LocoWM: High-Precision Locomotion through World-Model-Guided Residual Adaptation

2026-09-30

AI Summary

This study addresses the limitations of insufficient end-to-end optimization and reactive control latency in high-precision motion. To overcome these challenges, we propose a world-model-guided pre-activated residual adaptation framework. Specifically, this method leverages an action-conditioned world model to predict future states, thereby generating anticipatory action corrections. Furthermore, a pre-activated residual mechanism decouples motion acquisition from precision adaptation, while a two-stage training strategy ensures efficient learning. Experimental results demonstrate that the proposed framework significantly outperforms existing baseline methods in both control accuracy and disturbance robustness across tasks such as terrain leveling and acceleration compensation.

Abstract

High-precision locomotion combines motion-command tracking with precise regulation of task-relevant physical states, enabling robots to interact reliably with their surroundings during motion. Joint end-to-end optimization can leave precision objectives insufficiently optimized, while reactive residual control adjusts actions only after deviations become observable. We present \textbf{LocoWM}, a world-model-guided preactive residual adaptation framework for high-precision locomotion. A base policy provides command-following locomotion, while an action-conditioned world model predicts a sequence of future physical states from proprioceptive history and the proposed base action. A residual adapter conditions on this predicted sequence to generate additive action corrections that compensate for anticipated deviations. Two-stage training first learns locomotion and action-conditioned dynamics, then freezes both modules while training the adapter, separating locomotion acquisition from precision adaptation. Experiments spanning terrain leveling, acceleration compensation, and push recovery demonstrate improved control precision and disturbance robustness over end-to-end and reactive residual baselines. Demos and code are available at: https://zhaozijie2022.github.io/LocoWM

Problem

• high-precision locomotion
• residual control
• motion-command tracking
• physical state regulation
• disturbance robustness

Innovation

• World Model
• Residual Adaptation
• Preactive Control
• High-Precision Locomotion
• Two-Stage Training