A Surprisingly Efficient Representation for Multi-Finger Grasping

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yan, Hengxu, Fang, Hao-Shu, Lu, Cewu
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866929449626238976
author Yan, Hengxu
Fang, Hao-Shu
Lu, Cewu
author_facet Yan, Hengxu
Fang, Hao-Shu
Lu, Cewu
contents The problem of grasping objects using a multi-finger hand has received significant attention in recent years. However, it remains challenging to handle a large number of unfamiliar objects in real and cluttered environments. In this work, we propose a representation that can be effectively mapped to the multi-finger grasp space. Based on this representation, we develop a simple decision model that generates accurate grasp quality scores for different multi-finger grasp poses using only hundreds to thousands of training samples. We demonstrate that our representation performs well on a real robot and achieves a success rate of 78.64% after training with only 500 real-world grasp attempts and 87% with 4500 grasp attempts. Additionally, we achieve a success rate of 84.51% in a dynamic human-robot handover scenario using a multi-finger hand.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02455
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Surprisingly Efficient Representation for Multi-Finger Grasping
Yan, Hengxu
Fang, Hao-Shu
Lu, Cewu
Robotics
The problem of grasping objects using a multi-finger hand has received significant attention in recent years. However, it remains challenging to handle a large number of unfamiliar objects in real and cluttered environments. In this work, we propose a representation that can be effectively mapped to the multi-finger grasp space. Based on this representation, we develop a simple decision model that generates accurate grasp quality scores for different multi-finger grasp poses using only hundreds to thousands of training samples. We demonstrate that our representation performs well on a real robot and achieves a success rate of 78.64% after training with only 500 real-world grasp attempts and 87% with 4500 grasp attempts. Additionally, we achieve a success rate of 84.51% in a dynamic human-robot handover scenario using a multi-finger hand.
title A Surprisingly Efficient Representation for Multi-Finger Grasping
topic Robotics
url https://arxiv.org/abs/2408.02455