Traffic state determination

Abstract

The server accesses vehicle data of each CV in a subset of multiple connected vehicles (CVs) on a road section, where the vehicle data includes at least one of position, speed, and headway. The server generates a long-term shared world model based on the accessed vehicle data. The server generates a data structure that represents predicted future speeds on the road section by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model. The server transmits a control signal for controlling the operation of the connected autonomous vehicle (CAV) based on the generated data structure to the CAV.

Description

Technical Field

[0001] The present disclosure generally relates to networked vehicles and networked autonomous vehicles, and more particularly, to generating a long-term shared world model of a road and using the long-term shared world model for the operation of networked autonomous vehicles. Background Art

[0002] Traffic congestion has high costs in terms of, for example, lost man-hours, excessive carbon emissions, and increased likelihood of vehicle accidents. The proportion of vehicles on the road that are networked vehicles (CVs) capable of transmitting data over a network and networked autonomous vehicles (CAVs) capable of transmitting data over a network and receiving control signals over the network is increasing. Summary of the Invention

[0003] Aspects, features, elements, implementations, and embodiments of using belief state determination for real-time decision-making while a vehicle is traveling through a vehicle transportation network are disclosed herein.

[0004] One aspect of the disclosed embodiments is a method for generating a control signal and transmitting the control signal to a vehicle. The method includes: accessing vehicle data from each of a plurality of networked vehicles, i.e., a subset of a plurality of CVs, on a road segment, the vehicle data including at least one of position, speed, and headway. The method includes generating a long-term shared world model based on the accessed vehicle data. The method includes: generating a data structure that represents predicted future speeds on the road segment by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model. The method includes transmitting a control signal for controlling the operation of the networked autonomous vehicle, i.e., CAV, based on the generated data structure to the CAV.

[0005] One aspect of the disclosed embodiments is an apparatus for generating a control signal and transmitting the control signal to a vehicle. The apparatus includes a processor and a memory. The memory stores instructions. The processor executes the instructions to: access vehicle data of each of a subset of a plurality of connected vehicles (CVs) on a road section, the vehicle data including at least one of position, speed, and headway. The processor executes the instructions to generate a long-term shared world model based on the accessed vehicle data. The processor executes the instructions to: generate a data structure that represents a predicted future speed on the road section by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model. The processor executes the instructions to transmit a control signal for controlling the operation of a connected autonomous vehicle (CAV) based on the generated data structure to the CAV.

[0006] One aspect of the disclosed embodiments is a computer-readable medium for generating a control signal and transmitting the control signal to a vehicle. The computer-readable medium stores instructions. The instructions include code to: access vehicle data of each of a subset of a plurality of connected vehicles (CVs) on a road section, the vehicle data including at least one of position, speed, and headway. The instructions include code to generate a long-term shared world model based on the accessed vehicle data. The instructions include code to: generate a data structure that represents a predicted future speed on the road section by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model. The instructions include code to: transmit a control signal for controlling the operation of a connected autonomous vehicle (CAV) based on the generated data structure to the CAV.

[0007] These and other aspects, features, elements, implementations, and variations of the methods, apparatuses, processes, and algorithms disclosed herein are described in further detail below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Various aspects disclosed herein will become more apparent by reference to the following description and the examples provided in the drawings, in which like reference numerals refer to like elements.

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

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

[0011] Figure 3 is a data flow diagram of a technique for generating control signals using vehicle data according to an embodiment of the present disclosure.

[0012] Figure 4 is a data flow diagram of a long-term shared world model architecture according to an embodiment of the present disclosure.

[0013] Figure 5 Illustrates a flow diagram in space and time according to an embodiment of the present disclosure.

[0014] Figure 6 Illustrates speed and headway values measured for a detection vehicle according to an embodiment of the present disclosure.

[0015] Figure 7 is a data flow diagram for traffic state determination according to an embodiment of the present disclosure.

[0016] Figure 8 Illustrates an example vehicle communication and control architecture according to an embodiment of the present disclosure.

[0017] Figure 9 is a data flow diagram for vehicle communication and control according to an embodiment of the present disclosure.

[0018] Figure 10 is a flowchart of a method for operating a vehicle using a long-term shared world model according to an embodiment of the present disclosure.

[0019] Figure 11 is a flowchart of a method for predicting future traffic data according to an embodiment of the present disclosure.

[0020] Figure 12 is a flowchart of a method for controlling a vehicle using a multi-vehicle policy selector according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0021] As described above, traffic congestion has high costs in terms of, for example, lost man-hours, excessive carbon emissions, and increased likelihood of vehicle accidents. The proportion of vehicles on the road that are connected vehicles (CVs) capable of transmitting data over a network and connected automated vehicles (CAVs) capable of transmitting data over a network and receiving control signals over the network is increasing. Techniques that may be desirable to utilize CV or CAV technology to reduce traffic congestion are provided.

[0022] According to some embodiments, a vehicle control server (which may be implemented as one or more physical or virtual machines) accesses vehicle data from each of a subset of multiple CVs on a road section. Vehicle data from road sensors may also be accessed. The vehicle data may include the location of the vehicle providing the data or other vehicles, the speed of the vehicle providing the data or other vehicles, and / or the following distance of the vehicle providing the data or other vehicles. The vehicle control server stores the accessed vehicle data in a long-term shared world model. The vehicle control server generates a data structure representing the predicted future speed on the road section by location and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model. The traffic flow model may be, for example, an artificial intelligence model trained using at least one of supervised learning, unsupervised learning, reinforcement learning, and online learning, etc. The vehicle control server transmits a control signal to the CAV for controlling the operation of the CAV based on the generated data structure.

[0023] As used herein, the term "model" may include at least one of a classical planning model, an artificial intelligence (AI) model, and a machine learning (ML) model using supervised learning, unsupervised learning, or reinforcement learning, etc. The model may be based on data generated in the past and may be used to predict future data. For example, a long-term shared world model of a road section may store data related to the average speed and congestion (e.g., the number of vehicles per unit distance) of the road section in the past (e.g., at multiple times in the past three years) and be used to predict the average speed and congestion of the road section in the future (e.g., at 9 am next Monday). For example, AI or ML techniques or other mathematical modeling techniques may be used for prediction.

[0024] As used herein, the term "shared" may indicate a shared item accessed by at least two entities, etc. For example, at least two vehicles may contribute data to a shared model and / or receive data derived from the shared model. As used herein, the term "long-term" indicates that the data is based on a time period exceeding a threshold. For example, a long-term model may be based on data generated over a time period exceeding one hour, two hours, one day, three days, one week, five weeks, one month, six months, or one year, etc. As used herein, the term "world" may indicate data based on two or more points in space, etc.

[0025] As used herein, a road section may include a continuous portion of a road (e.g., a 1-2 km extension of a road). The road section may be subdivided into multiple road segments. For example, a 1 km road section may be divided into 10 mutually exclusive and collectively exhaustive road segments each 100 meters in length.

[0026] Note that every CAV is a CV. However, a vehicle can be a CV and not a CAV. For example, a vehicle that is operated by a human driver and is capable of communicating over a network would be a CV and not a CAV. In some implementations, with appropriate permission, CV technology can be implemented by an on-vehicle computing device (e.g., a mobile phone) on the vehicle. For example, the computing device can determine the speed of the vehicle (e.g., using the global positioning system (GPS) on the device and the clock on the device) and communicate the speed of the vehicle over the network.

[0027] Figure 1 is a diagram of examples of vehicles that can implement the aspects, features, and elements disclosed herein. As shown, vehicle 100 includes a chassis 110, a powertrain 120, a controller 130, and wheels 140. Although vehicle 100 is shown for simplicity as including four wheels 140, any other one or more propulsion devices (such as thrusters or treads, etc.) can be used. In Figure 1 this, the lines interconnecting elements such as powertrain 120, controller 130, and wheels 140 indicate that information such as data or control signals, power such as electricity or torque, or both information and power can communicate between the respective elements. For example, controller 130 can receive power from powertrain 120 and can communicate with powertrain 120, wheels 140, or both to control vehicle 100, which can include accelerating, decelerating, steering, or otherwise controlling vehicle 100.

[0028] As shown, powertrain 120 includes a power source 121, a transmission 122, a steering unit 123, and an actuator 124. Other elements of the powertrain (such as a suspension, a drive shaft, an axle, or an exhaust system, etc.) or combinations of elements can be included. Although shown separately, wheels 140 can be included in powertrain 120.

[0029] Power source 121 can include an engine, a battery, or a combination thereof. Power source 121 can be any device or combination of devices operable to provide energy (such as electrical energy, thermal energy, or kinetic energy, etc.). For example, power source 121 can include an engine (such as an internal combustion engine, an electric motor, or a combination of an internal combustion engine and an electric motor, etc.) and can be operable to provide kinetic energy as motive power to one or more of wheels 140. Power source 121 can include potential energy units, such as one or more dry batteries (such as nickel-cadmium (NiCd) batteries, nickel-zinc (NiZn) batteries, nickel-metal hydride (NiMH) batteries, lithium-ion (Li-ion) batteries, etc.), solar cells, fuel cells, or any other device capable of providing energy, etc.

[0030] The transmission 122 can receive energy (such as kinetic energy, etc.) from the power source 121 and can transmit this energy to the wheels 140 to provide motive power. The transmission 122 can be controlled by the controller 130, the actuator 124, or both. The steering unit 123 can be controlled by the controller 130, the actuator 124, or both, and the steering unit 123 can control the wheels 140 to steer the vehicle. The actuator 124 can receive signals from the controller 130 and can actuate or control the power source 121, the transmission 122, the steering unit 123, or any combination thereof to operate the vehicle 100.

[0031] As shown in the figure, the controller 130 can include a positioning unit 131, an electronic communication unit 132, a processor 133, a memory 134, a user interface 135, a sensor 136, an electronic communication interface 137, or any combination thereof. Although shown as a single unit, any one or more elements of the controller 130 can be integrated into any number of separate physical units. For example, the user interface 135 and the processor 133 can be integrated in a first physical unit, and the memory 134 can be integrated in a second physical unit. Although not shown in Figure 1 it, the controller 130 can include a power source such as a battery. Although shown as separate elements, the positioning unit 131, the electronic communication unit 132, the processor 133, the memory 134, the user interface 135, the sensor 136, the electronic communication interface 137, or any combination thereof can be integrated in one or more electronic units, circuits, or chips.

[0032] The processor 133 can include any device or combination of devices, existing or subsequently developed, capable of manipulating or processing signals or other information. The processor 133 includes an optical processor, a quantum processor, a molecular processor, or a combination thereof. For example, the processor 133 can include one or more dedicated processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more microcontrollers, one or more integrated circuits, one or more application-specific integrated circuits, one or more field-programmable gate arrays, one or more programmable logic arrays, one or more programmable logic controllers, one or more state machines, or any combination thereof. The processor 133 can be operably coupled to the positioning unit 131, the memory 134, the electronic communication interface 137, the electronic communication unit 132, the user interface 135, the sensor 136, the powertrain 120, or any combination thereof. For example, the processor can be operably coupled to the memory 134 via a communication bus 138.

[0033] The memory 134 may include any tangible non-transitory computer-usable or computer-readable medium that can, for example, contain, store, communicate, or transport machine-readable instructions or any information associated therewith for use by or in connection with the processor. The memory 134 may be, for example, one or more solid state drives, one or more memory cards, one or more removable media, one or more read-only memories, one or more random access memories, one or more disks (including hard disks, floppy disks, optical disks), magnetic cards or optical cards, or any type of non-transitory medium suitable for storing electronic information or any combination thereof.

[0034] The communication interface 137 may be a wireless antenna, a wired communication port, an optical communication port as shown in the figure, or any other wired or wireless unit capable of interacting with a wired or wireless electronic communication medium 150. Although Figure 1 the communication interface 137 is shown communicating via a single communication link, the communication interface may be configured to communicate via multiple communication links. Although Figure 1 a single communication interface 137 is shown, the vehicle may include any number of communication interfaces.

[0035] The communication unit 132 may be configured to send or receive signals via a wired or wireless electronic communication medium 150 (such as via the communication interface 137, etc.). Although not explicitly shown in Figure 1 it, the communication unit 132 may be configured to transmit, receive, or both via any wired or wireless communication medium (such as radio frequency (RF), ultraviolet (UV), visible light, optical fiber, wired line, or a combination thereof, etc.). Although Figure 1 a single communication unit 132 and a single communication interface 137 are shown, any number of communication units and any number of communication interfaces may be used. In some embodiments, the communication unit 132 may include a dedicated short range communication (DSRC) unit, an on-board unit (OBU), or a combination thereof.

[0036] The positioning unit 131 may determine geographical location information, such as the longitude, latitude, altitude, driving direction, or speed of the vehicle 100, etc. For example, the positioning unit may include a global positioning system (GPS) unit, such as a National Marine Electronics Association (NMEA) unit enabled with a Wide Area Augmentation System (WAAS), a radio triangulation unit, or a combination thereof, etc. The positioning unit 131 may be used to obtain information representing, for example, the current heading of the vehicle 100, the current position of the vehicle 100 in two or three dimensions, the current angular orientation of the vehicle 100, or a combination thereof.

[0037] The user interface 135 may include any unit capable of interacting with a person, such as a virtual or physical keyboard, touchpad, display, touch display, heads-up display, virtual display, augmented reality display, haptic display, feature tracking device (such as an eye tracking device, etc.), speaker, microphone, camera, sensor, printer, or any combination thereof. As shown, the user interface 135 may be operably coupled to the processor 133, or to any other element of the controller 130. Although shown as a single unit, the user interface 135 may include one or more physical units. For example, the user interface 135 may include an audio interface for audio communication with a person, and a touch display for visual and touch-based communication with a person. The user interface 135 may include multiple displays, such as multiple physically separate units, multiple defined portions within a single physical unit, or a combination thereof.

[0038] The sensor 136 may include one or more sensors (such as a sensor array, etc.), which may be operable to provide information that can be used to control the vehicle. The sensor 136 may provide information related to the current operating characteristics of the vehicle 100. The sensor 136 may, for example, include a speed sensor, an acceleration sensor, a steering angle sensor, a traction-related sensor, a brake-related sensor, a steering wheel position sensor, an eye tracking sensor, a seat position sensor, or any sensor or combination of sensors that are operable to report information related to certain aspects of the current dynamic situation of the vehicle 100.

[0039] The sensor 136 may include one or more sensors operable to obtain information related to the physical environment around the vehicle 100. For example, one or more sensors may detect road geometry and features (such as lane lines, etc.) and obstacles (such as fixed obstacles, vehicles, and pedestrians, etc.). The sensor 136 may be or may include one or more cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of in-vehicle environment sensing device, or combination of devices, known now or developed subsequently. In some embodiments, the sensor 136 and the positioning unit 131 may be a combined unit.

[0040] Although not shown separately, vehicle 100 may include a trajectory controller. For example, controller 130 may include a trajectory controller. The trajectory controller is operable to obtain information for describing the current state of vehicle 100 and the route planned for vehicle 100, and to determine and optimize the trajectory of vehicle 100 based on this information. In some embodiments, the trajectory controller may output a signal operable to control vehicle 100 such that vehicle 100 follows the trajectory determined by the trajectory controller. For example, the output of the trajectory controller may be an optimized trajectory, which may be supplied to powertrain 120, wheel 140, 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 point or a position. In some embodiments, the optimized trajectory may be one or more paths, routes, curves, or a combination thereof.

[0041] One or more of wheels 140 may be: a steering wheel that can pivot to a steering angle under the control of steering unit 123; a drive wheel that can be twisted to propel vehicle 100 under the control of transmission 122; or a steer-drive wheel that can steer and propel vehicle 100.

[0042] The vehicle may include units or components not explicitly shown in Figure 1 such as a housing, (Bluetooth) module, frequency modulation (FM) radio unit, near field communication (NFC) module, liquid crystal display (LCD) display unit, organic light emitting diode (OLED) display unit, speaker, or any combination thereof, etc.

[0043] Vehicle 100 may be an autonomous vehicle that is autonomously controlled to traverse a portion of a vehicle transportation network without direct human intervention. Although not shown separately in Figure 1 the autonomous vehicle may include an autonomous vehicle control unit that may perform autonomous vehicle routing, navigation, and control. The autonomous vehicle control unit may be integrated with other units of the vehicle. For example, controller 130 may include the autonomous vehicle control unit. The teachings herein also apply to semi-autonomous vehicles.

[0044] An autonomous vehicle control unit can control or operate a vehicle 100 to traverse a portion of a vehicle transportation network based on current vehicle operation parameters. The autonomous vehicle control unit can control or operate the vehicle 100 to perform defined operations or maneuvers, such as parking the vehicle, etc. The autonomous vehicle control unit can generate a travel route from a starting point, such as the current location of the vehicle 100, to a destination based on vehicle information, environmental information, vehicle transportation network data representing the vehicle transportation network, or a combination thereof, and can control or operate the vehicle 100 to traverse the vehicle transportation network according to the route. For example, the autonomous vehicle control unit can output the travel route to a trajectory controller, and the trajectory controller can use the generated route to operate the vehicle 100 to travel from the starting point to the destination.

[0045] Figure 2 FIG. is an example of a part of a vehicle transportation and communication system that can implement the aspects, features, and elements disclosed herein. The vehicle transportation and communication system 200 can include one or more vehicles 210 / 211, such as the vehicle 100 shown, Figure 1 which can travel via one or more portions of one or more vehicle transportation networks 220 and can communicate via one or more electronic communication networks 230. Although not explicitly shown in Figure 2 FIG., the vehicle can traverse areas (such as off-road areas, etc.) that are not explicitly or fully included in the vehicle transportation network.

[0046] The electronic communication network 230 can be, for example, a multiple access system and can provide communication between the vehicles 210 / 211 and one or more communication devices 240, such as voice communication, data communication, video communication, messaging communication, or a combination thereof. For example, the vehicles 210 / 211 can receive information, such as information representing the vehicle transportation network 220, from the communication device 240 via the network 230.

[0047] In some embodiments, the vehicles 210 / 211 can communicate via a wired communication link (not shown), a wireless communication link 231 / 232 / 237, or a combination of any number of wired or wireless communication links. For example, as shown in the figure, the vehicles 210 / 211 can communicate via a terrestrial wireless communication link 231, via a non-terrestrial wireless communication link 232, or via a combination thereof. The terrestrial wireless communication link 231 can include an Ethernet link, a serial link, a Bluetooth link, an infrared (IR) link, a UV link, or any link capable of providing electronic communication.

[0048] Vehicle 210 / 211 can communicate with another vehicle 210 / 211. For example, the host vehicle or main vehicle body (HV) 210 can receive one or more inter-vehicle automation messages (such as a basic safety message (BSM), etc.) from a remote or target vehicle (RV) 211 via a direct communication link 237 or via a network 230. For example, the remote vehicle 211 can broadcast the message to the host vehicle within a defined broadcast range (such as 300 meters, etc.). In some embodiments, the host vehicle 210 can receive the message via a third party such as a signal repeater (not shown) or other remote vehicles (not shown). Vehicles 210 / 211 can periodically send one or more inter-vehicle automation messages based on, for example, a defined interval (such as 100 milliseconds, etc.).

[0049] Inter-vehicle automation messages can include vehicle identification information, geospatial status information (such as longitude, latitude, or altitude information, etc.), geospatial location accuracy information, kinematic status information (such as vehicle acceleration information, yaw rate information, speed information, vehicle heading information, brake system status information, throttle information, steering wheel angle information, etc.), or vehicle routing information, or vehicle operating status information (such as vehicle size information, headlight status information, turn signal information, wiper status information, transmission information, or any other information or combination of information related to changing the vehicle status, etc.). For example, the transmission status information can indicate whether the transmission that changes the vehicle speed is in a neutral state, a parked state, a forward state, or a reverse state.

[0050] Vehicle 210 can communicate with communication network 230 via access point 233. The access point 233, which can include a computing device, can be configured to communicate with vehicle 210, with communication network 230, with one or more communication devices 240, or a combination thereof via a wired or wireless communication link 231 / 234. For example, the access point 233 can be a base station, a base transceiver station (BTS), a Node-B, an enhanced Node-B (eNode-B), a Home Node-B (HNode-B), a wireless router, a wired router, a hub, a repeater, a switch, or any similar wired or wireless device. Although shown as a single unit in Figure 2 it can include any number of interconnected elements.

[0051] Vehicle 210 may communicate with communication network 230 via satellite 235 or other non-ground communication devices. Satellite 235, which may include a computing device, may be configured to communicate with vehicle 210, with communication network 230, with one or more communication devices 240, or a combination thereof via one or more communication links 232 / 236. Although shown as a single unit in Figure 2 the satellite may include any number of interconnected elements.

[0052] Electronic communication network 230 may be any type of network configured to provide voice communication, data communication, or any other type of electronic communication. For example, electronic communication network 230 may include a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a mobile or cellular telephone network, the Internet, or any other electronic communication system. Electronic communication network 230 may use communication protocols such as Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Internet Protocol (IP), Real-Time Transport Protocol (RTP), Hypertext Transfer Protocol (HTTP), or a combination thereof. Although shown as a single unit in Figure 2 the electronic communication network may include any number of interconnected elements.

[0053] Vehicle 210 may identify a portion or condition of vehicle transportation network 220. For example, vehicle 210 may include one or more on-vehicle sensors (such as Figure 1 sensor 136 shown in

[0054] ), and the one or more on-vehicle sensors 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 condition of vehicle transportation network 220. Sensor data may include lane line data, remote vehicle location data, or both.

[0055] Although for simplicity, Figure 2 two vehicles 210, 211, one vehicle transportation network 220, one electronic communication network 230, and one communication device 240 are shown, any number of vehicles, networks, or computing devices may be used. Vehicle transportation and communication system 200 may include components not shown in Figure 2The devices, units, or components shown. Although the vehicle 210 is shown as a single unit, the vehicle can include any number of interconnected components.

[0056] Although the vehicle 210 is shown as communicating with the communication device 240 via the network 230, the vehicle 210 can communicate with the communication device 240 via any number of direct or indirect communication links. For example, the vehicle 210 can communicate with the communication device 240 via a direct communication link such as a Bluetooth communication link.

[0057] In some embodiments, the vehicle 210 / 211 can be associated with an entity 250 / 260 (such as a driver, operator, or owner of the vehicle, etc.). In some embodiments, the entity 250 / 260 associated with the vehicle 210 / 211 can be associated with one or more personal electronic devices 252 / 254 / 262 / 264 (such as a smart phone 252 / 262 or a computer 254 / 264, etc.). In some embodiments, the personal electronic devices 252 / 254 / 262 / 264 can communicate with the corresponding vehicle 210 / 211 via a direct or indirect communication link. Although in Figure 2 one entity 250 / 260 is shown as being associated with the corresponding vehicle 210 / 211, any number of vehicles can be associated with an entity, and any number of entities can be associated with a vehicle.

[0058] The vehicle transportation network 220 only shows the navigable areas (e.g., roads), but the vehicle transportation network can also include one or more non-navigable areas (such as buildings, etc.), one or more partially navigable areas (such as parking areas or sidewalks) or a combination thereof. The vehicle transportation network 220 can also include one or more interchanges between one or more navigable or partially navigable areas. A part of the vehicle transportation network 220 (such as a road, etc.) can include one or more lanes and can be associated with one or more driving directions.

[0059] A vehicle transportation network or a portion thereof may be represented as vehicle transportation network data. For example, the vehicle transportation network data may be expressed as a hierarchy of elements (such as markup language elements, etc.), and these elements may be stored in a database or a file. For simplicity, the drawings in this document depict the vehicle transportation network data representing a portion of the vehicle transportation network as a graph or a map; however, the vehicle transportation network data may be expressed in any computer-usable form capable of representing the vehicle transportation network or a portion thereof. The vehicle transportation network data may include vehicle transportation network control information, such as driving direction information, speed limit information, toll information, slope information (such as inclination or angle information, etc.), surface material information, aesthetic information, defined hazard information, or a combination thereof.

[0060] A portion or a combination of portions of the vehicle transportation network 220 may be identified as a point of interest or a destination. For example, the vehicle transportation network data may identify a building as a point of interest or a destination. Points of interest or destinations may be identified using discrete, uniquely identifiable geographical locations. For example, the vehicle transportation network 220 may include defined locations for destinations, such as street addresses, postal addresses, vehicle transportation network addresses, GPS addresses, or a combination thereof.

[0061] Figure 3 is a data flow diagram of a technique 300 for generating a control signal using vehicle data according to an embodiment of the present disclosure.

[0062] As shown, a connected vehicle (CV) 302 transmits vehicle data 304 to a long-term shared world model 306. Although a single CV 302 is illustrated, multiple CVs including CV 302 may transmit vehicle data 304 to the long-term shared world model 306. The vehicle data 304 may include at least one of location data, speed data, and headway (e.g., following distance) data, etc. The vehicle data 304 may relate to the CV or other vehicles close to the CV. Although the vehicle data 304 is shown as being transmitted from the CV 302, all or part of the vehicle data may be transmitted from road sensors (e.g., radar, lidar, or computer vision-based sensors). The vehicle data 304 is used to generate or modify the long-term shared world model 306. The long-term shared world model 306 stores historical traffic speed, congestion, and / or headway data related to multiple road segments and may be used to predict future traffic speed, congestion, and / or headway data for all or part of the multiple road segments. As shown, a prediction engine 308 accesses the long-term shared world model 306 to make predictions related to future traffic speed, congestion, and / or headway data for a road segment. The prediction is stored in a prediction data structure 310. A control signal 312 is generated based on the prediction data structure 310 and the control signal 312 is transmitted to a connected automated vehicle (CAV) 314. The control signal 312 controls the speed or driving path of the CAV 314.

[0063] Location data may represent the geographical location of a vehicle. For example, the location data may indicate the latitude and longitude of the vehicle, the street address of the vehicle, or other identifiers of the geographical location. Location data may be obtained using road sensors at the vehicle, using global positioning system (GPS) technology, and / or using cellular tower triangulation. Speed data represents the speed and direction of travel of the vehicle. The speed data may include measurements in terms of speed (e.g., kilometers per hour) and direction (e.g., n degrees north of east, where n is a number). Headway data represents the distance between the front end of a vehicle and the front end (or alternatively, the rear end) of another vehicle that the vehicle is following. The headway data may be measured in terms of distance (e.g., meters).

[0064] CV 302 and / or CAV 314 may correspond to one or more of the vehicles 100, 210, 211. The long-term shared world model 306, prediction engine 308, and / or prediction data structure 310 may be implemented using software and / or hardware residing at a server connected to the vehicle transportation network 220 and / or the electronic communication network 230. For example, the long-term shared world model 306, prediction engine 308, and / or prediction data structure 310 may be implemented using software and / or hardware residing at the communication device 240.

[0065] According to some implementations, the long-term shared world model 306 accesses and stores vehicle data 304 from the CV 302. The prediction engine 308 generates the prediction data structure 310 by applying a traffic flow model to the long-term shared world model 306, where the prediction data structure 310 represents predicted future speeds on a road segment by location and time. The traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment during a time slice, the vehicle density in at least one road segment during a time slice, and the flow or net flow of vehicles entering or leaving at least one road segment during a time slice. A control signal 312 is generated based on the prediction data structure 310 and transmitted to the CAV 314 to control its operation (e.g., speed or driving path). The term "time slice" may include a continuous time period (e.g., the time period between 4:00 PM and 4:02 PM on February 1, 2022).

[0066] Figure 4 is a data flow diagram of a long-term shared world model architecture 400 according to an embodiment of the present disclosure. As shown, the vehicle 402 provides vehicle data (e.g., GPS data) to the transmission engine 404. The transmission engine 404 transmits the vehicle data 406 to the positioning engine 408. The positioning engine 408 calculates the position, speed, and headway 410 of the vehicle and provides the position, speed, and headway 410 to the estimation engine 412. The estimation engine 412 estimates the flow, density, and speed 414 and provides the data to the transmission engine 404 and the vehicle 402 for controlling the vehicle (e.g., through an autonomous driving engine or by a human driver).

[0067] Some implementations relate to reducing traffic congestion. The long-term shared world models 306, 400 may include a traffic state estimator that collects and aggregates data from probe vehicles throughout the network to produce a meaningful macroscopic prediction of the state and evolution of traffic. This information is maintained in a database (or other data storage unit) and provided to control strategies at a later stage to help improve the decision-making and coordination of CVs and CAVs.

[0068] The transfer engine 404 aggregates data from vehicle 402 (which can be a CV or CAV) into vehicle data 406 and, in some cases, aggregates data from other vehicles into a shared data repository stored on the network and accessible in real time. The transfer engine 404 can collect GPS, controller area network (CAN), and other available data sources from vehicle 402 and can transmit this data to the server. The transfer engine 404 also stores data that can be accessed by vehicle 402. The structure of the available shared repository can be optimized to reduce the overhead associated with storing and accessing individual vehicle data points.

[0069] The positioning engine 408 extracts and processes relevant information from the vehicle data 406. The vehicle data 406 can be collected from the shared data repository. The positioning engine 408 can perform filtering operations to reduce noise. The information collected by the positioning engine 408 at time t for each vehicle i can include the information shown in Table 1.

[0070] Table 1

[0071] x i (t): The position of vehicle i (relative to some fixed reference point)

[0072] v i (t): The speed of vehicle i

[0073] h i (t): The headway (front bumper to front bumper) between vehicle i and the vehicle leading vehicle i

[0074] v i,lead (t): The speed of the leading vehicle in the same lane as vehicle i

[0075] v L i,lead (t): The speed of the leading vehicle in the lane to the left of vehicle i

[0076] h L i,lead (t): The headway of the leading vehicle in the lane to the left of vehicle i

[0077] v L i,follow (t): The speed of the following vehicle in the lane to the left of vehicle i

[0078] h L i,follow (t): The headway of the following vehicle in the lane to the left of vehicle i

[0079] v R i,lead (t): The speed of the leading vehicle in the right lane of vehicle i

[0080] h R i,lead (t): The headway of the leading vehicle in the right lane of vehicle i

[0081] v R i,follow (t): The speed of the following vehicle in the right lane of vehicle i

[0082] h R i,follow (t): The headway of the following vehicle in the right lane of vehicle i

[0083] The estimation engine 412 collects information (e.g., position, speed, and headway 410) stored by the transfer engine 404 and modified by the positioning engine 408, and uses this information to approximate the macroscopic state of traffic at different road segments. In particular, consider a road portion of length L and total time T seconds. N and M are integers. The estimation engine 412 discretizes time and space with N time steps J j (0 <= j <= N) and M spatial cells I i (0 <= i <= M) of length Δt = T / N and length Δx = L / M, respectively, and computes the metrics shown in Table 2 for each spatio-temporal region.

[0084] Table 2

[0085] v i j : The average speed of vehicles in road segment i over time interval j

[0086] ρ i j : The vehicle density in road segment i over time interval j

[0087] q i j : The flow of vehicles from road segment i to road segment i + 1 over time interval j

[0088] The information (flow, density, and speed 414) computed by the estimation engine 412 is provided to the transfer engine 404 for storage in the data repository or for use by vehicles (e.g., vehicle 402) communicating with the transfer engine 404.

[0089] One advantage of architecture 400 is the flexibility provided by the modularity of the different sub-components. This allows some implementations to generalize various features to multiple different vehicles and estimation algorithms. For example, if multiple vehicles with different sensing / communication specifications are utilized, the errors associated with each type of vehicle can be adjusted by using different positioning modules for each vehicle type while keeping all other modules static. Additionally, if penetration effects or other specifications require the use of different estimated traffic state estimation algorithms, the algorithm can simply be replaced without modifying anything else.

[0090] The data repository in the transfer engine 404 can be a database (e.g., SQL, MongoDB, etc.) or other data storage unit. The type of information shared between vehicles (e.g., vehicle 402) accessing the transfer engine 404 can depend on the sensors available on board. The positioning engine 408 can use different filtering techniques to access and process historical data. The estimation engine 412 can utilize different traffic state estimators. For example, when less than a threshold amount of data is available, statistical or data-driven estimators can be used to produce moderately granular results. When more than the threshold amount of data is available, model-based estimators (e.g., AI or ML estimators) can be used to produce more fine-grained estimates.

[0091] To enable CVs and CAVs to efficiently cooperate and regulate traffic flow, a long-term shared world model 306 (or other shared model of traffic state) can be used. Traffic state estimation algorithms can provide techniques for defining such a model. Some techniques transform local vehicle sensor data (vehicle position, headway, and speed) into quantities that can define a shared state among vehicles in a spatial and temporal region (e.g., one or more road segments). Due to limitations in the sensing infrastructure, etc., some techniques rely on sparse amounts of data. The rise of vehicle automation has greatly improved the quality of on-board vehicle sensing, resulting in vehicles that can sense not only what is happening in front of the vehicle but also what is happening in adjacent lanes. Some implementations take advantage of the improvements in the sensing infrastructure and define a process by which these additional observations can be used to improve the quality of existing traffic state estimation methods.

[0092] Some implementations involve replicating an Edie flow from the perspective of a probe vehicle. However, the estimator utilized (for replicating the Edie flow) may be prone to errors. Errors in the estimation may arise from biases in the sample (probe) vehicle data. In some cases, some vehicles may drive faster or slower (or have longer or shorter headways) than other vehicles, and additional corrections can be used to produce more accurate results. In some implementations, for a spatio-temporal region (e.g., a road portion, a road segment, multiple road portions, or multiple road segments) A corresponding to a spatial interval i and a temporal interval j i j , r 1 can be a speed correction factor, and r 2 can be a headway correction factor. The relationship between the true traffic state and the estimated traffic state can be:

[0093]

[0094] In the above equation, q i j and q_hat i j are the true and predicted average flows in the spatial interval i and the temporal interval j respectively; v i j and v_hat i j are the true and predicted average speeds in the spatial interval i and the temporal interval j respectively; ρ i j and ρ_hat i j are the true and predicted average densities in the spatial interval i and the temporal interval j respectively.

[0095] Some implementations involve defining the values of r 1 and r 2 . The true values of r 1 and r 2 can depend on global state information, which may be unknown. To estimate the values of r 1 and r 2 , some implementations rely on data from lanes adjacent to the lane of the probe vehicle as well as data from the lane of the probe vehicle. Some implementations collect data related to speed (e.g., in units of distance divided by time) and headway (e.g., in units of distance) from adjacent lanes and the probe lane. For example, the data shown in Table 1 can be collected. After collecting the data, r 1 and r 2 can be calculated as follows:

[0096]

[0097] In the above equation, t i,j n is the time step spent by vehicle n in area A i j . Adding 0.5 in the speed correction is intended to balance the influence of each lane on the cumulative estimation. It should be noted that whenever only a subset of the above data is available, this value is ignored and averaging is performed on a smaller subset.

[0098] Figure 5 Illustrate the flow graph in space and time. Graph line 502 depicts the spatio-temporal region, and graph line 504 depicts the data used in the prediction techniques disclosed herein. Figure 6 Illustrate the speed and headway values 600 measured for the detection vehicle 602.

[0099] This correction may be important in many cases because variations between driving behaviors between lanes may reduce the accuracy of the generated estimates. Examples of situations where such concerns may arise include the presence of a truck downstream in one lane (e.g., the truck is larger and travels slower than a passenger vehicle), or the presence of a high-occupancy vehicle (HOV) or other fast-moving lanes not used by the detected vehicles. By sensing and correcting the behavior of vehicles in adjacent lanes, some implementations can mitigate the influence of lane-level features on the returned estimated values.

[0100] In some implementations, the correction factors r 1 and r 2 can be calculated based on local real-time sensor data. Some implementations include Bayesian priors for modeling the lane-level dynamics distribution to improve the accuracy in the presence of sparse data. Some implementations represent the corrected values of flow and density as a function of the offset of the average speed. This is relevant when neither the leading vehicle nor the following vehicle in the adjacent lane can be found, thus presenting the quantification of the headway. For example, by using a triangular fundamental diagram to define the form of the flow-density relationship and calibrating the model of this relationship can help generate approximations of the correction factors r 1 and r 2 .

[0101] Figure 7 is a data flow diagram for traffic state determination 700 according to an embodiment of the present disclosure. As Figure 7 shown, the CV 702 (e.g., corresponding to the CV 302) provides speed data 704 and headway data 706 (e.g., all or part of the speed data and headway data listed in Table 1) to the vehicle control server 708. The vehicle control server 708 calculates the speed correction factor 710 (r 1 ) and the headway correction factor 712 (r2 )。(For example, the prediction engine 714 corresponding to the prediction engine 308) accesses the speed data 704 and the headway data 706, and predicts (e.g., using artificial intelligence, machine learning, and / or mathematical formulas) the future flow 716, the future average speed 718, and the future density 720 of at least one road segment or road portion. The predicted future flow 716, future average speed 718, and future density 720, together with the calculated speed correction factor 710 and the headway connection factor 712, are provided to the adjustment engine 722 of the vehicle control server 708. The adjustment engine adjusts the predicted future flow 716, future average speed 718, and future density 720, and provides an output to the control signal generator 724 based on the adjustment. The control signal generator 724 generates a control signal 726 for controlling (e.g., the CAV 728 corresponding to the CAV 314), and provides the control signal 726 to the CAV 728. The CAV 728 adjusts the operation (e.g., speed or driving path) of the CAV 728 in response to the control signal 726.

[0102] Increased traffic congestion increases fuel consumption and greenhouse gas emissions, while reducing driving comfort and driving safety. Technologies that use connected and / or automated vehicle technologies to reduce traffic congestion may be desirable.

[0103] In some implementations, a portion of the vehicles are connected vehicles (vehicles that can share information with the cloud but are manually driven by a human driver), a portion of the vehicles are connected and automated vehicles (vehicles that can share information and are automatically controlled by the cloud), and a portion of the vehicles are human-driven vehicles that are neither connected nor automated (without connectivity to the cloud). CVs and CAVs can share traffic-related measurements using on-vehicle sensors (including vehicle speed, acceleration, relative distance and relative speed to surrounding vehicles, etc.) with the cloud.

[0104] Figure 8Exemplary vehicle communication and control architecture 800 is shown. As shown, vehicle communication and control architecture 800 includes non-connected vehicle 802, CV 804, CAV 806, and roadside unit (RSU) 808 on road portion 810. Non-connected vehicle 802 can be a traditional vehicle operated by a human driver and may not be able to transmit traffic state information (e.g., speed information, travel path information, or information obtained by on-vehicle sensors, etc.) to the network. RSU 808 can include a router for transmitting network communication to CV 804 and CAV 806 and receiving network communication from CV 804 and CAV 806. RSU 808 can include road sensors (e.g., camera system, radar system, or lidar system). As shown, CV 804, CAV 806, and RSU 808 communicate to generate situation and perception data 812 for long-term shared world model 814. Long-term shared world model 814 can correspond to long-term shared world model 306. As shown, long-term shared world model 814 is accessed by collaborative multi-vehicle policy selector 816. Collaborative multi-vehicle policy selector 816 transmits control signal 818 to CAV 806. Control signal 818 is coordinated and optimized to achieve traffic control objectives, such as reducing traffic inflow 820 or reducing stop-and-go traffic 822 at various portions of road portion 810, etc. As shown, long-term shared world model 814 and collaborative multi-vehicle policy selector 816 are stored on network 824, e.g., stored at a server or data repository connected to network 824.

[0105] According to some implementations, via wireless communication, an engine of network 824 (e.g., long-term shared world model 814 or collaborative multi-vehicle policy selector 816) receives information from CV 804 and / or CAV 806 and sends information to CV 804 and / or CAV 806. Situation and perception data 812 from CV 804 and / or CAV 806 are processed, and then control signal 818 is sent to CAV 806.

[0106] The long-term shared world model 814 is a real-time and accurate traffic state model based on the status and perception data 812 from the CV 804 and CAV 806. The long-term shared world model 814 is used to provide the information required for the cooperative multi-vehicle policy selector 816 to generate the control signal 818 for the CAV 806. The data from the long-term shared world model 814 can be used in two ways: directly sharing the traffic conditions with the CAV 806 to allow each CAV 806 to use its on-vehicle computer to adapt to the traffic conditions, or enabling the cooperative multi-vehicle policy selector 816 to determine the optimal actions of the CAV 806 based on macroscopic metrics (such as network throughput, traffic rate change, or greenhouse gas emissions, etc.). The optimal actions of each CAV 806 are communicated from the cooperative multi-vehicle policy selector 816 to the associated CAV 806 using the control signal 818. By coordinating the driving behaviors of the CAV 806, the traffic flow can be controlled and optimized more efficiently, the traffic inflow in the road area can be reduced, and / or the stop-and-go traffic can be reduced.

[0107] Figure 9 FIG. is a data flow diagram of a vehicle communication and control 900 according to an embodiment of the present disclosure. As shown, the CV 902 generates traffic state information 904 and provides the traffic state information 904 to the long-term shared world model 906. The CV902 may correspond to one of the CV 804 or one of the CAV 806. The traffic state information 904 may correspond to the status and perception data 812 or other information generated or available at the CV 902. The long-term shared world model 906 may correspond to at least one of the long-term shared world models 306, 814.

[0108] As shown, the long-term shared world model 906 communicates data to the multi-vehicle policy selector 908 (e.g., the cooperative multi-vehicle policy selector 816). The multi-vehicle policy selector 908 utilizes an optimization engine 910 to optimize the traffic conditions (e.g., reducing the traffic inflow to a high-traffic area and / or reducing the stop-and-go traffic) to generate a control signal 912 (e.g., from the control signal 818) for the CAV 914 (e.g., one of the CAV 806). The multi-vehicle policy selector 908 transmits the control signal 912 to the CAV 914. The CAV 914 adjusts its operation (e.g., its speed or its driving path) based on the control signal 912.

[0109] Figure 10FIG. 1000 is a flowchart of a method 1000 for operating a vehicle using a long-term shared world model according to an embodiment of the present disclosure. The method 1000 may be implemented using a server. The server may include a server connected to a vehicle transportation network 220 and / or an electronic communication network 230. The server may include a single computing device or multiple computing devices working together.

[0110] At block 1002, the server accesses vehicle data from each CV in a subset of multiple CVs on a road section. The vehicle data may include at least one of position, speed, and headway. The server may also access additional data from road sensors. The additional data may include vehicle position data, vehicle speed data, and / or vehicle headway data. The additional data may be sensed at the road sensors using computer vision, radar, and / or lidar. The vehicle data may be associated with the CV itself or other vehicles (e.g., other CVs or non-networked vehicles) whose data accessible by in-vehicle sensors of the CV are close to the CV. The additional data may be associated with the CV or non-networked vehicles.

[0111] At block 1004, the server generates a long-term shared world model (e.g., one of long-term shared world models 306, 814, 906) based on the accessed vehicle data and / or additional data. In some cases, the accessed vehicle data is received from a first vehicle and includes the position, speed, or headway of a second vehicle. The first vehicle is different from the second vehicle. For example, the second vehicle may be traveling immediately in front of the first vehicle, immediately behind the first vehicle, or in a driving lane adjacent to the driving lane of the first vehicle.

[0112] At block 1006, the server generates a data structure representing predicted future speeds on the road section by position and time by applying a traffic flow model to the long-term shared world model. For example, the data structure may be a two-dimensional array, where one dimension represents the road segment and the other dimension represents the time slice. The value in each cell of the two-dimensional array may represent the predicted future speed for the corresponding road segment and time slice.

[0113] According to some implementations, the road section is subdivided into multiple road segments. The traffic flow model is based on at least one of the average vehicle speed in at least one road segment during a time slice, the vehicle density in at least one road segment during a time slice, and the flow or net flow of vehicles entering or leaving at least one road segment during a time slice. The long-term shared world model may be used to calculate the average vehicle speed, vehicle density, flow, or net flow.

[0114] At block 1008, the server transmits a control signal to the CAV for controlling the operation of the CAV based on the generated data structure. The CAV may adjust its operation based on the control signal. For example, the CAV may adjust its speed or its driving path based on the control signal.

[0115] Figure 11 is a flowchart of a method 1100 for predicting future traffic data according to an embodiment of the present disclosure. The server may include a vehicle control server 708 or a server connected to the vehicle transportation network 220 and / or the electronic communication network 230. The server may include a single computing device or multiple computing devices working together.

[0116] At block 1102, the server receives speed data from the CV representing the speeds of the CV and additional vehicles approaching the CV. The server calculates a speed correction factor based on the speed data, for example, using Equation 4 above. The additional vehicles approaching the CAV may include vehicles in a lane adjacent to the CV in front of the CV or vehicles in a lane adjacent to the CV behind the CV.

[0117] At block 1104, the server receives headway data from the CV representing the headways of the CV and additional vehicles approaching the CV. The server calculates a headway correction factor based on the headway data, for example, using Equation 5 above. In some implementations, the server receives speed data and headway data from multiple CVs including the CV. The speed correction factor is calculated based on the speed data from the multiple CVs. The headway correction factor is calculated based on the headway data from the multiple CVs.

[0118] At block 1106, the server uses a prediction engine at the server to determine a future flow, a future average speed, and a future density for a segment of a road. In some implementations, the prediction engine utilizes a long-term shared world model (e.g., one of the long-term shared world models 306, 814, 906) that stores data received from multiple CVs and multiple road sensors.

[0119] At block 1108, the server adjusts the determined future flow based on the speed correction factor and the headway correction factor. The server adjusts the determined future average speed based on the speed correction factor. The server adjusts the determined future density based on the headway correction factor. Adjusting the determined future flow based on the speed correction factor and the headway correction factor may include multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor. Adjusting the determined future average speed based on the speed correction factor may include multiplying the determined future average speed by the speed correction factor. Adjusting the determined future density based on the headway correction factor may include dividing the determined future density by the headway correction factor.

[0120] According to some implementations, the server generates a control signal for a CAV based on at least one of the following: the determined future traffic flow, the determined future average speed, and the determined future density. The server transmits the generated control signal to the CAV.

[0121] Figure 12 FIG. 1200 is a flowchart of a method for controlling a vehicle using a multi-vehicle policy selector according to an embodiment of the present disclosure. Method 1200 may be implemented using a server. The server may include a server connected to a vehicle transportation network 220 and / or an electronic communication network 230. The server may include a single computing device or multiple computing devices working together.

[0122] At block 1202, the server receives traffic state information from road sensors, CVs, and CAVs. The traffic state information may include at least one of the location of a vehicle, the speed of the vehicle, the following distance between the vehicle and another vehicle, and the number of vehicles on a road segment. The vehicle may be a non-connected vehicle, a CV, or a CAV. For a non-connected vehicle, the traffic state information may be determined (and transmitted to the server) by at least one of a road sensor, a CV, and a CAV that is close to the non-connected vehicle. The CVs, CAVs, and / or non-connected vehicles may be traveling on a road segment. Alternatively, the CVs, CAVs, and / or non-connected vehicles may include vehicles that are not traveling on a road segment (e.g., a vehicle approaching a road segment or a vehicle that has recently left a road segment).

[0123] At block 1204, the server generates a long-term shared world model (e.g., one of long-term shared world models 306, 814, 906) based on the received traffic state information. The long-term shared world model may use any modeling technique. For example, the long-term shared world model may use statistical modeling, machine learning, or artificial intelligence techniques.

[0124] At block 1206, the server uses a multi-vehicle policy selector (e.g., multi-vehicle policy selector 908) to generate a control signal for controlling a CAV based on the long-term shared world model. The multi-vehicle policy selector uses an optimization for reducing congestion on a road segment to generate the control signal. Each control signal is transmitted to the associated CAV and controls the speed or travel path of the associated CAV. The optimization for reducing congestion on the road includes at least ensuring a minimum threshold following distance between each CAV and the vehicle in front of the CAV.

[0125] Some implementations are described below as numbered examples (Example 1, 2, 3, etc.). These examples are provided only as examples and do not limit other implementations disclosed herein.

[0126] Example 1 is a method for generating a control signal and transmitting the control signal to a vehicle, the method comprising: accessing vehicle data from each of a subset of a plurality of connected vehicles (CVs) on a road section, the vehicle data including at least one of position, speed, and headway; generating a long-term shared world model based on the accessed vehicle data; generating a data structure by applying a traffic flow model to the long-term shared world model, the data structure representing a predicted future speed on the road section by position and time; and transmitting a control signal to a connected autonomous vehicle (CAV) for controlling the operation of the CAV based on the generated data structure.

[0127] In Example 2, the subject matter of Example 1 includes: accessing additional data from a road sensor, the additional data including at least one of vehicle position data, vehicle speed data, and vehicle headway data; and storing the accessed additional data in the long-term shared world model.

[0128] In Example 3, the subject matter of Examples 1 to 2 includes, wherein the vehicle position data, the vehicle speed data, or the vehicle headway data is associated with a non-connected vehicle.

[0129] In Example 4, the subject matter of Examples 1 to 3 includes, wherein the road section is subdivided into a plurality of road segments, and wherein the traffic flow model is based on at least one of: an average vehicle speed in at least one road segment during a time slice, a vehicle density in the at least one road segment during the time slice, and a flow or net flow of vehicles entering or leaving the at least one road segment during the time slice.

[0130] In Example 5, the subject matter of Example 4 includes, wherein the long-term shared world model is used to calculate the average vehicle speed, the vehicle density, the flow, or the net flow.

[0131] In Example 6, the subject matter of Examples 1 to 5 includes, wherein the accessed vehicle data is received from a first vehicle and includes the position, speed, or headway of a second vehicle, wherein the first vehicle is different from the second vehicle.

[0132] In Example 7, the subject matter of Example 6 includes, wherein the second vehicle is traveling immediately in front of the first vehicle, immediately behind the first vehicle, or in a driving lane adjacent to the driving lane of the first vehicle.

[0133] Example 8 is a device for generating a control signal and transmitting the control signal to a vehicle. The device includes: a memory that stores instructions; and a processor configured to execute the stored instructions to: access vehicle data from each of a subset of a plurality of connected vehicles, i.e., a plurality of CVs, on a road section, the vehicle data including at least one of position, speed, and headway; generate a long-term shared world model based on the accessed vehicle data; generate a data structure representing predicted future speeds on the road section by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model; and transmit a control signal to a connected autonomous vehicle, i.e., a CAV, for controlling the operation of the CAV based on the generated data structure.

[0134] In Example 9, the subject matter of Example 8 includes that the processor executes the stored instructions to: access additional data from a road sensor, the additional data including at least one of vehicle position data, vehicle speed data, and vehicle headway data; and store the accessed additional data in the long-term shared world model.

[0135] In Example 10, the subject matter of Examples 8 to 9 includes that the vehicle position data, the vehicle speed data, or the vehicle headway data is associated with a non-connected vehicle.

[0136] In Example 11, the subject matter of Examples 8 to 10 includes that the road section is subdivided into a plurality of road segments, and the traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment during a time slice, the vehicle density in the at least one road segment during the time slice, and the flow or net flow of vehicles entering or leaving the at least one road segment during the time slice.

[0137] In Example 12, the subject matter of Example 11 includes that the average vehicle speed, the vehicle density, the flow, or the net flow is calculated using the long-term shared world model.

[0138] In Example 13, the subject matter of Examples 8 to 12 includes that the accessed vehicle data is received from a first vehicle and includes the position, speed, or headway of a second vehicle, where the first vehicle is different from the second vehicle.

[0139] In Example 14, the subject matter of Example 13 includes, wherein the second vehicle is traveling immediately in front of the first vehicle, immediately behind the first vehicle, or in a driving lane adjacent to the driving lane of the first vehicle.

[0140] Example 15 is a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations including: accessing vehicle data of each connected vehicle (CV) from a subset of a plurality of connected vehicles on a road section, the vehicle data including at least one of position, speed, and headway; generating a long-term shared world model based on the accessed vehicle data; generating a data structure representing predicted future speeds on the road section by position and time by applying a traffic flow model to the long-term shared world model and using the long-term shared world model; and transmitting a control signal for controlling the operation of a connected autonomous vehicle (CAV) based on the generated data structure to the CAV.

[0141] In Example 16, the subject matter of Example 15 includes, wherein the operations further include: accessing additional data from a road sensor, the additional data including at least one of vehicle position data, vehicle speed data, and vehicle headway data; and storing the accessed additional data in the long-term shared world model.

[0142] In Example 17, the subject matter of Examples 15 to 16 includes, wherein the vehicle position data, the vehicle speed data, or the vehicle headway data is associated with a non-connected vehicle.

[0143] In Example 18, the subject matter of Examples 15 to 17 includes, wherein the road section is subdivided into a plurality of road segments, and wherein the traffic flow model is based on at least one of: an average vehicle speed in at least one road segment during a time slice, a vehicle density in the at least one road segment during the time slice, and a flow or net flow of vehicles entering or leaving the at least one road segment during the time slice.

[0144] In Example 19, the subject matter of Example 18 includes, wherein the average vehicle speed, the vehicle density, the flow, or the net flow is calculated using the long-term shared world model.

[0145] In Example 20, the subject matter of Examples 15 to 19 includes, wherein the accessed vehicle data is received from a first vehicle and includes the position, speed, or headway of a second vehicle, wherein the first vehicle is different from the second vehicle.

[0146] Example 21 is a method that includes: receiving, at a control server and from a connected vehicle (CV), speed data representing the speed of the CV and an additional vehicle approaching the CV; calculating a speed correction factor based on the speed data; receiving, at the control server and from the CV, headway data representing the headway between the CV and the additional vehicle approaching the CV; calculating a headway correction factor based on the headway data; using a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; adjusting the determined future flow based on the speed correction factor and the headway correction factor; adjusting the determined future average speed based on the speed correction factor; adjusting the determined future density based on the headway correction factor; generating, at the control server, a control signal for a connected and automated vehicle (CAV) based on at least one of the determined future flow, the determined future average speed, and the determined future density; and transmitting the generated control signal to the CAV.

[0147] In example 22, the subject matter of example 21 includes, wherein the additional vehicle approaching the CV includes at least one of the following: a vehicle in front of the CV in a lane adjacent to the CV, and a vehicle behind the CV in a lane adjacent to the CV.

[0148] In example 23, the subject matter of examples 21 - 22 includes, wherein the control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and wherein the headway correction factor is calculated based on the headway data from the plurality of CVs.

[0149] In example 24, the subject matter of examples 21 - 23 includes, wherein the prediction engine utilizes a long - term shared world model that stores data received from the plurality of CVs and a plurality of road sensors.

[0150] In example 25, the subject matter of examples 21 - 24 includes, wherein adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

[0151] In example 26, the subject matter of examples 21 - 25 includes, wherein adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

[0152] In Example 27, the subject matter of Examples 21 to 26 includes, wherein adjusting the determined future density based on the headway correction factor includes: dividing the determined future density by the headway correction factor.

[0153] Example 28 is an apparatus including: a memory that stores instructions; and a processor configured to execute the stored instructions to: at a control server and receive from a connected vehicle, i.e., a CV, speed data representing the speed of the CV and an additional vehicle approaching the CV; calculate a speed correction factor based on the speed data; at the control server and receive from the CV headway data representing the headway between the CV and the additional vehicle approaching the CV; calculate a headway correction factor based on the headway data; use a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; adjust the determined future flow based on the speed correction factor and the headway correction factor; adjust the determined future average speed based on the speed correction factor; adjust the determined future density based on the headway correction factor; generate at the control server a control signal for a connected automated vehicle, i.e., a CAV, based on at least one of the determined future flow, the determined future average speed, and the determined future density; and transmit the generated control signal to the CAV.

[0154] In Example 29, the subject matter of Example 28 includes, wherein the additional vehicle approaching the CV includes at least one of the following: a vehicle in a lane adjacent to the CV and in front of the CV, and a vehicle in a lane adjacent to the CV and behind the CV.

[0155] In Example 30, the subject matter of Examples 28 to 29 includes, wherein the control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and wherein the headway correction factor is calculated based on the headway data from the plurality of CVs.

[0156] In Example 31, the subject matter of Examples 28 to 30 includes, wherein the prediction engine utilizes a long-term shared world model that stores data received from the plurality of CVs and a plurality of road sensors.

[0157] In Example 32, the subject matter of Examples 28 to 31 includes, wherein adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

[0158] In Example 33, the subject matter of Examples 28 to 32 includes, wherein adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

[0159] In Example 34, the subject matter of Examples 28 to 33 includes, wherein adjusting the determined future density based on the headway correction factor includes: dividing the determined future density by the headway correction factor.

[0160] Example 35 is a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations including: receiving, at a control server and from a networked vehicle, i.e., a CV, speed data representing the speed of the CV and an additional vehicle approaching the CV; calculating a speed correction factor based on the speed data; receiving, at the control server and from the CV, headway data representing the headway between the CV and the additional vehicle approaching the CV; calculating a headway correction factor based on the headway data; using a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; adjusting the determined future flow based on the speed correction factor and the headway correction factor; adjusting the determined future average speed based on the speed correction factor; adjusting the determined future density based on the headway correction factor; generating, at the control server, a control signal for a networked automated vehicle, i.e., a CAV, based on at least one of the determined future flow, the determined future average speed, and the determined future density; and transmitting the generated control signal to the CAV.

[0161] In Example 36, the subject matter of Example 35 includes, wherein the additional vehicle approaching the CV includes at least one of the following: a vehicle in front of the CV in a lane adjacent to the CV, and a vehicle behind the CV in a lane adjacent to the CV.

[0162] In Example 37, the subject matter of Examples 35 to 36 includes, wherein the control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and wherein the headway correction factor is calculated based on the headway data from the plurality of CVs.

[0163] In Example 38, the subject matter of Examples 35 to 37 includes, wherein the prediction engine utilizes a long-term shared world model storing data received from the plurality of CVs and a plurality of road sensors.

[0164] In Example 39, the subject matter of Examples 35 to 38 includes, wherein adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

[0165] In Example 40, the subject matter of Examples 35 to 39 includes, wherein adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

[0166] Example 41 is a method including: receiving traffic state information from road sensors, connected vehicles (CVs), and connected automated vehicles (CAVs); generating a long-term shared world model based on the received traffic state information; and using a multi-vehicle strategy selector to generate control signals for controlling the CAVs based on the long-term shared world model, wherein the multi-vehicle strategy selector uses an optimization for reducing congestion on a road section to generate the control signals, and wherein each control signal controls the speed or travel path of an associated CAV.

[0167] In Example 42, the subject matter of Example 41 includes, wherein the optimization for reducing congestion on the road includes at least ensuring a minimum threshold following distance between each CAV and the vehicle in front of that CAV.

[0168] In Example 43, the subject matter of Examples 41 to 42 includes, wherein the traffic state information includes at least one of the location of a vehicle, the speed of the vehicle, the following distance between the vehicle and other vehicles, and the number of vehicles on the road section.

[0169] In Example 44, the subject matter of Example 43 includes, wherein the vehicle includes a CV or a CAV.

[0170] In Example 45, the subject matter of Examples 43 to 44 includes, wherein the vehicle includes a non-connected vehicle, and wherein one or more of the road sensors are used to determine the traffic state information of the non-connected vehicle.

[0171] In Example 46, the subject matter of Examples 43 to 45 includes, wherein the vehicle includes a non-connected vehicle, and wherein at least one of the CV and the CAV is used to determine the traffic state information of the non-connected vehicle.

[0172] In Example 47, the subject matter of Examples 41 to 46 includes, wherein the CVs, the CAVs, and the non-connected vehicles are traveling on the road section.

[0173] In Example 48, the subject matter of Examples 41 to 47 includes, wherein the CV or the CAV includes at least one vehicle not on the road portion.

[0174] Example 49 is an apparatus, including: a memory that stores instructions; and a processor for executing the stored instructions to: receive traffic state information from a road sensor, a connected vehicle (CV) and a connected automated vehicle (CAV); generate a long-term shared world model based on the received traffic state information; and use a multi-vehicle policy selector to generate a control signal for controlling the CAV based on the long-term shared world model, wherein the multi-vehicle policy selector uses an optimization for reducing congestion on a road portion to generate the control signal, and wherein each control signal controls the speed or the driving path of an associated CAV.

[0175] In Example 50, the subject matter of Example 49 includes, wherein the optimization for reducing congestion on the road includes at least ensuring a minimum threshold following distance between each CAV and the vehicle in front of that CAV.

[0176] In Example 51, the subject matter of Examples 49 to 50 includes, wherein the traffic state information includes at least one of a location of a vehicle, a speed of the vehicle, a following distance between the vehicle and other vehicles, and a number of vehicles on the road portion.

[0177] In Example 52, the subject matter of Example 51 includes, wherein the vehicle includes a CV or a CAV.

[0178] In Example 53, the subject matter of Examples 51 to 52 includes, wherein the vehicle includes a non-connected vehicle, and wherein one or more of the road sensors are used to determine traffic state information of the non-connected vehicle.

[0179] In Example 54, the subject matter of Examples 51 to 53 includes, wherein the vehicle includes a non-connected vehicle, and wherein at least one of the CV and the CAV is used to determine traffic state information of the non-connected vehicle.

[0180] In Example 55, the subject matter of Examples 49 to 54 includes, wherein the CV, the CAV and the non-connected vehicle are traveling on the road portion.

[0181] In Example 56, the subject matter of Examples 49 to 55 includes, wherein the CV or the CAV includes at least one vehicle not on the road portion.

[0182] Example 57 is a non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations including: receiving traffic state information from road sensors, connected vehicles (CVs), and connected automated vehicles (CAVs); generating a long-term shared world model based on the received traffic state information; and using a multi-vehicle policy selector to generate control signals for controlling the CAVs based on the long-term shared world model, wherein the multi-vehicle policy selector uses an optimization for reducing congestion on a road portion to generate the control signals, and wherein each control signal controls the speed or driving path of an associated CAV.

[0183] In example 58, the subject matter of example 57 includes, wherein the optimization for reducing congestion on the road includes at least ensuring a minimum threshold following distance between each CAV and the vehicle in front of that CAV.

[0184] In example 59, the subject matter of examples 57 to 58 includes, wherein the traffic state information includes at least one of the location of a vehicle, the speed of the vehicle, the following distance between the vehicle and other vehicles, and the number of vehicles on the road portion.

[0185] In example 60, the subject matter of example 59 includes, wherein the vehicle includes a CV or a CAV.

[0186] Example 61 is at least one machine-readable medium including instructions that, when executed by a processing circuit, cause the processing circuit to perform operations to implement any one of examples 1 to 60.

[0187] Example 62 is a device including components for implementing any one of examples 1 to 60.

[0188] Example 63 is a system for implementing any one of examples 1 to 60.

[0189] Example 64 is a method for implementing any one of examples 1 to 60.

[0190] As used herein, the term "instruction" may include an indication or expression for performing any method disclosed herein or any one or more arbitrary parts thereof, and may be implemented in hardware, software, or any combination thereof. For example, an instruction may be implemented as information stored in a memory (such as a computer program, etc.), and the instruction may be executed by a processor to perform any one of the various methods, algorithms, aspects, or combinations thereof described herein. A part of an instruction or the instruction itself may be implemented as a dedicated processor or circuit, and the dedicated processor or circuit may include dedicated hardware for executing any one of the methods, algorithms, aspects, or combinations thereof described herein. In some implementations, a part of an instruction may be distributed across multiple processors on a single device or multiple devices, and these devices may communicate directly or across a network (such as a local area network, a wide area network, the Internet, or a combination thereof, etc.).

[0191] As used herein, the terms "example", "embodiment", "implementation", "aspect", "feature", or "element" indicate being used as an example, instance, or illustration. Unless explicitly indicated, 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.

[0192] As used herein, the terms "determine" and "identify" or any variant thereof include selecting, ascertaining, calculating, finding, receiving, determining, establishing, obtaining, or otherwise identifying or determining in any way using one or more of the devices shown and described herein.

[0193] As used herein, unless otherwise specified or clear from the context, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". Additionally, unless otherwise specified or clearly referring to the singular form, the articles "a" and "an" used in this application and the appended claims should generally be understood to mean "one or more than one".

[0194] Furthermore, for simplicity of explanation, although the drawings and descriptions herein may include a sequence or series of steps or stages, the elements of the methods disclosed herein may occur in various orders or in parallel. Additionally, the elements of the methods disclosed herein may occur together with other elements not explicitly presented and described herein. Moreover, not all elements of the methods described herein may be required to implement the methods according to the present invention. Although aspects, features, and elements are described herein in specific combinations, each aspect, feature, or element may be used independently, or may be used in various combinations with other aspects, features, and elements or in various combinations without other aspects, features, and elements.

[0195] For the purpose of enabling an easy understanding of the present invention, the above aspects, examples and implementations are described, but the present invention is not restrictive. In contrast, the present invention covers various modifications and equivalent arrangements included within the scope of the appended claims, which scope should be given the broadest interpretation to cover all such modifications and equivalent structures as are permitted by law.

Claims

1. A method for controlling a connected and automated vehicle, i.e., a CAV, comprising: receiving, at a control server and from a connected vehicle, i.e., a CV, speed data representing the speed of the CV and an additional vehicle approaching the CV; calculating a speed correction factor based on the speed data; receiving, at the control server and from the CV, headway data representing the headway between the CV and the additional vehicle approaching the CV; calculating a headway correction factor based on the headway data; using a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; adjusting the determined future flow based on the speed correction factor and the headway correction factor; adjusting the determined future average speed based on the speed correction factor; adjusting the determined future density based on the headway correction factor; generating, at the control server, a control signal for the CAV based on at least one of the determined future flow, the determined future average speed, and the determined future density; and transmitting the generated control signal to the CAV, wherein the additional vehicle approaching the CV includes at least one of the following: a vehicle in front of the CV in a lane adjacent to the CV, and a vehicle behind the CV in a lane adjacent to the CV.

2. The method according to claim 1, wherein the control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and wherein the headway correction factor is calculated based on the headway data from the plurality of CVs.

3. The method according to claim 1, wherein the prediction engine utilizes a long-term shared world model storing data received from a plurality of CVs including the CV and a plurality of road sensors associated with at least one road used by the plurality of CVs.

4. The method according to claim 1, wherein adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

5. The method according to claim 1, wherein adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

6. The method according to claim 1, wherein adjusting the determined future density based on the headway correction factor includes: dividing the determined future density by the headway correction factor.

7. An apparatus for controlling a connected and automated vehicle, i.e., a CAV, comprising: a memory storing instructions; and a processor for executing the stored instructions to: receive, at a control server and from a connected vehicle, i.e., a CV, speed data representing the speed of the CV and an additional vehicle approaching the CV; Calculate a speed correction factor based on the speed data; At the control server and receive headway data from the CV representing the headway between the CV and the additional vehicle approaching the CV; Calculate a headway correction factor based on the headway data; Use a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; Adjust the determined future flow based on the speed correction factor and the headway correction factor; Adjust the determined future average speed based on the speed correction factor; Adjust the determined future density based on the headway correction factor; Generate a control signal for the CAV at the control server based on at least one of the determined future flow, the determined future average speed, and the determined future density; And Transmit the generated control signal to the CAV, Wherein, the additional vehicle approaching the CV includes at least one of the following: a vehicle in front of the CV in a lane adjacent to the CV, and a vehicle behind the CV in a lane adjacent to the CV.

8. The apparatus according to claim 7, Wherein, The control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and the headway correction factor is calculated based on the headway data from the plurality of CVs.

9. The apparatus according to claim 7, Wherein, The prediction engine utilizes a long-term shared world model that stores data received from a plurality of CVs including the CV and a plurality of road sensors associated with at least one road used by the plurality of CVs.

10. The apparatus according to claim 7, Wherein, Adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

11. The apparatus according to claim 7, Wherein, Adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

12. The apparatus according to claim 7, Wherein, Adjusting the determined future density based on the headway correction factor includes: dividing the determined future density by the headway correction factor.

13. A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations, the operations Include: At a control server and receive speed data from a connected vehicle, i.e., a CV, representing the speed of the CV and an additional vehicle approaching the CV; Calculate a speed correction factor based on the speed data; At the control server and receive headway data from the CV representing the headway between the CV and the additional vehicle approaching the CV; Calculate a headway correction factor based on the headway data; Use a prediction engine at the control server to determine a future flow, a future average speed, and a future density for a segment of a road; Adjust the determined future flow based on the speed correction factor and the headway correction factor; Adjust the determined future average speed based on the speed correction factor; Adjust the determined future density based on the headway correction factor; Generate, at the control server, a control signal for a connected and automated vehicle (CAV) based on at least one of the determined future flow, the determined future average speed, and the determined future density; And Transmit the generated control signal to the CAV, wherein the additional vehicle approaching the CV includes at least one of the following: a vehicle in front of the CV in a lane adjacent to the CV, and a vehicle behind the CV in a lane adjacent to the CV.

14. The computer-readable medium according to claim 13, wherein, the control server receives the speed data and the headway data from a plurality of CVs including the CV, wherein the speed correction factor is calculated based on the speed data from the plurality of CVs, and wherein the headway correction factor is calculated based on the headway data from the plurality of CVs.

15. The computer-readable medium according to claim 13, wherein, the prediction engine utilizes a long-term shared world model storing data received from a plurality of CVs including the CV and a plurality of road sensors associated with at least one road used by the plurality of CVs.

16. The computer-readable medium according to claim 13, wherein, adjusting the determined future flow based on the speed correction factor and the headway correction factor includes: multiplying the determined future flow by the quotient of the speed correction factor and the headway correction factor.

17. The computer-readable medium according to claim 13, wherein, adjusting the determined future average speed based on the speed correction factor includes: multiplying the determined future average speed by the speed correction factor.

18. A computer program product comprising a program for causing a computer to perform the method according to any one of claims 1 to 6.

Images