Disclosed is technology for controlling deep reinforcement learning-based legged robot locomotion by inferring implicit terrain information. A legged robot control method may include inferring an action of a quadrupedal robot from proprioception through a deep reinforcement learning-legged robot model, and a locomotion policy that implicitly infers properties of terrains through which the quadrupedal robot moves may be learned in the legged robot model.


    Access

    Download


    Export, share and cite



    Title :

    LEARNING ROBUST LEGGED ROBOT LOCOMOTION WITH IMPLICIT TERRAIN IMAGINATION VIA DEEP REINFORCEMENT LEARNING


    Contributors:

    Publication date :

    2025-01-16


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B25J Manipulatoren , MANIPULATORS / B62D MOTOR VEHICLES , Motorfahrzeuge



    LEARNING ROBUST LEGGED ROBOT LOCOMOTION WITH IMPLICIT TERRAIN IMAGINATION VIA DEEP REINFORCEMENT LEARNING

    MYUNG HYUN / NAHRENDRA I MADE ASWIN / YU BYEONGHO | European Patent Office | 2025

    Free access

    RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control

    Gangapurwala, S / Geisert, M / Orsolino, R et al. | BASE | 2022

    Free access

    On Terrain-Aware Locomotion for Legged Robots

    FAHMI, AHMED MOHAMED SHAMEL BAHAAELDEEN | BASE | 2021

    Free access

    All-terrain wheel-legged robot

    YANG ZIZHAO / HE LEIBO / ZHANG ZHIHAO et al. | European Patent Office | 2021

    Free access

    A Bayesian regression approach to terrain mapping and an application to legged robot locomotion

    Plagemann, C. / Mischke, S. / Prentice, S. et al. | British Library Online Contents | 2009