CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 先进机器人
Object Recognition, Localization and Grasp Detection Using a Unified Deep Convolutional Neural Network with Multi-task Loss
Qun, Jia1,2; Zhiqiang, Cao1,2; Xionglei, Zhao1,2; Lei, Pang1,2; Yingying, Yu1,2; Junzhi, Yu1,2
2018-12
Conference NameIEEE International Conference on Robotics and Biomimetics
Source PublicationIEEE International Conference on Robotics and Biomimetics
Pages1545-1550
Conference Date2018年12月12~15号
Conference Place吉隆坡
Abstract

Recognize an object and detect a good grasp in unstructured scenes is still a challenge. In this paper, the problem of detecting robotic grasps is expressed by a two-point representation in an unstructured scene with an RGB-D camera. A deep Convolutional Neural Network is designed to predict good grasps in real-time on GTX1080, with using region proposal techniques. A contribution of this work is our proposed network framework can perform classification, location and grasp detection simultaneously so that in a single step, it not only recognizes the category and bounding-box of the object, but also finds a good grasp line. Besides, in training process, we minimize a multi-task loss objective function of object classification, location and grasp detection in order to train the network endto-end. Our experimental evaluation on a real robotic manipulator demonstrates that the robotic manipulator can fulfill the grasping task effectively.

Indexed ByEI
Language英语
Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/23604
Collection复杂系统管理与控制国家重点实验室_先进机器人
复杂系统管理与控制国家重点实验室
Corresponding AuthorZhiqiang, Cao
Affiliation1.中国科学院自动化研究所
2.中国科学院大学
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Qun, Jia,Zhiqiang, Cao,Xionglei, Zhao,et al. Object Recognition, Localization and Grasp Detection Using a Unified Deep Convolutional Neural Network with Multi-task Loss[C],2018:1545-1550.
Files in This Item: Download All
File Name/Size DocType Version Access License
robio18-252.pdf(2230KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qun, Jia]'s Articles
[Zhiqiang, Cao]'s Articles
[Xionglei, Zhao]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qun, Jia]'s Articles
[Zhiqiang, Cao]'s Articles
[Xionglei, Zhao]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qun, Jia]'s Articles
[Zhiqiang, Cao]'s Articles
[Xionglei, Zhao]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: robio18-252.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.