Dynamic Adaptive Legged Locomotion Policy via Decoupling Reaction Force Control and Gait Control

2025/09/17 by Renjie Wang, Wang, Renjie, Shangke Lyu +3
Computer Science · Engineering · #FOS: Computer and information sciences #Prosthetics and Rehabilitation Robotics #Reinforcement Learning in Robotics #Robotic Locomotion and Control #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2509.13737

openalex publication_date 2025/09/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

While Reinforcement Learning (RL) has achieved remarkable progress in legged locomotion control, it often suffers from performance degradation in out-of-distribution (OOD) conditions and discrepancies between the simulation and the real environments. Instead of mainly relying on domain randomization (DR) to best cover the real environments and thereby close the sim-to-real gap and enhance robustness, this work proposes an emerging decoupled framework that acquires fast online adaptation ability and mitigates the sim-to-real problems in unfamiliar environments by isolating stance-leg control and swing-leg control. Various simulation and real-world experiments demonstrate its effectiveness against horizontal force disturbances, uneven terrains, heavy and biased payloads, and sim-to-real gap.

Citations

• Integrating Trajectory Optimization and Reinforcement Learning for Quadrupedal Jumping with Terrain-Adaptive Landing
• A Modular Residual Learning Framework to Enhance Model-Based Approach for Robust Locomotion
• Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
• High-speed control and navigation for quadrupedal robots on complex and discrete terrain
• Learning Robotic Policy with Imagined Transition: Mitigating the Trade-off between Robustness and Optimality
• Chance-Constrained Convex MPC for Robust Quadruped Locomotion Under Parametric and Additive Uncertainties
• Learning-based legged locomotion; state of the art and future perspectives
• Learning Agile Locomotion and Adaptive Behaviors via RL-augmented MPC
• DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning
• Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behavior
• Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models
• Rapid Locomotion via Reinforcement Learning
• Quadruped Capturability and Push Recovery via a Switched-Systems Characterization of Dynamic Balance
• Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning
• Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
• RMA: Rapid Motor Adaptation for Legged Robots
• Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Control
• Learning agile and dynamic motor skills for legged robots
• Sim-to-Real: Learning Agile Locomotion For Quadruped Robots
• Proximal Policy Optimization Algorithms

Related

• Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robots
• Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World
• Learning and Deploying Robust Locomotion Policies with Minimal Dynamics Randomization
• Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
• Integrating Model-Based Footstep Planning with Model-Free Reinforcement Learning for Dynamic Legged Locomotion