UniDexTok：基于真实数据的统一灵巧手分词器
UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data
- Fudan University（复旦大学）
- Hefei University of Technology（合肥工业大学）
- Rimbot
- Beijing University of Posts and Telecommunications（北京邮电大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出统一灵巧手模型(UDHM)将人手和机器人手状态映射到共享22自由度语义接口，并基于此开发UniDexTok，一种免重定向的状态分词器，学习基于真实关节状态的离散token，实现异构灵巧手的统一表示，误差降低98%以上。
AI中文摘要：
灵巧手对于精细操作至关重要，但其硬件设计在不同实施例之间存在显著差异。运动学、关节定义和自由度方面的差异使得定义共享状态表示变得困难，与平行夹爪相比更是如此。因此，灵巧手数据仍然碎片化，难以用于联合训练。在这项工作中，我们提出了统一灵巧手模型（UDHM），它将人手和机器人手状态映射到一个共享的22自由度语义接口。基于UDHM，我们引入了UniDexTok，一种免重定向的状态分词器，它从标准化的真实关节状态中学习基于实施例的离散token。UniDexTok为异构灵巧手提供了统一表示，无需依赖重定向或仿真数据。与最近的基线UniHM相比，UniDexTok将MPJAE从15.63度降低到0.16度，MPJPE从18.51毫米降低到0.18毫米，误差分别减少了98.98%和99.03%。这些结果将重建精度从厘米级提升到亚毫米级。实验进一步表明，来自其他实施例的数据提高了目标实施例的重建精度，证明了跨实施例分词的优势。当引入新的灵巧手时，UniDexTok还表现出强大的零样本和少样本重建能力。
英文摘要：
Dexterous hands are essential for fine-grained manipulation, but their hardware designs vary substantially across embodiments. Differences in kinematics, joint definitions, and degrees of freedom make it difficult to define a shared state representation compared with parallel grippers. As a result, dexterous-hand data remains fragmented and difficult to use for joint training. In this work, we propose the Unified Dexterous Hand Model (UDHM), which maps human and robot hand states into a shared 22-DoF semantic interface. Based on UDHM, we introduce UniDexTok, a retargeting-free state tokenizer that learns embodiment-conditioned discrete tokens from standardized real joint states. UniDexTok provides a unified representation for heterogeneous dexterous hands without relying on retargeting or simulation data. Compared with the recent baseline UniHM, UniDexTok reduces MPJAE from 15.63 degrees to 0.16 degrees and MPJPE from 18.51 mm to 0.18 mm, corresponding to error reductions of 98.98% and 99.03%, respectively. These results improve reconstruction from centimeter-scale to sub-millimeter accuracy. Experiments further show that data from other embodiments improves target-embodiment reconstruction accuracy, demonstrating the benefit of cross-embodiment tokenization. UniDexTok also shows strong zero-shot and few-shot reconstruction ability when new dexterous hands are introduced.
