The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers

Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on reinforcement learning only. This is thought to be a result of intelligent behaviour selection on t...

Full description

Bibliographic Details
Main Authors: Whitbrook, Amanda, Aickelin, Uwe, Garibaldi, Jonathan M.
Format: Article
Published: 2009
Online Access:https://eprints.nottingham.ac.uk/1326/
_version_ 1848790586076692480
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 Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on reinforcement learning only. This is thought to be a result of intelligent behaviour selection on the part of the idiotypic robot. In this paper an attempt is made to imitate idiotypic dynamics by creating controllers that use reinforcement with a number of different probabilistic schemes to select robot behaviour. The aims are to show that the idiotypic system is not merely performing some kind of periodic random behaviour selection, and to try to gain further insight into the processes that govern the idiotypic mechanism. Trials are carried out using simulated Pioneer robots that undertake navigation exercises. Results show that a scheme that boosts the probability of selecting highly-ranked alternative behaviours to 50% during stall conditions comes closest to achieving the properties of the idiotypic system, but remains unable to match it in terms of all round performance.
first_indexed 2025-11-14T18:14:58Z
format Article
id nottingham-1326
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:14:58Z
publishDate 2009
recordtype eprints
repository_type Digital Repository
spelling nottingham-13262020-05-04T20:27:07Z https://eprints.nottingham.ac.uk/1326/ The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers Whitbrook, Amanda Aickelin, Uwe Garibaldi, Jonathan M. Previous work has shown that robot navigation systems that employ an architecture based upon the idiotypic network theory of the immune system have an advantage over control techniques that rely on reinforcement learning only. This is thought to be a result of intelligent behaviour selection on the part of the idiotypic robot. In this paper an attempt is made to imitate idiotypic dynamics by creating controllers that use reinforcement with a number of different probabilistic schemes to select robot behaviour. The aims are to show that the idiotypic system is not merely performing some kind of periodic random behaviour selection, and to try to gain further insight into the processes that govern the idiotypic mechanism. Trials are carried out using simulated Pioneer robots that undertake navigation exercises. Results show that a scheme that boosts the probability of selecting highly-ranked alternative behaviours to 50% during stall conditions comes closest to achieving the properties of the idiotypic system, but remains unable to match it in terms of all round performance. 2009 Article PeerReviewed Whitbrook, Amanda, Aickelin, Uwe and Garibaldi, Jonathan M. (2009) The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers. Journal of Systemics, Cybernetics and Informatics, 7 (6). pp. 72-79. ISSN 1690-4524 http://www.iiisci.org/journal/sci/Abstract.asp?var=&id=GS788HN
spellingShingle Whitbrook, Amanda
Aickelin, Uwe
Garibaldi, Jonathan M.
The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title_full The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title_fullStr The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title_full_unstemmed The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title_short The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers
title_sort use of probabilistic systems to mimic the behaviour of idiotypic ais robot controllers
url https://eprints.nottingham.ac.uk/1326/
https://eprints.nottingham.ac.uk/1326/