The embodiment of the invention relates to the technical field of intelligent traffic and automatic driving, in particular to a vehicle-road cooperative multi-hop method based on reinforcement learning, which comprises the following steps: acquiring road accident information, and establishing multi-hop connection to relay nodes around a road accident site to transmit the road accident information; the vehicle transmits the road accident information and the vehicle driving information to surrounding vehicles and relay nodes; and the relay node receives the vehicle driving information and determines whether to stop sending the road accident information according to the vehicle driving information. Once an accident is detected, related road accident information is collected immediately. Multi-hop connection is established to surrounding relay nodes, and road accident information is spread outwards from an accident site so as to achieve the coverage of the widest range. After the vehicle receives the road accident information from the relay node, the vehicle sends the information and the driving information of the vehicle to surrounding vehicles and the relay node. Information is transmitted through multi-hop connection, the information spreading range can be expanded, and the road traffic safety is improved.
本发明实施例涉及智能交通及自动驾驶技术领域,具体涉及一种基于强化学习的车路协同多跳方法,获取道路事故信息,向道路事故地点周围的中继节点建立多跳连接传递道路事故信息;车辆将道路事故信息和车辆行驶信息传递给周围车辆和中继节点;中继节点接收车辆行驶信息,根据车辆行驶信息确定是否停止发送道路事故信息。一旦检测到事故立即采集相关的道路事故信息。向周围的中继节点建立多跳连接,将道路事故信息从事故地点开始向外扩散,以达到最广范围的覆盖。车辆接收到来自中继节点的道路事故信息后,车辆会将该信息和自身行驶信息发送给周围车辆和中继节点。通过多跳连接传递信息,可以扩大信息传播范围,提高道路交通安全性。
Vehicle infrastructure cooperative multi-hop method based on reinforcement learning
一种基于强化学习的车路协同多跳方法
2023-08-15
Patent
Electronic Resource
Chinese
Cooperative Infrastructure-Based Vehicle Positioning
IEEE | 2016
|Vehicle infrastructure collaborative awareness method based on deep reinforcement learning
European Patent Office | 2025
|Multi-UAV Cooperative Target Assignment Method Based on Reinforcement Learning
DOAJ | 2024
|