Home // ADAPTIVE 2013, The Fifth International Conference on Adaptive and Self-Adaptive Systems and Applications // View article

EvoRoF: A Framework for On-line and On-board Evolutionary Robotics

Authors:
Florian Schlachter
Patrick Alschbach
Katja Deuschl

Keywords: on-line evolution; recurrent neural networks; reconfigurable robotics; evolutionary robotics

Abstract:
In this paper, we present an evolutionary robotics framework (EvoRoF) for on-line and off-line evolution, as well as on-board and off-board evolution for swarm and reconfigurable robotics. It enables both, the use of artificial neural networks and spiking neural networks and combines both with structural evolution of recurrent networks. It is evaluated with benchmark tests and several use cases are outlined.

Pages: 77 to 82

Copyright: Copyright (c) IARIA, 2013

Publication date: May 27, 2013

Published in: conference

ISSN: 2308-4146

ISBN: 978-1-61208-274-5

Location: Valencia, Spain

Dates: from May 27, 2013 to June 1, 2013