用约束强化学习让点脚机器人稳定行走，实现从仿真到现实的迁移。
Constrained Reinforcement Learning for Unstable Point-Feet Bipedal Locomotion Applied to the Bolt Robot
- 引入约束即终止机制，结合领域随机化提升训练鲁棒性。
- 在模拟中实现平衡维持、速度控制及抗滑推扰动，性能显著优于基线。
- 适合研究足式机器人控制与仿真实现迁移的开发者参考。
双足步行是机器人领域的关键挑战，尤其对于如Bolt这类采用点脚设计的欠驱动机器人。本文探索利用约束强化学习控制此类不稳定机器人，解决其无手臂、足部驱动能力有限的问题。提出一种结合约束即终止与领域随机化的方法，以支持从仿真到现实的迁移。通过一系列定性与定量实验，评估了方法在保持平衡、速度控制以及应对滑倒和推力干扰方面的表现。同时，通过能耗（成本）与地面反作用力等指标分析自主性。结果表明，该方法显著提升了点脚双足机器人的控制鲁棒性，为更广泛的步态运动提供了新思路。
原文摘要 · Abstract (English)
Bipedal locomotion is a key challenge in robotics, particularly for robots like Bolt, which have a point-foot design. This study explores the control of such underactuated robots using constrained reinforcement learning, addressing their inherent instability, lack of arms, and limited foot actuation. We present a methodology that leverages Constraints-as-Terminations and domain randomization techniques to enable sim-to-real transfer. Through a series of qualitative and quantitative experiments, we evaluate our approach in terms of balance maintenance, velocity control, and responses to slip and push disturbances. Additionally, we analyze autonomy through metrics like the cost of transport and ground reaction force. Our method advances robust control strategies for point-foot bipedal robots, offering insights into broader locomotion.
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。