仅用少量人类示范，让机器人学会防跌、减冲、快起全流程安全应对。
Unified Humanoid Fall-Safety Policy from a Few Demonstrations
- 融合人类示范与强化学习，构建统一的跌倒应对策略
- 仿真与真实机器人测试中均实现更低冲击力和更快恢复
- 适用于需高鲁棒性的复杂环境人形机器人
跌倒对人形机器人是固有风险。保持稳定是机器人控制与学习的核心安全目标，但现有方法无法完全避免失衡。当不稳定发生时，以往工作仅关注跌倒的单一环节：避免跌倒、可控下落或事后起身。因此，人形机器人缺乏整合的冲击缓解与快速恢复策略。本文旨在超越维持平衡，实现跌倒-恢复全过程的安全自主：可能时防止跌倒，不可避免时减轻冲击，跌倒后迅速起身。通过融合稀疏的人类示范、强化学习以及基于自适应扩散的记忆机制，我们训练出统一的全身行为策略，同时实现防跌、减冲与快速恢复。在仿真和Unitree G1机器人上的实验表明，该策略具备稳健的模拟到现实迁移能力，显著降低冲击力，并在多种扰动下实现一致快速恢复，推动真实环境中更安全、更具韧性的机器人发展。视频见https://firm2025.github.io/。
原文摘要 · Abstract (English)
Falling is an inherent risk of humanoid mobility. Maintaining stability is thus a primary safety focus in robot control and learning, yet no existing approach fully averts loss of balance. When instability does occur, prior work addresses only isolated aspects of falling: avoiding falls, choreographing a controlled descent, or standing up afterward. Consequently, humanoid robots lack integrated strategies for impact mitigation and prompt recovery when real falls defy these scripts. We aim to go beyond keeping balance to make the entire fall-and-recovery process safe and autonomous: prevent falls when possible, reduce impact when unavoidable, and stand up when fallen. By fusing sparse human demonstrations with reinforcement learning and an adaptive diffusion-based memory of safe reactions, we learn adaptive whole-body behaviors that unify fall prevention, impact mitigation, and rapid recovery in one policy. Experiments in simulation and on a Unitree G1 demonstrate robust sim-to-real transfer, lower impact forces, and consistently fast recovery across diverse disturbances, pointing towards safer, more resilient humanoids in real environments. Videos are available at https://firm2025.github.io/.
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。