Artificial Lampreys: Comparing Naturally and Artificially Evolved Swimming Controllers

This paper studies and compares naturally and arti cially evolved neural networks controlling the motion of an animal the anguilliform swim ming of a lamprey The swimming controller of the lamprey extensively studied and modeled by Grillner and Ekeberg is reproduced A real number Genetic Algorithm is used to de velop alternative arti cial controllers composed of neurons similar to those of the biological model We examine the feasibility of using Genetic Al gorithms to evolve neural controllers and evaluate the quality of the evolved networks by compar ing them with the biological controller Results show that arti cial controllers can be obtained with architectures other than the biological one and which in some ways are more e cient