On the evolution of homogeneous two-robot teams: clonal versus aclonal approaches

Article


Tuci, E. and Trianni, V. 2014. On the evolution of homogeneous two-robot teams: clonal versus aclonal approaches. Neural Computing and Applications. 25 (5), pp. 1063-1076. https://doi.org/10.1007/s00521-014-1594-0
TypeArticle
TitleOn the evolution of homogeneous two-robot teams: clonal versus aclonal approaches
AuthorsTuci, E. and Trianni, V.
Abstract

This study compares two different evolutionary approaches (clonal and aclonal) to the design of homogeneous two-robot teams (i.e. teams of morphologically identical agents with identical controllers) in a task that requires the agents to specialise to different roles. The two approaches differ mainly in the way teams are formed during evolution. In the clonal approach, a team is formed from a single genotype within one population of genotypes. In the aclonal approach, a team is formed from multiple genotypes within one population of genotypes. In both cases, the goal is the synthesis of individual generalist controllers capable of integrating role execution and role allocation mechanisms for a team of homogeneous robots. Our results diverge from those illustrated in a similar comparative study, which supports the superiority of the aclonal versus the clonal approach. We question this result and its theoretical underpinning, and we bring new empirical evidence showing that the clonal outperforms the aclonal approach in generating homogeneous teams required to dynamically specialise for the benefit of the team. The results of our study suggest that task-specific elements influence the evolutionary dynamics more than the genetic relatedness of the team members. We conclude that the appropriateness of the clonal approach for role allocation scenarios is mainly determined by the specificity of the collective task, including the evaluation function, rather than by the way in which the solutions are evaluated during evolution.

Research GroupArtificial Intelligence group
PublisherSpringer
JournalNeural Computing and Applications
ISSN0941-0643
Publication dates
Online23 Apr 2014
Print01 Oct 2014
Publication process dates
Deposited13 Jun 2017
Accepted07 Apr 2014
Output statusPublished
Accepted author manuscript
Copyright Statement

The final publication is available at Springer via http://dx.doi.org/10.1007/s00521-014-1594-0

Digital Object Identifier (DOI)https://doi.org/10.1007/s00521-014-1594-0
LanguageEnglish
Permalink -

https://repository.mdx.ac.uk/item/86zyy

Download files


Accepted author manuscript
  • 15
    total views
  • 3
    total downloads
  • 0
    views this month
  • 0
    downloads this month

Export as