The invention provides a reinforcement learning intelligent traffic light control method based on an Internet-of-things platform. The reinforcement learning intelligent traffic light control method mainly comprises the following steps of: step 1, completing simulation of urban traffic and traffic flow through microscopic traffic simulation software; step 2, acquiring equipment state information from a simulation equipment end through a OneNET cloud platform, issuing the equipment state information to a control end by the OneNET, receiving a control command, and sending the control command to the simulation equipment end to realize information communication between the simulation traffic flow and the control end; and step 3, using a DDQN neural network model to realize real-time coordination control of traffic lights according to intersection traffic flow conditions, and minimizing average waiting time of all vehicles. A reinforcement learning agent controls each intersection, each intersection trains the corresponding reinforcement learning agent, and communication is realized by sharing information among the agents. The invention further provides a reinforcement learning intelligent traffic light control system based on an Internet-of-things platform.

    本发明提出了一种基于物联网平台的强化学习智能交通信号灯控制方法,主要包含以下几方面的内容:步骤1:通过微观交通模拟软件完成对城市交通和交通流量的模拟;步骤2:通过OneNET云平台从模拟设备端获取设备状态信息,同时OneNET向控制端下发设备状态信息,接受控制命令,再向模拟设备端发送控制命令,实现模拟交通车流与控制端的信息通讯;步骤3:使用DDQN神经网络模型,实现根据路口车流情况对交通信号灯的实时协调控制,最小化所有车辆的平均等待时间;强化学习智能体控制每个路口,每个交叉口分别训练强化学习智能体,并且通过共享智能体之间的信息实现通信。本发明还提出了一种基于物联网平台的强化学习智能交通信号灯控制系统。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Reinforcement learning intelligent traffic light control method and system based on Internet-of-things platform


    Weitere Titelangaben:

    基于物联网平台的强化学习智能交通信号灯控制方法及系统


    Beteiligte:
    CHEN MINGSONG (Autor:in) / MA YANYUE (Autor:in) / SHAO MINGLI (Autor:in) / ZHAO WUPAN (Autor:in) / CAO E (Autor:in)

    Erscheinungsdatum :

    26.02.2021


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Traffic light intelligent control system and method based on Internet of Things letter fusion cloud platform

    CHEN MINGSONG / XIAO SIHUI / XU JINGWEN et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Intelligent traffic management method and platform based on Internet of Things cloud platform

    ZHANG NING / JIA SHIWEN / SUN SHANSHAN | Europäisches Patentamt | 2024

    Freier Zugriff

    Intelligent traffic control system based on Internet of Things

    HUANG HAO | Europäisches Patentamt | 2015

    Freier Zugriff

    Green ecological intelligent traffic system based on Internet of Things cloud platform

    LIU YONGJIE | Europäisches Patentamt | 2020

    Freier Zugriff

    Suats Internet of things intelligent traffic control system

    PANG MINGZHOU / SUN MIN / YUAN XIAOGANG et al. | Europäisches Patentamt | 2015

    Freier Zugriff