让自行车机器人学会自旋翻跟头，靠的是迭代模仿不完美动作。
Flip Stunts on Bicycle Robots using Iterative Motion Imitation
- 通过迭代模仿前期策略生成的轨迹，逐步优化动作可行性。
- 在真实机器人上实现地面到地面、地面到台面的前空翻，成功率更高。
- 适合对复杂运动控制感兴趣的工程师和研究者参考。
本工作通过强化学习实现自行车机器人完成前空翻动作，特别针对难以执行且不完美的参考轨迹进行模仿。为此提出迭代运动模仿（Iterative Motion Imitation, IMI）方法，通过不断模仿先前策略生成的轨迹，从动力学或运动学上不可行的初始参考轨迹出发，训练出可行且敏捷的控制策略。实验在设计用于高机动性的超移动车辆（Ultra-Mobility Vehicle, UMV）上进行，基于模型控制器生成的自碰撞桌地翻转参考轨迹，成功训练出可实现地-地与地-桌前空翻的策略。相比单次运动模仿，IMI显著提升成功率，并具备良好的现实世界迁移能力。据我们所知，这是该平台首次实现无需辅助的特技翻转行为。
原文摘要 · Abstract (English)
This work demonstrates a front-flip on bicycle robots via reinforcement learning, particularly by imitating reference motions that are infeasible and imperfect. To address this, we propose Iterative Motion Imitation(IMI), a method that iteratively imitates trajectories generated by prior policy rollouts. Starting from an initial reference that is kinematically or dynamically infeasible, IMI helps train policies that lead to feasible and agile behaviors. We demonstrate our method on Ultra-Mobility Vehicle (UMV), a bicycle robot that is designed to enable agile behaviors. From a self-colliding table-to-ground flip reference generated by a model-based controller, we are able to train policies that enable ground-to-ground and ground-to-table front-flips. We show that compared to a single-shot motion imitation, IMI results in policies with higher success rates and can transfer robustly to the real world. To our knowledge, this is the first unassisted acrobatic flip behavior on such a platform.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。