Unified Humanoid Fall-Safety Policy from a Few Demonstrations

TL;DR

This paper presents an integrated approach combining demonstrations, reinforcement learning, and diffusion-based memory to enable humanoid robots to prevent falls, mitigate impacts, and recover quickly, enhancing safety and resilience.

Contribution

It introduces a novel unified policy that combines fall prevention, impact mitigation, and recovery, learned from demonstrations and reinforcement learning, for humanoid robots.

Findings

Robust sim-to-real transfer demonstrated in experiments

Lower impact forces during falls and recoveries

Consistent fast recovery across diverse disturbances

Abstract

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/.