Solving the optimal path planning of a mobile robot using improved Q-learning

Q-learning, a type of reinforcement learning, has gained increasing popularity in autonomous mobile robot path planning recently, due to its self-learning ability without requiring a priori model of the environment. Yet, despite such advantage, Q-learning exhibits slow convergence to the optimal sol...

Full description

Bibliographic Details
Main Authors: Low, Ee Soong, Ong, Pauline, Cheah, Kah Chun
Format: Article
Language:English
Published: Elsevier 2019
Subjects:
Online Access:http://eprints.uthm.edu.my/4217/
http://eprints.uthm.edu.my/4217/1/AJ%202019%20%28253%29.pdf
_version_ 1848888227410214912
author Low, Ee Soong
Ong, Pauline
Cheah, Kah Chun
author_facet Low, Ee Soong
Ong, Pauline
Cheah, Kah Chun
author_sort Low, Ee Soong
building UTHM Institutional Repository
collection Online Access
description Q-learning, a type of reinforcement learning, has gained increasing popularity in autonomous mobile robot path planning recently, due to its self-learning ability without requiring a priori model of the environment. Yet, despite such advantage, Q-learning exhibits slow convergence to the optimal solution. In order to address this limitation, the concept of partially guided Q-learning is introduced wherein, the flower pollination algorithm (FPA) is utilized to improve the initialization of Q-learning. Experimental evaluation of the proposed improved Q-learning under the challenging environment with a different layout of obstacles shows that the convergence of Q-learning can be accelerated when Q-values are initialized appropriately using the FPA. Additionally, the effectiveness of the proposed algorithm is validated in a real-world experiment using a three-wheeled mobile robot.
first_indexed 2025-11-15T20:06:56Z
format Article
id uthm-4217
institution Universiti Tun Hussein Onn Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T20:06:56Z
publishDate 2019
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling uthm-42172021-12-01T05:41:23Z http://eprints.uthm.edu.my/4217/ Solving the optimal path planning of a mobile robot using improved Q-learning Low, Ee Soong Ong, Pauline Cheah, Kah Chun LB1050.9-1091 Educational psychology TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General) Q-learning, a type of reinforcement learning, has gained increasing popularity in autonomous mobile robot path planning recently, due to its self-learning ability without requiring a priori model of the environment. Yet, despite such advantage, Q-learning exhibits slow convergence to the optimal solution. In order to address this limitation, the concept of partially guided Q-learning is introduced wherein, the flower pollination algorithm (FPA) is utilized to improve the initialization of Q-learning. Experimental evaluation of the proposed improved Q-learning under the challenging environment with a different layout of obstacles shows that the convergence of Q-learning can be accelerated when Q-values are initialized appropriately using the FPA. Additionally, the effectiveness of the proposed algorithm is validated in a real-world experiment using a three-wheeled mobile robot. Elsevier 2019 Article PeerReviewed text en http://eprints.uthm.edu.my/4217/1/AJ%202019%20%28253%29.pdf Low, Ee Soong and Ong, Pauline and Cheah, Kah Chun (2019) Solving the optimal path planning of a mobile robot using improved Q-learning. Robotics and Autonomous Systems, 115. pp. 143-161. ISSN 0921-8890 https://doi.org/10.1016/j.robot.2019.02.013
spellingShingle LB1050.9-1091 Educational psychology
TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General)
Low, Ee Soong
Ong, Pauline
Cheah, Kah Chun
Solving the optimal path planning of a mobile robot using improved Q-learning
title Solving the optimal path planning of a mobile robot using improved Q-learning
title_full Solving the optimal path planning of a mobile robot using improved Q-learning
title_fullStr Solving the optimal path planning of a mobile robot using improved Q-learning
title_full_unstemmed Solving the optimal path planning of a mobile robot using improved Q-learning
title_short Solving the optimal path planning of a mobile robot using improved Q-learning
title_sort solving the optimal path planning of a mobile robot using improved q-learning
topic LB1050.9-1091 Educational psychology
TJ210.2-211.47 Mechanical devices and figures. Automata. Ingenious mechanisms. Robots (General)
url http://eprints.uthm.edu.my/4217/
http://eprints.uthm.edu.my/4217/
http://eprints.uthm.edu.my/4217/1/AJ%202019%20%28253%29.pdf