The invention discloses a hybrid electric vehicle energy management method based on machine vision and deep learning, which belongs to the field of hybrid electric vehicle energy management. The method mainly comprises the following steps of: extracting available visual information from a vehicle-mounted camera by using a target detection method based on a convolutional neural network (CNN); further establishing a visual processing module based on the camera and the CNN; establishing a hybrid electric vehicle energy management method based on the DRL by utilizing a DRL algorithm; further utilizing a depth deterministic strategy gradient (DDPG) algorithm to construct a DDPG controller; combining a vision processing module and a DRL-based energy management method, establishing a hybrid electric vehicle energy management method based on machine vision and deep reinforcement learning through the DDPG controller, and achieving online real-time control over vehicle power distribution. According to the method provided by the invention, the visual perception sensor of the autonomous vehicle can be shared, the real-time performance of an energy management strategy is ensured, and the fuel economy of the vehicle is further improved.

    本发明公开了一种基于机器视觉和深度学习的混合动力汽车能量管理方法,属于混合动力汽车能量管理领域,方法主要包括:基于卷积神经网络(CNN)的目标检测方法,从车载摄像机中提取可用的视觉信息,进一步建立基于摄像机和CNN的视觉处理模块;利用DRL算法,建立基于DRL的混合动力汽车能量管理方法;进一步利用深度确定性策略梯度(DDPG)算法,构建DDPG控制器;将视觉处模块和基于DRL的能量管理方法相结合,通过DDPG控制器,建立基于机器视觉和深度强化学习的混合动力汽车能量管理方法,实现在线实时控制车辆的功率分配。本发明所提出的方法能够共用自动驾驶汽车的视觉感知传感器,保证能量管理策略的实时性,进一步提高车辆的燃油经济性。


    Access

    Download


    Export, share and cite



    Title :

    Hybrid electric vehicle energy management method based on machine vision and deep learning


    Additional title:

    基于机器视觉和深度学习的混合动力汽车能量管理方法


    Contributors:
    PENG JIANKUN (author) / WANG YONG (author) / NAN SIRUI (author) / TAN HUACHUN (author) / WU YUANKAI (author) / DING FAN (author)

    Publication date :

    2021-01-01


    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




    Hybrid electric vehicle energy management method based on traffic information and deep reinforcement learning

    TANG XIAOLIN / ZHU HELONG / DENG LEI et al. | European Patent Office | 2022

    Free access

    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 energy management method based on reinforcement learning

    LOU DIMING / ZHAO YINGHUA | European Patent Office | 2021

    Free access

    Unmanned vehicle machine vision deep learning system

    CHEN QIAOSONG / ZHU XIAOLANG / PARK CHANG HO | European Patent Office | 2024

    Free access