全息交通感知环境下干线协调控制方法研究  

Research on Coordinated Control Method of Trunk Line in Holographic Traffic Perception Environment

作　　者：秦瑞阳 张存保[1] 李雪梅[1] 王厚沂 QIN Ruiyang;ZHANG Cunbao;LI Xuemei;WANG Houyi(Wuhan University of Technology School of Intelligent Transportation Systems Research Center,Wuhan 430063,China)

机构地区：[1]武汉理工大学智能交通系统研究中心,武汉430063

出　　处：《武汉理工大学学报（交通科学与工程版）》2024年第4期622-627,共6页Journal of Wuhan University of Technology（Transportation Science & Engineering）

基　　金：国家重点研发计划项目(2020YFB1600500)。

摘　　要：文中提出了一种改进的基于多智能体深度强化学习的干线协调控制模型.将全息交叉口的实时交通信息离散化建模,与车流的延误、停车次数等交通特征参数共同作为状态输入智能体;将干线车流的延误与停车次数作为奖励函数,逐渐调整干线交叉口的公共周期,按时间步长更新交叉口之间相位差,实现干线交叉口的自适应控制;以传统深度强化学习(deep reinforcement learning,DRL)控制方法及MAXBAND协调控制方法为参照模型,分别在低峰期、平峰期及高峰期时段,对比车均延误及平均排队长度两项指标.该控制模型使车均延误降低了21.6%、31.8%和22.1%,平均排队长度降低了34.3%、18.4%和24.1%,表明在全息感知环境下,所提方法可有效提高干线通行效率.An improved trunk coordinated control model based on multi-agent deep reinforcement learning was proposed in this paper.The real-time traffic information of holographic intersection was modeled discretely,and it was used as the state input agent together with traffic characteristic parameters such as traffic delay and parking times.Taking the delay of trunk traffic flow and the number of stops as reward functions,the public period of trunk intersections was gradually adjusted.The phase difference between intersections was updated by time step,and then the adaptive control of trunk intersections was realized.Taking the traditional deep reinforcement learning(DRL)control method and MAXBAND coordinated control method as reference models,the average vehicle delay and average queue length were compared in low peak period,flat peak period and peak period respectively.The results show that the control model can reduce the average vehicle delay by 21.6%,31.8%and 22.1%,and the average queue length by 34.3%,18.4%and 24.1%,which shows that the proposed method can effectively improve the trunk line traffic efficiency in the holographic sensing environment.

关 键 词：全息交通感知 干线协调控制 深度强化学习 多智能体 

分 类 号：U491.5[交通运输工程—交通运输规划与管理]