Evolutionary Bits'n'Spikes

Dario Floreano, Nicolas Schoeni, Gilles Caprari, Jesper Blynel
Autonomous Systems Laboratory (asl.epfl.ch), Institute of Systems Engineering
Swiss Federal Institute of Technology (EPFL), CH-1015, Lausanne, Switzerland

Abstract:

We describe a model and implementation of evolutionary spiking neurons  for embedded microcontrollers with few bytes of memory and very low power consumption. The approach is tested with an autonomous microrobot  of less than 1 in3 that evolves the ability to move in a small maze without human intervention and external computers. Considering the very large diffusion, small size, and low cost of embedded microcontrollers, the approach described here could find its way in several intelligent devices with sensors and/or actuators, as well as in smart credit cards.



Russell Standish
2002-11-13