ROI-based Robotic Grasp Detection for Object Overlapping Scenes

Grasp detection considering the affiliations between grasps and their owner in object overlapping scenes is a necessary and challenging task for the practical use of the robotic grasping approach. In this paper, a robotic grasp detection algorithm named ROI-GD is proposed to provide a feasible solut...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems pp. 4768 - 4775
Main Authors: Zhang, Hanbo, Lan, Xuguang, Bai, Site, Zhou, Xinwen, Tian, Zhiqiang, Zheng, Nanning
Format: Conference Proceeding
Language:English
Published: IEEE 01.11.2019
Subjects:
Detection algorithms
Detectors
Feature extraction
Grasping
Intelligent robots
Labeling
Proposals
Robots
Visualization
ISSN:2153-0866
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Grasp detection considering the affiliations between grasps and their owner in object overlapping scenes is a necessary and challenging task for the practical use of the robotic grasping approach. In this paper, a robotic grasp detection algorithm named ROI-GD is proposed to provide a feasible solution to this problem based on Region of Interest (ROI), which is the region proposal for objects. ROI-GD uses features from ROIs to detect grasps instead of the whole scene. It has two stages: the first stage is to provide ROIs in the input image and the second-stage is the grasp detector based on ROI features. We also contribute a multi-object grasp dataset, (a) which is much larger than Cornell Grasp Dataset, by labeling Visual Manipulation Relationship Dataset. Experimental results demonstrate that ROI-GD performs much better in object overlapping scenes and at the meantime, remains comparable with state-of-the-art grasp detection algorithms on Cornell Grasp Dataset and Jacquard Dataset. Robotic experiments demonstrate that ROI-GD can help robots grasp the target in single-object and multi-object scenes with the overall success rates of 92.5% and 83.8% respectively.
ISSN:2153-0866
DOI:10.1109/IROS40897.2019.8967869