用图结构统一建模不同机械臂，直接生成可执行抓取姿态。
GraspGraphNet: Graph-Structured Multi-Embodiment Dexterous Grasp Generation
- 将机械臂构型抽象为图结构，结合物体表面编码与动态消息传递。
- 40个物体上平均成功率83.48%，单次推理仅需40ms。
- 无需重训练即可适应手指缺失等拓扑变化，适合多型号机械臂部署。
跨机器人手的灵巧抓取生成极具挑战性，因手部在运动学拓扑、驱动维度和原生命令空间上存在差异。我们提出GraspGraphNet，一种拓扑感知的抓取生成框架，将每只手表示为基于URDF的运动学图，并直接生成可执行的掌面姿态与关节配置。该方法融合分层物体表面编码、可微分正向运动学与动态世界边消息传递，以建模不断演化的机器人-物体交互。它在可执行的掌面姿态与关节状态空间中直接应用条件流匹配，避免了后处理优化、逆运动学求解和姿态重映射。使用在Barrett Hand、Allegro Hand和Shadow Hand上联合训练的共享模型，在40个物体基准上实现了83.48%的平均成功率，单次抓取推理时间仅为40ms。无需重训练，同一模型在受控手指移除变体上仍达到72.70%成功率，表明其对机械手拓扑变化具有强鲁棒性。结果表明，图结构的手部表示能有效支持具有不同运动学结构的灵巧抓取生成。
原文摘要 · Abstract (English)
Dexterous grasp generation across robot hands is challenging because hands differ in kinematic topology, actuation dimensions, and native command spaces. We introduce GraspGraphNet, a topology-aware grasp generation framework that represents each hand as a URDF-derived kinematic graph and directly generates executable palm poses and joint configurations. GraspGraphNet combines hierarchical object surface encoding, differentiable forward kinematics, and dynamic world-edge message passing to model evolving robot-object interactions. It applies conditional flow matching directly in executable palm-pose and joint-state space, avoiding post-processing optimization, inverse kinematics, and retargeting. Using a shared model trained on Barrett Hand, Allegro Hand, and Shadow Hand, GraspGraphNet achieves an average success rate of 83.48% with 40ms inference time per grasp on a 40-object benchmark. Without retraining, the same model achieves 72.70% success on controlled finger-removal variants, demonstrating robustness to hand-topology variations. These results suggest that graph-structured hand representations can effectively support dexterous grasp generation across robot hands with different kinematic structures. Project: https://lysees.github.io/graspgraphnet-page
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。