在野外环境中学习鲁棒、敏捷、自然的腿式运动技能
Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
AI总结：
针对强化学习习得的机器人腿式步态保守不自然的问题，提出融合动物运动数据对抗训练的师生训练框架，实现了鲁棒、敏捷、自然且高能效的四足机器人复杂地形运动。
摘要：
近年来，强化学习已成为机器人腿式运动领域一种颇具前景的热门解决方案。与基于模型的控制相比，基于强化学习的控制器通过从仿真到现实（sim-to-real）的学习，能更好地应对环境不确定性，鲁棒性更强。但相应习得的步态通常过于保守且不自然。本文提出一种新框架，用于在复杂地形上学习鲁棒、敏捷且自然的腿式运动技能。我们在用于鲁棒sim-to-real迁移的师生训练流水线基础上，加入了一个基于真实动物运动数据的对抗训练分支。在四足机器人的仿真与现实实验中，结果表明本文提出的算法仅靠本体感知，就能让机器人稳健穿越楼梯、岩石地面、湿滑地板等复杂地形。同时，与基线方法相比，其步态更敏捷、更自然且能效更高。本文同时给出了定性与定量结果。
英文摘要：
Recently, reinforcement learning has become a promising and polular solution for robot legged locomotion. Compared to model-based control, reinforcement learning based controllers can achieve better robustness against uncertainties of environments through sim-to-real learning. 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, the gaits are more agile, natural, and energy efficient compared to the baselines. Both qualitative and quantitative results are presented in this paper.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
