The invention discloses an automatic driving vehicle lane changing decision method, system and device based on deep Q learning and a medium, and the method comprises the steps: S1, determining lane changing parameters according to the information of a vehicle and other surrounding vehicles; s2, collecting an award function of lane changing of the vehicle, and storing and forming a function matrix; s3, learning the function matrix by using a depth Q algorithm to generate a neural network; and S4, collecting information in an actual scene, and inputting the information into the neural network to obtain an optimal lane changing strategy. According to the invention, the automatic driving vehicle behavior decision model based on integrated deep reinforcement learning is adopted, the deep Q learning algorithm and the deep reinforcement learning network are taken as the basis, the award function method is adopted to integrate the strategy, the automatic driving vehicle behavior lane changing model is established, the traffic efficiency can be obviously improved, and the blocking rate is reduced.

    基于深度Q学习的自动驾驶车辆换道决策方法、系统、设备及介质,方法包括S1,根据自身车辆及周边其他车辆的信息,确定换道参数;S2,收集自身车辆换道的奖励函数,储存并形成函数矩阵;S3,采用深度Q算法对函数矩阵进行学习,生成神经网络;S4,采集实际场景中的信息,并输入神经网络,获得换道最优策略。本发明通过基于集成的深度强化学习的自动驾驶车辆行为决策模型,以深度Q学习算法深度强化学习网络为基础,采用奖励函数方法集成策略,建立自动驾驶车辆行为换道模型,能够显著提升交通效率,降低阻塞率。


    Access

    Download


    Export, share and cite



    Title :

    Deep Q learning-based automatic driving vehicle lane changing decision-making method, system and equipment, and medium


    Additional title:

    基于深度Q学习的自动驾驶车辆换道决策方法、系统、设备及介质


    Contributors:
    WANG JIAWEN (author) / ZHANG LINGZHI (author) / ZHANG YUDI (author) / CHEN HAO (author) / WEN XIANTANG (author)

    Publication date :

    2024-09-06


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion



    Hybrid automatic driving lane changing decision-making method based on deep reinforcement learning

    LIANG SHANSHAN / ZHANG JIE / CHEN CHONGCHONG et al. | European Patent Office | 2024

    Free access

    Automatic driving vehicle lane changing decision system and method based on deep reinforcement learning

    XIONG MINGQIANG / QIAO JIE / JIANG MENG et al. | European Patent Office | 2022

    Free access

    Automatic driving lane changing decision-making method, device and equipment and storage medium

    ZHANG ZHONGJU / LIU YANG / ZOU BINGYU et al. | European Patent Office | 2023

    Free access

    Automatic driving lane changing decision making method and device and vehicle

    XUE BING / XU CHUANLUO / HAN ZHIHUA et al. | European Patent Office | 2021

    Free access

    Automatic driving lane changing decision-making and model training method, device, equipment and vehicle

    PAN AN / WANG ZEXU / LIU JINGKAI et al. | European Patent Office | 2024

    Free access