The invention relates to a large-scale intersection management method based on multi-agent reinforcement learning. The method comprises the following steps: constructing an intersection scene model; a central intelligent agent and vehicle intelligent agents are defined, the central intelligent agent represents an intersection calculation unit, each vehicle intelligent agent represents an intelligent network connection vehicle in an intersection, and a state space, an action space and a reward function of each intelligent agent are set; the central intelligent agent is used for observing intersection environment variables and interacting with the vehicle intelligent agents at the same time; constructing a multi-agent reinforcement learning model, and training the reinforcement learning model to obtain an optimized reinforcement learning model; and deploying the optimized reinforcement learning model into each agent to guide the operation of the intelligent network connection vehicle. Compared with the prior art, the method has the advantages of low model calculation complexity, good practicability and the like.

    本发明涉及一种基于多智能体强化学习的大型路口管理方法,包括以下步骤:构建交叉路口场景模型;定义中心式智能体和车辆智能体,中心式智能体代表路口计算单元,每个车辆智能体分别代表路口中的一辆智能网联车,分别设定每个智能体的状态空间、动作空间及奖励函数;中心式智能体用于观测路口环境变量,同时与各个车辆智能体进行交互;构建多智能体强化学习模型,对强化学习模型进行训练,得到优化的强化学习模型;将优化的强化学习模型部署到各个智能体中,以引导智能网联车运行。与现有技术相比,本发明具有模型计算复杂度低、实用性良好等优点。


    Access

    Download


    Export, share and cite



    Title :

    Large-scale intersection management method based on multi-agent reinforcement learning


    Additional title:

    一种基于多智能体强化学习的大型路口管理方法


    Contributors:
    ZHAO SHENGJIE (author) / XUE JINWEI (author) / DENG HAO (author)

    Publication date :

    2023-07-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    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



    Intersection decision-making method based on multi-agent deep reinforcement learning

    DU YU / JIANG ANNI / ZHAO SHIXIN et al. | European Patent Office | 2024

    Free access

    Multi-Agent Mix Hierarchical Deep Reinforcement Learning for Large-Scale Fleet Management

    Huang, Xiaohui / Ling, Jiahao / Yang, Xiaofei et al. | IEEE | 2023


    End-to-End Intersection Handling using Multi-Agent Deep Reinforcement Learning

    Capasso, Alessandro Paolo / Maramotti, Paolo / Dell'Eva, Anthony et al. | IEEE | 2021


    Multi-agent reinforcement learning traffic signal cooperative control method considering intersection heterogeneity

    BIE YIMING / JI YUTING / JI JINHUA et al. | European Patent Office | 2024

    Free access