The invention relates to a traffic control method, system and device based on a posterior reward gradient and a medium, and the method comprises the steps: obtaining intersection physical information and intersection traffic flow information of a preset traffic intersection; building an intersection simulation platform of a preset traffic intersection based on the intersection physical information and the intersection traffic flow information; based on the given ideal state of the traffic intersection and the intersection simulation platform, an intersection signal lamp control strategy of the preset traffic intersection is trained through a posterior reward gradient algorithm, and the intersection signal lamp control strategy is used for controlling signal lamps of the preset traffic intersection. According to the method and the device, the problem of how to accurately control the traffic signal lamp of the traffic intersection is solved, the exploratory performance and the data utilization efficiency of the control strategy are enhanced based on the posterior distribution of the posterior reward gradient algorithm, and the traffic control accuracy based on the posterior reward gradient is improved. And the signal lamp of each traffic intersection can be accurately controlled in a targeted manner.

    本申请涉及一种基于后验奖励梯度的交通管控方法、系统、装置和介质,其中,该方法包括:获取预设交通路口的路口物理信息和路口车流信息;基于路口物理信息和路口车流信息,搭建预设交通路口的路口仿真平台;基于给定的交通路口理想状态与路口仿真平台,通过后验奖励梯度算法训练预设交通路口的路口信号灯控制策略,其中,路口信号灯控制策略用于对预设交通路口的信号灯进行控制。通过本申请,解决了如何精准控制交通路口的交通信号灯的问题,实现了基于后验奖励梯度算法的后验分布来增强控制策略的探索性和数据利用效率,提高对应基于后验奖励梯度的交通管控精准度,可以有针对性地对各个交通路口的信号灯作出准确控制。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Traffic control method, system and device based on posterior reward gradient and medium


    Weitere Titelangaben:

    基于后验奖励梯度的交通管控方法、系统、装置和介质


    Beteiligte:
    ZHANG BUHAO (Autor:in) / WU YUE (Autor:in) / WU MENGLI (Autor:in) / WANG TENG (Autor:in) / HAN ZHENXING (Autor:in) / CHENG PING (Autor:in)

    Erscheinungsdatum :

    2024-05-24


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Reinforcement learning traffic signal control method based on internal reward enhancement

    REN YILONG / FU XIANG / CHEN JIAXU et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    URBAN ROAD NETWORK TRAFFIC LIGHT CONTROL METHOD BASED ON EXPECTED REWARD ESTIMATION

    HUANG QIAN / WU KAN / ZHU YONGDONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Adaptive traffic signal control system using composite reward architecture based deep reinforcement learning

    Jamil, Abu Rafe Md / Ganguly, Kishan Kumar / Nower, Naushin | IET | 2021

    Freier Zugriff

    Adaptive traffic signal control system using composite reward architecture based deep reinforcement learning

    Jamil, Abu Rafe Md / Ganguly, Kishan Kumar / Nower, Naushin | Wiley | 2020

    Freier Zugriff