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

• URL: http://arxiv.org/abs/2603.16806v2
• Date: Wed, 18 Mar 2026 02:53:12 GMT
• Title: DexGrasp-Zero: A Morphology-Aligned Policy for Zero-Shot Cross-Embodiment Dexterous Grasping
• Abstract summary: Cross-embodiment grasping is challenging due to heterogeneous hand kinematics and physical constraints.<n>Existing approaches typically predict intermediate motion targets and retarget them to each embodiment.<n>We propose DexGrasp-Zero, a policy that learns universal grasping skills from diverse embodiments.
• Score: 46.96135601170059
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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 Morphology-Aligned Graph Convolutional Network (MAGCN) to encode the graph for policy learning. MAGCN incorporates a 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.

Related papers

• MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping [82.63833405368159]
  Cross-embodiment dexterous grasping aims to synthesize stable grasps across heterogeneous multi-fingered hands with little or no embodiment-specific tuning.<n>We propose MANGO-Grasp, an anisotropic interaction framework that represents objects as geometry-oriented 3D Gaussian primitives and robot hands as surface keypoints encoded into morpho-kinematic descriptors.
  arXiv  Detail & Related papers  (2026-08-03T10:12:15Z)
• X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models [39.033717938466246]
  We propose X-DiffVLA, a diffusion-based VLA model featuring a unified cross-embodied action head.<n>X-DiffVLA can leverage the generative strengths of diffusion models to capture both the diversity and latent correlations in cross-embodied datasets.<n>We show that X-DiffVLA achieves state-of-the-art performance, with improvements of 15.3% and 12.5%, respectively.
  arXiv  Detail & Related papers  (2026-05-24T12:41:34Z)
• Structural Action Transformer for 3D Dexterous Manipulation [80.07649565189035]
  Cross-embodiment skill transfer is a challenge for high-DoF robotic hands.<n>Existing methods, often relying on 2D observations and temporal-centric action representation, struggle to capture 3D spatial relations.<n>This paper proposes a new 3D dexterous manipulation policy that challenges this paradigm by introducing a structural-centric perspective.
  arXiv  Detail & Related papers  (2026-03-04T11:38:12Z)
• One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation [23.25726061664319]
  We introduce a parameterized canonical representation that unifies a broad spectrum of dexterous hand architectures.<n>It comprises a unified parameter space and a canonical URDF format, offering three key advantages.<n>We validate these advantages through extensive analysis and experiments, including grasp policy replay, VAE latent encoding, and cross-embodiment zero-shot transfer.
  arXiv  Detail & Related papers  (2026-02-18T18:59:57Z)
• MOTIF: Learning Action Motifs for Few-shot Cross-Embodiment Transfer [55.982504915794514]
  Cross-embodiment policies typically rely on shared-private architectures.<n>We introduce MOTIF for efficient few-shot cross-embodiment transfer.<n>We show that MOTIF significantly outperforms strong baselines in few-shot transfer scenarios.
  arXiv  Detail & Related papers  (2026-02-14T13:21:40Z)
• UniMorphGrasp: Diffusion Model with Morphology-Awareness for Cross-Embodiment Dexterous Grasp Generation [63.13144787866563]
  Cross-embodiment grasping aims to generate stable and diverse grasps for robotic hands with heterogeneous kinematic structures.<n>We propose textbfUniMorphGrasp, a diffusion-based framework that incorporates hand morphological information into the grasp generation process.<n>UniMorphGrasp achieves state-of-the-art performance on existing dexterous grasp benchmarks and exhibits strong zero-shot generalization to previously unseen hand structures.
  arXiv  Detail & Related papers  (2026-01-31T21:56:16Z)
• Cross-Embodiment Dexterous Hand Articulation Generation via Morphology-Aware Learning [82.63833405368159]
  Existing end-to-end methods require training on large-scale datasets for specific hands.<n>We propose an eigengrasp-based, end-to-end framework for cross-embodiment grasp generation.
  arXiv  Detail & Related papers  (2025-10-07T15:57:00Z)
• A Graph-Based Framework for Interpretable Whole Slide Image Analysis [86.37618055724441]
  We develop a framework that transforms whole-slide images into biologically-informed graph representations.<n>Our approach builds graph nodes from tissue regions that respect natural structures, not arbitrary grids.<n>We demonstrate strong performance on challenging cancer staging and survival prediction tasks.
  arXiv  Detail & Related papers  (2025-03-14T20:15:04Z)
• DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness [38.310226324389596]
  A dexterous hand capable of grasping any object is essential for the development of general-purpose embodied robots.<n>We introduce DexGrasp Anything, a method that integrates physical constraints into the training and sampling phases of a diffusion-based generative model.<n>We present a new dexterous grasping dataset containing over 3.4 million diverse grasping poses for more than 15k different objects.
  arXiv  Detail & Related papers  (2025-03-11T10:21:50Z)
• Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation [27.206656215734295]
  We propose a novel Decomposed Vector-Quantized Variational Autoencoder (DVQ-VAE) to generate realistic human grasps. Part-aware decomposed architecture facilitates more precise management of the interaction between each component of hand and object. Our model achieved about 14.1% relative improvement in the quality index compared to the state-of-the-art methods in four widely-adopted benchmarks.
  arXiv  Detail & Related papers  (2024-07-19T06:41:16Z)
• Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition [49.163326827954656]
  We propose a novel multi-granular-temporal graph network for skeleton-based action classification. We develop a dual-head graph network consisting of two inter-leaved branches, which enables us to extract at least two-temporal resolutions. We conduct extensive experiments on three large-scale datasets.
  arXiv  Detail & Related papers  (2021-08-10T09:25:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.