SafeFall: Learning Protective Control for Humanoid Robots
Ziyu Meng, Tengyu Liu, Le Ma, Yingying Wu, Ran Song, Wei Zhang, Siyuan Huang
- Year
- 2025
- Access
- Open access
Abstract
Bipedal locomotion makes humanoid robots inherently prone to falls, causing catastrophic damage to the expensive sensors, actuators, and structural components of full-scale robots. To address this critical barrier to real-world deployment, we present \method, a framework that learns to predict imminent, unavoidable falls and execute protective maneuvers to minimize hardware damage. SafeFall is designed to operate seamlessly alongside existing nominal controller, ensuring no interference during normal operation. It combines two synergistic components: a lightweight, GRU-based fall predictor that continuously monitors the robot's state, and a reinforcement learning policy for damage mitigation. The protective policy remains dormant until the predictor identifies a fall as unavoidable, at which point it activates to take control and execute a damage-minimizing response. This policy is trained with a novel, damage-aware reward function that incorporates the robot's specific structural vulnerabilities, learning to shield critical components like the head and hands while absorbing energy with more robust parts of its body. Validated on a full-scale Unitree G1 humanoid, SafeFall demonstrated significant performance improvements over unprotected falls. It reduced peak contact forces by 68.3\%, peak joint torques by 78.4\%, and eliminated 99.3\% of collisions with vulnerable components. By enabling humanoids to fail safely, SafeFall provides a crucial safety net that allows for more aggressive experiments and accelerates the deployment of these robots in complex, real-world environments.
Keywords
Related papers
Trajectory tracking control for 6WID/4WIS UGV via nonlinear sliding mode-model predictive control with adaptive following steering and dynamic-static constraints
Shengyang Lu, Guanpeng Chen, Lijing Zhao +2 more
Robotics and Autonomous Systems · 2026
Bioinspired underwater robotics: Advances across the materials, design, control, and applications
Dilip Muchhala, Pramod Kumar Maurya, Adarsh Raut +3 more
Robotics and Autonomous Systems · 2026
Modeling and control of a rigid–soft hybrid-link humanoid robot
Zewen He, Taiki Ishigaki, Ko Yamamoto
Robotics and Autonomous Systems · 2026
Artificial pushing adaptive coordinated control for the human-exoskeleton-walker system
Xinhao Zhang, Chen Yang, Chaobin Zou +4 more
Robotics and Autonomous Systems · 2026