SegGrasp: Zero-Shot Task-Oriented Grasping via Semantic and Geometric Guided Segmentation

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Haosheng, Mao, Weixin, Deng, Weipeng, Meng, Chenyu, Zhang, Rui, Jia, Fan, Wang, Tiancai, Fan, Haoqiang, Wang, Hongan, Deng, Xiaoming
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929540254662656
author Li, Haosheng
Mao, Weixin
Deng, Weipeng
Meng, Chenyu
Zhang, Rui
Jia, Fan
Wang, Tiancai
Fan, Haoqiang
Wang, Hongan
Deng, Xiaoming
author_facet Li, Haosheng
Mao, Weixin
Deng, Weipeng
Meng, Chenyu
Zhang, Rui
Jia, Fan
Wang, Tiancai
Fan, Haoqiang
Wang, Hongan
Deng, Xiaoming
contents Task-oriented grasping, which involves grasping specific parts of objects based on their functions, is crucial for developing advanced robotic systems capable of performing complex tasks in dynamic environments. In this paper, we propose a training-free framework that incorporates both semantic and geometric priors for zero-shot task-oriented grasp generation. The proposed framework, SegGrasp, first leverages the vision-language models like GLIP for coarse segmentation. It then uses detailed geometric information from convex decomposition to improve segmentation quality through a fusion policy named GeoFusion. An effective grasp pose can be generated by a grasping network with improved segmentation. We conducted the experiments on both segmentation benchmark and real-world robot grasping. The experimental results show that SegGrasp surpasses the baseline by more than 15\% in grasp and segmentation performance.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08901
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SegGrasp: Zero-Shot Task-Oriented Grasping via Semantic and Geometric Guided Segmentation
Li, Haosheng
Mao, Weixin
Deng, Weipeng
Meng, Chenyu
Zhang, Rui
Jia, Fan
Wang, Tiancai
Fan, Haoqiang
Wang, Hongan
Deng, Xiaoming
Robotics
Task-oriented grasping, which involves grasping specific parts of objects based on their functions, is crucial for developing advanced robotic systems capable of performing complex tasks in dynamic environments. In this paper, we propose a training-free framework that incorporates both semantic and geometric priors for zero-shot task-oriented grasp generation. The proposed framework, SegGrasp, first leverages the vision-language models like GLIP for coarse segmentation. It then uses detailed geometric information from convex decomposition to improve segmentation quality through a fusion policy named GeoFusion. An effective grasp pose can be generated by a grasping network with improved segmentation. We conducted the experiments on both segmentation benchmark and real-world robot grasping. The experimental results show that SegGrasp surpasses the baseline by more than 15\% in grasp and segmentation performance.
title SegGrasp: Zero-Shot Task-Oriented Grasping via Semantic and Geometric Guided Segmentation
topic Robotics
url https://arxiv.org/abs/2410.08901