让机器人摔倒时更安全且可控，还能自由设定落地姿势。
Robot Crash Course: Learning Soft and Stylized Falling
- 用奖励函数平衡落地姿态与减震保护，适配任意机器人
- 模拟生成多种起始和目标姿态，提升策略泛化能力
- 实测证明双足机器人可实现受控软着陆，适合复杂环境应用
尽管在稳健行走方面取得进展，双足机器人在真实环境中仍面临摔倒风险。现有研究多聚焦于防跌，本文则关注摔倒过程本身。目标是降低机器人物理损伤，同时让用户可控地指定落地姿态。为此，提出一种与机器人无关的奖励函数，在强化学习中兼顾期望落姿、冲击最小化及关键部件保护。为增强策略对各种初始跌倒状态的鲁棒性，并支持推理时指定任意未见落姿，引入基于仿真的初始与目标姿态采样策略。通过仿真与真实实验验证，即使双足机器人也能实现受控、柔和的跌落。
原文摘要 · Abstract (English)
Despite recent advances in robust locomotion, bipedal robots operating in the real world remain at risk of falling. While most research focuses on preventing such events, we instead concentrate on the phenomenon of falling itself. Specifically, we aim to reduce physical damage to the robot while providing users with control over a robot's end pose. To this end, we propose a robot agnostic reward function that balances the achievement of a desired end pose with impact minimization and the protection of critical robot parts during reinforcement learning. To make the policy robust to a broad range of initial falling conditions and to enable the specification of an arbitrary and unseen end pose at inference time, we introduce a simulation-based sampling strategy of initial and end poses. Through simulated and real-world experiments, our work demonstrates that even bipedal robots can perform controlled, soft falls.
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。