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

2026-01-31

AI Summary

Existing methods struggle to generalize across dexterous hands with diverse morphologies and fail to generate stable, diverse grasp poses for novel hand designs outside the training distribution. This work proposes a diffusion-based framework for cross-morphology dexterous grasp generation. By mapping grasps from various robotic hands into a unified canonical human hand pose space, the approach leverages hand kinematic graph structures and object geometry as conditioning inputs for generative modeling. A morphology-aware mechanism is introduced to construct a unified grasp representation, complemented by a kinematics-aware hierarchical supervision loss. The method achieves state-of-the-art performance on multiple dexterous grasping benchmarks and demonstrates strong zero-shot generalization to unseen hand morphologies.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Web Mining and Content Analysis: Web data generation and simulation

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.

Problem

• cross-embodiment
• dexterous grasping
• hand morphology
• generalization
• kinematic structure

Innovation

• diffusion model
• cross-embodiment
• morphology-awareness
• dexterous grasp generation
• graph-based kinematic representation