Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots

2025-05-31

AI Summary

Legged robots suffer degraded locomotion performance in uncertain environments due to payload variations and external disturbances. To address this, we propose a hybrid force-position control framework featuring two key innovations: (1) a disturbance-aware adaptive compensation (DAAC) mechanism, and (2) joint force-position action-space modeling, enabling real-time torque-space disturbance estimation and compensation. Our method integrates end-to-end reinforcement learning policy training, online external disturbance estimation, and co-optimization of target joint positions and feedforward torques. It is rigorously validated through combined simulation and real-robot experiments. Results demonstrate substantial improvements over state-of-the-art RL-based approaches: enhanced payload adaptability and disturbance rejection capability, with quadruped gait stability increased by over 40%. These findings confirm the framework’s robustness and practical efficacy in realistic dynamic environments.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Reinforcement Learning (RL)-based methods have significantly improved the locomotion performance of legged robots. However, these motion policies face significant challenges when deployed in the real world. Robots operating in uncertain environments struggle to adapt to payload variations and external disturbances, resulting in severe degradation of motion performance. In this work, we propose a novel Hybrid Force-Position Locomotion Policy (HFPLP) learning framework, where the action space of the policy is defined as a combination of target joint positions and feedforward torques, enabling the robot to rapidly respond to payload variations and external disturbances. In addition, the proposed Disturbance-Aware Adaptive Compensation (DAAC) provides compensation actions in the torque space based on external disturbance estimation, enhancing the robot's adaptability to dynamic environmental changes. We validate our approach in both simulation and real-world deployment, demonstrating that it outperforms existing methods in carrying payloads and resisting disturbances.

Problem

• Adapt legged robots to payload variations
• Compensate for external disturbances in locomotion
• Improve robot adaptability in dynamic environments

Innovation

• Hybrid Force-Position Locomotion Policy learning framework
• Disturbance-Aware Adaptive Compensation for torque space
• Combines target joint positions and feedforward torques