CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12702 > Article
Paper
16 June 2023 Learning separate objects in clutter with deep reinforcement learning
Jiangming Li, Xinyan Li, Hao Li
Author Affiliations +
Proceedings Volume 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023); 127022T (2023) https://doi.org/10.1117/12.2680487
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 2023, Changsha, China
Abstract
When the robot grasps the objects in the stack, it fails because the objects block each other and cannot find the appropriate grasping point and grasping path. Humans usually separate objects from each other before grasping stacked objects, so how to let robots effectively separate objects is crucial to achieve stable grasping. At present, many traditional analysis methods have problems such as poor generalization effect and difficulty in establishing appropriate mathematical models. Therefore, a method based on deep reinforcement learning is proposed, which trains the robot end-to-end in the continuous action space of the robot, inputs the depth map of the scene, and outputs the robot's push action. At the same time, an algorithm for judging the separation degree of a pile of objects is proposed to judge the separation degree of objects before and after the push action. The experimental results show that our method can effectively separate a pile of objects.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Jiangming Li, Xinyan Li, and Hao Li "Learning separate objects in clutter with deep reinforcement learning", Proc. SPIE 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 127022T (16 June 2023); https://doi.org/10.1117/12.2680487
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
;
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 6 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Machine learning
Deep learning
Clutter
Mathematical modeling
Neural networks
Scientific research
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top