Conference Paper

Evolution and analysis of mixed mode neural networks for walking: Mixed pattern generators

Dept. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH
DOI: 10.1109/CEC.2001.934418 Conference: Evolutionary Computation, 2001. Proceedings of the 2001 Congress on, Volume: 1
Source: IEEE Xplore


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

0 Reads
Show more