Evolving the morphology of a neural network for controlling a foveating retina: and its test on a real robot
Peter Eggenberger Hotz, Gabriel Gómex, Rolf Pfeifer · 2002
The standard approach in evolutionary robotics is to evolve neural networks for control by encoding the parameters of the network in the genome. By contrast, we have evolved a neural controller based on biological principles from molecular and developmental biology. The key principles employed in our algorithms model the specific ligand-receptor interactions and gene regulation.