让机器人用工具更稳，靠的是算出握力如何受力
Physics-Conditioned Grasping for Stable Tool Use
- 根据任务轨迹预估受力，选能扛住冲击的抓法
- 实测减少17.6%扭矩，成功率提升17.5%
- 适合做真实场景下工具操作的机器人研发
工具使用失败往往不是因为识别错误，而是抓握无法承受任务引发的力矩。现有视觉语言操控系统虽能从语言中定位工具和接触区域，但抓握选择仍基于准静态或仅几何假设。实际交互中，惯性冲量与杠杆效应会放大腕部扭矩和切向载荷，导致滑动与旋转。本文提出逆向工具使用规划（iTuP），通过最小化任务轨迹上的预测交互力矩来选择抓握。基于刚体力学，推导出扭矩、滑动与对齐惩罚项，并训练稳定动态抓握网络（SDG-Net）实时估算这些轨迹相关成本。在模拟与硬件上测试锤击、扫除、敲击和伸手任务，SDG-Net将诱发扭矩降低最高达17.6%，抓握位置移至经验不稳定性阈值以下，实机成功率较组合基线提升17.5%。改进集中在力矩放大的场景，表明机器人工具使用需力矩感知的抓握选择，而不仅是感知能力。
原文摘要 · Abstract (English)
Tool use often fails not because robots misidentify tools, but because grasps cannot withstand task-induced wrench. Existing vision-language manipulation systems ground tools and contact regions from language yet select grasps under quasi-static or geometry-only assumptions. During interaction, inertial impulse and lever-arm amplification generate wrist torque and tangential loads that trigger slip and rotation. We introduce inverse Tool-use Planning (iTuP), which selects grasps by minimizing predicted interaction wrench along a task-conditioned trajectory. From rigid-body mechanics, we derive torque, slip, and alignment penalties, and train a Stable Dynamic Grasp Network (SDG-Net) to approximate these trajectory-conditioned costs for real-time scoring. Across hammering, sweeping, knocking, and reaching in simulation and on hardware, SDG-Net suppresses induced torque up to 17.6%, shifts grasps below empirically observed instability thresholds, and improves real-world success by 17.5% over a compositional baseline. Improvements concentrate where wrench amplification dominates, showing that robot tool use requires wrench-aware grasp selection, not perception alone.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。