Function beyond Form: Functional Correspondence for Cross-Embodiment Dexterous Grasp Generation
作者: Bolin Zou, Wenlong Dong, Mu Ai, Chao Tang, Aoxiang Gu, Lipeng Chen, Hong Zhang
分类: cs.RO
发布日期: 2026-09-30
💡 一句话要点
提出FunCo-Grasp以解决跨实体灵巧抓取生成问题
🎯 匹配领域: 支柱七:动作重定向 (Motion Retargeting)
关键词: 跨实体抓取 功能对应 灵巧抓取 机器人手 迁移学习 深度学习 抓取生成
📋 核心要点
- 现有方法在跨实体灵巧抓取生成中缺乏结构上不同手部区域的功能对应,限制了模型的泛化能力。
- 本文提出FunCo-Grasp,通过功能部件对齐和规范框架对齐,实现不同手之间的功能对应,促进抓取知识的迁移。
- 在模拟实验中,FunCo-Grasp在已见手上成功率达到92.40%,在未见手上成功率为74.02%,显示出良好的迁移能力。
📝 摘要(中文)
跨实体灵巧抓取生成面临挑战,因为机器人手在几何、拓扑和运动学上存在显著差异。现有方法往往缺乏在结构上不同的手部区域之间的明确对应关系,导致模型学习到的是特定手的交互模式,而非可迁移的抓取知识。为了解决这一限制,本文提出了FunCo-Grasp,通过建立异构手体之间的功能对应关系,提供了一种一致的表示方法,使得模型能够跨手学习可迁移的抓取知识。在未见手的适应中,仅需其几何和运动学模型及一次轻量级的功能注释,无需目标手抓取数据、微调或学习重定向。实验结果表明,FunCo-Grasp在未见手上的抓取知识迁移效果显著。
🔬 方法详解
问题定义:本文旨在解决跨实体灵巧抓取生成中的功能对应问题。现有方法往往专注于特定手的交互模式,缺乏对不同手部区域功能的明确对应,导致泛化能力不足。
核心思路:FunCo-Grasp的核心思路是通过功能部件对齐和规范框架对齐来建立不同手之间的功能对应关系。这种设计使得模型能够学习到跨手的可迁移抓取知识,而不仅仅是特定手的抓取模式。
技术框架:整体架构包括两个主要模块:功能部件对齐和规范框架对齐。功能部件对齐将每个手映射到一个规范功能模式,而规范框架对齐则在规范局部框架中表达这些功能部件。最后,基于对齐的手表示和物体几何,扩散模型生成目标功能部件的空间排列。
关键创新:最重要的技术创新在于建立了功能对应的概念,使得不同结构的手能够在功能上进行有效的对齐。这一方法与现有方法的本质区别在于其关注功能而非形状,从而提升了抓取知识的迁移能力。
关键设计:关键设计包括对功能部件的轻量级功能注释,模型仅需几何和运动学模型即可适应未见手。此外,采用的损失函数和网络结构经过优化,以确保对齐过程的准确性和有效性。
🖼️ 关键图片
📊 实验亮点
在模拟实验中,FunCo-Grasp在三种已见手上实现了92.40%的平均成功率,而在四种未见手上也达到了74.02%的成功率。在真实世界实验中,该模型在两种未见手上取得了76.00%的整体成功率,显示出其在抓取任务中的有效性。
🎯 应用场景
该研究的潜在应用领域包括人形机器人、智能抓取系统以及自动化生产线等。通过实现跨实体的抓取知识迁移,FunCo-Grasp能够显著提升机器人在复杂环境中的灵活性和适应能力,推动智能机器人技术的进步。
📄 摘要(原文)
Cross-embodiment dexterous grasp generation remains challenging because robotic hands differ substantially in geometry, topology, and kinematics. Existing approaches often lack explicit correspondences between structurally different hand regions that play similar functional roles in a grasp, a concept we refer to as functional correspondence. Consequently, their models tend to learn hand-specific interaction patterns rather than transferable grasp knowledge, limiting generalization to unseen hands. To address this limitation, we introduce FunCo-Grasp, which establishes functional correspondences across heterogeneous hand embodiments. Specifically, Functional Part Alignment aligns each hand to a canonical functional schema by mapping physical links to shared functional parts according to their grasping roles, while Canonical Frame Alignment expresses these parts in canonical local frames. These two alignments provide a consistent representation for inter-part and hand-object interactions, allowing the model to learn transferable grasp knowledge across hands. Conditioned on the aligned hand representation and object geometry, a diffusion model generates the target spatial arrangement of the functional parts, which are then converted into an executable joint configuration. Adapting FunCo-Grasp to an unseen hand requires only its geometric and kinematic models and a one-time lightweight functional annotation, without target-hand grasp data, fine-tuning, or learned retargeting. In simulation on held-out objects from the filtered CMapDataset, we achieves average success rates of 92.40% on three seen hands and 74.02% on four unseen hands. In real-world experiments, the same model achieves an overall success rate of 76.00% on two unseen hands without additional training or fine-tuning. These results demonstrate the effectiveness of FunCo-Grasp in transferring grasp knowledge to unseen hands.