Stability-Driven Motion Generation for Object-Guided Human-Human Co-Manipulation

TL;DR

This paper introduces a flow-matching framework for object-guided human-human co-manipulation that ensures natural, stable, and goal-oriented motion generation, addressing limitations of prior single-character focused methods.

Contribution

It presents a novel flow-matching approach incorporating manipulation strategies, natural interaction priors, and stability-driven simulation for improved co-manipulation motion quality.

Findings

Achieves higher contact accuracy than baselines

Reduces penetration in simulated interactions

Enhances naturalness and stability of generated motions

Abstract

Co-manipulation requires multiple humans to synchronize their motions with a shared object while ensuring reasonable interactions, maintaining natural poses, and preserving stable states. However, most existing motion generation approaches are designed for single-character scenarios or fail to account for payload-induced dynamics. In this work, we propose a flow-matching framework that ensures the generated co-manipulation motions align with the intended goals while maintaining naturalness and effectiveness. Specifically, we first introduce a generative model that derives explicit manipulation strategies from the object's affordance and spatial configuration, which guide the motion flow toward successful manipulation. To improve motion quality, we then design an adversarial interaction prior that promotes natural individual poses and realistic inter-person interactions during co-manipulation. In addition, we also incorporate a stability-driven simulation into the flow matching process, which refines unstable interaction states through sampling-based optimization and directly adjusts the vector field regression to promote more effective manipulation. The experimental results demonstrate that our method achieves higher contact accuracy, lower penetration, and better distributional fidelity compared to state-of-the-art human-object interaction baselines. The code is available at https://github.com/boycehbz/StaCOM.