CompliantWBC: Whole-Body Compliance for Heavy Humanoids via Force Latent Estimation and Residual Impedance Targets

2026-09-27

AI Summary

This study addresses the absence of compliant control methods that coordinate lower limbs for heavy-duty humanoid robots subjected to arbitrary whole-body perturbations. To this end, we propose a reinforcement learning-based whole-body impedance control framework. Cartesian impedance is extended to arbitrary links via Phong-weighted sampling and axis-decoupled pelvis anchors. A base policy achieves multi-part impedance tracking, while a residual policy corrects force estimation errors; curriculum learning further induces coordinated compliant responses in the lower limbs. In simulation, trajectory deviation is limited to 2.58 cm. On physical hardware, the robot successfully performs dynamic and static disturbance rejection, loaded squatting, and collaborative transport tasks, demonstrating an interpretable approach to whole-body compliant control.

Abstract

Whole-body compliant control is essential for deploying heavy humanoids under high payload in human-centric environments. Most prior force-aware learning-based pipelines focus on end-effector resistance, per-link upper-body springs, or end-effector stiffness modulation, leaving arbitrary-site perturbations on heavy platforms with lower-body engagement largely unaddressed. We close this gap with CompliantWBC comprising: (1) A base policy trained with RL to maximize compliance-fidelity reward, guided by a multi-site whole-body impedance reference controller, extending classical Cartesian impedance to any controlled link; (2) A bounded residual policy that edits the per-link impedance equilibrium over a frozen base, correcting the coarse but structured wrench estimate supplied by a force encoder co-trained behind a gradient barrier; (3) A Phong-weighted force-origin sampler with an axis-decoupled pelvis anchor induces lower-body-inclusive compliance curriculum training via two interpretable parameters. We evaluate CompliantWBC in simulation against both compliant and stiff baselines, achieving best compliant fidelity of 2.58cm deviation from analytical solutions, and demonstrate it on a real heavy humanoid across static/dynamic force reaction, board wiping, squat under payload, and cooperative payload transport. Project website: https://dotandung.github.io/compliantwbc/

Problem

• Whole-body compliance
• Heavy humanoids
• Force-aware control
• Impedance control
• Arbitrary-site perturbations

Innovation

• Whole-Body Compliance
• Force Latent Estimation
• Residual Impedance
• Reinforcement Learning
• Heavy Humanoids