Evolving Team Behaviour for Real Robots

Quinn, Matt, Smith, Lincoln, Mayley, Giles and Husbands, Phil (2002) Evolving Team Behaviour for Real Robots. In: Proceedings Artificial Life VIII.

Full text not available from this repository.

Abstract

We report on recent work in which we employed
artificial evolution to design neural network con-
trollers for small, homogeneous teams of mobile
autonomous robots. The robots are evolved to
perform a formation movement task from ran-
dom starting positions, equipped only with in-
frared sensors. The dual constraints of homogene-
ity and minimal sensors make this a non-trivial
task. We describe the behaviour of a successful
evolved team in which robots adopt and main-
tain functionally distinct roles in order to achieve
the task. We believe this to be the first example
of the use of artificial evolution to design coordi-
nated, cooperative behaviour for real robots.

Item Type: Conference or Workshop Item (Paper)
Schools and Departments: School of Engineering and Informatics > Informatics
Depositing User: Douglas Lincoln Smith
Date Deposited: 06 Feb 2012 20:37
Last Modified: 12 Apr 2012 11:47
URI: http://sro.sussex.ac.uk/id/eprint/27016
📧 Request an update