|
Advances in Aircraft and Spacecraft Science Volume 1, Number 2, April 2014 , pages 219-232 DOI: https://doi.org/10.12989/aas.2014.1.2.219 |
||
|
Evolving swarm of UAVs |
||
T-Z. Chia, Hayong Chengb, J.R. Pagec and N A Ahmed
|
||
| Abstract | ||
| This paper reports on an ongoing study investigating the feasibility of using an evolutionary method to develop the rules governing Self-Organised (SO) systems for use in swarms of unmanned aerial vehicles. In general, it is difficult to design swarm systems that follow explicit global behaviour. Unlike optimising a predefined objective function, the solution to the problem is the emergent behaviour in the SO systems which results from simultaneous interactions among agents and between agents and their environment. In this study, evolutionary algorithms are used to investigate their control and effectiveness in synthesising the weighting of different rules on SO emergent behaviour. Both homogeneous swarms and heterogeneous swarms were considered though the results provided are for a case study investigating the simplest problem a homogeneous swarm without mutation. Though simple this study does indicate the potential of the approach. | ||
| Key Words | ||
| evolution; multi-agent; self-organising swarms; search and rescue | ||
| Address | ||
| T-Z. Chia, Hayong Chengb, J.R. Pagec and N A Ahmed : School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, New South Wales, 2052, Australia | ||
