基于少量演示的统一人形机器人跌倒安全策略
Unified Humanoid Fall-Safety Policy from a Few Demonstrations
AI总结：
本文提出一种融合稀疏人类演示、强化学习与自适应扩散记忆的统一策略，使人形机器人能够在单一策略中同时实现跌倒预防、冲击缓解和快速恢复，并在仿真和Unitree G1上验证了其有效性。
摘要：
跌倒是人形机器人移动过程中固有的风险。因此，保持稳定性是机器人控制与学习中的首要安全关注点，然而现有方法均无法完全避免失去平衡。当不稳定确实发生时，先前的工作仅针对跌倒的孤立方面进行处理：避免跌倒、编排受控下降动作，或在跌倒后重新站起。因此，人形机器人缺乏在真实跌倒超出这些预设脚本时进行冲击缓解和快速恢复的综合策略。我们的目标超越保持平衡，使整个跌倒与恢复过程安全且自主：在可能时预防跌倒，在不可避免时减少冲击，在跌倒后重新站起。通过将稀疏人类演示与强化学习以及基于自适应扩散的安全反应记忆相融合，我们学习到自适应全身行为，将跌倒预防、冲击缓解和快速恢复统一在单一策略中。在仿真和Unitree G1上的实验表明，该方法具有稳健的从仿真到真实迁移能力、更低的冲击力，以及在多种扰动下持续快速的恢复能力，指向在真实环境中更安全、更具韧性的人形机器人。视频见 https://firm2025.github.io/。
英文摘要：
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/.
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。
