基于多智能体的城市交通区域协调控制方法

An Approach to Urban Road Traffic Signal Coordination Control Based on Multi-Agent System

在分析城市道路交通信号控制特点的基础上,提出了基于多智能体的城市道路区域协调控制方法.在单路口Agent中引入加强学习方法,实现交通信号实时在线调整;在由多交叉口构成的区域路网中,以车辆平均延误为目标,通过多路口Agent之间的协调机制,实现城市交通区域信号控制的智能协调和全局优化,提高整个区域交通的效率,减少车辆的延误.通过仿真实验,与定时控制和感应控制相比,该方法使车辆的平均延误明显减小.

The characteristic of traffic signal control system is analysed, and an urban road traffic area- wide coordination control method based on Multi-Agent technology is proposed in this paper. The rein- forcement learning is introduced in the agent model of single traffic intersection, and the time of green light can be adjusted dynamically on line . In the road network of multiple intersections, the average delay of vehicles is employed as objective function in Multi-Agent control system ,and the intelligent coordination and optimization of whole area control system in urban road network are realized through the coordination of each agent. The average delay time is reduced, and the traffic efficiency is improved. The computer simulation results indicate that the control algorithm is effective compared with fixed-time control and actuated-control.