Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Image Preprocessing-based Generalization and Transfer of Learning for Grasping in Cluttered Environments

Authors
Ahn, Kuk-HyunSong, Jae-Bok
Issue Date
9월-2020
Publisher
INST CONTROL ROBOTICS & SYSTEMS, KOREAN INST ELECTRICAL ENGINEERS
Keywords
AI-based application; grasping; reinforcement learning; sim-to-real transfer
Citation
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, v.18, no.9, pp.2306 - 2314
Indexed
SCIE
SCOPUS
KCI
Journal Title
INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS
Volume
18
Number
9
Start Page
2306
End Page
2314
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/53265
DOI
10.1007/s12555-019-9618-z
ISSN
1598-6446
Abstract
In a cluttered environment in which objects are lying very closely to each other, the arranging motion is required before the robot attempts to grasp the target object. Thus, a robot must determine which motion to perform based on a given situation. This study presents an approach to learning a decision-making ability for the robot to grasp the target object after rearranging the surrounding objects obstructing the target object. The learning is performed in the virtual environment, and the image, which is an input of the deep Q-network, is preprocessed to directly apply the results of the learning to the real environment. That is, the difference between the two environments is minimized by making the states obtained from the virtual and real environments similar to each other. In addition, image preprocessing can be used to generalize the results of learning so that the robot can determine the appropriate actions to take when objects that were not used for learning are given. A hierarchical structure, which consists of high-level and low-level motion selectors, is used for the learning: the former determines the grasping or pushing actions while the latter determines how to perform such selected actions. The results of various experiments show that the proposed scheme is effective in grasping the target object in a cluttered environment without the need for any additional learning in the real world.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > Department of Mechanical Engineering > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Song, Jae Bok photo

Song, Jae Bok
공과대학 (기계공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE