The invention discloses an automatic driving decision-making method and system in a complex traffic scene based on reinforcement learning, which can process different traffic scenes through a reinforcement learning method and has good generalization. Based on a traditional reinforcement learning framework, a self-attention network is used for extracting feature quantities of environment information and vehicle information to serve as observation spaces, main vehicles are screened, the driving area of the main vehicles at the next moment is predicted, and the vehicle driving safety and the adaptability to complex environments are improved. And the risk correction module is added on the basis, so that the dangerous lane changing action of the vehicle can be shielded, the driving safety of the vehicle is greatly improved, collision accidents are reduced, and the safety of passengers is ensured.

    本发明公开了基于强化学习的复杂交通场景下自动驾驶决策方法及系统,通过强化学习方法处理不同交通场景,具有较好的泛化性。基于传统强化学习框架,使用自注意力网络提取环境信息和车辆信息的特征量作为观测空间,筛选主要车辆,对主要车辆下一时刻行驶区域做出预测,提高车辆行驶安全性以及复杂环境的适应能力。在此基础上增加的风险矫正模块,可以屏蔽车辆的危险换道动作,从而大大提高车辆行驶安全性,降低碰撞事故的发生,保证乘员安全。


    Access

    Download


    Export, share and cite



    Title :

    Automatic driving decision-making method and system in complex traffic scene based on reinforcement learning


    Additional title:

    基于强化学习的复杂交通场景下自动驾驶决策方法及系统


    Contributors:
    WU ZHIFEI (author) / ZHANG SHAOJIE (author) / WU XIN (author) / WANG ZENGRONG (author) / LI SHOUBIAO (author)

    Publication date :

    2023-12-15


    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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 decision-making method based on rule-assisted reinforcement learning

    ZHENG KAI / SU HAN / ZENG XIMU | European Patent Office | 2023

    Free access

    Automatic driving vehicle microscopic decision-making method based on reinforcement learning

    ZHENG KAN / LIU JIE / ZHAO LONG | European Patent Office | 2020

    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