Evolution and analysis of mixed mode neural networks for walking: mixed pattern generators
John Christopher Gallagher · 2002
This paper summarizes the results of the dynamical systems analysis of nearly four hundred continuous-time recurrent neural network (CTRNN) single-leg locomotion controllers evolved under conditions where sensory information was unreliable and in which the body the controller was embedded in could change its physical properties. The general principles underlying the operation of all the resulting mixed pattern generators (MPGs) are discussed. Several MPG operational features are explained and verified. Finally, discussion is made of future extensions of this research.