通过对抗运动先验在四足机器人上学习双足行走
Learning Bipedal Walking on a Quadruped Robot via Adversarial Motion Priors
AI总结：
本文将融合 Adversarial Motion Priors 的师生学习框架迁移到双足模式四足机器人，实现盲走，并在仿真中验证其可稳定通过平地、楼梯及不平坦地形。
摘要：
先前研究已成功证明四足机器人可在具有挑战性的地形上实现敏捷且鲁棒的运动。然而，四足机器人的双足运动模式仍未得到验证。本文探索将最初为四足机器人设计的学习框架进行适配，使其在双足模式下执行盲走运动。我们利用一个融合 Adversarial Motion Priors（对抗运动先验）与师生策略的框架，以实现对参考轨迹的模仿以及在崎岖地形上的导航。本研究包括在双足模式的四足机器人上迁移并评估类似的学习框架，目标是在平坦和复杂地形上实现稳定行走。仿真结果表明，经过训练的策略使四足机器人能够在平坦及具有挑战性的地形上导航，包括楼梯和不平坦表面。
英文摘要：
Previous studies have successfully demonstrated agile and robust locomotion in challenging terrains for quadrupedal robots. However, the bipedal locomotion mode for quadruped robots remains unverified. This paper explores the adaptation of a learning framework originally designed for quadrupedal robots to operate blind locomotion in biped mode. We leverage a framework that incorporates Adversarial Motion Priors with a teacher-student policy to enable imitation of a reference trajectory and navigation on tough terrain. Our work involves transferring and evaluating a similar learning framework on a quadruped robot in biped mode, aiming to achieve stable walking on both flat and complicated terrains. Our simulation results demonstrate that the trained policy enables the quadruped robot to navigate both flat and challenging terrains, including stairs and uneven surfaces.
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。
