Fuzzy classifier system architectures for mobile robotics: An experimental comparison

Pipe, A. G. and Carse, B. (2005) Fuzzy classifier system architectures for mobile robotics: An experimental comparison. International Journal of Intelligent Systems, 22 (9). pp. 993-1019. ISSN 1098-111X

Full text not available from this repository

Publisher's URL: http://dx.doi.org/10.1002/int.20235


Item Type:Article
Additional Information:Learning Classifier Systems (LCSs) are proposed as the universal learning system, and could therefore be used in a wide range of applications. They represent powerful linguistically interpretable rule-based structures, combined with versatile self-adaptive algorithms. However, in standard form, they lack interfaces to continuously varying inputs and outputs. Combining them with Fuzzy Logic solves this problem, but leads to other internal difficulties for the learning system. This article presents an experimental comparison of the two main types of LCS applied to mobile robot control, and suggests some underlying reasons for the remaining learning difficulties.
Uncontrolled Keywords:fuzzy classifier system architectures, mobile robotics
Faculty/Department:Faculty of Environment and Technology
ID Code:5899
Deposited By: R. Upload account
Deposited On:22 Jan 2010 15:10
Last Modified:12 Mar 2014 16:45

Request a change to this item

Copyright 2013 © UWE better together