UCT CS Research Document Archive

Evolving Robust Robot Team Morphologies for Collective Construction

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

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

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.

EPrint Type:Conference Paper
Subjects:I Computing Methodologies: I.2 ARTIFICIAL INTELLIGENCE
ID Code:1196
Deposited By:Nitschke, Geoff
Deposited On:23 November 2017