构建可扩展的工具抓握数据集，让机械手高效抓取各类日常物品。
ScaleADFG: Affordance-based Dexterous Functional Grasping via Scalable Dataset
- 基于功能属性自动合成多样抓握姿态，支持不同尺寸手物比例。
- 含五类物体、超6万组抓握数据，覆盖15种尺度变化。
- 轻量网络零样本迁移，真实机器人验证效果优异。
灵巧工具使用抓握对机器人有效操作工具至关重要。现有方法在构建大规模数据集及保证对日常物品尺度的泛化能力方面面临挑战，主要源于机械手与人手尺寸不匹配以及现实物体尺度多样性。为此，我们提出ScaleADFG框架，包含全自动数据构建流程和轻量级抓握生成网络。数据集采用基于功能属性的算法，无需专家示范即可合成多样化工具使用抓握配置，支持灵活的手物尺寸比例，使大尺寸机械手能有效抓握日常物品。同时利用预训练模型生成大量3D资产，并高效检索物体功能属性。数据集涵盖五类物体，每类超过1000种独特形状，15种尺度变化，经筛选后每种灵巧机械手包含超6万组抓握。在此数据基础上，训练轻量级单阶段抓握生成网络，损失函数设计简单，无需后处理优化。实验表明，该框架在仿真与真实机器人上均展现出对不同尺度物体的强大适应性，提升功能性抓握的稳定性、多样性与泛化能力。网络还实现对真实物体的有效零样本迁移。项目页面见 https://sizhe-wang.github.io/ScaleADFG_webpage
原文摘要 · Abstract (English)
Dexterous functional tool-use grasping is essential for effective robotic manipulation of tools. However, existing approaches face significant challenges in efficiently constructing large-scale datasets and ensuring generalizability to everyday object scales. These issues primarily arise from size mismatches between robotic and human hands, and the diversity in real-world object scales. To address these limitations, we propose the ScaleADFG framework, which consists of a fully automated dataset construction pipeline and a lightweight grasp generation network. Our dataset introduce an affordance-based algorithm to synthesize diverse tool-use grasp configurations without expert demonstrations, allowing flexible object-hand size ratios and enabling large robotic hands (compared to human hands) to grasp everyday objects effectively. Additionally, we leverage pre-trained models to generate extensive 3D assets and facilitate efficient retrieval of object affordances. Our dataset comprising five object categories, each containing over 1,000 unique shapes with 15 scale variations. After filtering, the dataset includes over 60,000 grasps for each 2 dexterous robotic hands. On top of this dataset, we train a lightweight, single-stage grasp generation network with a notably simple loss design, eliminating the need for post-refinement. This demonstrates the critical importance of large-scale datasets and multi-scale object variant for effective training. Extensive experiments in simulation and on real robot confirm that the ScaleADFG framework exhibits strong adaptability to objects of varying scales, enhancing functional grasp stability, diversity, and generalizability. Moreover, our network exhibits effective zero-shot transfer to real-world objects. Project page is available at https://sizhe-wang.github.io/ScaleADFG_webpage
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。