MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Heng, Ma, Kevin Yuchen, Shou, Mike Zheng, Lin, Weisi, Wu, Yan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908867669000192
author Zhang, Heng
Ma, Kevin Yuchen
Shou, Mike Zheng
Lin, Weisi
Wu, Yan
author_facet Zhang, Heng
Ma, Kevin Yuchen
Shou, Mike Zheng
Lin, Weisi
Wu, Yan
contents Dexterous grasping with multi-fingered hands remains challenging due to high-dimensional articulations and the cost of optimization-based pipelines. Existing end-to-end methods require training on large-scale datasets for specific hands, limiting their ability to generalize across different embodiments. We propose MachaGrasp, an eigengrasp-based, end-to-end framework for cross-embodiment grasp generation. From a hand's morphology description, we derive a morphology embedding and an eigengrasp set. Conditioned on these, together with the object point cloud and wrist pose, an amplitude predictor regresses articulation coefficients in a low-dimensional space, which are decoded into full joint articulations. Articulation learning is supervised with a Kinematic-Aware Articulation Loss (KAL) that emphasizes fingertip-relevant motions and injects morphology-specific structure. In simulation on unseen objects across three dexterous hands, MachaGrasp attains a 91.9% average grasp success rate with less than 0.4 seconds inference per grasp. With few-shot adaptation to an unseen hand, it achieves 85.6% success on unseen objects in simulation, and real-world experiments on this few-shot-generalized hand achieve an 87% success rate. The code and additional materials are available on our project website https://connor-zh.github.io/MachaGrasp.
format Preprint
id arxiv_https___arxiv_org_abs_2510_06068
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping
Zhang, Heng
Ma, Kevin Yuchen
Shou, Mike Zheng
Lin, Weisi
Wu, Yan
Robotics
Artificial Intelligence
Dexterous grasping with multi-fingered hands remains challenging due to high-dimensional articulations and the cost of optimization-based pipelines. Existing end-to-end methods require training on large-scale datasets for specific hands, limiting their ability to generalize across different embodiments. We propose MachaGrasp, an eigengrasp-based, end-to-end framework for cross-embodiment grasp generation. From a hand's morphology description, we derive a morphology embedding and an eigengrasp set. Conditioned on these, together with the object point cloud and wrist pose, an amplitude predictor regresses articulation coefficients in a low-dimensional space, which are decoded into full joint articulations. Articulation learning is supervised with a Kinematic-Aware Articulation Loss (KAL) that emphasizes fingertip-relevant motions and injects morphology-specific structure. In simulation on unseen objects across three dexterous hands, MachaGrasp attains a 91.9% average grasp success rate with less than 0.4 seconds inference per grasp. With few-shot adaptation to an unseen hand, it achieves 85.6% success on unseen objects in simulation, and real-world experiments on this few-shot-generalized hand achieve an 87% success rate. The code and additional materials are available on our project website https://connor-zh.github.io/MachaGrasp.
title MachaGrasp: Morphology-Aware Cross-Embodiment Dexterous Hand Articulation Generation for Grasping
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2510.06068