The invention discloses an automatic driving decision-making method based on a finite hierarchy state machine and deep reinforcement learning, and the method comprises the following steps: S1, achieving environment perception and fusion, and completing the unification and conversion of coordinates; s2, scene analysis is carried out based on the information after coordinate unification; s3, performing top-layer state transfer output based on a scene analysis result; s4, performing a bottom layer decision based on a deep reinforcement learning algorithm; and S5, outputting a decision result. According to the method, deep reinforcement learning is used in a bottom-layer decision planning stage, and training learning is performed on top-layer transfer states, so that the coupling degree of various states can be reduced, the data volume required by deep learning in each state is reduced, and the algorithm efficiency of reinforcement learning is improved.

    本发明公开了基于有限层次状态机和深度强化学习的自动驾驶决策方法,包括下列步骤:S1、实现环境感知与融合,并完成坐标的统一与转换;S2、基于统一坐标后的信息进行场景分析;S3、基于场景分析的结果进行顶层状态转移输出;S4、进行基于深度强化学习算法的底层决策;S5、输出决策结果。本发明在底层决策规划阶段使用深度强化学习,对顶层转移状态分别进行训练学习,不仅能降低各种状态的耦合程度,而且在每种状态进行深度学习时所要求的数据量都将降低,提高了强化学习的算法效率。


    Access

    Download


    Export, share and cite



    Title :

    Automatic driving decision-making method based on finite hierarchy state machine and deep reinforcement learning


    Additional title:

    基于有限层次状态机和深度强化学习的自动驾驶决策方法


    Contributors:
    GU TAOTAO (author) / WU YONG (author) / DAI XINGMIN (author) / ZHAI XIANXU (author) / WANG DONG (author) / WU XUDONG (author) / LIU HENG (author) / JIANG MIN (author) / WANG KAI (author) / ZHOU QI (author)

    Publication date :

    2023-10-24


    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 decision-making method based on deep reinforcement learning

    LIU CHENGQI / LIU SHAOWEIHUA / ZHANG YUJIE et al. | European Patent Office | 2024

    Free access

    Automatic driving behavior decision-making method based on deep reinforcement learning

    YANG MINGZHU / LIU XIANGWEI / LI ZHUOLUO | European Patent Office | 2020

    Free access

    Automatic driving vehicle overtaking decision-making method based on deep reinforcement learning

    LIU JIA / LI HUIYUN / CUI YUNDUAN | European Patent Office | 2022

    Free access

    Automatic driving decision-making system based on deep reinforcement learning

    ZHENG XIAOYAO / YAO QINGHE / ZHANG JIANPENG et al. | European Patent Office | 2024

    Free access

    Automatic driving behavior decision-making method based on deep reinforcement learning

    ZOU JUNYI / WANG HAIXIN | European Patent Office | 2024

    Free access