The invention provides an automatic driving vehicle lane changing method based on double-layer deep reinforcement learning, and the method comprises the steps: dividing the lane changing behavior of an automatic driving vehicle into a lane changing decision stage and a lane changing motion stage through the combination of human driving behaviors, carrying out the training of a lane changing decision and a motion track through a deep reinforcement learning DQN network and a DDPG network, and carrying out the training of the lane changing decision and the motion track. Finally, intelligent decision making can be carried out on the current driving state in the prediction process, and decision making and movement functions of the automatic driving vehicle in the lane changing behavior are integrally completed. According to the method, a double-layer deep reinforcement learning method is adopted to simulate actual driving behaviors of human beings, and finally the purpose of intelligent lane changing behaviors of the automatic driving vehicle is achieved.

    本发明提出了一种基于双层深度强化学习的自动驾驶车辆换道方法,所述方法包括:结合人类驾驶行为,将自动驾驶车辆换道行为分为换道决策阶段和换道运动阶段,分别使用深度强化学习DQN网络与DDPG网络进行换到决策和运动轨迹的训练,最终可在预测过程中将对当前行车状态进行智能决策,一体化的完成自动驾驶车辆在换道行为中决策和运动功能。本发明实现了采用双层深度强化学习方法模拟人类实际驾驶行为,最终实现自动驾驶车辆智能换道行为的目标。


    Access

    Download


    Export, share and cite



    Title :

    Automatic driving vehicle lane changing method based on double-layer deep reinforcement learning


    Additional title:

    一种基于双层深度强化学习的自动驾驶车辆换道方法


    Contributors:
    PENG JIANKUN (author) / SHEN YANG (author) / ZHANG SIYU (author) / FAN YI (author) / ZHOU JIAMING (author) / YI FENGYAN (author)

    Publication date :

    2023-08-25


    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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    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 control method based on rule fusion reinforcement learning

    XIONG LU / LI ZHUOREN / YANG RUOLIN et al. | European Patent Office | 2022

    Free access

    Harmonious Lane Changing via Deep Reinforcement Learning

    Wang, Guan / Hu, Jianming / Li, Zhiheng et al. | IEEE | 2022


    Deep Reinforcement Learning Approach for Automated Vehicle Mandatory Lane Changing

    Ammourah, Rami / Talebpour, Alireza | Transportation Research Record | 2022