Title :
A compact evolutionary algorithm for integer spiking neural network robot controllers
Author :
Capuozzo, Mario D. ; Livingston, David L.
Author_Institution :
Constellation Energy, Baltimore, MD, USA
Abstract :
In order to facilitate online training of a robot controller composed of a spiking neural network, we propose the creation of a method dubbed a `compact evolutionary algorithm´. The compact evolutionary algorithm, derived from the compact genetic algorithm, greatly reduces the memory requirements for evolutionary optimization and also obviates the need for floating-point arithmetic capabilities allowing its efficient implementation by microcontrollers. The compact evolutionary algorithm is compared to the traditional evolutionary algorithm for solving three cyclic functions that are of use in a walking robot.
Keywords :
control engineering computing; genetic algorithms; microcontrollers; mobile robots; neurocontrollers; compact evolutionary algorithm; compact genetic algorithm; cyclic functions; evolutionary optimization; floating-point arithmetic capabilities; integer spiking neural network robot controllers; microcontrollers; online training; walking robot; Biological neural networks; Evolutionary computation; Genetic algorithms; Legged locomotion; Microcontrollers; Neurons;
Conference_Titel :
Southeastcon, 2011 Proceedings of IEEE
Conference_Location :
Nashville, TN
Print_ISBN :
978-1-61284-739-9
DOI :
10.1109/SECON.2011.5752941