state factors indicate the lane, road segment, or road corresponding to the vehicle's position in the vehicular traffic network, which is expressed as (S i l ) The lane status factor may indicate a lane, road segment, or road identifier, which may be unique within a region or vehicular traffic network, or may have semantic meaning such as the name of the road, lane number, and distance from a defined point along the road.

[0139] Although described with respect to lane state data, in some embodiments, the per-vehicle state factors may include other data. For example, the per-vehicle state factors may include temporal data, such as temporal data indicating a time span of a vehicle at a location. In some implementations, the per-vehicle state factors may include speed or velocity data. In some implementations, the per-vehicle state factors may include acceleration data, such as lateral acceleration, longitudinal acceleration, or both. In some implementations, the per-vehicle state factors may include aggregated relative control data. The aggregated relative control data may be obtained, for example, using a machine learning classifier and a defined set of previous vehicle control data for each vehicle. The defined set of previous vehicle control data may be vehicle control data for a defined time span, such as one minute, and may include data such as vehicle speed data, velocity data, acceleration data, or a combination thereof, which may include lateral and longitudinal data. The aggregated relative control data may represent a probabilistic classification or measurement of vehicle behavior corresponding to input vehicle control data, which may be relative to corresponding target control data.

[0140] Systematic utility intersection guidance models may include one or more state factors included in each model as aggregate state factors or per-vehicle state factors. For example, an aggregate speed or velocity state factor may be included as S s and may represent an aggregate measure of vehicle speed within a region, such as the average or median speed of vehicles within the region. i sA per-vehicle speed or speed state factor, which may be expressed as , may indicate the reported or observed speed of each vehicle. Increasing the spatial range of a state factor or other factor of a systematic utility vehicle guidance model, such as from an aggregated factor to a per-vehicle factor, may increase the accuracy, the computational complexity, or both of solving the systematic utility vehicle guidance model. The uncertainty associated with reported vehicle behavior data, such as speed data, may be different from, e.g., smaller than, the uncertainty associated with observed vehicle behavior data. As used herein, the term "reported" with respect to data refers to data identified by a subject of the data, such as a sensor on a vehicle identifying the vehicle's speed. As used herein, the term "observed" with respect to data refers to data identified by a party other than the subject of the data, such as a sensor on a vehicle identifying the state of a traffic control device or the speed of another vehicle, or by a sensor on an infrastructure device identifying the vehicle's speed.

[0141] The systematic utility intersection guidance model may include a right-of-way priority state factor that indicates right-of-way priority for vehicles within the region, which is S o In some embodiments, the right-of-way priority may indicate the vehicle that has the current right-of-way priority. In some embodiments, the right-of-way priority may indicate the relative position or order of each vehicle with respect to the right-of-way priority.

[0142] For a region of a vehicle traffic network representing an intersection, the state factors of the systematic utility intersection guidance model may include a lane state factor for each vehicle, an aggregate speed factor, and an aggregate priority factor, which are expressed as S=× i (S i l )×S s ×S o It may be expressed as:

[0143] In another example, for a region of a vehicular traffic network representing an intersection, the state factors of the systematic utility intersection guidance model may include a lane state factor per vehicle, a speed factor per vehicle, and an aggregate priority factor, which are expressed as S=× i (Si l ×S i s )×S o It may be expressed as:

[0144] The systematic utility intersection guidance model may include vehicle-specific control guidance actions such as "stop," "go," and "go" vehicle control guidance actions.

[0145] The "stop" control guidance action may indicate guidance to perform the "stop" vehicle control action described herein. In the case of a manually controlled vehicle, the "stop" control guidance action may be presented to an occupant, such as a driver of the vehicle. For an autonomous vehicle or a vehicle performing autonomous navigation, the autonomous vehicle may perform the "stop" vehicle control action in response to receiving systematic utility vehicle guidance data that includes the "stop" control guidance action.

[0146] The "go forward" control guidance action may indicate guidance to perform the "go forward" vehicle control action described herein. In the case of a manually controlled vehicle, the "go forward" control guidance action may be presented to an occupant, such as a driver of the vehicle. For an autonomous vehicle or a vehicle performing autonomous navigation, the autonomous vehicle may perform the "go forward" vehicle control action in response to receiving systematic utility vehicle guidance data that includes the "go forward" control guidance action.

[0147] The "go" control guidance action may indicate guidance for performing the "go" vehicle control action described herein. In the case of a manually controlled vehicle, the "go" control guidance action may be presented to an occupant, such as a driver of the vehicle. For an autonomous vehicle or a vehicle performing autonomous navigation, the autonomous vehicle may perform the "go" vehicle control action in response to receiving systematic utility vehicle guidance data that includes the "go" control guidance action.

[0148] The systematic utility intersection guidance model may include a reward function (R), which may be a piecewise function. i o), and the reward is zero (0). A positive reward such as 1 may also be used. Otherwise, the reward is calculated based on the observed speed (S i s ), whereby vehicles that traverse an intersection in violation of the right-of-way priority are penalized in proportion to the vehicle's speed. A fixed negative reward or cost, such as negative one, may also be used.

[0149] In one example, a region of a vehicle network may include geographically related roads or portions thereof within the vehicle network, which may be of relatively high spatial extent compared to other regions described herein. A systematic utility vehicle guidance model (systematic utility vehicle routing guidance model) for the region may be implemented by a centralized infrastructure device.

[0150] The systematic utility vehicle routing guidance model may include a vehicle-specific state factor. For example, a vehicle-specific lane state factor indicates the lane, road segment, or road corresponding to the vehicle's location in the vehicle network, which is expressed as (S i l ) The lane status factor may indicate a lane, road segment, or road identifier, which may be unique within a region or vehicular traffic network, or may have semantic meaning such as the name of the road, lane number, and distance from a defined point along the road.

[0151] The systematic utility routing guidance model may include a density condition factor for each vehicle that indicates the local density of vehicles in the operating environment of each current vehicle, such as within 50 m of the current vehicle, which is (S i d )

[0152] The systematic utility routing guidance model may include a speed or speed condition factor for each vehicle, which is (S i s ) and indicates the reported or observed speed of each vehicle.

[0153] For the region of the vehicle traffic network represented by the systematic utility routing guidance model, the state factors of the systematic utility routing guidance model may include a lane state factor for each vehicle, a speed factor for each vehicle, and a vehicle density factor for each vehicle, which is S=× i (S i l ×S i s ×S i d )

[0154] The systematic utility routing guidance model may include per-vehicle control guidance actions, which are per-vehicle speed guidance actions (A i s ) and may indicate the target speed for each vehicle. In some embodiments, the action space may indicate the target lane guidance action (A i l ), which may indicate the target lane for each vehicle. In some embodiments, the action space may include target route guidance actions (A i r ), which may indicate a target route for each vehicle. The target route may indicate a route from each vehicle's location to each vehicle's target destination, as indicated in the vehicle operation data for the region obtained in step 5200 for each vehicle.

[0155] The systematic utility routing guidance model may include a reward function (R) that may reflect the average travel time of vehicles within the region, which may be the negative of the sum of the difference in lane or road length and observed speed for each vehicle, which is sum(lane_length(S i l) / S_observed_speed for i in 1:k) and may be averaged by dividing by k, where k may represent, for example, a defined target average speed. In some embodiments, the reward function may be the maximum time to travel between vehicles operating in an area. In some embodiments, the reward function for two or more vehicles in a road segment or intersection may be negative one simultaneously, and may be zero for vehicles in the road segment or intersection if there are no other operating vehicles.

[0156] In one example, a region of a vehicular network may be a continuous sequence of roads or road segments within the vehicular network, which may be of intermediate spatial extent compared to other regions described herein. A systematic utility vehicle guidance model (systematic utility flow guidance model) for a region (flow guidance region) may be implemented by distributed infrastructure devices or centralized infrastructure devices.

[0157] In a flow guidance region where a set of vehicles operating within the region omits participating vehicles, vehicle control is based on vehicle-specific operating utility as understood by a human driver or determined by the vehicle's autonomous processes. For example, vehicles operating in a low-vehicle density portion of the region may accelerate or change lanes to minimize inter-vehicle distances at or near a relatively minimum safe operating distance, thereby maximizing vehicle density in the portion of the region corresponding to these vehicles and correspondingly lowering vehicle density in subsequent vehicles or other portions of the region. For a vehicle, low vehicle density may indicate that the relative distance between the vehicle and another vehicle directly ahead of it in the current lane is greater than the minimum safe operating distance. Delays in responding to changes in the operating environment (response delays) may reduce operating utility as a function of vehicle density. Thus, the current vehicle's operating utility is at least partially inversely correlated with the density of vehicles operating in the current vehicle's operating environment. Furthermore, the concentration or count of vehicles operating in a portion of an area where vehicle density is relatively high and therefore operating utility is relatively low is relatively high, and the concentration or count of vehicles operating in a portion of an area where vehicle density is relatively low is relatively low corresponding to the relatively high operating utility of that portion, so that the average systemic operating utility of that area is suboptimal. While the predicted per-vehicle operating utility is maximized, the actions of other vehicles that maximize their respective per-vehicle operating utility affect the current vehicle's operation, resulting in a decrease in the observed per-vehicle operating utility, as reflected in the suboptimal systemic utility. This example may be referred to as elastic congestion. While described with reference to elastic congestion, other vehicle actions optimized for per-vehicle operating utility may also correlate with suboptimal systemic utility.

[0158] For example, multiple vehicles that may be in a low-vehicle-density portion of the area may each operate, such as by accelerating, to minimize the distance between them to a minimum safe operating distance, thereby forming a high-density cluster of vehicles in a high-vehicle-density portion of the area. A first vehicle in the high-density cluster may slow down by braking, and the distance between the first vehicle and a second vehicle immediately behind the first vehicle in the direction of travel may decrease due to, for example, a response delay by the second vehicle. The decreased distance between the first and second vehicles may be less than the minimum safe operating distance. The response delay may cause the second vehicle to slow down. The second vehicle may slow down more rapidly than the first vehicle (response amplification) due to the distance between the first and second vehicles being less than the minimum safe operating distance, uncertainty, or other factors. Other vehicles in the high-density cluster further back in the direction of travel may have similar response delays and cascading increases in deceleration rates. This may reduce the average speed or other aggregate measure of the vehicles in the high-density cluster, increasing the risk per vehicle and thereby reducing the operating utility of the high-vehicle-density portion.

[0159] In a flow guidance region, where vehicles operating within the region include one or more participating vehicles and the region may include non-participating vehicles, participating vehicles may operate at speeds or in lanes identified according to systematic utility vehicle guidance data that may be identified to optimize systematic operating utility for the region. For example, a vehicle may receive, or otherwise access, the systematic utility vehicle guidance data output in step 5230, which may indicate a target speed that is equal to or less than the speed of the vehicle immediately preceding the vehicle in its current lane. The target speed indicated by the systematic utility vehicle guidance data may differ from the target speed identified based on per-vehicle operating utility. Operating participating vehicles according to the systematic utility vehicle guidance data may reduce the effects of elastic congestion and increase system operating utility.

[0160] For example, multiple vehicles may be operating within a region of a vehicular traffic network. Some non-participating vehicles may operate to minimize inter-vehicle distance, subject to the non-participating vehicles' minimum safe operating distance relative to a preceding vehicle in their direction of travel. Participating vehicles operating according to systematic utility vehicle guidance data may operate to maintain or increase their inter-vehicle distance from a preceding vehicle in their direction of travel. Because participating vehicles operating according to systematic utility vehicle guidance data omit minimizing inter-vehicle distance, the number of vehicles forming a dense cluster may be reduced. The inter-vehicle distance between a leading non-participating vehicle and a trailing participating vehicle may be relatively large. The leading non-participating vehicle may slow down by braking, and the distance between the leading non-participating vehicle and the trailing participating vehicle may decrease due to, for example, a delayed response by the trailing participating vehicle. Because the inter-vehicle distance before slowing down is relatively large, the decreased inter-vehicle distance between the leading non-participating vehicle and the trailing participating vehicle may be greater than the minimum safe operating distance. Due to the delayed response, the second vehicle may slow down. Because the distance between the leading non-participating vehicle and the trailing participating vehicle exceeds the minimum safe operating distance, the trailing participating vehicle may decelerate at a rate substantially similar to the deceleration rate of the leading non-participating vehicle. Response amplification may be reduced or avoided. The degree of cascading response amplification may be reduced, per-vehicle risk may be maintained, and reductions in average vehicle speed or other aggregate measures may be minimized, thereby maintaining or increasing the relative systematic operating utility for the region.

[0161] The systematic utility flow guidance model may include per-vehicle state factors. For example, per-vehicle lane state factors indicate the lane, road segment, or road corresponding to the vehicle's position in the vehicular traffic network, which is expressed as (S i l ) The lane status factor may indicate a lane, road segment, or road identifier, which may be unique within a region or vehicular traffic network, or may have semantic meaning such as the name of the road, lane number, and distance from a defined point along the road.

[0162] The systematic utility flow guidance model may include one or more aggregated condition factors for the region. For example, an aggregated vehicle density condition factor indicates the density of vehicles in the region, which is (S d ) The density of vehicles within a region may be a function of the number, count, or concentration of vehicles operating within the region, including participating and non-participating vehicles, which may be expressed as an aggregate value such as the average or median number of vehicles per unit distance, such as per mile or kilometer of road, per square meter, etc. In some embodiments, the aggregated vehicle density condition factor may represent an aggregate value such as the average or median number of vehicles per unit distance, such as per mile or kilometer of road, per square meter, etc.

[0163] The systematic utility flow guidance models may include one or more state factors included in each model as aggregate state factors or per-vehicle state factors. For example, an aggregate speed or velocity state factor may be S s may be expressed as (S s ) may indicate the reported or observed speed of each vehicle. Increasing the relative granularity or resolution of the state factors or other factors of the systematic utility vehicle guidance model, such as from aggregate factors to per-vehicle factors, may increase the accuracy, the computational complexity, or both of solving the systematic utility vehicle guidance model.

[0164] For a region of a vehicle traffic network represented by the systematic utility vehicle flow guidance model, the state factors of the systematic utility vehicle flow guidance model may include a lane state factor for each vehicle, an aggregated observed speed factor, and an aggregated vehicle density factor, and S=× i (S i l )×S s ×S d It may be expressed as:

[0165] The systematic utility vehicle flow guidance model may include control guidance actions for each vehicle, which may indicate a target speed for each vehicle.

[0166] The systematic utility vehicle flow guidance model may include a reward function (R), which may be the negative of the sum of the difference between the vehicle's observed speeds and the target speeds indicated by the actions, and may be expressed as sum(S_observed_speeds[i]-A_speed[i] for i in 1:k). The systematic utility vehicle flow guidance model may be optimized to minimize the difference between the target speeds and the observed speeds.

[0167] In step 5230, the systematic utility vehicle guidance data is output. The systematic utility vehicle guidance data, or portions thereof, may be transmitted or otherwise made available to participating vehicles in the region. For example, the infrastructure device may transmit the systematic utility vehicle guidance data to each participating vehicle in the region using any communication link described herein, including a combination of communication links or dedicated short-range communications. In some embodiments, for example, in embodiments in which the current participating vehicle implements a systematic utility vehicle guidance model, transmitting the systematic utility vehicle guidance data to other participating vehicles may be omitted.

[0168] The systematic utility vehicle guidance data output in step 5230 for each participating vehicle may indicate per-vehicle control guidance actions generated in step 5220 from the systematic utility vehicle guidance model operated in step 5210 in response to the vehicle operation data for the area obtained in step 5200. In some embodiments, the systematic utility vehicle guidance data output in step 5230 for each participating vehicle may indicate the systematic utility vehicle guidance policy obtained in step 5210, the vehicle operation data for the area obtained in step 5200, or a portion thereof, or a combination thereof.

[0169] A portion of the vehicle network in this region is traveled in accordance with the systematic utility vehicle guidance data in step 5110. For example, a vehicle may receive or otherwise access and obtain the systematic utility vehicle guidance data output in step 5230 and travel through the portion of the vehicle network in step 5110 in accordance with the systematic utility vehicle guidance data.

[0170] In some embodiments, navigating the portion of the vehicle network according to the systematic utility vehicle guidance data in step 5110 includes outputting a representation of at least a portion of the systematic utility vehicle guidance data for presentation to an occupant of a vehicle (the current vehicle). For example, the systematic utility vehicle guidance data may indicate a target speed, and navigating the portion of the vehicle network according to the systematic utility vehicle guidance data may include outputting a representation of the target speed for presentation to the driver of the vehicle by highlighting the target speed on the vehicle's speedometer. Other representations, such as visual, audio, tactile, or combinations thereof, of the systematic utility vehicle guidance data may also be used.

[0171] In some embodiments, navigating the portion of the vehicle network in accordance with the systematic utility vehicle guidance data in Step 5110 includes autonomously controlling a vehicle (the current vehicle) to perform autonomous navigation in accordance with the systematic utility vehicle guidance data, such as in response to receiving the systematic utility vehicle guidance data. For example, the systematic utility vehicle guidance data may indicate a target speed, and the autonomous vehicle may accelerate or decelerate to traverse the portion of the vehicle network at or about the target speed.

[0172] In some embodiments, navigating the portion of the vehicle network in accordance with the systematic utility vehicle guidance data in Step 5110 includes outputting a representation of at least a portion of the systematic utility vehicle guidance data for presentation to an occupant of the vehicle, and autonomously controlling the vehicle to perform autonomous navigation in accordance with the systematic utility vehicle guidance data, such as in response to receiving the systematic utility vehicle guidance data. For example, the systematic utility vehicle guidance data may indicate a target speed, and the autonomous vehicle may accelerate or decelerate to traverse the portion of the vehicle network at or near the target speed, and may output the representation of the systematic utility vehicle guidance data as an indication of the reason or explanation for traversing the portion of the vehicle network at the target speed.

[0173] In some embodiments, a participating vehicle may receive systematic utility vehicle guidance data from two or more overlapping regions, and navigating the portion of the vehicle network according to the systematic utility vehicle guidance data in step 5110 includes, for each systematic utility vehicle guidance data, outputting a representation of at least a portion of the systematic utility vehicle guidance data for presentation to an occupant of the vehicle (the current vehicle), where the selected (or selected) systematic utility vehicle guidance data may be identified in response to an input, such as a user input, indicating the systematic utility vehicle guidance data. In some embodiments, the vehicle may autonomously traverse the portion of the vehicle network according to the selected systematic utility vehicle guidance data.

[0174] Although aspects of the state space, action space, transition probabilities, and reward function are described for the systematic utility vehicle guidance model described herein, the systematic utility vehicle guidance model may implement other aspects. For example, the state space of the model may include other state factors. In another example, the model may include other aspects, such as a set of observations (Ω) and a set of conditional observation probabilities (O).

[0175] As used herein, the term "computer" or "computing device" includes any unit or combination of units, or any part or parts thereof, that is capable of performing any of the methods disclosed herein.

[0176] As used herein, the term "processor" refers to one or more processors, such as one or more special purpose processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more microcontrollers, one or more application processors, one or more application specific integrated circuits, one or more application specific standard integrated circuits, one or more field programmable gate arrays, any other type or combination of integrated circuits, one or more state machines, or any combination thereof.

[0177] As used herein, the term "memory" refers to any computer-usable or computer-readable medium or device that can tangibly hold, store, communicate, or carry any signals or information that can be used by or associated with any processor. For example, memory may be one or more read-only memories (ROMs), one or more random access memories (RAMs), one or more registers, low-power DDR (LPDDR) memories, 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.

[0178] As used herein, the term "instructions" may include instructions or expressions for performing any method disclosed herein, or any part or parts thereof, and may be implemented in hardware, software, or any combination thereof. For example, instructions may be implemented as information, such as a computer program stored in a memory, that can be executed by a processor to perform any of the methods, algorithms, aspects, or combinations thereof described herein. In some embodiments, instructions or portions thereof may be implemented as a dedicated processor or circuitry, which may include dedicated hardware for performing any of the methods, algorithms, aspects, or combinations thereof described herein. In some implementations, portions of instructions may be distributed across multiple devices, multiple processors on a single device, that may communicate directly or over a network, such as a local area network, a wide area network, the Internet, or a combination thereof.

[0179] As used herein, the terms "example," "embodiment," "implementation," "aspect," "feature," or "element" indicate serving as an example, example, or illustration. Unless expressly stated otherwise, any example, embodiment, implementation, aspect, feature, or element is independent of each other example, embodiment, implementation, aspect, feature, or element and may be used in combination with any other example, embodiment, implementation, aspect, feature, or element.

[0180] As used herein, the terms "determining" and "identifying" or any variations thereof include selecting, ascertaining, calculating, retrieving, receiving, determining, establishing, obtaining, or otherwise identifying or determining in any manner using one or more of the devices shown and described herein.

[0181] As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified or clear from the context, "X includes A or B" is intended to indicate any natural inclusive permutation. That is, if X includes A, X includes B, or X includes both A and B, then "X includes A or B" is satisfied by any of the above examples. Furthermore, the articles "a" and "an" as used in this application and the appended claims should generally be construed to mean "one or more" unless the context clearly indicates a singular reference or unless otherwise specified.

[0182] Furthermore, although for brevity of explanation, the figures and descriptions herein may include a series of steps or stages or sequences, elements of the methods disclosed herein may occur in various orders or simultaneously. Moreover, elements of the methods disclosed herein may occur with other elements not explicitly shown and disclosed herein. Moreover, not all elements of the methods described herein are required to implement a method in accordance with the present disclosure. Although aspects, features, and elements are described herein in particular combinations, each aspect, feature, or element may be used independently or in various combinations with or without other aspects, features, and elements.

[0183] The above aspects, examples, and implementations are provided to facilitate understanding of the present disclosure and are not intended to be limiting. To the contrary, the present disclosure encompasses various modifications and equivalent arrangements included within the scope of the appended claims, which should be accorded the broadest interpretation so as to encompass all such modifications and equivalent arrangements permitted by law.

Claims

1. In the method used for the passage of vehicular traffic networks, The method includes traveling through a vehicular traffic network with a current vehicle; Passing through the vehicle traffic network obtaining, by the current vehicle, systematic utility vehicle guidance data for the current portion from an instance of a systematic utility vehicle guidance policy generated by solving a systematic utility vehicle guidance model that maximizes systematic utility for a plurality of vehicles operating within a region of the vehicle network that includes the current portion of the vehicle network; and traveling, by the current vehicle, through the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data; A method comprising:

2. and navigating the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data includes outputting a representation of the systematic utility vehicle guidance data for presentation to an occupant of the current vehicle. The method of claim 1 , comprising:

3. Traveling through the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data includes: controlling the current vehicle to perform autonomous navigation in accordance with the systematic utility vehicle guidance data; The method of claim 1 , comprising:

4. The systematic utility vehicle guidance data includes: a target speed for the current vehicle to travel through the current portion of the vehicular network; a target lane for the current vehicle to travel through the current portion of the vehicular network; a target route for the current vehicle to traverse the current portion of the vehicular network from the current location of the current vehicle to a target destination; or a target right-of-way priority for the current vehicle to traverse an intersection in the vehicular network, the current portion of the vehicular network including the intersection; The method of claim 1 , wherein the at least one of

5. obtaining the systematic utility vehicle guidance data includes: obtaining the systematic utility vehicle guidance data from an external device by the current vehicle; The method of claim 1 , comprising:

6. the external device is a remote vehicle; the external device is a centralized infrastructure device; or The method of claim 5 , wherein the external device is a distributed infrastructure device.

7. The method of claim 1 , wherein the systematic utility vehicle guidance model is a probabilistic model.

8. The probabilistic model is Markov decision process models, Probabilistic shortest path model, Partially Observable Markov Decision Process Model, Markov game model, Partially Observable Markov Game Model, or The method of claim 7, wherein the method is a distributed partially observable Markov decision process model.

9. Obtaining the systematic utility vehicle guidance data includes: operating the probabilistic model according to the current vehicle. The method of claim 7, comprising:

10. obtaining vehicle operation data for a region of a vehicle network, the vehicle operation data including current operation data for a plurality of vehicles operating in the region; operating a systematic utility vehicle guidance model for the plurality of vehicles operating within the region that maximizes systematic utility for the region; obtaining systematic utility vehicle guidance data for the region from the systematic utility vehicle guidance model in response to the vehicle operation data; and outputting said systematic utility vehicle guidance data; A method comprising:

11. The method of claim 10 , wherein obtaining systematic utility vehicle guidance data for the region includes obtaining vehicle-by-vehicle systematic utility vehicle guidance data for participating vehicles in the region.

12. The obtaining of systematic utility vehicle guidance data includes: a target speed for a vehicle to travel through the portion of the vehicular network; a target lane for the vehicle to travel through the portion of the vehicular network; a target route for the vehicle to traverse the portion of the vehicular network from the vehicle's current location to a target destination for the vehicle; or a target right-of-way priority for the vehicle to travel through an intersection in the vehicular network, the portion of the vehicular network including the intersection; The method of claim 10 , comprising obtaining the systematic utility vehicle guidance data to include at least one of:

13. Operating the systematic utility vehicle guidance model includes: vehicle, Centralized infrastructure device, or Distributed infrastructure device The method of claim 10, wherein the method is performed by

14. The systematic utility vehicle guidance model comprises: Markov decision process models, Probabilistic shortest path model, Partially Observable Markov Decision Process Model, Markov game model, Partially Observable Markov Game Model, or The method of claim 10, wherein the method is a distributed partially observable Markov decision process model.

15. Operating the systematic utility vehicle guidance model includes: generating the systematic utility vehicle guidance model using the vehicle operation data; and solving the systematic utility vehicle guidance model to obtain a systematic utility vehicle guidance policy; The method of claim 10, comprising:

16. Obtaining the systematic utility vehicle guidance data includes generating the systematic utility vehicle guidance data using the systematic utility vehicle guidance policy.

16. The method of claim 15, comprising:

17. In the method used for the passage of vehicular traffic networks, The method includes traveling through a vehicular traffic network with a current vehicle; Passing through the vehicle traffic network obtaining, by the current vehicle, systematic utility vehicle guidance data for a current portion of the vehicle network, wherein obtaining the systematic utility vehicle guidance data includes: obtaining vehicle operation data for a region of a vehicle network, the vehicle operation data including current operation data for a plurality of vehicles operating in the region; operating a systematic utility vehicle guidance model for the region responsive to the vehicle operation data to maximize systematic utility for the plurality of vehicles operating within the region; and obtaining the systematic utility vehicle guidance data for the region from a policy generated by the systematic utility vehicle guidance model; and traveling, by the current vehicle, through the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data; A method comprising:

18. Traveling through the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data includes: outputting a representation of the systematic utility vehicle guidance data for presentation to an occupant of the current vehicle.

18. The method of claim 17, comprising:

19. Traveling through the current portion of the vehicle network in accordance with the systematic utility vehicle guidance data includes: controlling the current vehicle to perform autonomous navigation in accordance with the systematic utility vehicle guidance data; 18. The method of claim 17, comprising:

20. The systematic utility vehicle guidance data includes: a target speed for the current vehicle to travel through the current portion of the vehicular network; a target lane for the current vehicle to travel through the current portion of the vehicular network; a target route for the current vehicle to traverse the current portion of the vehicular network from the current location of the current vehicle to a target destination; or a target right-of-way priority for the current vehicle to traverse an intersection in the vehicular network, the current portion of the vehicular network including the intersection; The method of claim 17, wherein the method exhibits at least one of the following:

Images