CN-121686788-B - Vehicle-road cooperative traffic management method, system, equipment and storage medium

CN121686788BCN 121686788 BCN121686788 BCN 121686788BCN-121686788-B

Abstract

The application provides a vehicle-road cooperative traffic management method, a system, equipment and a storage medium, which relate to the technical field of traffic management and comprise the steps of receiving traffic event information and instruction messages from a traffic management cloud control platform, controlling a vehicle-road cooperative traffic management system to move to a target point according to the instruction messages, acquiring observation data of all resource nodes in a target service area according to the traffic event information and the instruction messages, fusing the observation data of all the resource nodes in the target service area by adopting a preset fusion algorithm to generate a state estimation sequence of each traffic participant, carrying out track prediction by adopting a preset track prediction model based on the state estimation sequence of each traffic participant, outputting a multi-mode prediction track cluster with probability weight, and sending decision suggestions to corresponding traffic participants based on the multi-mode prediction track cluster of each traffic participant. The application can realize flexible and dynamic traffic management through the vehicle-road cooperative traffic management method.

Inventors

YANG XU
LIU LEI
XU KE
ZHONG SHENGZHI
YANG QIMING
LEI YU

Assignees

武汉理工大学

Dates

Publication Date: 20260512
Application Date: 20260210

Claims (8)

1. The vehicle-road cooperative traffic management method is characterized by being applied to a vehicle-road cooperative traffic management system with mobile cooperative capability, and comprises the following steps: Receiving traffic event information and an instruction message from a traffic management cloud control platform, and controlling the vehicle-road cooperative traffic management system to move to a target point according to the instruction message, wherein the traffic event information comprises at least one of a real-time road condition event list of an authorized traffic information service platform and monitoring information of the vehicle-road cooperative traffic management system; broadcasting cooperative service signaling and receiving response information of each communication terminal in a service range; Registering each communication terminal as a resource node according to response information of each communication terminal, and recording attribute information of each resource node, wherein the attribute information comprises an ID, position information and a dynamic capability set; Determining a target service area according to the traffic event information and the instruction message, and constructing a dynamic resource map of the target service area, wherein the target service area is an area to be managed of an accident point or a congestion section, the dynamic resource map comprises at least one resource node, and the resource node comprises local sensing equipment carried by a system and distributed sensing resources of an accessed vehicle-road cooperative network in the target service area; Determining a current macroscopic task according to the instruction message, decomposing the current macroscopic task into a plurality of microscopic subtasks, optimally matching each microscopic subtask with the capacity of each resource node respectively, distributing the execution task of each resource node according to a matching result, and obtaining observation data obtained by executing the distribution task by each resource node; Fusing the observation data of each resource node in the target service area by adopting a preset fusion algorithm to generate a state estimation sequence of each traffic participant, wherein the preset fusion algorithm is a self-adaptive unscented Kalman filtering algorithm or an unscented Kalman filtering algorithm; based on the state estimation sequence of each traffic participant, carrying out track prediction by adopting a preset track prediction model, and outputting a multi-mode prediction track cluster with probability weights, wherein the probability weight value reflects the occurrence probability of the corresponding track; and sending decision suggestions to the corresponding traffic participants based on the multi-mode prediction track clusters of the traffic participants.
2. The vehicle-road cooperative traffic management method according to claim 1, wherein the fusing the observed data of each resource node in the target service area by using a preset fusion algorithm to generate a state estimation sequence of each traffic participant comprises: Synchronizing the observed data of each resource node to a unified space-time reference to obtain space-time aligned multi-source observed data; Respectively establishing a high-dimensional state vector for each traffic participant in the target service area based on the time-space aligned multi-source observation data, wherein the high-dimensional state vector comprises a position, a speed, a course angle and a yaw rate; Performing Sigma point sampling and nonlinear prediction on each high-dimensional state vector to obtain a state predicted value, matching by calculating covariance of an observed innovation sequence based on the state predicted value, dynamically adjusting a process noise matrix and an observed noise matrix by adopting a self-adaptive unscented Kalman filtering algorithm, and calculating key filtering parameters, wherein the innovation sequence is a difference between an actual observed value and a predicted observed value; mapping the space-time aligned multi-source observation data to a unified state space, and calculating an optimal Kalman gain by combining a self-adaptive adjusted process noise matrix, an observation noise matrix and the key filtering parameters; and optimally fusing the time-space aligned multi-source observation data and the state prediction value according to the optimal Kalman gain to generate a state estimation sequence of each traffic participant.
3. The vehicle-road cooperative traffic management method according to claim 1, wherein the performing the trajectory prediction by using a preset trajectory prediction model based on the state estimation sequence of each traffic participant, and outputting the multi-modal predicted trajectory cluster with probability weights, comprises: Inputting a state estimation sequence of a target traffic participant into a pre-trained driving behavior intention inference model as an observation sequence to obtain probability distribution of each behavior intention of the target traffic participant at the current moment, wherein the driving behavior intention inference model is a hidden Markov model; Obtaining a historical track of the target traffic participant based on the state estimation sequence of the target traffic participant, matching the historical track of the target traffic participant with a preset typical track template corresponding to each behavior intention, and outputting a multi-mode prediction track cluster with probability weight based on a matching result and probability distribution of each behavior intention of the target traffic participant at the current moment.
4. The vehicular collaborative traffic management method according to claim 1, wherein the sending decision advice to the corresponding traffic participants based on the multi-modal predicted trajectory clusters of each of the traffic participants comprises: determining traffic conflict risk information based on the multi-mode prediction track clusters of the traffic participants; and generating a traffic planning strategy according to the traffic conflict risk information, and sending decision suggestions to corresponding traffic participants based on the traffic planning strategy.
5. The vehicular cooperative traffic management method according to claim 4, wherein the determining traffic collision risk information based on the multi-modal predicted trajectory clusters of each of the traffic participants includes: Acquiring a multi-mode prediction track cluster of a target traffic participant combination pair; determining predicted track combinations of target traffic participant combination pairs, and judging whether space-time overlapping points exist in each predicted track combination pair in a future preset time period; Determining a predicted track combination pair with space-time overlapping points as a conflict track combination pair, calculating the joint conflict probability corresponding to each conflict track combination pair, and adding the joint probabilities of each conflict track combination pair to obtain the conflict probability of a target traffic participant combination pair; and generating risk early warning information of corresponding grade according to the conflict probability of the target traffic participant combination pair.
6. The vehicle-road cooperative traffic management system is characterized by comprising a mobile carrier, a sensing module and a processing module; the mobile carrier is used for bearing the sensing module and the processing module; the sensing module is used for scanning the surrounding wide area environment to obtain monitoring information; The processing module is respectively connected with the mobile carrier and the sensing module, and is used for controlling the mobile carrier to move and executing the vehicle-road cooperative traffic management method according to any one of claims 1 to 5.
7. An electronic device comprising a processor and a memory, the memory having a stored computer program, wherein the computer program when executed by the processor implements the vehicle-road cooperative traffic management method of any of claims 1 to 5.
8. A non-transitory computer storage medium having a computer program stored thereon, wherein the computer program when executed by a processor implements the vehicle-road cooperative traffic management method according to any of claims 1 to 5.

Description

Vehicle-road cooperative traffic management method, system, equipment and storage medium Technical Field The present application relates to the field of traffic management technologies, and in particular, to a method, a system, an apparatus, and a storage medium for vehicle-road cooperative traffic management. Background The intelligent traffic system (INTELLIGENT TRANSPORTATION SYSTEM, ITS) is a development direction of future traffic systems, and is a comprehensive traffic management system which is established by effectively integrating advanced information technology, data communication transmission technology, electronic sensing technology, control technology, computer technology and the like into a whole ground traffic management system, plays a role in a large range and in all directions, is real-time, accurate and efficient, can effectively solve the modern traffic jam, optimizes traffic routes and improves the traffic capacity of road networks. Among them, vehicle-to-evaluation (V2X) plays an increasingly important role in improving traffic safety, improving road traffic, supporting automatic driving, and the like. However, the conventional vehicle-road cooperation technology often depends on a fixed design system, and requires a lot of time for installation and debugging, and is difficult to cope with a scene of frequently changing a location or configuration. Moreover, when dealing with complex scenes, efficiency and accuracy in the aspect of multi-source data real-time processing are still insufficient, and an ideal traffic management effect is difficult to achieve. Disclosure of Invention In view of the above, the application provides a vehicle-road cooperative traffic management method, a system, equipment and a storage medium. In a first aspect, the application provides a vehicle-road cooperative traffic management method, which is applied to a vehicle-road cooperative traffic management system with mobile cooperative capability, and comprises the following steps: Receiving traffic event information and an instruction message from a traffic management cloud control platform, and controlling the vehicle-road cooperative traffic management system to move to a target point according to the instruction message, wherein the traffic event information comprises at least one of a real-time road condition event list of an authorized traffic information service platform and monitoring information of the vehicle-road cooperative traffic management system; obtaining observation data of each resource node in a target service area according to the traffic event information and the instruction message; Fusing the observation data of each resource node in the target service area by adopting a preset fusion algorithm to generate a state estimation sequence of each traffic participant, wherein the preset fusion algorithm is a self-adaptive unscented Kalman filtering algorithm or an unscented Kalman filtering algorithm; based on the state estimation sequences of the traffic participants, carrying out track prediction by adopting a preset track prediction model, and outputting a multi-mode prediction track cluster with probability weight; and sending decision suggestions to the corresponding traffic participants based on the multi-mode prediction track clusters of the traffic participants. In an embodiment, the obtaining the observed data of each resource node in the target service area according to the traffic event information and the instruction packet includes: determining a target service area according to the traffic event information and the instruction message, and constructing a dynamic resource map of the target service area, wherein the dynamic resource map comprises at least one resource node; And distributing the execution tasks of the resource nodes according to the instruction message and the dynamic resource map, and obtaining the observation data obtained by executing the distribution tasks of the resource nodes. In an embodiment, before constructing the dynamic resource map of the target service area, the method further includes: broadcasting cooperative service signaling and receiving response information of each communication terminal in a service range; Registering each communication terminal as a resource node according to response information of each communication terminal, and recording attribute information of each resource node, wherein the attribute information comprises an ID, position information and a dynamic capability set; The allocating the execution task of each resource node according to the instruction message and the dynamic resource map comprises the following steps: determining a current macroscopic task according to the instruction message; Decomposing the current macroscopic task into a plurality of microscopic subtasks, optimally matching each microscopic subtask with the capacity of each resource node, and distributing the execution task of each resource node according