The invention discloses an intersection signal control optimization method based on temporal difference (TD) learning. The method comprises the following steps: 1) collecting the number of vehicles ofall lanes of an intersection and the state of a signal lamp of each lane according to a time sequence; 2) initializing related parameters of TD learning; 3) traversing different learning parameters to obtain different Q value tables, and selecting an optimal Q value table; and 4) selecting an optimal action from the Q value table according to an optimal signal control scheme of the intersection signal lamp at the next moment. Compared with the prior art, the method of the invention has the advantages that intersection traffic flow with high randomness is adapted through real-time signal control, and compared with a traditional timing control timing scheme, the traffic signal timing scheme designed by the invention can improve the traffic efficiency of vehicles at the intersection better.
一种基于时间差分(Temporal Difference,TD)学习的交叉口信号控制优化方法,包括如下步骤:1)按照时间顺序采集交叉口所有车道的车辆数目以及每个车道的信号灯状态;2)初始化TD学习的相关参数;3)遍历不同的学习参数得到不同的Q值表,选取一个最优Q值表4)交叉口信号灯的下一时刻最优的信号控制方案即可从Q值表中选取最优动作得到。与现有技术相比,本发明通过实时信号控制来适应随机性较大的交叉口车流量,本发明所设计的交通信号配时方案比传统的定时控制配时方案更能提高交叉口车辆的通行效率。
Intersection traffic control optimization method based on temporal difference learning
一种基于时间差分学习的交叉口交通控制优化方法
2021-01-22
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Single-intersection traffic signal optimization control method
European Patent Office | 2015
|Intersection traffic signal phase difference alignment adjustment method
European Patent Office | 2024
|European Patent Office | 2024
|