The invention provides a humanoid robot reinforcement learning training method, device and equipment and a storage medium, and the method comprises the steps: obtaining a model file of a humanoid robot; analyzing the model file to obtain a position relation of two feet of the humanoid robot and part constraint information of the humanoid robot, and establishing a reference coordinate system according to the position relation of the two feet; according to the reference coordinate system and the component constraint information, a parallel ankle joint mechanism model of the humanoid robot is constructed, and inverse kinematics information is determined according to the parallel ankle joint mechanism model; and training a reinforcement learning strategy of the humanoid robot according to the inverse kinematics information and the component constraint information. According to the method, series-parallel connection conversion in a resolving mode in the training process is avoided, the operation efficiency is improved, meanwhile, the requirement for reinforcement learning parallel sampling efficiency is lowered, the training process is simplified, and the convergence speed of reinforcement learning strategies is increased.

    本申请提供了一种人形机器人强化学习训练方法、装置、设备及存储介质,其中,该方法包括:获取人形机器人的模型文件;对模型文件进行解析,得到人形机器人的双脚的位置关系以及人形机器人的部件约束信息,并根据双脚的位置关系,建立基准坐标系;根据基准坐标系以及部件约束信息,构建得到人形机器人的并联踝关节机构模型,并根据并联踝关节机构模型确定逆运动学信息;根据逆运动学信息以及部件约束信息,对人形机器人的强化学习策略进行训练。本申请避免了训练过程中通过解算的方式进行串并联转换,提高了运算效率,同时,还降低了对强化学习并行采样效率的要求,简化了训练过程,加快强化学习策略的收敛速度。


    Access

    Download


    Export, share and cite



    Title :

    Humanoid robot reinforcement learning training method, device and equipment and storage medium


    Additional title:

    人形机器人强化学习训练方法、装置、设备及存储介质


    Contributors:
    HAN GANG (author) / GUO YIJIE (author) / ZHANG QIANG (author) / ZHAO WEN (author) / SUN JINGKAI (author)

    Publication date :

    2025-05-23


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B25J Manipulatoren , MANIPULATORS / B62D MOTOR VEHICLES , Motorfahrzeuge / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung



    Method for estimating pose of humanoid robot, humanoid robot and computer-readable storage medium

    XIE YAN / ZHAO MINGGUO / XIONG YOUJUN | European Patent Office | 2025

    Free access

    Humanoid robot control method and system, humanoid robot and medium

    LI WEICHONG | European Patent Office | 2024

    Free access

    METHOD FOR ESTIMATING POSE OF HUMANOID ROBOT, HUMANOID ROBOT AND COMPUTER-READABLE STORAGE MEDIUM

    XIE YAN / ZHAO MINGGUO / XIONG YOUJUN | European Patent Office | 2023

    Free access

    HUMANOID ROBOT THIGH, HUMANOID ROBOT, AND MANUFACTURING METHOD

    NIE DAMING / ZHU SHIQIANG / KONG LINGYU et al. | European Patent Office | 2025

    Free access

    Application to Swim Action of the Small Humanoid Robot by Reinforcement Learning

    Kobayashi, S. / Suzuki, K. / Study Group of Aero Aqua Bio-mechanisms | British Library Conference Proceedings | 2006