Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot. In contrast, approximate reduced-order models are commonly used for many model predictive control strategies. In this work we abandon the conventional use of high-fidelity dynamics models in RL and we instead seek to understand what can be achieved when using RL with a much simpler centroidal model when applied to quadrupedal locomotion. We show that RL-based control of the accelerations of a centroidal model is surprisingly effective, when combined with a quadratic program to realize the commanded actions via ground contact forces. It allows for a simple reward structure, reduced computational costs, and robust sim-to-real transfer. We show the generality of the method by demonstrating flat-terrain gaits, stepping-stone locomotion, two-legged in-place balance, balance beam locomotion, and direct sim-to-real transfer.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model


    Weitere Titelangaben:

    Springer Proceedings in Advanced Robotics


    Beteiligte:
    LaValle, Steven M. (Herausgeber:in) / O’Kane, Jason M. (Herausgeber:in) / Otte, Michael (Herausgeber:in) / Sadigh, Dorsa (Herausgeber:in) / Tokekar, Pratap (Herausgeber:in) / Xie, Zhaoming (Autor:in) / Da, Xingye (Autor:in) / Babich, Buck (Autor:in) / Garg, Animesh (Autor:in) / de Panne, Michiel van (Autor:in)

    Kongress:

    International Workshop on the Algorithmic Foundations of Robotics ; 2022 ; , MD, USA June 22, 2022 - June 24, 2022



    Erscheinungsdatum :

    2022-12-15


    Format / Umfang :

    17 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    GLIiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model

    Xie, Zhaoming / Da, Xingye / Babich, Buck et al. | TIBKAT | 2023


    Direct Centroidal Control for Balanced Humanoid Locomotion

    Ficht, Grzegorz / Behnke, Sven | Springer Verlag | 2022


    Quadrupedal locomotion based in a purely reflex controller

    Ferreira, Cesar / Matos, Vitor / Santos, Cristina P. et al. | IEEE | 2014


    Unique Aspects of Quadrupedal Locomotion in Nonhuman Primates

    Larson, S. G. | British Library Conference Proceedings | 1998


    Low Energy Consumption Quadrupedal Locomotion with Quasi-resonant Compliant Backbone

    Ricaurte, Edgar Andres Parra / Dominguez, S. / Rossi, C. | TIBKAT | 2022