S4G: Amodal Single-view Single-Shot SE(3) Grasp Detection in Cluttered Scenes

Grasping is among the most fundamental and long-lasting problems in robotics study. This paper studies the problem of 6-DoF(degree of freedom) grasping by a parallel gripper in a cluttered scene captured using a commodity depth sensor from a single viewpoint. We address the problem in a learning-bas...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Qin, Yuzhe, Chen, Rui, Zhu, Hao, Song, Meng, Xu, Jing, Su, Hao
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 31.10.2019
Subjects
Annotations
Grasping (robotics)
Neural networks
Parallel degrees of freedom
Robotics
Online AccessGet full text

Cover

More Information
Summary:Grasping is among the most fundamental and long-lasting problems in robotics study. This paper studies the problem of 6-DoF(degree of freedom) grasping by a parallel gripper in a cluttered scene captured using a commodity depth sensor from a single viewpoint. We address the problem in a learning-based framework. At the high level, we rely on a single-shot grasp proposal network, trained with synthetic data and tested in real-world scenarios. Our single-shot neural network architecture can predict amodal grasp proposal efficiently and effectively. Our training data synthesis pipeline can generate scenes of complex object configuration and leverage an innovative gripper contact model to create dense and high-quality grasp annotations. Experiments in synthetic and real environments have demonstrated that the proposed approach can outperform state-of-the-arts by a large margin.
ISSN:2331-8422