Long-term shared road model

Abstract

A server accesses vehicle data from each connected vehicle of a subset of the plurality of connected vehicles (CVs) on the road segment, the vehicle data including at least one of position, speed, or following distance. The server generates a long-term shared world model based on the accessed vehicle data. The server generates a data structure representing future predicted speeds of the road segment by position and time using the long-term shared world model by applying a traffic flow model to the long-term shared world model. The server transmits a control signal to a connected autonomous vehicle (CAV) based on the generated data structure to control operation of the connected autonomous vehicle.

Description

[Technical Field]

[0001] This disclosure generally relates to connected vehicles and connected autonomous vehicles, and more specifically to the generation and use of long-term shared world models of roads for the operation of connected autonomous vehicles. [Background technology]

[0002] Traffic congestion has high costs, such as lost human time, excessive carbon emissions, and an increased likelihood of vehicle accidents. The proportion of connected vehicles (CVs) that can transmit data via a network and connected autonomous vehicles (CAVs) that can transmit data and receive control signals via a network is increasing among vehicles on the road. [Overview of the Initiative]

[0003] This specification discloses aspects, features, elements, implementations, and embodiments of using belief state determination for real-time decision-making while a vehicle is traveling through a vehicle traffic network.

[0004] Aspects of the disclosed embodiments include a method for generating and transmitting control signals to a vehicle. This method includes accessing vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including at least one of location, speed, or distance between vehicles. This method includes generating a long-term shared world model based on the accessed vehicle data. This method includes using the long-term shared world model to generate a data structure representing predicted future speeds of a road section by location and time, by applying a traffic flow model to the long-term shared world model. This method includes transmitting control signals to a connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle, based on the generated data structure.

[0005] An aspect of the disclosed embodiment is a device for generating and transmitting control signals to a vehicle. The device includes a processor and a memory, the memory for storing instructions. The processor executes instructions to access vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including at least one of location, speed, or distance between vehicles. Based on the accessed vehicle data, the processor executes instructions to generate a long-running shared world model. The processor executes instructions to use the long-running shared world model to generate a data structure representing future predicted speeds of the road section by location and time, by applying a traffic flow model to the long-running shared world model. Based on the generated data structure, the processor executes instructions to transmit control signals to a connected autonomous vehicle (CAV) for controlling the operation of the connected autonomous vehicle.

[0006] One aspect of the disclosed embodiments is a computer-readable medium for generating and transmitting control signals to a vehicle. The computer-readable medium stores instructions. The instructions include codes for accessing vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including at least one of position, speed, or distance between vehicles. The instruction includes code that generates a long-term shared world model based on accessed vehicle data. The instruction includes code that uses the long-term shared world model to generate a data structure that represents the predicted future speed of a road section by location and time by applying a traffic flow model to the long-term shared world model. The instruction includes code that transmits control signals to a connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle, based on the generated data structure.

[0007] The following describes in further detail variations of these and other aspects, features, elements, implementations and embodiments of the methods, apparatus, procedures and algorithms disclosed herein. [Brief explanation of the drawing]

[0008] The various aspects disclosed in this specification will become more apparent by reference to the examples provided in the following description and drawings. Where the same reference numbers refer to the same elements.

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

[0010] [Figure 2] It is a diagram showing an example of a part of a vehicle traffic and communication system in which the aspects, features, and elements disclosed in this specification can be implemented.

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

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

[0013] [Figure 5] It shows a flow graph over space and time according to an embodiment of the present disclosure.

[0014] [Figure 6] It shows values of speed and inter-vehicle distance measured for a probe vehicle according to an embodiment of the present disclosure.

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

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

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

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

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

[0020] [Figure 12] This is a flowchart illustrating a method for controlling vehicles using a multiple vehicle policy selector according to an embodiment of the present disclosure. [Modes for carrying out the invention]

[0021] As mentioned above, traffic congestion has high costs, such as lost human time, excessive carbon emissions, and an increased likelihood of vehicle accidents. The proportion of connected vehicles (CVs) that can transmit data via a network and connected autonomous vehicles (CAVs) that can both transmit data and receive control signals via a network is increasing among vehicles on the road. Technologies that utilize CV or CAV technology are desirable in some cases to reduce traffic congestion.

[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 vehicle conduits (CVs) in a section of road. The vehicle data may be accessed from road sensors. The vehicle data may include the position of the vehicle or other vehicle providing the data, the speed of the vehicle or other vehicle providing the data, and / or the distance the vehicle or other vehicle is following. The vehicle control server stores the accessed vehicle data in a long-term shared world model. The vehicle control server uses the long-term shared world model to generate a data structure that represents the predicted future speed of the road section by position and time by applying a traffic flow model to the long-term shared world model. The traffic flow model may be an artificial intelligence model trained using at least one of, for example, supervised learning, unsupervised learning, reinforcement learning, or online learning. Based on the generated data structure, the vehicle control server sends control signals to the CAV to control the operation of the CAV.

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

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

[0025] As used herein, a road section may include a continuous portion of a road (for example, a roadway that extends for 1 to 2 kilometers). A road section may be subdivided into multiple road segments. For example, a 1-kilometer road section may be divided into 10 road segments, each 100 meters long, without any overlap or omissions.

[0026] It should be noted that all CAVs are CVs. However, a vehicle may be a CV but not a CAV. For example, a vehicle operated by a human driver who can transmit data over a network is a CV but not a CAV. In some implementations, with appropriate permission, CV technology may be implemented by a computer device (e.g., a mobile phone) installed in the vehicle. For example, the computer device may determine the vehicle's speed (e.g., using a built-in global positioning system (GPS) and a built-in clock) and transmit the vehicle's speed over a network.

[0027] Figure 1 shows an example of a vehicle in which embodiments, features, and elements disclosed herein may be implemented. As shown in the figure, the vehicle 100 includes a chassis 110, a powertrain 120, a controller 130, and wheels 140. For simplicity, the vehicle 100 is shown to include four wheels 140, but one or more of any other propulsion devices, such as a propeller or tread, may be used. In Figure 1, the lines interconnecting elements such as the powertrain 120, the controller 130, and the wheels 140 indicate that information, such as data or control signals, force, such as power or torque, or both, may be transmitted between the elements. For example, the controller 130 may receive power from the powertrain 120 and communicate with the powertrain 120, the wheels 140, or both to control the vehicle 100, which may include accelerating, decelerating, steering, or otherwise controlling the vehicle 100.

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

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

[0030] The transmission 122 may receive energy such as kinetic energy from the power supply 121 and may send energy to the wheels 140 to provide driving force. The transmission 122 may be controlled by the controller 130, the actuator 124, or both. The steering system 123 may be controlled by the controller 130, the actuator 124, or both and may control the wheels 140 to steer the vehicle. The actuator 124 may receive signals from the controller 130 and may actuate or control the power supply 121, the transmission 122, the steering system 123, or any combination thereof to operate the vehicle 100.

[0031] As shown in the figure, the controller 130 may include a positioning device 131, an electronic communication device 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 device, any one or more elements of the controller 130 may be incorporated into any number of separate physical devices. For example, the user interface 135 and the processor 133 may be incorporated into a first physical device, and the memory 134 may be incorporated into a second physical device. Although not shown in Figure 1, the controller 130 may include a power supply 1210 such as a battery. Although shown as individual elements, the positioning device 131, the electronic communication device 132, the processor 133, the memory 134, the user interface 135, the sensor 136, the electronic communication interface 137, or any combination thereof may be incorporated into one or more electronic devices, circuits, or chips.

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

[0033] Memory 134 may include any tangible, non-temporary, computer-usable or computer-readable medium that is used by or connected to processor 133 and capable of holding, storing, transmitting or transporting machine-readable instructions or any information associated therewith. Memory 134 may include, for example, one or more semiconductor drives, one or more memory cards, one or more removable media, one or more read-only memories, one or more random-access memories, one or more disks including hard disks, floppy disks, optical disks, magnetic or optical cards, or any type of non-temporary 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, or any other wired or wireless device capable of interfacering with a wired or wireless electronic communication medium 150, as shown in the figure. Although Figure 1 shows a communication interface 137 that communicates over a single communication link, the communication interface may be configured to communicate over multiple communication links. Although Figure 1 shows a single communication interface 137, the vehicle may include any number of communication interfaces.

[0035] The communication device 132 may be configured to transmit or receive signals via a wired or wireless electronic communication medium 150, such as a communication interface 137. Although not explicitly shown in Figure 1, the communication device 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. Figure 1 shows a single communication device 132 and a single communication interface 137, but any number of communication devices and any number of communication interfaces may be used. In some embodiments, the communication device 132 may include a narrow-range communication (DSRC) device, an onboard unit (OBU), or a combination thereof.

[0036] The positioning device 131 may determine geographic information of the vehicle 100, such as its longitude, latitude, altitude, direction of travel, or speed. For example, the positioning device may include a Global Positioning System (GPS) device such as a Wide Area Augmentation System (WAAS) compatible National Marine Electronics Association (NMEA) device, a radio triangulation device, or a combination thereof. The positioning device 131 may be used to obtain information representing, for example, the current orientation of the vehicle 100, the current location of the vehicle 100 in two or three dimensions, the current angular direction of the vehicle 100, or a combination thereof.

[0037] The user interface 135 may include any device capable of interfacing with a person, such as a virtual or physical keypad, contact pad, display, touch display, head-up display, virtual display, augmented reality display, haptic display, feature tracking device such as an eye-tracking device, speaker, microphone, video camera, sensor, printer, or any combination thereof. The user interface 135 may be operably coupled with the processor 133 or any other element of the controller 130, as shown in the figure. Although shown as a single device, the user interface 135 may include one or more physical devices. For example, the user interface 135 may include an audio interface for voice 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 devices, multiple defining parts within a single physical device, or a combination thereof.

[0038] Sensor 136 may include one or more sensors, such as an array of sensors, that can operate to provide information that can be used to control the vehicle. Sensor 136 may provide information about the current operating characteristics of the vehicle 100. Sensor 136 may include, for example, a speed sensor, an acceleration sensor, a steering angle sensor, a traction-related sensor, a braking-related sensor, a steering wheel position sensor, an eye-tracking sensor, a seating position sensor, or any sensor or combination of sensors that can operate to report information about any aspect of the current dynamic situation of the vehicle 100.

[0039] Sensor 136 may include one or more sensors capable of acquiring information about the physical environment surrounding the vehicle 100. For example, one or more sensors may detect road features and shapes such as lanes, and obstacles such as fixed obstacles, vehicles, and pedestrians. Sensor 136 may be one or more known or later developed video cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of in-vehicle environment sensing device, or a combination thereof. In some embodiments, sensor 136 and positioning device 131 may be a combined device.

[0040] Although not shown otherwise, the vehicle 100 may include a track controller. For example, controller 130 may include a track controller. The track controller may be able to acquire information describing the current state of the vehicle 100 and the planned path for the vehicle 100, and based on this information, determine and optimize the track for the vehicle 100. In some embodiments, the track controller may output a signal that can be operated to control the vehicle 100 so that it follows the track determined by the track controller. For example, the output of the track controller may be an optimized track that can be supplied to the powertrain 120, the wheels 140, or both. In some embodiments, the optimized track may be a set of control inputs, such as steering angles, where each steering angle corresponds to a single point in time or position. In some embodiments, the optimized track may be one or more paths, lines, curves, or a combination thereof.

[0041] One or more wheels 140 may be steered wheels that can pivot to a steering angle under the control of the steering device 123, propelled wheels that can be given torque to propel the vehicle 100 under the control of the transmission 122, or steered and propelled wheels that can steer and propel the vehicle 100.

[0042] The vehicle may include devices or elements not explicitly shown in Figure 1, such as an enclosure, a Bluetooth® module, a frequency modulation (FM) radio device, a near-field communication (NFC) module, a liquid crystal display (LCD) display device, an organic light-emitting diode (OLED) display device, a speaker, or any combination thereof.

[0043] Vehicle 100 may be an autonomous vehicle that is autonomously controlled without direct human intervention to move within a portion of a traffic network. Although not separately shown in Figure 1, the autonomous vehicle may include an autonomous vehicle control system capable of routing, navigating, and controlling the autonomous vehicle. The autonomous vehicle control system may be integrated with other devices in the vehicle. For example, controller 130 may include an autonomous vehicle control system. The teachings herein are equally applicable to semi-autonomous vehicles.

[0044] The autonomous vehicle control system may control or operate the vehicle 100 to move through a portion of the traffic network according to the current vehicle operation parameters. The autonomous vehicle control system may control or operate the vehicle 100 to perform defined actions or maneuvers, such as parking the vehicle. The autonomous vehicle control system may 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, traffic network data representing the traffic network, or a combination thereof, and may control or operate the vehicle 100 to move through the traffic network according to the route. For example, the autonomous vehicle control system may output the travel route to a trajectory controller, and the trajectory controller may operate the vehicle 100 to move from the starting point to the destination using the generated route.

[0045] Figure 2 is an illustrative diagram of some of the vehicle traffic and communication systems in which embodiments, features, and elements disclosed herein may be implemented. The vehicle traffic and communication system 200 may include one or more vehicles 210 / 211, such as the vehicle 100 shown in Figure 1, which may travel on one or more parts of one or more vehicle traffic networks 220 and communicate via one or more electronic communication networks 230. Although not explicitly shown in Figure 2, vehicles may travel in areas not explicitly or completely included in the vehicle traffic network, such as off-road areas.

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

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

[0048] Vehicles 210 / 211 may communicate with other vehicles 210 / 2110. For example, a host or target vehicle (HV) 210 may receive one or more autonomous vehicle-to-vehicle messages, such as a basic safety message (BSM), from a remote or target vehicle (RV) 211 via a direct communication link 237 or via the network 230. For example, a remote vehicle 211 may broadcast a message to a host vehicle within a defined broadcast range, such as 300 meters. In some embodiments, the host vehicle 210 may receive messages via a third party, such as a signal repeater (not shown) or another remote vehicle (not shown). Vehicles 210 / 211 may periodically transmit one or more autonomous vehicle-to-vehicle messages based on a defined interval, such as 100 milliseconds.

[0049] Automatic vehicle-to-vehicle messages may include vehicle identification information, geospatial state information such as longitude, latitude, or altitude information, geospatial position accuracy information, vehicle acceleration information, yaw rate information, speed information, vehicle orientation information, braking system status information, throttle information, steering angle information, or vehicle path information, or vehicle operation 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 the transmitting vehicle status. For example, transmission status information may indicate whether the transmitting vehicle's transmission is in neutral, parked, forward, or reverse.

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

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

[0052] The electronic communication network 230 may be any type of network configured to provide voice, data, or any other type of electronic communication device. For example, the 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. The electronic communication network 230 may use communication protocols such as the Transmission Control Protocol (TCP), User Datagram Protocol (UDP), Internet Protocol (IP), Real-time Transport Protocol (RTP), Hypertext Transport Protocol (HTTP), or a combination thereof. Although shown as a single device in Figure 2, the electronic communication network may include any number of interconnected elements.

[0053] Vehicle 210 may identify part or state of the vehicle traffic network 220. For example, vehicle 210 may include one or more on-board sensors, such as the sensor 136 shown in Figure 1, which may include a speed sensor, wheel speed sensor, camera, gyroscope, optical sensor, laser sensor, radar sensor, acoustic sensor, or any other sensor or device, or combination thereof, capable of determining or identifying part or state of the vehicle traffic network 220. Sensor data may include lane data, remote vehicle position data, or both.

[0054] The vehicle 210 may move through one or more parts of one or more vehicle traffic networks 220 using information transmitted via a network 230, such as information representing the traffic network 220, one or more onboard sensors, or a combination thereof.

[0055] For simplicity, Figure 2 shows two vehicles 210 and 211, one vehicle traffic network 220, one electronic communication network 230, and one communication network 240, but any number of networks or computer devices may be used. The vehicle traffic and communication system 200 may include devices, units, or elements not shown in Figure 2. Although vehicle 210 is shown as a single device, a vehicle may include any number of interconnecting elements.

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

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

[0058] The vehicle traffic network 220 shows only passable areas (e.g., roads), but the vehicle traffic network may also include one or more impassable areas such as buildings, one or more partially passable areas such as parking areas or pedestrian walkways, or a combination thereof. The vehicle traffic network 220 may include one or more interchanges between one or more passable or partially passable areas. Parts of the vehicle traffic network 220, such as roads, may include one or more lanes and may be associated with one or more directions of travel.

[0059] A vehicle traffic network or a portion thereof may be represented as vehicle traffic network data. For example, vehicle traffic network data may be represented as a hierarchy of elements such as markup language elements, which may be stored in a database or file. For simplicity, the drawings in this specification show vehicle traffic network data representing a portion of a vehicle traffic network as a diagram or map. However, vehicle traffic network data may be represented in any computer-readable format capable of representing a vehicle traffic network or a portion thereof. Vehicle traffic network data may include information such as direction of travel, speed limit information, toll booth information, gradient information such as incline or angle information, surface material information, aesthetic information, defined hazard information, or a combination thereof.

[0060] Parts or combinations of parts of the vehicle traffic network 220 may be identified as specific locations or destinations. For example, vehicle traffic network data may identify a building as a specific location or destination. Specific locations or destinations may be identified using individual, uniquely identifiable geographic locations. For example, the vehicle traffic network 220 may include defined locations such as a location address, address, vehicle traffic network address, GPS address, or a combination thereof, relating to a destination.

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

[0062] As shown in the figure, a connected vehicle (CV) 302 transmits vehicle data 304 to a long-term shared world model 306. Although a single CV 302 is shown, 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 the following: location data, speed data, inter-vehicle distance (e.g., follow distance) data, etc. The vehicle data 304 may be related to the CV or other vehicles in close proximity to the CV. Although the vehicle data 304 is shown to be transmitted from 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 may store historical traffic speed, congestion, and / or roadway data for multiple road segments and may be used to predict future traffic speed, congestion, and / or roadway data for all or part of multiple road segments. As shown in the figure, the prediction engine 308 accesses the long-term shared world model 306 to predict future traffic speeds, congestion, and / or roadway data for road segments. The predictions are stored in the prediction data structure 310. Control signals 312 are generated based on the prediction data structure 310 and transmitted to the connected autonomous vehicle (CAV) 314. The control signals 312 control the speed or travel path of the CAV 314.

[0063] Location data may represent the geographical location of the vehicle. For example, location data may indicate the vehicle's latitude and longitude, its address, or another identifier for its geographical location. Location data may be obtained in the vehicle using road sensors, Global Positioning System (GPS) technology, and / or cellular tower triangulation. Speed ​​data represents the vehicle's speed and direction of travel. Speed ​​data may include measurements in units of speed (e.g., kilometers per hour) and direction (e.g., n degrees north latitude, where n is a number). Following distance data represents the distance between the front end of the vehicle and the front end (or rear end) of another vehicle that this vehicle is following. Following distance data may be measured in units of distance (e.g., meters).

[0064] CV302 and / or CAV314 may correspond to one or more of vehicles 100, 210, and 211. The long-term shared world model 306, the prediction engine 308, and / or the prediction data structure 310 may be implemented using software and / or hardware residing on a server connected to the vehicle traffic network 220 and / or the electronic communication network 230. For example, the long-term shared world model 306, the prediction engine 308, and / or the prediction data structure 310 may be implemented using software and / or hardware residing on a 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 uses the Long-Term Shared World Model 306 to generate a Prediction Data Structure 310, which represents future predicted speeds on road segments by location and time by applying a traffic flow model to the Long-Term Shared World Model 306. The traffic flow model is based on at least one of the following: average vehicle speed in at least one road segment within a time slice, vehicle density in at least one road segment within the time slice, or traffic flow or net traffic flow of vehicles entering and leaving at least one road segment within the time slice. Control signals 312 are generated based on the Prediction Data Structure 310 and transmitted to the CAV 314 to control its operation (e.g., speed or travel path). The term “time slice” may include, in particular, a continuous period, for example, the period from 4:00 PM to 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, vehicle 402 provides vehicle data (e.g., GPS data) to transfer engine 404. Transfer engine 404 transfers vehicle data 406 to localization engine 408. Localization engine 408 calculates the vehicle's position, speed, and inter-vehicle distance 410 and provides the position, speed, and inter-vehicle distance 410 to estimation engine 412. Estimation engine 412 estimates flow rate, density, and speed 414 and provides this data to transfer engine 404 and vehicle 402 to control the vehicle (e.g., by an autonomous driving engine or a human driver).

[0067] Some implementations relate to reducing traffic congestion. The long-term shared world model 306,400 may include a traffic state estimator that collects and aggregates data from probe vehicles across the network to generate significant macroscopic predictions of traffic conditions and changes. This information is maintained in a database (or other data storage device) and provided to control policies at a later stage to help improve decision-making and coordination by CVs and CAVs.

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

[0069] The localization engine 408 extracts and processes relevant information from the vehicle data 406. The vehicle data 406 may be collected from a shared data repository. The localization engine 408 may perform a filtering operation to reduce noise. The information collected by the localization engine 408 for each vehicle i at time t may include the information shown in Table 1. [Table 1] x i (t): Position of vehicle i (from a certain fixed reference point) v i (t): Speed of vehicle i h i (t): Distance between vehicle i and the vehicle preceding vehicle i (between front bumpers) v i,lead (t): Speed of the leading vehicle in the same lane as vehicle i v L i,lead (t): Speed of the leading vehicle in the left lane of vehicle i h L i,lead (t): Distance between vehicle i and the leading vehicle in the left lane of vehicle i v L i,follow (t): Speed of the following vehicle in the left lane of vehicle i h L i,follow (t): Distance between vehicle i and the following vehicle in the left lane of vehicle i v R i,lead (t): Speed of the leading vehicle in the right lane of vehicle i h R i,lead (t): Distance between vehicle i and the leading vehicle in the right lane of vehicle i v R i,follow (t): Speed of the following vehicle in the right lane of vehicle i h R i,follow (t): Distance between vehicle i and the following vehicle in the right lane of vehicle i

[0070] The estimation engine 412 collects information (e.g., position, speed, and inter-vehicle distance 410) stored by the transfer engine 404 and modified by the localization engine 408, and uses this information to approximate the macroscopic state of traffic in different road segments. Specifically, consider a road segment of length L and a total time T seconds, where N and M are integers. The estimation engine 412 measures time and space in N steps J of length Δt = T / N. j (0<=j<=N) and M-space cell I of length Δx=L / M i The data is discretized into (0 <= i <= M) and the metrics shown in Table 2 are calculated for each spatiotemporal domain. [Table 2] v i j :Average vehicle speed on road segment i over time interval j ρ i j Vehicle density of road segment i over time interval j q i j : Vehicle flow from road segment i to road segment i+1 over a time interval j

[0071] The information calculated by the estimation engine 412, namely flow rate, density, and speed 414, is provided to the transfer engine 404 for storage in a data repository or for use by a vehicle (e.g., vehicle 402) communicating with the transfer engine 404.

[0072] One advantage of Architecture 400 is the flexibility provided by the modularity of its different subcomponents. This allows for the generalization of various features to a large number of different vehicles and estimation algorithms in several implementations. For example, when multiple vehicles with different sensing / communication specifications are used, errors associated with each vehicle type can be adjusted by using a different localization module for each vehicle type, while keeping all other modules fixed. Furthermore, if market penetration effects or other specifications require the use of a different estimated traffic state estimation algorithm, this can simply be substituted without changing anything else.

[0073] The data repository within the transport engine 404 may be a database (e.g., SQL, MongoDB, etc.) or another data storage unit. The type of information shared among vehicles (e.g., vehicle 402) accessing the transport engine 404 may depend on onboard sensors. The localization engine 408 may use different filtering techniques to access and process historical data. The estimation engine 412 may utilize different traffic state estimators. For example, a statistical or data-driven estimator may be used to produce reasonably granular results when data below a threshold amount is available. A model-type estimator (e.g., an AI or ML estimator) may be used to produce more granular estimations when data above a threshold amount is available.

[0074] To enable CVs and CAVs to cooperate efficiently and to regulate traffic flow, a long-term shared world model 306 (or other shared models of traffic conditions) may be used. Traffic condition estimation algorithms can provide methods for defining such models. In some techniques, local vehicle sensor data, i.e., vehicle position, inter-vehicle distance, and speed, are transformed into quantities that can define shared conditions between vehicles in the spatial and temporal domains (e.g., one or more road sections). Some techniques rely on small amounts of data, particularly due to limitations in sensing infrastructure. With the rise of vehicle automation, the quality of onboard vehicle sensing has improved significantly, producing vehicles that can recognize not only what is in front of them but also what is happening in adjacent lanes. In some implementations, procedures may be defined to leverage improvements generated in the sensing infrastructure and use these additional observations to improve the quality of existing traffic condition estimation methods.

[0075] Some implementations relate to the reproduction of Edie flow from the perspective of probe vehicles. However, the estimators used (to reproduce Edie flow) may be prone to errors. Estimation errors can arise from bias in the sample (probe) vehicle data. In some situations, some vehicles may travel faster or slower (or with longer or shorter intervals) than others, and additional corrections may be used to produce more accurate results. In some implementations, r1 is a speed correction factor, and r2 is a spatiotemporal domain A corresponding to the spatial interval i and time interval j. i j This may be a vehicle-to-vehicle distance correction coefficient for a road section, road segment, multiple road sections, or multiple road segments. The relationship between the true traffic condition and the estimated traffic condition may be as follows:

number

[0076] In the above equation, q i j and q_hat ij These are the true mean flow rate and the predicted mean flow rate at spatial interval i and time interval j, respectively. i j and v_hat i j ρ represents the true average velocity and the predicted average velocity at spatial interval i and time interval j, respectively. i j and ρ_hat i j These are the true average density and the predicted average density at spatial interval i and time interval j, respectively.

[0077] Some implementations involve defining the values ​​of r1 and r2. The true values ​​of r1 and r2 may depend on global state information, which may be unknown. To estimate the values ​​of r1 and r2, some implementations rely not only on data from the probe vehicle's lane but also on data from lanes adjacent to the probe vehicle's lane. Some implementations collect speed (e.g., distance divided by time) and inter-vehicle distance (e.g., distance) data from adjacent lanes and the probe lane. For example, the data shown in Table 1 may be collected. After the data has been collected, r1 and r2 may be calculated as follows:

number

[0078] In the above equation, t i,j n Vehicle n is in area A i j This is the time step spent. The addition of 0.5 in the speed correction is designed to balance the influence of each lane on the cumulative estimate. Note that whenever only a subset of the above data is available, the value is ignored and the smaller subset is averaged.

[0079] Figure 5 shows flow graphs over space and time. Graph 502 shows the spatiotemporal domain, and Graph 504 shows the data used in the prediction techniques disclosed herein. Figure 6 shows the speed and inter-vehicle distance values ​​600 measured for the probe vehicle 602.

[0080] This correction can be important in many cases, as variations in driving behavior between lanes can reduce the accuracy of the generated estimates. Examples of situations where such concerns may arise include the presence of trucks (e.g., larger and slower than passenger cars) downstream in one lane, or the presence of other high-speed lanes not used by high-occupancy vehicles (HOVs) or probe vehicles. By recognizing and correcting for the behavior of vehicles in adjacent lanes, some implementations can mitigate the impact of lane-level features on the returned estimates.

[0081] In some implementations, the correction coefficients r1 and r2 may be calculated from local real-time sensor data. Some implementations include a Bayesian prior distribution that models the distribution of lane-level dynamics to improve accuracy when sparse data is present. In some implementations, the correction values ​​for flow rate and density are expressed as a function of change in average speed. This is relevant when neither a preceding nor following vehicle in an adjacent lane is found, thereby providing a quantification of the inter-vehicle distance. For example, defining the form of the flow rate-density relationship using a triangular base diagram and adjusting the model of this relationship may help generate approximations of the correction coefficients r1 and r2.

[0082] Figure 7 is a data flow diagram of the traffic condition determination 700 according to an embodiment of the present disclosure. As shown in Figure 7, CV702 (corresponding to, for example, CV302) provides speed data 704 and inter-vehicle distance data 706 (for example, all or part of the speed data and inter-vehicle distance data listed in Table 1) to the vehicle control server 708. The vehicle control server 708 calculates a speed correction coefficient 710(r1) and an inter-vehicle distance correction coefficient 712(r2). The prediction engine 714 (corresponding to, for example, prediction engine 308) accesses the speed data 704 and inter-vehicle distance data 706 and predicts future flow rate 716, future average speed 718, and future density 720 for at least one road segment or section of road (for example, using artificial intelligence, machine learning, and / or mathematical formulas). The predicted future flow rate 716, future average speed 718, and future density 720, along with the calculated speed correction coefficient 710 and inter-vehicle distance correction coefficient 712, are provided to the adjustment engine 722 of the vehicle control server 708. The adjustment engine adjusts the predicted future flow rate 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 the CAV728 (e.g., corresponding to CAV314) and provides the control signal 726 to the CAV728. In response to the control signal 726, the CAV728 adjusts its operation (e.g., speed or travel path).

[0083] Traffic congestion increases fuel consumption and greenhouse gas emissions, and reduces driving comfort and safety. Technologies that reduce traffic congestion using connected vehicles and / or automated vehicle technologies may be desirable.

[0084] In some implementations, some vehicles are connected vehicles (vehicles that can share information to the cloud but are manually driven by a human driver), some are connected autonomous vehicles (vehicles that may share information and are automatically controlled by the cloud), and some are unconnected and non-automated (not connected to the cloud) human-driven vehicles. CVs and CAVs may share traffic-related measurements from onboard sensors, including vehicle speed, acceleration, relative distance, and relative velocity, with surrounding vehicles and others via the cloud.

[0085] Figure 8 shows an example of a vehicle communication and control architecture 800. As shown, the vehicle communication and control architecture 800 includes an unconnected vehicle 802, a CV 804, a CAV 806, and a roadside unit (RSU) 808 in the road section 810. The unconnected vehicle 802 may be a legacy vehicle operated by a human driver and may not be able to transmit traffic condition information (e.g., speed information, route information, or information obtained by onboard sensors) to the network. The RSU 808 may include a router for sending and receiving network communications with the CV 804 and CAV 806. The RSU 808 may include road sensors (e.g., a camera system, a radar system, or a lidar system). As shown, the CV 804, CAV 806, and RSU 808 communicate state and recognition data 812 to generate a Long-Term Shared World Model 814. The Long-Term Shared World Model 814 may correspond to a Long-Term Shared World Model 306. As shown in the figure, the Long-Term Shared World Model 814 is accessed by the Cooperative Multiple Vehicle Policy Selector 816. The Cooperative Multiple Vehicle Policy Selector 816 transmits control signals 818 to the CAV 806. The control signals 818 are adjusted and optimized to achieve traffic control objectives such as reducing traffic inflow 820 or reducing stop-go traffic 822 in various parts of the road section 810. As shown in the figure, the Long-Term Shared World Model 814 and the Cooperative Multiple Vehicle Policy Selector 816 are stored in the network 824, for example, in a server or data repository connected to the network 824.

[0086] According to some implementations, via wireless communication, the engine of network 824 (e.g., Long-Term Shared World Model 814 or Cooperative Multiple Vehicle Policy Selector 816) sends and receives information with CV804 and / or CAV806. Once the state and recognition data 812 from CV804 and / or CAV806 has been processed, a control signal 818 is sent to CAV806.

[0087] The Long-Term Shared World Model 814 is a real-time, accurate traffic state model based on state and recognition data 812 from CV804 and CAV806. The Long-Term Shared World Model 814 is used to provide the Cooperative Multi-Vehicle Policy Selector 816 with the information necessary to generate control signals 818 for the CAV806. The data from the Long-Term Shared World Model 814 may be used in two ways: to share traffic states directly with the CAV806s to enable each CAV806 to adapt to the traffic state using its onboard computer, or to cause the Cooperative Multi-Vehicle Policy Selector 816 to determine the optimal action for each CAV806 based on macroeconomic metrics (e.g., network throughput, traffic speed fluctuations, greenhouse gas emissions, etc.). The optimal action for each CAV806 is communicated from the Cooperative Multi-Vehicle Policy Selector 816 to the relevant CAV806 using control signals 818. By adjusting the driving behavior of the CAV806s, traffic flow may be more effectively controlled and optimized, reducing traffic inflow in certain areas of the road and / or reducing stop-and-go traffic.

[0088] Figure 9 is a data flow diagram for vehicle communication and control 900 according to an embodiment of the present disclosure. As shown, CV902 generates traffic state information 904 and provides the traffic state information 904 to the Long-Term Shared World Model 906. CV902 may correspond to one of CV804 or one of CAV806. The traffic state information 904 may correspond to state and recognition data 812, or other information generated by CV902 or available in the CV. The Long-Term Shared World Model 906 may correspond to at least one of the Long-Term Shared World Models 306, 814.

[0089] As shown in the diagram, the long-term shared world model 906 communicates data to a multi-vehicle policy selector 908 (e.g., a cooperative multi-vehicle policy selector 816). The multi-vehicle policy selector 908 uses the optimization engine 910 to optimize traffic conditions (e.g., reduce traffic inflow into congested areas and / or reduce stop-and-go traffic) in order to generate a control signal 912 for a CAV 914 (e.g., one of several CAVs 806) (e.g., from among several control signals 818). 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 travel path) based on the control signal 912.

[0090] Figure 10 is a flowchart of a method 1000 for operating vehicles using a long-term shared world model according to an embodiment of the present disclosure. Method 1000 may be implemented using a server. The server may include a server connected to a vehicle traffic network 220 and / or an electronic communications network 230. The server may include a single computer device or multiple computer devices working together.

[0091] In block 1002, the server accesses vehicle data from each CV in a subset of multiple CVs in the road section. The vehicle data may include at least one of position, speed, or distance between vehicles. The server may access additional data from road sensors. The additional data may include vehicle position data, vehicle speed data, and / or distance between vehicles data. The additional data may be sensed by the road sensors using computer vision, radar, and / or lidar. The vehicle data may be associated with the CV itself, or with another vehicle (e.g., another CV or an unconnected vehicle) in close proximity to the CV whose data is accessible by the CV's onboard sensors. The additional data may be associated with either the CV or an unconnected vehicle.

[0092] In block 1004, the server generates a long-running shared world model (e.g., one of the long-running 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 distance between vehicles of a second vehicle. The first vehicle is different from the second vehicle. For example, the second vehicle may be traveling directly in front of the first vehicle, directly behind the first vehicle, or in a lane adjacent to the lane of the first vehicle.

[0093] In block 1006, the server uses the Long-Term Shared World model to generate a data structure that represents the predicted future speed of road segments by location 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 a road segment and the other dimension represents a time slice. The values ​​in each cell of the two-dimensional array may represent the predicted future speed for the corresponding road segment and time slice.

[0094] According to some implementations, a road section is subdivided into multiple road segments. The traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment within a time slice, the vehicle density in at least one road segment within the time slice, or the flow rate or net flow rate of vehicles entering and leaving at least one road segment within the time slice. The average vehicle speed, vehicle density, flow rate, or net flow rate may be calculated using a long-running shared world model.

[0095] In block 1008, the server sends a control signal to the CAV to control its operation 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 travel path based on the control signal.

[0096] 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 a vehicle traffic network 220 and / or an electronic communication network 230. The server may include a single computer device or multiple computer devices operating together.

[0097] In block 1102, the server receives speed data from the CV representing the speeds of the CV and any additional vehicles adjacent to the CV. The server calculates a speed correction coefficient based on the speed data, for example, using equation 4 described above. Additional vehicles adjacent to the CAV may include vehicles in front of the CV in a lane adjacent to the CV, or vehicles behind the CV in a lane adjacent to the CV.

[0098] In block 1104, the server receives inter-vehicle distance data from the CV, representing the distance between the CV and any additional vehicles adjacent to it. The server calculates an inter-vehicle distance correction coefficient based on the inter-vehicle distance data, for example, using equation 5 described above. In some embodiments, the server receives speed data and inter-vehicle distance data from multiple CVs, including the CV. The speed correction coefficient is calculated based on the speed data from the multiple CVs. The inter-vehicle distance correction coefficient is calculated based on the inter-vehicle distance data from the multiple CVs.

[0099] In block 1106, the server uses its prediction engine to determine future traffic flow, future average speed, and future density for a road segment. In some implementations, the prediction engine utilizes a long-running shared world model (e.g., one of the long-running shared world models 306,814,906) that stores data received from multiple CVs and multiple road sensors.

[0100] In block 1108, the server adjusts the determined future flow rate based on the speed correction coefficient and the inter-vehicle distance correction coefficient. The server adjusts the determined future average speed based on the speed correction coefficient. The server adjusts the determined future density based on the inter-vehicle distance correction coefficient. Adjusting the determined future flow rate based on the speed correction coefficient and the inter-vehicle distance correction coefficient may include multiplying the determined future flow rate by the quotient of the speed correction coefficient and the inter-vehicle distance correction coefficient. Adjusting the determined future average speed based on the speed correction coefficient may include multiplying the determined future average speed by the speed correction coefficient. Adjusting the determined future density based on the inter-vehicle distance correction coefficient may include dividing the determined future density by the inter-vehicle distance correction coefficient.

[0101] According to some implementations, the server generates control signals for the CAV based on at least one of the determined future flow rate, determined future average speed, or determined future density. The server then sends the generated control signals to the CAV.

[0102] Figure 12 is a flowchart of a method 1200 for controlling vehicles 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 traffic network 220 and / or an electronic communications network 230. The server may include a single computer device or multiple computer devices working together.

[0103] In block 1202, the server receives traffic condition information from road sensors, CVs, and CAVs. The traffic condition information may include at least one of the following: the position of a vehicle on the road, the speed of a vehicle, the distance between a vehicle and other vehicles, and the number of vehicles. A vehicle may be an unconnected vehicle, a CV, or a CAV. In the case of an unconnected vehicle, the traffic condition information may be determined (and transmitted to the server) by at least one of the road sensors, CVs, or CAVs that are close to the unconnected vehicle. CVs, CAVs, and / or unconnected vehicles may be traveling on the road. Alternatively, CVs, CAVs, and / or unconnected vehicles may include vehicles that are not traveling on the road (e.g., vehicles approaching the roadway, or vehicles that have recently left the roadway).

[0104] In block 1204, the server generates a long-running shared world model (e.g., one of the long-running shared world models 306,814,906) based on the received traffic status information. The long-running shared world model may use any modeling technique. For example, the long-running shared world model may use statistical modeling, machine learning, or artificial intelligence techniques.

[0105] In block 1206, the server uses a multi-vehicle policy selector (e.g., multi-vehicle policy selector 908) to generate control signals for controlling CAVs based on a long-term shared world model. The multi-vehicle policy selector generates control signals using optimizations to reduce road congestion. Each control signal is sent to the associated CAV to control the speed or travel path of the associated CAV. The optimizations to reduce road congestion include ensuring at least a minimum threshold following distance between each CAV and the vehicle ahead of it.

[0106] Several implementations are described below as numbered examples (Examples 1, 2, 3, etc.). These examples are provided for illustrative purposes only and do not limit other implementations disclosed herein.

[0107] Embodiment 1 is a method for generating and transmitting control signals to a vehicle, the method comprising accessing vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including location, speed, or distance between vehicles, generating a long-term shared world model based on the accessed vehicle data, applying a traffic flow model to the long-term shared world model to generate a data structure using the long-term shared world model that represents a predicted future speed in the road section by location and time, and This includes transmitting control signals to a connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle, based on the generated data structure.

[0108] In Example 2, the subject of Example 1 is accessing additional data from a road sensor, the additional data including at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and storing the accessed additional data in the long-term shared world model.

[0109] In Example 3, the subject matter of Examples 1 and 2 is further described by the fact that the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

[0110] In Example 4, the subject matter of Examples 1 to 3 is further 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 in the time slice, the vehicle density in at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving at least one road segment in the time slice.

[0111] In Example 5, the subject of Example 4 is that the average vehicle speed, the vehicle density, the flow rate, or the net flow rate are calculated using the long-term shared world model.

[0112] In Example 6, the subject matter of Examples 1 to 5 is as follows: the accessed vehicle data is received from the first vehicle and includes the position, speed, or distance between vehicles of the second vehicle, and the first vehicle is different from the second vehicle.

[0113] In Example 7, the subject of Example 6 is further described by the fact that the second vehicle is traveling in a lane immediately in front of the first vehicle, immediately behind the first vehicle, or in a lane adjacent to the lane in which the first vehicle is traveling.

[0114] Embodiment 8 is a device for generating and transmitting control signals to a vehicle, the device comprising a memory for storing instructions and a processor for executing the stored instructions, wherein the stored instructions involve accessing vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including at least one of location, speed, or distance between vehicles, generating a long-term shared world model based on the accessed vehicle data, using the long-term shared world model to generate a data structure representing a predicted future speed in the road section by location and time by applying a traffic flow model to the long-term shared world model, and transmitting control signals to a connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle based on the generated data structure.

[0115] In Embodiment 9, the subject of Embodiment 8 is to have the processor execute stored instructions to access additional data from road sensors, wherein the additional data includes at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and to store the accessed additional data in the long-term shared world model.

[0116] In Example 10, the subject matter of Examples 8-9 is that the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

[0117] In Example 11, the subject matter of Examples 8-10 is further 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 in the time slice, the vehicle density in at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving at least one road segment in the time slice.

[0118] In Example 12, the subject of Example 11 is that the average vehicle speed, the vehicle density, the flow rate, or the net flow rate are calculated using the long-term shared world model.

[0119] In Example 13, the subject matter of Examples 8 to 12 is that the accessed vehicle data is received from a first vehicle and includes the position, speed, or distance between vehicles of a second vehicle, and the first vehicle is different from the second vehicle.

[0120] In Example 14, the subject of Example 13 is further described by the fact that the second vehicle is traveling in a lane immediately in front of the first vehicle, immediately behind the first vehicle, or in a lane adjacent to the lane in which the first vehicle is traveling.

[0121] Embodiment 15 is a non-temporary computer-readable medium that, when executed by a processor, stores instructions causing the processor to perform an action, the action comprising accessing vehicle data from each connected vehicle of a subset of multiple connected vehicles (CVs) in a road section, the vehicle data including location, speed, or distance between vehicles; generating a long-term shared world model based on the accessed vehicle data; using the long-term shared world model to generate a data structure representing a predicted future speed in the road section by location and time by applying a traffic flow model to the long-term shared world model; and transmitting a control signal to a connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle based on the generated data structure.

[0122] In Example 16, the subject of Example 15 is accessing additional data from a road sensor, wherein the additional data includes at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and further includes storing the accessed additional data in the long-term shared world model.

[0123] In Example 17, the subject matter of Examples 15-16 is that the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

[0124] In Example 18, the subject matter of Examples 15-17 is further 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 in the time slice, the vehicle density in at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving at least one road segment in the time slice.

[0125] In Example 19, the subject of Example 18 is that the average vehicle speed, the vehicle density, the flow rate, or the net flow rate are calculated using the long-term shared world model.

[0126] In Example 20, the subject matter of Examples 15-19 is as follows: the accessed vehicle data is received from a first vehicle and includes the position, speed, or distance between vehicles of a second vehicle, and the first vehicle is different from the second vehicle.

[0127] In Example 21, the method involves receiving speed data from a control server and a connected vehicle (CV) representing the speed of the connected vehicle and any additional vehicles adjacent to the connected vehicle, calculating a speed correction coefficient based on the speed data, receiving inter-vehicle distance data from the control server and the connected vehicle representing the inter-vehicle distance of the connected vehicle and any additional vehicles adjacent to the connected vehicle, calculating an inter-vehicle distance correction coefficient based on the inter-vehicle distance data, and using a prediction engine in the control server to predict future traffic flow for a road segment, future The process includes determining the average speed and future density of the vehicle, adjusting the determined future flow rate based on the speed correction coefficient and the inter-vehicle distance correction coefficient, adjusting the determined future average speed based on the speed correction coefficient, adjusting the determined future density based on the inter-vehicle distance correction coefficient, generating a control signal for the connected autonomous vehicle (CAV) in the control server based on at least one of the determined future flow rate, the determined future average speed, or the determined future density, and transmitting the generated control signal to the connected autonomous vehicle.

[0128] In Example 22, the subject of Example 21 includes the additional vehicle adjacent to the connected vehicle including a vehicle in front of the connected vehicle in a lane adjacent to the connected vehicle, or a vehicle in behind the connected vehicle in a lane adjacent to the connected vehicle.

[0129] In Example 23, the subject matter of Examples 21-22 is as follows: the control server receives speed data and inter-vehicle distance data from a plurality of connected vehicles, including the connected vehicle; the speed correction coefficient is calculated based on the speed data from the plurality of connected vehicles; and the inter-vehicle distance correction coefficient is calculated based on the inter-vehicle distance data from the plurality of connected vehicles.

[0130] In Example 24, the subject matter of Examples 21 to 23 is that the prediction engine utilizes a long-term shared world model that stores data received from the multiple connected vehicles and multiple road sensors.

[0131] In Example 25, the subject matter of Examples 21 to 24 includes adjusting the future flow rate determined based on the speed correction coefficient and the inter-vehicle distance correction coefficient, which involves multiplying the determined future flow rate by the quotient of the speed correction coefficient and the inter-vehicle distance correction coefficient.

[0132] In Example 26, the subject matter of Examples 21 to 25 is adjusted based on the speed correction coefficient, which includes multiplying the determined future average speed by the speed correction coefficient.

[0133] In Example 27, the subject matter of Examples 21 to 26 is adjusted based on the inter-vehicle distance correction coefficient, which includes dividing the determined future density by the inter-vehicle distance correction coefficient.

[0134] In Example 28, the device comprises a memory for storing instructions and a processor for executing the stored instructions, wherein the stored instructions include receiving speed data from a control server and a connected vehicle (CV) representing the speed of the connected vehicle and additional vehicles adjacent to the connected vehicle, calculating a speed correction coefficient based on the speed data, receiving inter-vehicle distance data from the control server and the connected vehicle representing the inter-vehicle distance of the connected vehicle and additional vehicles adjacent to the connected vehicle, calculating an inter-vehicle distance correction coefficient based on the inter-vehicle distance data, and using a prediction engine in the control server. The process includes determining future flow rate, future average speed, and future density for a road segment; adjusting the determined future flow rate based on the speed correction coefficient and the inter-vehicle distance correction coefficient; adjusting the determined future average speed based on the speed correction coefficient; adjusting the determined future density based on the inter-vehicle distance correction coefficient; generating a control signal for a connected autonomous vehicle (CAV) in the control server based on at least one of the determined future flow rate, the determined future average speed, or the determined future density; and transmitting the generated control signal to the connected autonomous vehicle.

[0135] In Example 29, the subject of Example 28 is further described by the fact that the additional vehicle adjacent to the connected vehicle includes a vehicle located in front of the connected vehicle in a lane adjacent to the connected vehicle, or a vehicle located behind the connected vehicle in a lane adjacent to the connected vehicle.

[0136] In Example 30, the subject matter of Examples 28-29 is as follows: the control server receives speed data and inter-vehicle distance data from a plurality of connected vehicles, including the connected vehicle; the speed correction coefficient is calculated based on the speed data from the plurality of connected vehicles; and the inter-vehicle distance correction coefficient is calculated based on the inter-vehicle distance data from the plurality of connected vehicles.

[0137] In Example 31, the subject matter of Examples 28-30 is that the prediction engine utilizes a long-term shared world model that stores data received from the multiple connected vehicles and multiple road sensors.

[0138] In Example 32, the subject matter of Examples 28 to 31 includes adjusting the future flow rate determined based on the speed correction coefficient and the inter-vehicle distance correction coefficient, which involves multiplying the determined future flow rate by the quotient of the speed correction coefficient and the inter-vehicle distance correction coefficient.

[0139] In Example 33, the subject matter of Examples 28-32 is adjusted based on the speed correction coefficient, which includes multiplying the determined future average speed by the speed correction coefficient.

[0140] In Example 34, the subject matter of Examples 28 to 33 is adjusted based on the inter-vehicle distance correction coefficient, which includes dividing the determined future density by the inter-vehicle distance correction coefficient.

[0141] Embodiment 35 is a non-temporary computer-readable medium that, when executed by a processor, stores instructions causing the processor to perform an operation, the operation being: receiving speed data representing the speed of the connected vehicle and additional vehicles adjacent to the connected vehicle from a control server and a connected vehicle (CV); calculating a speed correction coefficient based on the speed data; receiving inter-vehicle distance data representing the inter-vehicle distance between the connected vehicle and additional vehicles adjacent to the connected vehicle from the control server and the connected vehicle; calculating an inter-vehicle distance correction coefficient based on the inter-vehicle distance data; and predicting an inter-vehicle distance in the control server. The process includes using an engine to determine future flow rate, future average speed, and future density for a road segment; adjusting the determined future flow rate based on the speed correction coefficient and the inter-vehicle distance correction coefficient; adjusting the determined future average speed based on the speed correction coefficient; adjusting the determined future density based on the inter-vehicle distance correction coefficient; generating a control signal for a connected autonomous vehicle (CAV) in the control server based on at least one of the determined future flow rate, the determined future average speed, or the determined future density; and transmitting the generated control signal to the connected autonomous vehicle.

[0142] In Example 36, the subject of Example 35 is further described by the fact that the additional vehicle adjacent to the connected vehicle includes a vehicle located in front of the connected vehicle in a lane adjacent to the connected vehicle, or a vehicle located behind the connected vehicle in a lane adjacent to the connected vehicle.

[0143] In Example 37, the subject matter of Examples 35-36 is as follows: the control server receives speed data and inter-vehicle distance data from a plurality of connected vehicles, including the connected vehicle; the speed correction coefficient is calculated based on the speed data from the plurality of connected vehicles; and the inter-vehicle distance correction coefficient is calculated based on the inter-vehicle distance data from the plurality of connected vehicles.

[0144] In Example 38, the subject matter of Examples 35-37 is that the prediction engine utilizes a long-term shared world model that stores data received from the multiple connected vehicles and multiple road sensors.

[0145] In Example 39, the subject matter of Examples 35 to 38 is that adjusting the future flow rate determined based on the speed correction coefficient and the inter-vehicle distance correction coefficient includes multiplying the determined future flow rate by the quotient of the speed correction coefficient and the inter-vehicle distance correction coefficient.

[0146] In Example 40, the subject matter of Examples 35-39 is adjusted based on the speed correction coefficient, which includes multiplying the determined future average speed by the speed correction coefficient.

[0147] In Example 41, the method includes receiving traffic condition information from road sensors, connected vehicles (CVs), and connected autonomous vehicles (CAVs), generating a long-term shared world model based on the received traffic condition information, and generating control signals for controlling the connected autonomous vehicles based on the long-term shared world model using a multi-vehicle policy selector, wherein the multi-vehicle policy selector generates the control signals using optimizations to reduce congestion in road sections, and each control signal controls the speed or travel path of the associated CAV.

[0148] In Example 42, the subject of Example 41 is that the optimization for reducing road congestion includes ensuring at least a minimum threshold following distance between each connected autonomous vehicle and the vehicle in front of the connected autonomous vehicle.

[0149] In Example 43, the subject matter of Examples 41-42 is that the traffic condition information includes at least one of the following: the position of the vehicle on the road section, the speed of the vehicle, the distance between the vehicle and other vehicles, and the number of vehicles.

[0150] In Example 44, the subject of Example 43 is further defined as the vehicle including a CV or CAV.

[0151] In Example 45, the subject matter of Examples 43-44 is further described by the fact that the vehicle includes an unconnected vehicle, and the traffic condition information of the unconnected vehicle is determined using one or more road sensors.

[0152] In Example 46, the subject matter of Examples 43 to 45 is further described by the fact that the vehicle includes an unconnected vehicle, and the traffic condition information of the unconnected vehicle is determined using at least one of the connected vehicle or the connected autonomous vehicle.

[0153] In Example 47, the subject matter of Examples 41 to 46 includes the fact that the connected vehicle, the connected autonomous vehicle, and the non-connected vehicle are traveling on the road.

[0154] In Example 48, the subject matter of Examples 41 to 47 is further defined as the connected vehicle or the connected autonomous vehicle including at least one vehicle that is not on the road portion.

[0155] Embodiment 49 is a device comprising a memory for storing instructions and a processor for executing the stored instructions. The system comprises a stored command which includes receiving traffic condition information from road sensors, connected vehicles (CVs) and connected autonomous vehicles (CAVs), generating a long-term shared world model based on the received traffic condition information, and generating control signals for controlling the connected autonomous vehicles based on the long-term shared world model using a multi-vehicle policy selector, wherein the multi-vehicle policy selector generates the control signals using optimizations to reduce congestion in road sections, and each control signal controls the speed or travel path of the associated CAV.

[0156] In Example 50, the subject of Example 49 is that the optimization for reducing road congestion includes ensuring at least a minimum threshold following distance between each connected autonomous vehicle and the vehicle in front of the connected autonomous vehicle.

[0157] In Example 51, the subject matter of Examples 49-50 is that the traffic condition information includes at least one of the following: the position of the vehicle on the road section, the speed of the vehicle, the distance between the vehicle and other vehicles, and the number of vehicles.

[0158] In Example 52, the subject of Example 51 is further defined as the vehicle including a CV or CAV.

[0159] In Example 53, the subject matter of Examples 51-52 is further described by the fact that the vehicle includes an unconnected vehicle, and the traffic condition information of the unconnected vehicle is determined using one or more road sensors.

[0160] In Example 54, the subject matter of Examples 51 to 53 is further described by the fact that the vehicle includes an unconnected vehicle, and the traffic condition information of the unconnected vehicle is determined using at least one of the connected vehicle or the connected autonomous vehicle.

[0161] In Example 55, the subject matter of Examples 49 to 54 includes the fact that the connected vehicle, the connected autonomous vehicle, and the non-connected vehicle are traveling on the road.

[0162] In Example 56, the subject matter of Examples 49 to 55 is further defined as the connected vehicle or the connected autonomous vehicle including at least one vehicle that is not on the road portion.

[0163] Embodiment 57 is a non-temporary computer-readable medium that, when executed by a processor, stores instructions causing the processor to perform an operation, the operation comprising: receiving traffic condition information from road sensors, connected vehicles (CVs) and connected autonomous vehicles (CAVs); generating a long-term shared world model based on the received traffic condition information; and generating control signals for controlling the connected autonomous vehicles based on the long-term shared world model using a multi-vehicle policy selector, the multi-vehicle policy selector generating the control signals using optimizations to reduce congestion in road sections, and each control signal controlling the speed or travel path of the associated CAV.

[0164] In Example 58, the subject of Example 57 is that the optimization for reducing road congestion includes ensuring at least a minimum threshold following distance between each connected autonomous vehicle and the vehicle in front of the connected autonomous vehicle.

[0165] In Example 59, the subject matter of Examples 57-58 is that the traffic condition information includes at least one of the following: the position of the vehicle on the road section, the speed of the vehicle, the distance between the vehicle and other vehicles, and the number of vehicles.

[0166] In Example 60, the subject of Example 59 is further defined as the vehicle including a CV or CAV.

[0167] Example 61 is at least one machine-readable medium that, when executed by a processing circuit, includes instructions causing the processing circuit to perform an operation that implements any of Examples 1 to 60.

[0168] Example 62 is an apparatus that includes means for implementing any of Examples 1 to 60.

[0169] Example 63 is a system for implementing any of Examples 1 to 60.

[0170] Example 64 is a method for implementing any of Examples 1 to 60.

[0171] As used herein, the term “instruction” may include instructions or expressions, or any or more parts thereof, for performing any method disclosed herein, and may be implemented in hardware, software, or any combination thereof. For example, an instruction may be implemented as information such as a computer program stored in memory that can be executed by a processor to perform any of the methods, algorithms, embodiments, or combinations thereof described herein. An instruction or part thereof may be implemented as a dedicated processor or circuit that may include dedicated hardware for performing any method, algorithm, embodiment, or combination thereof described herein. In some implementations, parts of an instruction may be distributed to multiple devices or multiple processors on a single device that can communicate directly or via a network such as a local area network, wide area network, the Internet, or a combination thereof.

[0172] Where used herein, the terms “example,” “embodiment,” “implementation,” “aspect,” “feature,” or “element” indicate that they serve as examples, illustrations, or illustrative examples. Unless otherwise expressly stated, any example, embodiment, implementation, aspect, feature, or element is independent of each other and may be used in combination with any other example, embodiment, implementation, aspect, feature, or element.

[0173] As used herein, the terms “determine” and “identify” or any variation thereof include selecting, confirming, calculating, searching, receiving, determining, establishing, obtaining, or otherwise identifying or determining in any way using one or more of the illustrated and described apparatus herein.

[0174] Where used herein, the term “or” is intended to mean inclusive “or” rather than exclusive “or,” unless otherwise specified or evident from the context. Furthermore, the articles “a” and “an” as used in this application and the attached claims should generally be interpreted as meaning “one or more,” unless it is clear from the context or otherwise specified that they refer to a singular form.

[0175] Furthermore, for the sake of brevity, the drawings and descriptions herein may include a series of steps, stages, or sequences, but the elements of the methods disclosed herein may occur in various orders or simultaneously. Furthermore, the elements of the methods disclosed herein may occur together with other elements not expressly presented and disclosed herein. Furthermore, not all elements of the methods described herein are required to implement the methods disclosed herein. While the embodiments, features, and elements are described herein in specific combinations, each embodiment, feature, or element may be used independently or in various combinations, together with or without other embodiments, features, and elements.

[0176] The above embodiments, examples, and implementations are provided for the convenience of understanding this disclosure and are not limiting. In contrast, this disclosure encompasses a variety of modifications and equivalent structures included in the attached claims, and the claims should be interpreted most broadly to encompass all such modifications and equivalent structures that are legally recognized.

Claims

1. A method for generating and transmitting control signals to a vehicle, Accessing vehicle data from each connected vehicle in a subset of multiple connected vehicles (CVs) in a road section, wherein the vehicle data includes at least one of position, speed, or distance between vehicles. The method involves generating a long-term shared world model based on accessed vehicle data, wherein the long-term shared world model stores at least one of historical traffic speed, congestion, or inter-vehicle distance data for a plurality of road segments, and is used to predict at least one of future traffic speed, congestion, or inter-vehicle distance data for at least one of the plurality of road segments. Applying a traffic flow model to the long-term shared world model, the long-term shared world model is used to generate a data structure that represents the predicted future speed in the road section by location and time, wherein the traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment in a time slice, the vehicle density in the at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving the at least one road segment in the time slice, and Based on the generated data structure, a control signal is transmitted to the connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle. Includes, The long-term shared world model includes a transfer engine, a localization engine, and an estimation engine, wherein the transfer engine transfers accessed vehicle data to the localization engine, the localization engine calculates the vehicle's position, speed, and inter-vehicle distance and provides the position, speed, and inter-vehicle distance to the estimation engine, the estimation engine estimates the flow rate, density, and speed, and the localization engine modifies the localization module used based on the sensing specifications of the connected vehicle.

2. Accessing additional data from road sensors, wherein the additional data includes at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and storing the accessed additional data in the long-term shared world model. The method according to claim 1, further comprising:

3. The method according to claim 2, wherein the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

4. The method according to claim 1, wherein the average vehicle speed, the vehicle density, the flow rate, or the net flow rate is calculated using the long-term shared world model.

5. The method according to claim 1, wherein the accessed vehicle data is received from a first vehicle and includes the position, speed, or distance between vehicles of a second vehicle, and the first vehicle is different from the second vehicle.

6. The method according to claim 5, wherein the second vehicle is traveling in a lane immediately in front of the first vehicle, immediately behind the first vehicle, or in a lane adjacent to the lane in which the first vehicle is traveling.

7. A device that generates control signals and transmits them to a vehicle, Memory for storing instructions, A processor that executes stored instructions and The stored instructions are provided with, Accessing vehicle data from each connected vehicle in a subset of multiple connected vehicles (CVs) in a road section, wherein the vehicle data includes at least one of position, speed, or distance between vehicles. The method involves generating a long-term shared world model based on accessed vehicle data, wherein the long-term shared world model stores at least one of historical traffic speed, congestion, or inter-vehicle distance data for a plurality of road segments, and is used to predict at least one of future traffic speed, congestion, or inter-vehicle distance data for at least one of the plurality of road segments. Applying a traffic flow model to the long-term shared world model, the long-term shared world model is used to generate a data structure that represents the predicted future speed in the road section by location and time, wherein the traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment in a time slice, the vehicle density in the at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving the at least one road segment in the time slice, and Based on the generated data structure, a control signal is transmitted to the connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle. It is for the purpose of doing so, The long-term shared world model includes a transfer engine, a localization engine, and an estimation engine, wherein the transfer engine transfers accessed vehicle data to the localization engine, the localization engine calculates the vehicle's position, speed, and inter-vehicle distance and provides the position, speed, and inter-vehicle distance to the estimation engine, the estimation engine estimates flow rate, density, and speed, and the localization engine modifies the localization module used based on the sensing or communication specifications of the vehicle type of the connected vehicle.

8. The processor executes the stored instructions, Accessing additional data from road sensors, wherein the additional data includes at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and The accessed additional data is stored in the aforementioned long-term shared world model. The apparatus according to claim 7, which causes the following to be performed.

9. The apparatus according to claim 8, wherein the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

10. The apparatus according to claim 7, wherein the average vehicle speed, the vehicle density, the flow rate, or the net flow rate is calculated using the long-term shared world model.

11. The device according to claim 7, wherein the accessed vehicle data is received from a first vehicle and includes the position, speed, or distance between vehicles of a second vehicle, and the first vehicle is different from the second vehicle.

12. The apparatus according to claim 11, wherein the second vehicle is traveling in a lane immediately in front of the first vehicle, immediately behind the first vehicle, or in a lane adjacent to the lane in which the first vehicle is traveling.

13. A non-temporary computer-readable medium that stores instructions causing the processor to perform an action, and the action is: Accessing vehicle data from each connected vehicle in a subset of multiple connected vehicles (CVs) in a road section, wherein the vehicle data includes at least one of position, speed, or distance between vehicles. The method involves generating a long-term shared world model based on accessed vehicle data, wherein the long-term shared world model stores at least one of historical traffic speed, congestion, or inter-vehicle distance data for a plurality of road segments, and is used to predict at least one of future traffic speed, congestion, or inter-vehicle distance data for at least one of the plurality of road segments. Applying a traffic flow model to the long-term shared world model, the long-term shared world model is used to generate a data structure that represents the predicted future speed in the road section by location and time, wherein the traffic flow model is based on at least one of the following: the average vehicle speed in at least one road segment in a time slice, the vehicle density in the at least one road segment in the time slice, or the flow rate or net flow rate of vehicles entering and leaving the at least one road segment in the time slice, and Based on the generated data structure, a control signal is transmitted to the connected autonomous vehicle (CAV) to control the operation of the connected autonomous vehicle. The Long-Term Shared World Model includes a transfer engine, a localization engine, and an estimation engine, wherein the transfer engine transfers accessed vehicle data to the localization engine, the localization engine calculates the vehicle's position, speed, and distance and provides the position, speed, and distance to the estimation engine, the estimation engine estimates flow rate, density, and speed, and the localization engine modifies the localization module used based on the sensing specifications of the vehicle type of the connected vehicle, in a non-temporary computer-readable medium.

14. The aforementioned operation is, Accessing additional data from road sensors, wherein the additional data includes at least one of vehicle position data, vehicle speed data, or vehicle-to-vehicle distance data, and The accessed additional data is stored in the aforementioned long-term shared world model. The computer-readable medium according to claim 13, further comprising:

15. The computer-readable medium according to claim 14, wherein the vehicle position data, the vehicle speed data, or the vehicle-to-vehicle distance data is associated with an unconnected vehicle.

16. The computer-readable medium according to claim 13, wherein the average vehicle speed, the vehicle density, the flow rate, or the net flow rate is calculated using the long-term shared world model.

17. The computer-readable medium according to claim 13, wherein the accessed vehicle data is received from a first vehicle and includes the position, speed, or distance between vehicles of a second vehicle, and the first vehicle is different from the second vehicle.

Images