Dataset-Free Compliant Humanoid Loco-Manipulation with Dynamic Online Posture

2026-10-05

AI Summary

This study addresses the reliance of humanoid mobile manipulation on human motion data and external pose commands by proposing OCLO, a system that achieves whole-body coordination and compliant control using only end-effector goals. Methodologically, it introduces an analytical reachability prior to dynamically generate pelvis height and torso orientation online, while integrating policy loop sampling, spring-damper models, and reinforcement learning for whole-body compliance. Experiments demonstrate a 77.8% success rate in simulation, and deployment on the real-world G1 humanoid shows successful balance maintenance under perturbations across seven complex tasks. These results validate the generalization capability and robustness of the proposed system without requiring any human demonstration data.

Abstract

Most humanoid loco-manipulation controllers require human motion data to learn whole-body coordination and posture, leaving policies reliant on external sources to provide this data. We present OCLO (Online-posture Compliant LOco-manipulation), a humanoid loco-manipulation system trained without human motion data and commanded only through two end-effector targets. Because these targets do not uniquely determine whole-body posture, OCLO generates pelvis height and torso orientation online using an analytic reachability prior, further refined through policy-in-the-loop sampling with a task-agnostic cost. OCLO also learns whole-body compliance by displacing end-effector references according to measured forces through a spring-damper model, encouraging the legs, waist, and pelvis to yield to external loads. In simulation, using the reachability prior leads to a 77.8% success rate in acquiring the commanded reference, a vast improvement over the 37.8% success rate accomplished without the prior. Further, refinement reduces end-effector orientation error across all evaluated tasks. The same posture module improves a pretrained SONIC controller on four of five tasks. Without compliance training, policies tend to lose balance under disturbances rather than sacrifice tracking. On a Unitree G1, OCLO maintains balance under end-effector disturbances that cause its ablations to fail and performs seven loco-manipulation tasks, including crouched walking and picking up a box from a low surface. Project website: https://oclo-humanoid.github.io/

Problem

• Humanoid loco-manipulation
• Dataset-free control
• Whole-body posture
• Compliance
• Balance under disturbance

Innovation

• dataset-free
• loco-manipulation
• online posture generation
• reachability prior
• whole-body compliance