This work has developed a hybrid framework that combines machine learning and control approaches for legged robots to achieve new capabilities of balancing against external perturbations. The framework embeds a kernel which is a model-based, full parametric closed-loop and analytical controller as the gait pattern generator. On top of that, a neural network with symmetric partial data augmentation learns to automatically adjust the parameters for the gait kernel, and also generate compensatory actions for all joints, thus significantly augmenting the stability under unexpected perturbations. Seven Neural Network policies with different configurations were optimized to validate the effectiveness and the combined use of the modulation of the kernel parameters and the compensation for the arms and legs using residual actions. The results validated that modulating kernel parameters alongside the residual actions have improved the stability significantly. Furthermore, The performance of the proposed framework was evaluated across a set of challenging simulated scenarios, and demonstrated considerable improvements compared to the baseline in recovering from large external forces (up to 118%). Besides, regarding measurement noise and model inaccuracies, the robustness of the proposed framework has been assessed through simulations, which demonstrated the robustness in the presence of these uncertainties. Furthermore, the trained policies were validated across a set of unseen scenarios and showed the generalization to dynamic walking.


    Access

    Download


    Export, share and cite



    Title :

    Learning hybrid locomotion skills—Learn to exploit residual actions and modulate model-based gait control


    Contributors:
    Kasaei, M (author) / Abreu, M (author) / Lau, N (author) / Pereira, A (author) / Reis, LP (author) / Li, Z (author)

    Publication date :

    2023-04-10


    Remarks:

    Frontiers in Robotics and AI , 10 , Article 1004490. (2023)


    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Learning locomotion gait through hormone-based controller in modular robots

    Estévez Fernández, David | BASE | 2014

    Free access


    Accessibility-Based Clustering for Efficient Learning of Locomotion Skills

    Zhang, C / Yu, W / Li, Z | BASE | 2022

    Free access

    Learning Gait Parameters for Locomotion in Virtual Reality Systems

    Zhao, Jingbo / Allison, Robert S. | British Library Conference Proceedings | 2018


    Gait optimization method for quadruped locomotion

    Maicol Laurenza / Gianluca Pepe / Antonio Carcaterra | BASE | 2022

    Free access