Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
Keywords: Legged Locomotion, Reinforcement Learning, Adversarial Training, Sim to Real
Abstract: Recently, reinforcement learning has become a promising and polular solution for robot legged locomotion. However, the corresponding learned gaits are in general overly conservative and unatural. In this paper, we propose a new framework for learning robust, agile and natural legged locomotion skills over challenging terrain. We incorporate an adversarial training branch based on real animal locomotion data upon a teacher-student training pipeline for robust sim-to-real transfer. Empirical results on both simulation and real world of a quadruped robot demonstrate that our proposed algorithm enables robustly traversing challenging terrains such as stairs, rocky ground and slippery floor with only proprioceptive perception. Meanwhile, using diverse gait patterns, the gaits are more agile, natural, and energy efficient compared to the baselines. Both qualitative and quantitative results are presented in this paper. Videos are at: https://sites.google.com/view/adaptive-multiskill-locomotion.
Submission Number: 8
Loading