Traffic jam relieving method and system based on Internet of Vehicles, medium and equipment

Abstract

The invention discloses a traffic jam relieving method and system based on the Internet of Vehicles, a medium and equipment. The method comprises the following steps: an Internet of Vehicles communication step: carrying out real-time communication between vehicles, between a vehicle and an infrastructure, and between a vehicle and a cloud; a global traffic state sensing step: collecting position, speed and direction information of vehicles in a region and state data of traffic infrastructures through a multi-sensor fusion technology, and constructing a real-time traffic state diagram; according to the cooperative path planning step, path optimization is carried out on the vehicles in the area based on a centralized or distributed algorithm, and an efficient, flexible and safe intelligent traffic jam relieving scheme is provided by integrating the Internet of Vehicles technology, the multi-sensor fusion technology, the machine learning algorithm and the cooperative path planning method. According to the scheme, the traffic flow efficiency can be remarkably improved, reliable path planning and cooperative driving support can be provided for the automatic driving vehicle, and important social benefits and economic values are achieved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and particularly to a traffic congestion mitigation method, system, medium, and device based on vehicle-to-everything (V2X). Background Art

[0002] With the acceleration of urbanization and the continuous increase in the number of motor vehicles, traffic congestion has become a common problem faced by major cities around the world. Traditional traffic management methods mainly rely on fixed-timing traffic lights and manual scheduling, making it difficult to cope with dynamically changing traffic flows and sudden traffic events. In recent years, with the development of autonomous driving technology and vehicle-to-everything (V2X) technology, intelligent transportation systems have gradually become an important direction for solving traffic congestion problems. However, the existing technologies still have the following problems:

[0003] 1. Insufficient traffic state perception ability:

[0004] Existing systems mainly rely on a single data source (such as cameras or radars), making it difficult to achieve high-precision traffic state perception in complex environments (such as bad weather, night, or dense traffic flows);

[0005] Lack of in-depth integration of historical data and real-time data, making it impossible to accurately predict traffic flow changes and the formation of congestion points.

[0006] 2. Poor path planning coordination:

[0007] Existing path planning algorithms are mostly single-vehicle optimizations, lacking overall coordination of vehicles within a region, and easily leading to problems of local optimization while global sub-optimization;

[0008] In case of congestion, path conflicts and competitions between vehicles intensify, and there is a lack of an effective negotiation mechanism. Summary of the Invention

[0009] The technical problem solved by the present invention is to provide a traffic congestion mitigation method based on vehicle-to-everything (V2X) that can improve traffic state perception ability and enhance path planning coordination.

[0010] The technical solution adopted by the present invention to solve its technical problems is: A traffic congestion mitigation method based on vehicle-to-everything (V2X), comprising the following steps:

[0011] V2X communication step: Perform real-time communication between vehicles, between vehicles and infrastructure, and between vehicles and the cloud;

[0012] Global traffic state perception step: Collect the position, speed, and direction information of vehicles within a region and the status data of traffic infrastructure through multi-sensor fusion technology, and construct a real-time traffic state map;

[0013] Collaborative path planning steps: Optimize the paths of vehicles in the area based on centralized or distributed algorithms;

[0014] Dynamic traffic signal control steps: Adjust the timing plan of traffic lights according to the real-time traffic status.

[0015] Furthermore: In the vehicle-to-everything communication step, specifically:

[0016] Vehicle-to-vehicle communication is used to exchange information such as position, speed, direction, acceleration, and braking status

[0017] Vehicle-to-infrastructure communication is used to obtain traffic signal status, electronic road sign information, road construction information, and accident warning information;

[0018] Vehicle-to-cloud communication is used to upload vehicle status data and download global path planning results.

[0019] Furthermore: In the vehicle-to-vehicle communication step, the following steps are also included:

[0020] Vehicle platooning steps: Platoon vehicles moving in the same direction. The vehicles share speed, acceleration, and steering information in real time through V2V communication. The lead vehicle of the platoon is responsible for path planning and decision-making, and the following vehicles adjust their driving states according to the instructions of the lead vehicle. The distance between platooning vehicles is dynamically adjusted through V2V communication;

[0021] Collision warning steps: Vehicles broadcast their position, speed, and direction information in real time through V2V communication. When a potential collision risk is detected, the system sends a warning signal to the driver or the autonomous driving system;

[0022] Local path negotiation steps: Vehicles negotiate the passing sequence at intersections, lane changes, and overtaking behaviors through V2V communication and share local path planning results.

[0023] Furthermore: In the global traffic status perception step, specifically:

[0024] The multi-sensor fusion technology includes the data fusion of cameras, radars, lidars, and ultrasonic sensors;

[0025] The real-time traffic status map includes traffic flow distribution, congestion point locations, accident areas, construction areas, and weather impact information.

[0026] Furthermore: In the collaborative path planning step, specifically:

[0027] The centralized algorithm generates a globally optimal path for each vehicle through the cloud or the regional control center;

[0028] The distributed algorithm realizes local path adjustment through V2V communication between vehicles.

[0029] Furthermore, it also includes data security and privacy protection steps, specifically: encrypting and anonymizing communication data, and the processing steps include encrypted communication, blockchain technology or data anonymization.

[0030] Furthermore, it also includes traffic congestion prediction and diversion steps, specifically:

[0031] Traffic congestion prediction step: Using machine learning algorithms to build a prediction model, inputting historical data and real-time data into the prediction model, predicting traffic flow changes and congestion points within a certain period in the future, and generating congestion warning information according to the prediction results, including congestion location, expected congestion time and severity;

[0032] Diversion step: Sending diversion suggestions to vehicles through the vehicle networking communication step to guide vehicles to bypass the congested area.

[0033] The present invention discloses a traffic congestion mitigation system based on vehicle networking, including the above-mentioned traffic congestion mitigation method based on vehicle networking, and includes a vehicle networking communication module, a global traffic state perception module, a collaborative path planning module, and a dynamic traffic signal control module;

[0034] The vehicle networking communication module is used for real-time communication between vehicles, between vehicles and infrastructure, and between vehicles and the cloud;

[0035] The global traffic state perception module is used to collect the position, speed, direction information of vehicles in the area and the state data of traffic infrastructure through multi-sensor fusion technology, and construct a real-time traffic state map;

[0036] The collaborative path planning module is used to optimize the paths of vehicles in the area based on centralized or distributed algorithms;

[0037] The dynamic traffic signal control module is used to adjust the timing plan of traffic lights according to the real-time traffic state.

[0038] The present invention also discloses a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it realizes the steps of the above-mentioned traffic congestion mitigation method based on vehicle networking.

[0039] The present invention also discloses a computer device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface, and the memory complete mutual communication through the communication bus; wherein:

[0040] The memory is used to store a computer program;

[0041] The processor is configured to execute the steps of the above-mentioned traffic congestion mitigation method based on the vehicle-to-everything (V2X) network by running the program stored in the memory.

[0042] The beneficial effects of the present invention are as follows:

[0043] 1. By integrating V2X technology, multi-sensor fusion technology, machine learning algorithms, and collaborative path planning methods, the present invention provides an efficient, flexible, and safe intelligent traffic congestion mitigation solution. This solution can not only significantly improve traffic flow efficiency, reduce congestion time and fuel consumption, but also provide reliable path planning and cooperative driving support for autonomous vehicles, having important social and economic values.

[0044] 2. By setting up traffic congestion prediction and diversion steps, the present invention effectively solves the problems of inaccurate traffic congestion prediction and untimely diversion measures in the prior art. Through in-depth analysis of historical data and real-time data, and using advanced machine learning algorithms to build a prediction model, it can accurately predict traffic flow changes and the formation of congestion points in the future period, so as to take diversion measures in advance and guide vehicles to bypass congested areas, effectively alleviating traffic pressure. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a schematic flowchart of the traffic congestion mitigation method based on the vehicle-to-everything (V2X) network according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following detailed description of the specific embodiments of the present invention will be given with reference to the accompanying drawings.

[0047] As Figure 1 shown, the embodiments of the present application disclose a traffic congestion mitigation method based on the vehicle-to-everything (V2X) network, including the following steps:

[0048] V2X communication step: performing real-time communication between vehicles, between vehicles and infrastructure, and between vehicles and the cloud;

[0049] Global traffic state perception step: collecting the position, speed, and direction information of vehicles in the area and the status data of traffic infrastructure through multi-sensor fusion technology, and constructing a real-time traffic state map;

[0050] Collaborative path planning step: optimizing the paths of vehicles in the area based on centralized or distributed algorithms;

[0051] Dynamic traffic signal control step: adjusting the signal timing plan of traffic lights according to the real-time traffic state.

[0052] Specifically, it should be explained that vehicle-to-vehicle communication is V2V communication technology, vehicle-to-infrastructure communication is V2I communication technology, and the communication between the vehicle and the cloud is V2C communication technology.

[0053] The present invention provides an efficient, flexible, and safe intelligent traffic congestion mitigation solution by integrating vehicle networking technology, multi-sensor fusion technology, machine learning algorithms, and collaborative path planning methods. This solution can not only significantly improve traffic flow efficiency, reduce congestion time and fuel consumption, but also provide reliable path planning and cooperative driving support for autonomous vehicles, with important social and economic values.

[0054] In this embodiment, in the vehicle networking communication step, specifically:

[0055] Vehicle-to-vehicle communication is used to exchange position, speed, direction, acceleration, and braking state information;

[0056] Vehicle-to-infrastructure communication is used to obtain traffic signal status, electronic road sign information, road construction information, and accident warning information;

[0057] Vehicle-to-cloud communication is used to upload vehicle status data and download global path planning results.

[0058] Specifically, vehicles exchange position, speed, direction, acceleration, and braking state information with each other to achieve real-time status sharing among vehicles, which helps with cooperative driving and collision avoidance. At the same time, vehicles communicate with the infrastructure through V2I communication technology and can obtain traffic signal status, electronic road sign information, road construction information, and accident warning information in real time, so as to make driving decisions in advance and avoid entering congested areas or dangerous sections. In addition, vehicle-to-cloud communication realizes the upload of vehicle status data and the download of global path planning results. The cloud can provide the optimal path planning for vehicles based on the real-time traffic status and vehicle status, further improving traffic efficiency.

[0059] In this embodiment, in the vehicle-to-vehicle communication step, the following steps are further included:

[0060] Vehicle formation step: Vehicles in the same direction are formed into a formation. The vehicles share speed, acceleration, and steering information in real time through V2V communication. The leading vehicle in the formation is responsible for path planning and decision-making, and the following vehicles adjust their driving states according to the instructions of the leading vehicle. The distance between the formation vehicles is dynamically adjusted through V2V communication;

[0061] Collision warning step: Vehicles broadcast their own position, speed, and direction information in real time through V2V communication. When a potential collision risk is detected, the system sends a warning signal to the driver or the autonomous driving system;

[0062] Local path negotiation step: Vehicles negotiate the passing sequence at intersections, lane-changing, and overtaking behaviors through V2V communication and share the results of local path planning.

[0063] Specifically, in the vehicle formation step, the cooperative formation of vehicles in the same direction is achieved through V2V communication technology. Vehicles within the formation can share speed, acceleration, and steering information in real time, thereby improving driving consistency and safety. The lead vehicle of the formation is responsible for path planning and decision-making. Based on the real-time traffic status and the results of global path planning, it provides the optimal driving path for the vehicles within the formation. The following vehicles then adjust their driving states according to the instructions of the lead vehicle to maintain consistency and a safe distance from the lead vehicle. The distance between formation vehicles is dynamically adjusted through V2V communication to adapt to different traffic flow states and road conditions.

[0064] In the collision warning step, vehicles broadcast their position, speed, and direction information in real time through V2V communication technology, thereby achieving real-time perception of surrounding vehicles. When a potential collision risk is detected, the system will send a warning signal to the driver or the autonomous driving system, prompting the driver to take evasive measures or adjust the driving state to avoid the occurrence of a collision accident.

[0065] In the local path negotiation step, vehicles negotiate the passing sequence at intersections, lane-changing, and overtaking behaviors through V2V communication technology and share the results of local path planning. This helps to reduce path conflicts and competition between vehicles and improve the smoothness and safety of traffic flow. Through local path negotiation, vehicles can achieve more flexible and cooperative driving behaviors on the premise of ensuring safety and efficiency.

[0066] In this embodiment, in the global traffic status perception step, specifically:

[0067] The multi-sensor fusion technology includes the data fusion of cameras, radars, lidars, and ultrasonic sensors;

[0068] The real-time traffic status map includes traffic flow distribution, congestion point locations, accident areas, construction areas, and weather impact information.

[0069] Specifically, cameras can capture image information in the traffic scene, radars and lidars can provide distance and speed information of the vehicle, while ultrasonic sensors are used to detect obstacles at close range. These data are fused and processed to generate a high-precision real-time traffic status map, including traffic flow distribution, congestion point locations, accident areas, construction areas, and weather impact information, etc., providing reliable data support for subsequent path planning and traffic signal control.

[0070] In this embodiment, in the collaborative path planning step, specifically:

[0071] The centralized algorithm generates a globally optimal path for each vehicle through the cloud or the regional control center;

[0072] The distributed algorithm realizes local path adjustment through V2V communication between vehicles.

[0073] Specifically, the centralized algorithm can comprehensively consider the states of all vehicles and the traffic state in the region, generate a globally optimal path for each vehicle, and thus achieve the optimization of the overall traffic flow. The distributed algorithm, on the other hand, pays more attention to the local cooperation between vehicles, realizes real-time information sharing and path adjustment between vehicles through V2V communication to adapt to different traffic flow states and road conditions. The combined use of these two algorithms can further improve the effect and efficiency of traffic congestion mitigation.

[0074] In this embodiment, data security and privacy protection steps are further included, specifically: encrypting and anonymizing communication data, and the processing steps include encrypted communication, blockchain technology or data anonymization.

[0075] Specifically, in this method, the security of data transmission and storage is ensured by adopting encrypted communication, blockchain technology or data anonymization methods.

[0076] In this embodiment, traffic congestion prediction and diversion steps are further included, specifically:

[0077] Traffic congestion prediction step: Using machine learning algorithms to construct a prediction model, inputting historical data and real-time data into the prediction model, predicting the traffic flow changes and congestion points within a certain period in the future, and generating congestion warning information according to the prediction results, including congestion location, expected congestion time and severity;

[0078] Diversion step: Sending diversion suggestions to vehicles through the vehicle networking communication step to guide the vehicles to bypass the congested area.

[0079] Specifically, in the data collection phase, historical traffic flow data, including the number of vehicles in different time periods and on different road sections, is obtained from the traffic management department; historical accident data is obtained from the traffic police department to analyze accident-prone areas and times; historical weather data is obtained from the meteorological department to analyze the impact of weather on traffic flow; legal holidays, school vacations, etc. are obtained to analyze the impact of holidays on traffic flow; real-time location, speed, and direction information of vehicles is obtained through V2V and V2I communications; the real-time status of traffic lights is obtained through V2I communication; real-time information on road construction areas is obtained through V2I communication; real-time weather information is obtained from the meteorological department; a prediction model is constructed using machine learning algorithms (such as long short-term memory network LSTM and graph neural network GNN); historical data and real-time data are input into the prediction model to predict traffic flow changes and congestion points in the future period; and congestion warning information, including the congestion location, estimated congestion time, and severity, is generated based on the prediction results.

[0080] Next, diversion suggestions are sent to vehicles through the vehicle networking communication module to guide vehicles to bypass congested areas, specifically including: sending diversion route suggestions to vehicles about to enter the congested area, providing alternative routes to vehicles that have already entered the congested area, or adjusting the signal timing through the dynamic traffic signal control module to optimize traffic flow, or re-planning vehicle routes through the collaborative path planning module to avoid exacerbating congestion.

[0081] The present invention also discloses a traffic congestion mitigation system based on vehicle networking, including the above-mentioned traffic congestion mitigation method based on vehicle networking, and comprising a vehicle networking communication module, a global traffic state perception module, a collaborative path planning module, and a dynamic traffic signal control module;

[0082] The vehicle networking communication module is used for real-time communication between vehicles, between vehicles and infrastructure, and between vehicles and the cloud;

[0083] The global traffic state perception module is used to collect the position, speed, and direction information of vehicles in the area and the status data of traffic infrastructure through multi-sensor fusion technology, and construct a real-time traffic state map;

[0084] The collaborative path planning module is used to optimize the paths of vehicles in the area based on centralized or distributed algorithms;

[0085] The dynamic traffic signal control module is used to adjust the signal timing plan of traffic lights according to the real-time traffic state.

[0086] By integrating vehicle networking technology, multi-sensor fusion technology, machine learning algorithms, and collaborative path planning methods, this system provides an efficient, flexible, and safe intelligent traffic congestion mitigation solution. This solution can not only significantly improve traffic flow efficiency, reduce congestion time and fuel consumption, but also provide reliable path planning and cooperative driving support for autonomous vehicles, with important social and economic values.

[0087] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned vehicle-network-based traffic congestion mitigation method are implemented.

[0088] The present invention also discloses a computer device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus; where:

[0089] The memory is used to store a computer program;

[0090] The processor is used to execute the steps of the above-mentioned vehicle-network-based traffic congestion mitigation method by running the program stored on the memory.

[0091] The above specific embodiments have further elaborated on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A traffic congestion relief method based on Internet of Vehicles, characterized in that: The steps include: IoV communication steps: Real-time communication between vehicles, vehicles and infrastructure, and vehicles and the cloud; Global traffic status perception steps: collect the location, speed, direction information of vehicles in the area and the status data of traffic infrastructure through multi-sensor fusion technology, and build a real-time traffic status map; Collaborative path planning steps: Optimize the paths of vehicles in the area based on centralized or distributed algorithms; Dynamic traffic signal control steps: adjust the timing plan of traffic lights according to real-time traffic conditions.

2. The method for alleviating traffic congestion based on the Internet of Vehicles according to claim 1, characterized in that: The vehicle networking communication steps are specifically as follows: The vehicle-to-vehicle communication is used to exchange position, speed, direction, acceleration and braking status information; The vehicle-infrastructure communication is used to obtain traffic light status, electronic road sign information, road construction information and accident warning information; The vehicle communicates with the cloud to upload vehicle status data and download global path planning results.

3. The method for alleviating traffic congestion based on the Internet of Vehicles as claimed in claim 2, characterized in that: The vehicle-to-vehicle communication step further includes the following steps: Vehicle formation steps: vehicles in the same direction are formed into a platoon. The vehicles share speed, acceleration and steering information in real time through V2V communication. The leading vehicle in the platoon is responsible for path planning and decision-making. The following vehicles adjust their driving status according to the instructions of the leading vehicle. The distance between the platoon vehicles is dynamically adjusted through V2V communication. Collision warning steps: The vehicle broadcasts its position, speed and direction information in real time through V2V communication. When a potential collision risk is detected, the system sends a warning signal to the driver or the autonomous driving system; Local path negotiation step: Vehicles negotiate the intersection traffic order, lane change and overtaking behavior through V2V communication and share local path planning results.

4. The method for alleviating traffic congestion based on the Internet of Vehicles as claimed in claim 1, characterized in that: The global traffic state perception step is specifically as follows: The multi-sensor fusion technology includes data fusion of cameras, radars, lidars and ultrasonic sensors; The real-time traffic status map includes traffic flow distribution, congestion point locations, accident areas, construction areas and weather impact information.

5. The method for alleviating traffic congestion based on the Internet of Vehicles as claimed in claim 1, characterized in that: The collaborative path planning step is specifically as follows: The centralized algorithm generates a global optimal path for each vehicle through the cloud or a regional control center; The distributed algorithm implements local path adjustment through V2V communication between vehicles.

6. The method for alleviating traffic congestion based on the Internet of Vehicles as claimed in claim 1, characterized in that: It also includes data security and privacy protection steps, specifically: encrypting and anonymizing communication data, and the processing steps include encrypted communication, blockchain technology or data anonymization.

7. The method for alleviating traffic congestion based on the Internet of Vehicles as claimed in claim 1, characterized in that: It also includes traffic congestion prediction and diversion steps, specifically: Traffic congestion prediction steps: Use machine learning algorithms to build a prediction model, input historical data and real-time data into the prediction model, predict traffic flow changes and congestion points in the future, and generate congestion warning information based on the prediction results, including congestion location, expected congestion time and severity; Diversion step: Send diversion suggestions to vehicles through the Internet of Vehicles communication step to guide vehicles to bypass congested areas.

8. A traffic congestion relief system based on vehicle networking, comprising a traffic congestion relief method based on vehicle networking according to any one of claims 1 to 7, characterized in that: It includes Internet of Vehicles communication module, global traffic status perception module, collaborative path planning module, and dynamic traffic signal control module; The Internet of Vehicles communication module is used for real-time communication between vehicles, vehicles and infrastructure, and vehicles and the cloud; The global traffic status perception module is used to collect the position, speed, direction information of vehicles in the area and the status data of traffic infrastructure through multi-sensor fusion technology, and construct a real-time traffic status map; The collaborative path planning module is used to optimize the paths of vehicles in the area based on a centralized or distributed algorithm; The dynamic traffic signal control module is used to adjust the timing scheme of traffic lights according to real-time traffic conditions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for alleviating traffic congestion based on the Internet of Vehicles described in any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; wherein: The memory is used to store computer programs; The processor is used to execute the steps of the traffic congestion relief method based on the Internet of Vehicles as described in any one of claims 1 to 7 by running the program stored in the memory.

Images