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

Whitbrook, Amanda; Aickelin, Uwe; Garibaldi, Jonathan M.

Abstract

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.

Citation

Whitbrook, A., Aickelin, U., & Garibaldi, J. M. (2009). The use of probabilistic systems to mimic the behaviour of idiotypic AIS robot controllers. Journal of Systemics, Cybernetics and Informatics, 7(6), https://doi.org/10.2139/ssrn.2830328

• Journal Article Type: Article
• Publication Date: Jan 1, 2009
• Deposit Date: Jan 24, 2014
• Publicly Available Date: Jan 24, 2014
• Journal: Journal of Systemics, Cybernetics and Informatics
• Electronic ISSN: 1690-4524
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 6
• DOI: https://doi.org/10.2139/ssrn.2830328
• Public URL: https://nottingham-repository.worktribe.com/output/1015008
• Publisher URL: http://www.iiisci.org/journal/sci/Abstract.asp?var=&id=GS788HN