Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot

A combined short-term learning (STL) and long-term learning (LTL) approach to solving mobile-robot navigation problems is presented and tested in both the real and virtual domains. The LTL phase consists of rapid simulations that use a genetic algorithm to derive diverse sets of behaviours, encode...

Full description

Bibliographic Details
Main Authors: Whitbrook, Amanda, Aickelin, Uwe, Garibaldi, Jonathan M.
Format: Article
Published: Elsevier 2010
Online Access:https://eprints.nottingham.ac.uk/1322/
_version_ 1848790585564987392
author Whitbrook, Amanda
Aickelin, Uwe
Garibaldi, Jonathan M.
author_facet Whitbrook, Amanda
Aickelin, Uwe
Garibaldi, Jonathan M.
author_sort Whitbrook, Amanda
building Nottingham Research Data Repository
collection Online Access
description A combined short-term learning (STL) and long-term learning (LTL) approach to solving mobile-robot navigation problems is presented and tested in both the real and virtual domains. The LTL phase consists of rapid simulations that use a genetic algorithm to derive diverse sets of behaviours, encoded as variable sets of attributes, and the STL phase is an idiotypic artificial immune system. Results from the LTL phase show that sets of behaviours develop very rapidly, and significantly greater diversity is obtained when multiple autonomous populations are used, rather than a single one. The architecture is assessed under various scenarios, including removal of the LTL phase and switching off the idiotypic mechanism in the STL phase. The comparisons provide substantial evidence that the best option is the inclusion of both the LTL phase and the idiotypic system. In addition, this paper shows that structurally different environments can be used for the two phases without compromising transferability.
first_indexed 2025-11-14T18:14:57Z
format Article
id nottingham-1322
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:14:57Z
publishDate 2010
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling nottingham-13222020-05-04T20:26:04Z https://eprints.nottingham.ac.uk/1322/ Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot Whitbrook, Amanda Aickelin, Uwe Garibaldi, Jonathan M. A combined short-term learning (STL) and long-term learning (LTL) approach to solving mobile-robot navigation problems is presented and tested in both the real and virtual domains. The LTL phase consists of rapid simulations that use a genetic algorithm to derive diverse sets of behaviours, encoded as variable sets of attributes, and the STL phase is an idiotypic artificial immune system. Results from the LTL phase show that sets of behaviours develop very rapidly, and significantly greater diversity is obtained when multiple autonomous populations are used, rather than a single one. The architecture is assessed under various scenarios, including removal of the LTL phase and switching off the idiotypic mechanism in the STL phase. The comparisons provide substantial evidence that the best option is the inclusion of both the LTL phase and the idiotypic system. In addition, this paper shows that structurally different environments can be used for the two phases without compromising transferability. Elsevier 2010 Article NonPeerReviewed Whitbrook, Amanda, Aickelin, Uwe and Garibaldi, Jonathan M. (2010) Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot. Applied Soft Computing, 10 (3). pp. 876-887. ISSN 1568-4946 http://dx.doi.org/10.1016/j.asoc.2009.10.005 doi:10.1016/j.asoc.2009.10.005 doi:10.1016/j.asoc.2009.10.005
spellingShingle Whitbrook, Amanda
Aickelin, Uwe
Garibaldi, Jonathan M.
Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title_full Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title_fullStr Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title_full_unstemmed Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title_short Two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
title_sort two-timescale learning using idiotypic behaviour mediation for a navigating mobile robot
url https://eprints.nottingham.ac.uk/1322/
https://eprints.nottingham.ac.uk/1322/
https://eprints.nottingham.ac.uk/1322/