The invention discloses an adaptive traffic signal control method based on multi-agent reinforcement learning, and the method comprises the steps: building an agent network corresponding to each intersection in a traffic network by aiming at each intersection in the traffic network; acquiring real-time traffic characteristics in the traffic network; respectively transmitting the real-time trafficcharacteristics into an intelligent agent network corresponding to the intersection according to the position of the intersection to obtain the phase of the intersection outputted by the intelligent agent network, and executing traffic signal control of the intersection according to the phase of the intersection, wherein the intelligent agent network determines the phase of the intersection by taking the average value of the sum of the number of vehicles waiting on the entrance lanes of the intersection corresponding to the intelligent agent network and the intersection adjacent to the intersection. According to the invention, the coordination capability between independent intelligent agents is improved, and a solution is provided for traffic signal control in a complex road network environment.

    本发明公开了一种基于多智能体强化学习的自适应交通信号控制方法,包括:针对交通路网中每个交叉口,建立与所述交叉口对应的智能体网络;获取所述交通路网中的实时交通特征;将所述实时交通特征按照交叉口的位置分别传入与所述交叉口对应的智能体网络中,得到所述智能体网络输出的交叉口的相位,并按照所述交叉口的相位执行该交叉口的交通信号控制;其中,所述智能体网络以该智能体网络对应的交叉口以及该交叉口相邻的交叉口的进入车道上正在等待的车辆数量总和的平均值为奖励确定该交叉口的相位。本发明提高了独立智能体之间的协调能力,为复杂路网环境的交通信号控制提供解决方案。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Adaptive traffic signal control method based on multi-agent reinforcement learning


    Weitere Titelangaben:

    一种基于多智能体强化学习的自适应交通信号控制方法


    Beteiligte:
    ZHANG CHENGWEI (Autor:in) / JIN SHAN (Autor:in) / ZHENG KANGJIE (Autor:in)

    Erscheinungsdatum :

    2021-01-12


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06K Erkennen von Daten , RECOGNITION OF DATA



    Multi-agent reinforcement learning method for fair adaptive traffic signal control

    ZHANG CHENGWEI / FANG WANQING / ZHAO XINTIAN | Europäisches Patentamt | 2023

    Freier Zugriff

    Multi-agent reinforcement learning for integrated and networked adaptive traffic signal control

    EL-TANTAWY SAMAH / ABDULHAI BAHER | Europäisches Patentamt | 2017

    Freier Zugriff

    MULTI-AGENT REINFORCEMENT LEARNING FOR INTEGRATED AND NETWORKED ADAPTIVE TRAFFIC SIGNAL CONTROL

    EL-TANTAWY SAMAH / ABDULHAI BAHER | Europäisches Patentamt | 2018

    Freier Zugriff

    Traffic light signal control method based on multi-agent reinforcement learning

    ZHAO SHENGJIE / DENG HAO / CHEN ZHI | Europäisches Patentamt | 2022

    Freier Zugriff