Kasaei, M;
Abreu, M;
Lau, N;
Pereira, A;
Reis, LP;
Li, Z;
(2023)
Learning hybrid locomotion skills—Learn to exploit residual actions and modulate model-based gait control.
Frontiers in Robotics and AI
, 10
, Article 1004490. 10.3389/frobt.2023.1004490.
Preview |
Text
frobt-10-1004490.pdf - Published Version Download (13MB) | Preview |
Abstract
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.
| Type: | Article |
|---|---|
| Title: | Learning hybrid locomotion skills—Learn to exploit residual actions and modulate model-based gait control |
| Location: | Switzerland |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.3389/frobt.2023.1004490 |
| Publisher version: | https://doi.org/10.3389/frobt.2023.1004490 |
| Language: | English |
| Additional information: | Copyright © 2023 Kasaei, Abreu, Lau, Pereira, Reis and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (http://creativecommons.org/licenses/by/4.0/). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
| Keywords: | deep reinforcement learning (DRL), humanoid robot, learning motor skills, learning residual actions, modulate gait generator |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10169724 |
Archive Staff Only
 |
View Item |
