English

DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions

Robotics 2026-05-08 v1

Abstract

Learning dexterous manipulation from human-object interaction (HOI) data is a scalable alternative to teleoperation, but HOI demonstrations are sparse and provide only kinematic motion that is not directly executable under embodiment mismatch and contact-rich dynamics. We present DexSynRefine, a framework with three coupled components: HOI-MMFP, a task- and object-initial-state-conditioned extension of motion manifold primitives that synthesizes coordinated hand-object trajectories from sparse HOI demonstrations; a task-space residual RL policy that physically grounds the synthesized reference while inheriting its kinematic structure; and a contact-and-dynamics adaptation module that enables sim-to-real transfer from proprioceptive history. Across five dexterous manipulation tasks spanning pick-and-place, tool use, and object reorientation, our task-space residual policy outperforms prior action-representation baselines in simulations and transfers to a real robot on all five tasks, improving over kinematic retargeting by 50-70 percentage points.

Keywords

Cite

@article{arxiv.2605.05925,
  title  = {DexSynRefine: Synthesizing and Refining Human-Object Interaction Motion for Physically Feasible Dexterous Robot Actions},
  author = {Hyesung Lee and Hyunwoo Jung and Si-Hwan Heo and Sungwook Yang},
  journal= {arXiv preprint arXiv:2605.05925},
  year   = {2026}
}

Comments

Project page: https://dexsynrefine.github.io/

R2 v1 2026-07-01T12:54:29.585Z