Mobile robot path planning using q-learning with guided Distance
In path planning for mobile robot, classical Q-learning algorithm requires high iteration counts and longer time taken to achieve conver-gence. This is due to the beginning stage of classical Q-learning for path planning consists of mostly exploration, involving random di-rection decision making. Th...
Saved in:
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Science Publishing Corporation
2018
|
Subjects: | |
Online Access: | http://eprints.uthm.edu.my/3680/1/AJ%202018%20%28721%29%20Mobile%20robot%20path%20planning%20using%20q-learning%20with%20guided.pdf http://eprints.uthm.edu.my/3680/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
my.uthm.eprints.3680 |
---|---|
record_format |
eprints |
spelling |
my.uthm.eprints.36802021-11-21T07:05:25Z http://eprints.uthm.edu.my/3680/ Mobile robot path planning using q-learning with guided Distance Ee, Soong Low Pauline, Ong Cheng, Yee Low TJ1040-1119 Machinery exclusive of prime movers TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) In path planning for mobile robot, classical Q-learning algorithm requires high iteration counts and longer time taken to achieve conver-gence. This is due to the beginning stage of classical Q-learning for path planning consists of mostly exploration, involving random di-rection decision making. This paper proposed the addition of distance aspect into direction decision making in Q-learning. This feature is used to reduce the time taken for the Q-learning to fully converge. In the meanwhile, random direction decision making is added and activated when mobile robot gets trapped in local optima. This strategy enables the mobile robot to escape from local optimal trap. The results show that the time taken for the improved Q-learning with distance guiding to converge is longer than the classical Q-learning. However, the total number of steps used is lower than the classical Q-learning. Science Publishing Corporation 2018 Article PeerReviewed text en http://eprints.uthm.edu.my/3680/1/AJ%202018%20%28721%29%20Mobile%20robot%20path%20planning%20using%20q-learning%20with%20guided.pdf Ee, Soong Low and Pauline, Ong and Cheng, Yee Low (2018) Mobile robot path planning using q-learning with guided Distance. International Journal of Engineering & Technology, 7 (4.27). pp. 57-62. ISSN 2227-524X |
institution |
Universiti Tun Hussein Onn Malaysia |
building |
UTHM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Tun Hussein Onn Malaysia |
content_source |
UTHM Institutional Repository |
url_provider |
http://eprints.uthm.edu.my/ |
language |
English |
topic |
TJ1040-1119 Machinery exclusive of prime movers TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) |
spellingShingle |
TJ1040-1119 Machinery exclusive of prime movers TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) Ee, Soong Low Pauline, Ong Cheng, Yee Low Mobile robot path planning using q-learning with guided Distance |
description |
In path planning for mobile robot, classical Q-learning algorithm requires high iteration counts and longer time taken to achieve conver-gence. This is due to the beginning stage of classical Q-learning for path planning consists of mostly exploration, involving random di-rection decision making. This paper proposed the addition of distance aspect into direction decision making in Q-learning. This feature is used to reduce the time taken for the Q-learning to fully converge. In the meanwhile, random direction decision making is added and activated when mobile robot gets trapped in local optima. This strategy enables the mobile robot to escape from local optimal trap. The results show that the time taken for the improved Q-learning with distance guiding to converge is longer than the classical Q-learning. However, the total number of steps used is lower than the classical Q-learning. |
format |
Article |
author |
Ee, Soong Low Pauline, Ong Cheng, Yee Low |
author_facet |
Ee, Soong Low Pauline, Ong Cheng, Yee Low |
author_sort |
Ee, Soong Low |
title |
Mobile robot path planning using q-learning with guided
Distance |
title_short |
Mobile robot path planning using q-learning with guided
Distance |
title_full |
Mobile robot path planning using q-learning with guided
Distance |
title_fullStr |
Mobile robot path planning using q-learning with guided
Distance |
title_full_unstemmed |
Mobile robot path planning using q-learning with guided
Distance |
title_sort |
mobile robot path planning using q-learning with guided
distance |
publisher |
Science Publishing Corporation |
publishDate |
2018 |
url |
http://eprints.uthm.edu.my/3680/1/AJ%202018%20%28721%29%20Mobile%20robot%20path%20planning%20using%20q-learning%20with%20guided.pdf http://eprints.uthm.edu.my/3680/ |
_version_ |
1738581155048849408 |
score |
13.160551 |