论文部分内容阅读
为减少干线协调交叉口的车辆延误,基于多智能体系统与增强学习算法(RL)建立了一种新的分布式交通信号协调算法.增强学习算法通过训练各个智能体与外界环境的交互能力达到减少车辆延误的目的.为更精确地描述干线上的车队运动规律,引入了罗伯逊车队离散模型,并基于该模型以及HCM2000中的干线交叉口车流延误计算公式建立了RL中的回报函数.在Matlab中仿真验证了所建算法的控制效果,并在3种不同交通负荷下与传统信号协调算法进行对比.结果表明,该算法较传统算法能有效降低干线车流延误;并且随着干线饱和度的增加降低幅度逐渐增大.该结果验证了所建算法的可行性与有效性.
In order to reduce the vehicle delay at the intersection of trunk alignment, a new distributed traffic signal coordination algorithm based on multi-agent system and enhanced learning algorithm (RL) is established. The enhanced learning algorithm achieves Reduce the vehicle delay.To more accurately describe the movement of the team on the main line, the introduction of the Robertson fleet discrete model, and based on the model and the HCM2000 traffic flow at the intersection of crossroads established RL in the reward function. The simulation results show that the proposed algorithm can effectively reduce the delay of traffic flow in the main line compared with the traditional signal coordination algorithm under three different traffic loads.With the increase of trunk line saturation The decrease is gradually increasing.This result verifies the feasibility and effectiveness of the proposed method.