基于车辆诱导的交通灯动态配时算法研究

Research of Traffic Lights Dynamic Timing Algorithm Based on Vehicles Induction

随着城市交通流量日益增加,现有的交通灯固定时间控制系统不能很好解决交通拥堵问题。针对这一背景,采用基于Q_学习的交通灯控制策略(QTGCS)对交通灯进行动态配时,以减少车辆在交叉口的平均等待时间,通过模糊逻辑控制根据车辆诱导信息对Q_学习的动作选择进行优化(FQTGCS),以提高Q_学习算法的收敛速度。实验结果表明,所采用的交通灯控制策略可以很好地解决交通拥堵问题,能更好地提高交通系统的性能。

With the traffic flow increasing in our country,the fixed time traffic lights control system can′t very well solve the problem of traffic congestion. Under this background,the traffic light control strategy based on Q-learning algorithm （QTGCS ）for dynamic traffic light timing is put forward,in order to reduce the average waiting time of vehicles in inter-section,and by the fuzzy logic control algorithm and using vehicles induced information to optimize the action section of the Q-learning（FQTGCS）,the convergence speed of the Q-learning algorithm is improved. The experimental results show that the proposed traffic lights control strategy can solve the problem of traffic congestion,and better improve the perform-ance of transportation system.