It Takes Two: Learning Interactive Whole-Body Control Between Humanoid Robots

2025-10-11

AI Summary

Existing methods focus on autonomous control of individual humanoid robots and struggle to model physically grounded, full-body collaborative interactions between multiple robots, often resulting in contact misalignment, inter-penetration, and motion distortion. This paper proposes a contact-aware motion retargeting and interaction-driven control framework that, for the first time, enables coupled behavioral reproduction of human interactive motions and realistic physical contact modeling in a dual-robot system. The method integrates SMPL-guided vertex-level contact alignment, interaction-specific reward shaping, and a reinforcement learning–based controller to achieve high-fidelity motion transfer and physically plausible coordinated control. Experiments demonstrate significant improvements over single-agent baselines: the approach effectively eliminates inter-penetration and contact mismatches in interactive motion imitation, while markedly enhancing motion coordination and physical realism.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Assisted, interactive, and conversational search

Abstract

The true promise of humanoid robotics lies beyond single-agent autonomy: two or more humanoids must engage in physically grounded, socially meaningful whole-body interactions that echo the richness of human social interaction. However, single-humanoid methods suffer from the isolation issue, ignoring inter-agent dynamics and causing misaligned contacts, interpenetrations, and unrealistic motions. To address this, we present Harmanoid , a dual-humanoid motion imitation framework that transfers interacting human motions to two robots while preserving both kinematic fidelity and physical realism. Harmanoid comprises two key components: (i) contact-aware motion retargeting, which restores inter-body coordination by aligning SMPL contacts with robot vertices, and (ii) interaction-driven motion controller, which leverages interaction-specific rewards to enforce coordinated keypoints and physically plausible contacts. By explicitly modeling inter-agent contacts and interaction-aware dynamics, Harmanoid captures the coupled behaviors between humanoids that single-humanoid frameworks inherently overlook. Experiments demonstrate that Harmanoid significantly improves interactive motion imitation, surpassing existing single-humanoid frameworks that largely fail in such scenarios.

Problem

• Learning interactive whole-body control between dual humanoid robots
• Addressing misaligned contacts and unrealistic motions in interactions
• Transferring interacting human motions to robots with physical realism

Innovation

• Contact-aware motion retargeting aligns SMPL contacts
• Interaction-driven controller enforces coordinated keypoints
• Explicitly models inter-agent contacts and interaction dynamics