DexGrasp-Zero: A Morphology-Aligned Policy for Zero-Shot Cross-Embodiment Dexterous Grasping

2026-03-17

AI Summary

This work addresses the challenge of zero-shot cross-embodiment grasping for heterogeneous dexterous hands, where differences in kinematic structures and physical constraints hinder policy transfer. To overcome this, the authors propose a morphology-aligned grasping strategy that leverages anatomical node graphs, triaxial orthogonal motion primitives, and a physics-aware attribute injection mechanism to construct a Morphology-Aligned Graph Convolutional Network (MAGCN). This framework achieves structural and semantic alignment across diverse hand morphologies while adaptively compensating for hand-specific physical constraints. In simulation, the method attains an 85% zero-shot grasping success rate on unseen hand types, outperforming existing approaches by 25.5%. Real-world experiments further demonstrate an average success rate of 82% on novel objects, confirming the approach’s strong generalization and practical applicability.

Technology Category

• Intelligent Robots: Manipulation
• Computer Vision: Low Level & Physics-based Vision
• 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
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

To meet the demands of increasingly diverse dexterous hand hardware, it is crucial to develop a policy that enables zero-shot cross-embodiment grasping without redundant re-learning. Cross-embodiment alignment is challenging due to heterogeneous hand kinematics and physical constraints. Existing approaches typically predict intermediate motion targets and retarget them to each embodiment, which may introduce errors and violate embodiment-specific limits, hindering transfer across diverse hands. To overcome these limitations, we propose \textit{DexGrasp-Zero}, a policy that learns universal grasping skills from diverse embodiments, enabling zero-shot transfer to unseen hands. We first introduce a morphology-aligned graph representation that maps each hand's kinematic keypoints to anatomically grounded nodes and equips each node with tri-axial orthogonal motion primitives, enabling structural and semantic alignment across different morphologies. Relying on this graph-based representation, we design a \textit{Morphology-Aligned Graph Convolutional Network} (MAGCN) to encode the graph for policy learning. MAGCN incorporates a \textit{Physical Property Injection} mechanism that fuses hand-specific physical constraints into the graph features, enabling adaptive compensation for varying link lengths and actuation limits for precise and stable grasping. Our extensive simulation evaluations on the YCB dataset demonstrate that our policy, jointly trained on four heterogeneous hands (Allegro, Shadow, Schunk, Ability), achieves an 85\% zero-shot success rate on unseen hardware (LEAP, Inspire), outperforming the state-of-the-art method by 59.5\%. Real-world experiments further evaluate our policy on three robot platforms (LEAP, Inspire, Revo2), achieving an 82\% average success rate on unseen objects.

Problem

• zero-shot
• cross-embodiment
• dexterous grasping
• morphology alignment
• hand kinematics

Innovation

• zero-shot grasping
• cross-embodiment transfer
• morphology-aligned graph
• graph convolutional network
• physical constraint injection