FRASA: An End-to-End Reinforcement Learning Agent for Fall Recovery and Stand Up of Humanoid Robots

2024/10/11 by Clément Gaspard, Gaspard, Clément, Marc Duclusaud +7 · 6 citations
Computer Science · Engineering · #Context-Aware Activity Recognition Systems #FOS: Computer and information sciences #Modular Robots and Swarm Intelligence #Robotic Locomotion and Control #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2410.08655

openalex publication_date 2024/10/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Humanoid robotics faces significant challenges in achieving stable locomotion and recovering from falls in dynamic environments. Traditional methods, such as Model Predictive Control (MPC) and Key Frame Based (KFB) routines, either require extensive fine-tuning or lack real-time adaptability. This paper introduces FRASA, a Deep Reinforcement Learning (DRL) agent that integrates fall recovery and stand up strategies into a unified framework. Leveraging the Cross-Q algorithm, FRASA significantly reduces training time and offers a versatile recovery strategy that adapts to unpredictable disturbances. Comparative tests on Sigmaban humanoid robots demonstrate FRASA superior performance against the KFB method deployed in the RoboCup 2023 by the Rhoban Team, world champion of the KidSize League.

Cited by

• Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy
• UniReLo: Learning a Unified Humanoid Policy from Fall Recovery to Locomotion across Diverse Terrains
• Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery
• Towards Safe Maneuvering of Double-Ackermann-Steering Robots with a Soft Actor-Critic Framework
• FR-Net: Learning Robust Quadrupedal Fall Recovery on Challenging Terrains through Mass-Contact Prediction
• StableMimic: Smooth Human-Like Recovery for Humanoid Motion Tracking - Learning Beyond the Tracking Distribution for Structured Post-Fall Behavior

Related

• Discovering Self-Protective Falling Policy for Humanoid Robot via Deep Reinforcement Learning
• HiFAR: Multi-Stage Curriculum Learning for High-Dynamics Humanoid Fall Recovery
• Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy
• Unified Humanoid Fall-Safety Policy from a Few Demonstrations
• SafeFall: Learning Protective Control for Humanoid Robots