ZeroDexGrasp: Zero-Shot Task-Oriented Dexterous Grasp Synthesis with Prompt-Based Multi-Stage Semantic Reasoning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jian, Juntao, Wei, Yi-Lin, Mou, Chengjie, Lin, Yuhao, Zhu, Xing, Shen, Yujun, Zheng, Wei-Shi, Hu, Ruizhen
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917085639081984
author Jian, Juntao
Wei, Yi-Lin
Mou, Chengjie
Lin, Yuhao
Zhu, Xing
Shen, Yujun
Zheng, Wei-Shi
Hu, Ruizhen
author_facet Jian, Juntao
Wei, Yi-Lin
Mou, Chengjie
Lin, Yuhao
Zhu, Xing
Shen, Yujun
Zheng, Wei-Shi
Hu, Ruizhen
contents Task-oriented dexterous grasping holds broad application prospects in robotic manipulation and human-object interaction. However, most existing methods still struggle to generalize across diverse objects and task instructions, as they heavily rely on costly labeled data to ensure task-specific semantic alignment. In this study, we propose \textbf{ZeroDexGrasp}, a zero-shot task-oriented dexterous grasp synthesis framework integrating Multimodal Large Language Models with grasp refinement to generate human-like grasp poses that are well aligned with specific task objectives and object affordances. Specifically, ZeroDexGrasp employs prompt-based multi-stage semantic reasoning to infer initial grasp configurations and object contact information from task and object semantics, then exploits contact-guided grasp optimization to refine these poses for physical feasibility and task alignment. Experimental results demonstrate that ZeroDexGrasp enables high-quality zero-shot dexterous grasping on diverse unseen object categories and complex task requirements, advancing toward more generalizable and intelligent robotic grasping.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13327
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ZeroDexGrasp: Zero-Shot Task-Oriented Dexterous Grasp Synthesis with Prompt-Based Multi-Stage Semantic Reasoning
Jian, Juntao
Wei, Yi-Lin
Mou, Chengjie
Lin, Yuhao
Zhu, Xing
Shen, Yujun
Zheng, Wei-Shi
Hu, Ruizhen
Robotics
Task-oriented dexterous grasping holds broad application prospects in robotic manipulation and human-object interaction. However, most existing methods still struggle to generalize across diverse objects and task instructions, as they heavily rely on costly labeled data to ensure task-specific semantic alignment. In this study, we propose \textbf{ZeroDexGrasp}, a zero-shot task-oriented dexterous grasp synthesis framework integrating Multimodal Large Language Models with grasp refinement to generate human-like grasp poses that are well aligned with specific task objectives and object affordances. Specifically, ZeroDexGrasp employs prompt-based multi-stage semantic reasoning to infer initial grasp configurations and object contact information from task and object semantics, then exploits contact-guided grasp optimization to refine these poses for physical feasibility and task alignment. Experimental results demonstrate that ZeroDexGrasp enables high-quality zero-shot dexterous grasping on diverse unseen object categories and complex task requirements, advancing toward more generalizable and intelligent robotic grasping.
title ZeroDexGrasp: Zero-Shot Task-Oriented Dexterous Grasp Synthesis with Prompt-Based Multi-Stage Semantic Reasoning
topic Robotics
url https://arxiv.org/abs/2511.13327