arXiv 2505.010832025-05-02cs.RO

DexFlow：一种用于灵巧手姿态重定向与交互的统一方法

DexFlow: A Unified Approach for Dexterous Hand Pose Retargeting and Interaction

Institute of Computer Science, Wuhan University, Hubei, China（武汉大学计算机科学学院，湖北，中国）；Department of Mechanical Engineering, Massachusetts Institute of Technology（麻省理工学院机械工程系）；Department of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电气与计算机工程系）；Institute of Technological Sciences of Wuhan University, Wuhan, Hubei Province, China（武汉大学技术科学研究院，武汉，湖北省，中国）

Xiaoyi Lin, Kunpeng Yao, Lixin Xu, Xueqiang Wang, Xuetao Li, Yuchen Wang, Miao Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对机器人灵巧手操作数据生成中的精度低与交互伪影问题，提出结合多源数据的DexFlow数据转换流水线，利用微分损失约束与接触图优化重定向，显著提升了姿态的精度、自然度与多样性。

摘要：

尽管手物交互建模取得了进展，为机器人手生成逼真的灵巧操作数据仍具挑战。重定向方法常精度低且未考虑手物交互，导致互穿等伪影。生成方法缺乏人手先验，产生有限且不自然的姿态。我们提出一种数据转换流水线，结合多源的人手与物体数据以实现高精度重定向。该方法使用微分损失约束确保时序一致性，并生成接触图以优化手物交互。实验表明，该方法显著提升了姿态精度、自然度与多样性，为手物交互建模提供了稳健的解决方案。

英文摘要：

Despite advances in hand-object interaction modeling, generating realistic dexterous manipulation data for robotic hands remains a challenge. Retargeting methods often suffer from low accuracy and fail to account for hand-object interactions, leading to artifacts like interpenetration. Generative methods, lacking human hand priors, produce limited and unnatural poses. We propose a data transformation pipeline that combines human hand and object data from multiple sources for high-precision retargeting. Our approach uses a differential loss constraint to ensure temporal consistency and generates contact maps to refine hand-object interactions. Experiments show our method significantly improves pose accuracy, naturalness, and diversity, providing a robust solution for hand-object interaction modeling.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。