[2510.06068] MorphArtGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

Computer Science > Robotics arXiv:2510.06068 (cs) [Submitted on 7 Oct 2025 (v1), last revised 28 Feb 2026 (this version, v2)] Title:MorphArtGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping Authors:Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou, Weisi Lin, Yan Wu View a PDF of the paper titled MorphArtGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping, by Heng Zhang and 3 other authors View PDF HTML (experimental) Abstract:Dexterous grasping with multi-fingered hands remains challenging due to high-dimensional articulations and the cost of optimization-based pipelines. Existing end-to-end methods require training on large-scale datasets for specific hands, limiting their ability to generalize across different embodiments. We propose MorphArtGrasp, an eigengrasp-based, end-to-end framework for cross-embodiment grasp generation. From a hand's morphology description, we derive a morphology embedding and an eigengrasp set. Conditioned on these, together with the object point cloud and wrist pose, an amplitude predictor regresses articulation coefficients in a low-dimensional space, which are decoded into full joint articulations. Articulation learning is supervised with a Kinematic-Aware Articulation Loss (KAL) that emphasizes fingertip-relevant motions and injects morphology-specific structure. In simulation on unseen objects across three dexterous hands, MorphArtGrasp attains a 91.9% average g...