发表机构
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究跨机器人手的灵巧抓取生成难题，提出GraspGraphNet框架，将手表示为运动学图，结合多种技术建模交互，直接在相关空间应用条件流匹配，无需后处理等，共享模型在多场景取得高成功率，证明图结构手部表示的有效性。
AI 中文摘要
跨机器人手的灵巧抓取生成具有挑战性，因为手在运动拓扑、驱动维度和原生命令空间方面存在差异。我们引入了GraspGraphNet，这是一个拓扑感知的抓取生成框架，它将每只手表示为从URDF派生的运动学图，并直接生成可执行的手掌姿势和关节配置。GraspGraphNet结合了分层物体表面编码、可微正向运动学和动态世界边缘消息传递，以对不断演变的机器人-物体交互进行建模。它直接在可执行的手掌姿势和关节状态空间中应用条件流匹配，避免了后处理优化、逆运动学和重新定位。使用在巴雷特手、阿莱格罗手和影子手上训练的共享模型，GraspGraphNet在40个物体的基准测试中，每次抓取的推理时间为40毫秒，平均成功率达到83.48%。在不重新训练的情况下，同一模型在受控手指移除变体上的成功率为72.70%，证明了对手部拓扑变化的鲁棒性。这些结果表明，图结构的手部表示可以有效地支持具有不同运动结构的机器人手的灵巧抓取生成。
英文摘要
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
CommentsProject: https://lysees.github.io/graspgraphnet-page
