%0 Conference Paper %B In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics %D 2006 %T A collaborating team of Spiking Neural Network based Robotic Agents for Inaccessible Fluidic Environments %A Hani Hagras %A Martin Colley %A Anthony Pounds-Cornish %A Gustavo De Sousa %A Victor Callaghan %A George Nikiforidis %A Christos Argyropoulos %A Achilles Kameas %A Frank Murpfy %C Taipei, Taiwan %P 4867-4872 %V 6 %X
In this paper, we will introduce a novel system where identical miniaturized robotic agents with limited capabilities will collaborate to form a team that is capable of localizing and repairing scale formations in tanks and pipes within inaccessible fluidic environments. Each robotic agent is an autonomous entity that is based on the biologically inspired Spiking Neural Networks (SNNs) that communicate using pulses or spikes. The weights of the SNN are evolved using adaptive Genetic Algorithm (GA) that uses adaptive crossover and mutation to converge relatively fast to solutions that allow the robots to complete the desired tasks. The robotic agents communicate using indirect communication to move towards the site of scale formation and collaborate to repair damages.
%8 8-11 October %@ 1-4244-0100-3 %> http://daisy.cti.gr/files/50_A Collaborating Team of Spiking Neural Network Based Robotic.pdf