Evolving Robust Robot Team Morphologies for Collective Construction

Watson, James and Nitschke, Geoff (2015) Evolving Robust Robot Team Morphologies for Collective Construction, Proceedings of IEEE Symposium Series on Computational Intelligence (IEEE SSCI 2015), Cape Town, South Africa, 1039-1046, IEEE Press.

PDF 2015-Evolving_Robust_Robot_Team_Morphologies_for_Collective_Construction.pdf Download (196kB)

Abstract

This research falls within evolutionary robotics and the larger taxonomy of cooperative multi-robot systems. A study of comparative methods to adapt the behaviors and morphologies of simulated robot teams that must solve a collective construction task is presented. Multiple versions of an indirect encoding (developmental) method for the artificial evolution of team behaviors and morphologies were tested. Results indicated the developmental method was able to evolve effective robot team morphologies in a collective construction task, where evolved teams yielded a task performance comparable to optimal team morphologies manually designed specifically for the collective construction task. Results also indicated that the developmental method was appropriate for evolving controllers that were able to generalize to a range of different team morphologies that also solved the collective construction task with a high degree of task performance.

Item Type:	Conference paper
Subjects:	Computing methodologies > Artificial intelligence
Date Deposited:	23 Nov 2017
Last Modified:	10 Oct 2019 15:32
URI:	http://pubs.cs.uct.ac.za/id/eprint/1196

Actions (login required)

View Item