UniMorphGrasp: Diffusion Model with Morphology-Awareness for Cross-Embodiment Dexterous Grasp Generation

TL;DR

UniMorphGrasp introduces a diffusion-based framework that incorporates morphological information of robotic hands to generate stable, diverse grasps across different hand designs, demonstrating superior generalization and performance.

Contribution

It presents a novel diffusion model that unifies grasp synthesis across various hand morphologies by encoding hand kinematics as graphs and leveraging hierarchical supervision.

Findings

Achieves state-of-the-art results on dexterous grasp benchmarks.

Exhibits strong zero-shot generalization to unseen hand structures.

Enables scalable cross-embodiment grasp deployment.

Abstract

Cross-embodiment dexterous grasping aims to generate stable and diverse grasps for robotic hands with heterogeneous kinematic structures. Existing methods are often tailored to specific hand designs and fail to generalize to unseen hand morphologies outside the training distribution. To address these limitations, we propose \textbf{UniMorphGrasp}, a diffusion-based framework that incorporates hand morphological information into the grasp generation process for unified cross-embodiment grasp synthesis. The proposed approach maps grasps from diverse robotic hands into a unified human-like canonical hand pose representation, providing a common space for learning. Grasp generation is then conditioned on structured representations of hand kinematics, encoded as graphs derived from hand configurations, together with object geometry. In addition, a loss function is introduced that exploits the hierarchical organization of hand kinematics to guide joint-level supervision. Extensive experiments demonstrate that UniMorphGrasp achieves state-of-the-art performance on existing dexterous grasp benchmarks and exhibits strong zero-shot generalization to previously unseen hand structures, enabling scalable and practical cross-embodiment grasp deployment.