The invention discloses an intelligent vehicle scheduling method for a ramp convergence scene, and the method comprises the steps: receiving local state information transmitted by each intelligent network connection vehicle in the current ramp convergence scene, and combining the local state information with obtained global state information to form a combined state space; inputting the joint state space into a trained deep reinforcement learning model to obtain a joint action space of the intelligent network connection vehicle; scheduling each intelligent network connection vehicle according to the joint action space; wherein the deep reinforcement learning model comprises a current strategy network, a target strategy network and a value network; the deep reinforcement learning model acquisition method comprises the steps of iteratively executing a total loop step until a preset condition is met, and obtaining a trained deep reinforcement learning model. And training and updating parameters of a current strategy network, a target strategy network and a value network in the deep reinforcement learning model by utilizing interaction information of each step in the interaction process of the historical intelligent network connection vehicle and the environment. According to the invention, the vehicle throughput in the ramp convergence scene is improved.

    本发明公开了一种面向匝道汇流场景的智能车辆调度方法,包括:接收当前匝道汇流场景中各智能网联车辆发送的局部状态信息,与获取的全局状态信息组合成联合状态空间;将联合状态空间输入训练好的深度强化学习模型中,得到智能网联车辆的联合动作空间;根据所述联合动作空间,对各智能网联车辆进行调度;其中所述深度强化学习模型包括当前策略网络、目标策略网络以及价值网络;所述深度强化学习模型的获取方法包括:迭代执行总循环步骤,直至达到预设条件,得到训练好的深度强化学习模型。利用历史智能网联车辆与环境的交互过程中每一步的交互信息,训练更新深度强化学习模型中当前策略网络、目标策略网络以及价值网络的参数。本发明提高了匝道汇流场景中的车辆吞吐量。


    Access

    Download


    Export, share and cite



    Title :

    Intelligent vehicle scheduling method for ramp convergence scene


    Additional title:

    一种面向匝道汇流场景的智能车辆调度方法


    Contributors:
    TAN GUOPING (author) / RAO BOWEN (author) / HU HEXUAN (author) / ZHOU SIYUAN (author)

    Publication date :

    2024-03-29


    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



    Multi-scene vehicle ramp estimation method and module

    HOU SHICHANG / HE YICHAO / LI HAO et al. | European Patent Office | 2023

    Free access

    Intelligent vehicle highway ramp convergence decision-making method based on reinforcement learning

    HAN GUANGDE / ZHU WENTAO / XIE XIANYI et al. | European Patent Office | 2023

    Free access

    Vehicle control method, device and equipment in ramp scene

    ZHANG FANG / DONG ZHIHUA / XU JIANJIANG | European Patent Office | 2024

    Free access

    Vehicle control method, device and equipment for ramp convergence

    TANG TIANLONG / MO SIYAO / LI DONGCHEN et al. | European Patent Office | 2022

    Free access

    Ramp convergence decision control method, electronic equipment and vehicle

    YU CHEN / XIE JINJING / ZHOU WEIGUANG | European Patent Office | 2024

    Free access