ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation

2026-10-01

AI Summary

This study addresses the challenge of coordinating end-effector tracking with base motion in legged manipulation. To this end, it proposes a coupled framework integrating a response-shaping training strategy with closed-loop model predictive control (MPC). This approach pioneers the combination of response consistency and policy-aware MPC by unifying reinforcement learning, system identification, and response shaping techniques, effectively resolving command–response inconsistencies under dynamic loads. Simulation results demonstrate an approximate 28% reduction in position and orientation errors. Furthermore, the proposed method is successfully validated on a physical robot, exhibiting continuous coordinated manipulation capabilities between the mobile base and the robotic arm.

Abstract

Continuous legged manipulation requires accurate end-effector tracking while the base keeps walking. Combining reinforcement learning (RL) with model predictive control (MPC) suits this task: the learned policy provides robust locomotion, while MPC coordinates the base and arm to compensate for tracking errors. However, MPC can compensate only for base motion that it can predict, and a learned policy's command response varies with gait phase, contact, and payload. We present ReCo, a framework that couples response-consistent locomotion with policy-aware MPC for legged manipulation. Response shaping trains the policy to respond to commands consistently and repeatably across randomized dynamics. An identified closed-loop response model then lets MPC jointly plan locomotion commands and arm motion. On the simulation benchmark, ReCo reduces position and orientation root-mean-square error (RMSE) by 28.7% and 27.4% relative to the best baseline for each metric. Real-world experiments demonstrate onboard continuous legged manipulation with coordinated base and arm motion.

Problem

• legged manipulation
• model predictive control
• reinforcement learning
• end-effector tracking
• response inconsistency

Innovation

• Legged Manipulation
• Model Predictive Control
• Reinforcement Learning
• Response Shaping
• Policy-Aware MPC