DragMesh-2: 物理可信的灵巧手与铰接物体交互

摘要

与铰接物体的灵巧交互在家庭、辅助和人形机器人操作中具有重要意义，其中多指手能够提供超越平行夹爪抓取的柔性接触模式。然而，铰接物体操作与静态物体操作存在本质差异：目标部件无法直接驱动，其运动必须通过持续的手柄-物体接触实现。这使得从以物体为中心的铰接运动生成过渡到以手驱动的灵巧手-物体交互变得困难，因为几何轨迹重放或开环执行无法建模驱动铰接部件所需的接触动力学。此外，仅在固定动力学下为任务完成而训练的策略可能过度拟合标称接触载荷，尤其在缺乏触觉或力反馈的情况下，当接触载荷变化时性能会下降。为解决这些挑战，我们提出DragMesh-2，一种面向铰接物体灵巧交互的接触驱动框架，将铰接交互从以物体为中心的运动生成扩展到以手驱动的灵巧手-物体交互，其中铰接运动必须通过物理接触产生。我们进一步提出PICA，一种物理信息感知的接触感知训练机制，在无触觉或力反馈的条件下将物理信号注入策略学习，从而提升接触载荷变化时的鲁棒性和任务成功率。最后，我们针对多种阻尼条件和铰接物体类别开展系统性评估，研究接触载荷变化下的鲁棒性，并提供纯几何的灵巧交互资源以支持未来的移动操作和人形手-物体交互研究。在七个GAPartNet物体上，DragMesh-2在接触载荷变化下比对比方法展现出更强的鲁棒性，同时在不同阻尼条件下保持高任务成功率。

English

Dexterous interaction with articulated objects is important for household, assistive, and humanoid manipulation, where multi-finger hands can provide compliant contact patterns beyond parallel-jaw grasping. However, articulated-object manipulation differs from static-object manipulation: the target part cannot be directly actuated, and its motion must emerge through sustained physical hand--handle contact. This makes the transition from object-centric articulated generation to hand-driven dexterous hand--object interaction non-trivial, since geometric trajectory replay or open-loop execution does not model the contact dynamics required to move the articulated part. Moreover, policies trained only for task completion under fixed dynamics can overfit nominal contact loads, especially without tactile or force feedback, and may degrade when the contact load changes. To address these challenges, we present DragMesh-2, a contact-driven framework for dexterous interaction with articulated objects that extends articulated interaction from object-centric generation to hand-driven dexterous hand--object interaction, where articulated motion must arise through physical contact. We further propose PICA, a physically informed contact-aware training mechanism that injects physical signals into policy learning without tactile or force feedback, improving robustness and task success under changing contact loads. Finally, we conduct systematic evaluation across multiple damping conditions and articulated-object categories to study robustness under contact-load variation, and provide a pure-geometry dexterous interaction resource to support future loco-manipulation and humanoid hand--object interaction research. Across seven GAPartNet objects, DragMesh-2 achieves stronger robustness under contact-load variation than the compared methods while maintaining high task success across damping conditions.