Hierarchical gaussian reinforcement learning for path planning in uncertain environments

AlDahoul, Nouar and Htike@Muhammad Yusof, Zaw Zaw and Akmeliawati, Rini and Shafie, Amir Akramin (2015) Hierarchical gaussian reinforcement learning for path planning in uncertain environments. International Journal of Applied Engineering Research, 10 (8). pp. 20029-20040. ISSN 0973-4562

PDF Restricted to Repository staff only Download (661kB) | Request a copy

Abstract

Most of the issues in planning and controlling of robots are caused by uncertainties in the actuators and sensors of robots. Path planning is of paramount importance for autonomous mobile robots. This paper presents a path planning approach that is based on hierarchical Gaussian reinforcement learning. This approach differs from traditional Q-leaning in two ways: its ability to deal with continuous states and actions and its ability to work in uncertain (nondeterministic) environments. We propose a path planning algorithm for robots in uncertain environments by using hierarchical Gaussian Q-learning. We used Matlab to perform experiments in simulation. The simulation experimental results seem suggest the efficiency of the proposed algorithm in finding optimal paths of autonomous agents.

Item Type:	Article (Journal)
Additional Information:	6919/43050
Uncontrolled Keywords:	reinforcement learning, path planning, hierarchical Q-learning, Gaussian function, autonomous underwater vehicle.
Subjects:	A General Works > AI Indexes (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Engineering
Depositing User:	Mr. Zaw Zaw Htike
Date Deposited:	28 May 2015 09:21
Last Modified:	28 Oct 2015 16:50
URI:	http://irep.iium.edu.my/id/eprint/43050

Actions (login required)

View Item