Evolving robot sub-behaviour modules using Gene Expression Programming

Show simple item record

dc.contributor.author Mwaura, Jonathan
dc.contributor.author Keedwell, Ed
dc.date.accessioned 2014-08-12T05:32:30Z
dc.date.available 2014-08-12T05:32:30Z
dc.date.issued 2015-05
dc.description.abstract Many approaches to AI in robotics use a multi-layered approach to determine levels of behaviour from basic operations to goal-directed behaviour, the most well-known of which is the subsumption architecture. In this paper, the performances of the unigenic gene expression programming (ugGEP) and multigenic GEP (mgGEP) in evolving robot controllers for a wall following robot is analysed. Additionally, the paper introduces Regulatory Multigenic Gene Expression Programming (RMGEP), a new evolutionary technique that can be utilised to automatically evolve modularity in robot behaviour. The proposed technique extends the mgGEP algorithm, by incorporating a regulatory gene as part of the GEP chromosome. The regulatory gene, just as in systems biology, determines which of the genes in the chromosome to express and therefore how the controller solves the problem. In the initial experiments, the proposed algorithm is implemented for a robot wall following problem and the results compared to that of ugGEP and mgGEP. In addition to the wall following behaviour, a robot foraging behaviour is implemented with the aim of investigating whether the position of a speci c module (sub-expression tree (ET)) in the overall ET is of importance when coding for a problem. en_US
dc.description.embargo 2016-05-30
dc.description.librarian hb2014 en_US
dc.description.uri http://link.springer.com/journal/10710 en_US
dc.identifier.citation Mwaura, J & Keedwell, E 2015, 'Evolving robot sub-behaviour modules using Gene Expression Programming', Genetic Programming and Evolvable Machines, vol. 16, no. 2, pp. 95-131. en_US
dc.identifier.issn 1389-2576 (print)
dc.identifier.issn 1573-7632 (online)
dc.identifier.other 10.1007/s10710-014-9229-x
dc.identifier.uri http://hdl.handle.net/2263/41162
dc.language.iso en en_US
dc.publisher Springer en_US
dc.rights © Springer Science+Business Media New York 2014. The original publication is available at : http://link.springer.com/journal/10710. en_US
dc.subject Subsumption architecture en_US
dc.subject Layered learning en_US
dc.subject Evolutionary robotics en_US
dc.subject Robot behaviour coordination en_US
dc.subject Gene Expression Programming (GEP) en_US
dc.title Evolving robot sub-behaviour modules using Gene Expression Programming en_US
dc.type Postprint Article en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record