UniFucGrasp: 人类手启发的统一功能抓取标注策略与多样的灵巧手数据集
UniFucGrasp: Human-Hand-Inspired Unified Functional Grasp Annotation Strategy and Dataset for Diverse Dexterous Hands
- School of Artificial Intelligence and Robotics, Hunan University, China（人工智能与机器人学院，湖南大学）
- National Engineering Research Center of Robot Visual Perception and Control Technology, Hunan University, China（机器人视觉感知与控制技术国家工程研究中心，湖南大学）
- College of Mechanical and Vehicle Engineering, Hunan University, China（机械与车辆工程学院，湖南大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
UniFucGrasp提出了一种基于人类手启发的统一功能抓取标注策略与数据集，支持低成本高效收集多样化高质量功能抓取，提升多机器人手的抓取稳定性和适应性。
AI中文摘要：
灵巧抓取数据集对具身智能至关重要，但大多数侧重于抓取稳定性，忽略了开瓶盖或握杯柄等任务所需的功能性抓取。大多数依赖于笨重、昂贵且难以控制的高自由度影子手。受人类手的欠驱动机制启发，我们建立了UniFucGrasp，一种适用于多种灵巧手类型的统一功能抓取标注策略和数据集。基于仿生学，它将自然人体动作映射到多种手结构，并利用基于几何的力闭合来确保功能性强、稳定的类人抓取。该方法支持低成本、高效的收集多样、高质量的功能性抓取。最后，我们建立了首个多手功能抓取数据集，并提供了一个合成模型来验证其有效性。在UFG数据集、IsaacSim和复杂机器人任务上的实验表明，我们的方法提高了功能性操作的准确性和抓取稳定性，展示了在多种机器人手之间的适应性提升，有助于缓解灵巧抓取中的标注成本和泛化挑战。项目页面位于https://haochen611.github.io/UFG。
英文摘要：
Dexterous grasp datasets are vital for embodied intelligence, but mostly emphasize grasp stability, ignoring functional grasps needed for tasks like opening bottle caps or holding cup handles. Most rely on bulky, costly, and hard-to-control high-DOF Shadow Hands. Inspired by the human hand's underactuated mechanism, we establish UniFucGrasp, a universal functional grasp annotation strategy and dataset for multiple dexterous hand types. Based on biomimicry, it maps natural human motions to diverse hand structures and uses geometry-based force closure to ensure functional, stable, human-like grasps. This method supports low-cost, efficient collection of diverse, high-quality functional grasps. Finally, we establish the first multi-hand functional grasp dataset and provide a synthesis model to validate its effectiveness. Experiments on the UFG dataset, IsaacSim, and complex robotic tasks show that our method improves functional manipulation accuracy and grasp stability, demonstrates improved adaptability across multiple robotic hands, helping to alleviate annotation cost and generalization challenges in dexterous grasping. The project page is at https://haochen611.github.io/UFG.
