cs.ROOct 30, 2026

Online Learning of Heterogeneous Locomotion Dynamics under Reinforcement Learning Policies for Precise Loco-Manipulation

Authors: Tianlin Zhang, Weipeng Xia, Lingwei Zhang, Yiyang Shao, Zhongyu Li, Yun-Hui Liu

Organizations: The Chinese University of Hong Kong, Hong Kong SAR, China · Hong Kong Centre for Logistics Robotics, Hong Kong SAR, China

Abstract

How to reuse a pretrained locomotion policy for precise loco-manipulation is still an open problem. We propose an online method to learn the closed-loop dynamics under a frozen locomotion policy. The learned model predicts floating-base motion and improves loco-manipulation accuracy. However, unobserved latent conditions of the policy introduce heterogeneous responses, meaning that the same observed state will lead to different motions. Direct learning without accounting for this heterogeneity introduces bias and fluctuations into dynamics estimates, degrading floating-base prediction and end-effector tracking. To address this problem, a contaminated Gaussian model is proposed to approximate the effects of latent conditions. The model uses two Gaussian components to approximate predictable and unpredictable responses under the same observed state. Then, the contaminated Gaussian model is combined with a Gaussian process to construct an online learner using random Fourier features (RFFs). The learner estimates each response's probability of belonging to the predictable component and uses it to weight online updates, capturing predictable responses while reducing bias and fluctuations caused by heterogeneous observations. With consistent and unbiased dynamics estimates, model predictive control (MPC) predicts floating-base motion accurately and enables precise loco-manipulation. A finite-sample error bound is established to ensure uniform convergence in online learning. Simulation and hardware experiments demonstrate consistent end-effector tracking across different manipulator configurations and tasks, with errors of 0.01 m.

Figures & tables

Explore similar work

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

    Oct 1, 2026Kuankuan Sima, Yichao Gao, Chenxi Gu +2Model Predictive ControlRL for Legged Locomotion

  2. Force-Aware Reinforcement Learning with Hybrid Sensorless Force Estimation for Wheeled-Legged Loco-Manipulation

    Sep 12, 2026Xuanqi Zeng, Jiaming Wang, Tianlin Zhang +5Robotic Loco-ManipulationForce-Controlled Robotic Manipulation

  3. Learning Multi-Phase Robot Loco-Manipulation via Phase-Conditioned Policy Optimization

    Oct 26, 2026Simone Manni, Annika Wollschläger, Dario Bellicoso +4Robotic Loco-ManipulationLong-Horizon Robotic Manipulation