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.
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model
Springer Proceedings in Advanced Robotics
International Workshop on the Algorithmic Foundations of Robotics ; 2022 ; , MD, USA June 22, 2022 - June 24, 2022
2022-12-15
17 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Direct Centroidal Control for Balanced Humanoid Locomotion
Springer Verlag | 2022
|Unique Aspects of Quadrupedal Locomotion in Nonhuman Primates
British Library Conference Proceedings | 1998
|