CEER: Compliant End-Effector and Root Control as a Unified Interface for Hierarchical Humanoid Loco-Manipulation

2026-05-19

AI Summary

This work addresses the limitations of humanoid robots in contact-rich, long-horizon manipulation tasks, which stem from the absence of a unified control interface that integrates compliance, modularity, and compatibility with high-level planners. The authors propose CEER—a compliant end-effector-to-root (EE-root) control abstraction—that, for the first time, encapsulates whole-body compliant control into an interpretable task-space interface. Leveraging a teacher-student framework, a general-purpose motion controller is distilled into a low-level policy driven solely by EE-root commands, enabling plug-and-play integration with heterogeneous high-level planners for modular mobile manipulation. Experiments demonstrate significant improvements in end-effector tracking accuracy (3.3 cm), reduced jitter, and stable execution of contact-intensive tasks under teleoperation, achieving up to a 70% success rate in single-object mobile manipulation on both simulation and real hardware platforms.

Abstract

Humanoid robots have achieved impressive locomotion performance, yet contact-rich and long-horizon manipulation remains a major bottleneck. Manipulation is inherently contact-rich and demands compliant whole-body control for stable interaction, while its diversity and long-horizon nature favor modular, planner-compatible interfaces over joint-space tracking. We propose CEER, a compliant end-effector-root (EE-root) control abstraction for modular humanoid loco-manipulation within a hierarchical planning framework. CEER enables compliance-aware whole-body control in an interpretable task space defined by root motion commands and end-effector pose targets, and supports plug-and-play integration with heterogeneous high-level planners. A teacher-student framework is adopted to distill a general motion-tracking controller into a low-level policy that consumes only EE-root commands. We further construct a hierarchical system that integrates heterogeneous planners and task modules through the EE-root interface, enabling diverse manipulation tasks without retraining the underlying whole-body policy. Experiments in simulation and on hardware demonstrate 3.3 cm end-effector tracking accuracy with substantially reduced jerk compared to baselines, stable contact-rich manipulation under teleoperation, and up to 70% success in simulated single-object loco-manipulation tasks within a room-scale environment. These results indicate that compliant EE-root control provides a practical abstraction for humanoid loco-manipulation, enabling modular and scalable integration of diverse skills.

Problem

• humanoid robots
• contact-rich manipulation
• long-horizon tasks
• compliant control
• loco-manipulation

Innovation

• compliant control
• end-effector-root abstraction
• hierarchical planning
• loco-manipulation
• modular robotics