The invention relates to the field of road network signal lamp control, in particular to a data-driven networked traffic signal multi-agent adaptive coordination control method. According to the method, data interaction of queuing length and green light time is carried out through a traffic signal machine multi-agent system and network connection, and real-time online traffic data is provided. According to the method, the automobile queuing length serves as parameter input, the green light time serves as parameter output, queuing balance control over the multidirectional traffic flow through signal timing is achieved, and delay and queuing caused by green light waste in traditional intersection signal control are greatly reduced.
本发明涉及路网信号灯控制领域,尤其涉及一种数据驱动的网联交通信号多智能体自适应协调控制方法。该方法通过交通信号机多智能体系统,网联进行排队长度、绿灯时间的数据交互,提供实时在线的交通数据。该方法将汽车排队长度作为参数输入,绿灯时间作为参数输出,实现了通过信号配时对多向交通流的排队均衡控制,大大降低了传统交叉口信号控制中绿时浪费所导致的延误及排队。
Data-driven networked traffic signal multi-agent adaptive coordination control method
数据驱动的网联交通信号多智能体自适应协调控制方法
2023-07-07
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Multi-agent reinforcement learning for integrated and networked adaptive traffic signal control
European Patent Office | 2017
|MULTI-AGENT REINFORCEMENT LEARNING FOR INTEGRATED AND NETWORKED ADAPTIVE TRAFFIC SIGNAL CONTROL
European Patent Office | 2018
|Signal control method adaptive to traffic events in networked traffic environment
European Patent Office | 2024
|Multi-intersection traffic adaptive coordination control method
European Patent Office | 2022
|Multi-agent reinforcement learning method for fair adaptive traffic signal control
European Patent Office | 2023
|