The invention relates to an intelligent hybrid electric vehicle hierarchical control method based on visual perception and deep reinforcement learning, and belongs to the crossing field of new energyvehicles and intelligent vehicles. The method comprises the following steps: in an upper-layer environment, monitoring conditions of a front vehicle and a road surface in real time by utilizing a camera and a convolutional network through environmental perception of an intelligent vehicle, so that a real-time vehicle following distance is calculated according to a monocular camera distance measurement method and an optimal vehicle following distance is judged; in the middle-layer environment, controlling the longitudinal acceleration of the vehicle through a depth value network, so that intelligent vehicle following control over the hybrid electric vehicle is achieved; and in the lower-layer environment, controlling a parallel hybrid power system by using a depth value network algorithm tofinish cooperative control over the engine and the mechanical continuously variable transmission, so that energy management of the hybrid electric vehicle is conducted according to the real-time required power, and finally the optimal fuel economy of the intelligent hybrid electric vehicle is achieved.

    本发明涉及一种基于视觉感知与深度强化学习的智能混合动力汽车分层控制方法,属于新能源汽车与智能汽车的交叉领域。该方法包括:在上层环境中,通过智能汽车的环境感知,利用摄像头与卷积网络实时监测前方车辆与路面情况,从而根据单目摄像头测距方法计算出实时的跟车距离并且判断出最佳的跟车距离;在中层环境中,利用深度值网络控制车辆的纵向加速度,从而实现混合动力汽车的智能跟车控制;在下层环境中,利用深度值网络算法控制并联式混合动力系统,完成对发动机与机械式无极变速器的协同控制,从而依据实时的需求功率进行混合动力汽车能量管理,最终实现智能化混合动力汽车的最佳燃油经济性。


    Access

    Download


    Export, share and cite



    Title :

    Intelligent hybrid electric vehicle hierarchical control method based on visual perception and deep reinforcement learning


    Additional title:

    基于视觉感知与深度强化学习的智能混合动力汽车分层控制方法


    Contributors:
    TANG XIAOLIN (author) / CHEN JIAXIN (author) / DENG ZHONGWEI (author) / HU XIAOSONG (author) / LI JIACHENG (author)

    Publication date :

    2021-03-26


    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



    Hierarchical energy management method for hybrid electric vehicle based on deep reinforcement learning algorithm

    FU ZHUMU / GONG HUIXIAN / TAO FAZHAN et al. | European Patent Office | 2022

    Free access




    Hybrid Electric Vehicle Powertrain Control Based on Reinforcement Learning

    Yoon, Hwan-Sik / Yao, Zhengyu | SAE Technical Papers | 2021