DiffMorphGrasp: A Diffusion Framework Conditioned on Hand Morphology for Cross-Embodiment Grasp Generation

This paper proposes DiffMorphGrasp, the first diffusion-based framework that incorporates hand morphology information into the generative process for cross-embodiment dexterous grasping. The approach maps grasps from diverse robotic hands into a reference hand pose, and generates grasps conditioned on structured representations of hand kinematics and object geometry. The method is evaluated on a new benchmark, showing strong zero-shot generalization to unseen hand morphologies.