外观
论文arXiv 2610.1437919 天前
OATH：面向灵巧手的物体无关跟踪，实现快速基于物理的重定向
原文链接：OATH: Object-Agnostic Tracking for Dexterous Hands, Enabling Rapid Physics-based Retargeting（arXiv 2610.14379 · 发布日期：2026-10-09）
OATH: Object-Agnostic Tracking for Dexterous Hands, Enabling Rapid Physics-based Retargeting
OATH用结构化接触误差信号的残差策略解决灵巧手物理重定向，并在仿真DexYCB轨迹上验证。
核心要点
- 灵巧手演示重定向需处理复杂接触物理，现有方法常忽略约束或计算昂贵。
- 方法将问题重构为残差学习，在观测中加入局部接触误差信号指导各连杆。
- OATH每秒参考需0.4秒计算，速度为实时的2.4倍，较采样方法降本60-350倍。
- 在DexYCB留出与未见物体轨迹上分别恢复58%和54%，跟踪误差低于2厘米。
验证范围与局限：验证范围为仿真中对DexYCB留出和未见物体轨迹的重定向。
英文摘要 (Abstract)
Retargeting human demonstrations into dynamically feasible dexterous hand trajectories requires resolving complex contact physics, yet current methods either omit physical constraints or rely on computationally expensive sampling-based optimization in simulation. Reinforcement learning has previously been used to achieve planning and control through contact dynamics; however, standard policies require object-specific training and fail to generalize across arbitrary geometries. This work reframes physics-based retargeting as a residual learning problem, where we demonstrate that zero-shot generalization across objects relies on structured state representations. Specifically, formulating the observation space to include a localized contact-error signal guiding each robot link to its target coordinate on the object surface enables a single, unified residual policy to successfully grasp novel, unseen object geometries. Rolling out this policy in simulation on a kinematic reference trajectory yields a physics-based retargeter, OATH. Operating at 0.4 seconds of compute per second of reference, OATH achieves 2.4x faster-than-real-time performance and a 60-350x reduction in computational cost compared to sampling-based methods. The system recovers 58% of held-out and 54% of unseen-object DexYCB trajectories while maintaining a sub-2 cm tracking error.
作者：Solvin Sigurdson, Prasanna Sriganesh, Juan Borbon, Joel W. Burdick, Dingqi Zhang, Jiuguang Wang
来源
本页事实对应的公开页面，以原文为准。