Title :
Neutrality and ruggedness in robot landscapes
Author :
Smith, Tom ; Philippides, Andy ; Husbands, Phil ; O´Shea, Michael
Author_Institution :
Centre for Computational Neurosci. & Robotics (CCNR), Sussex Univ., Brighton, UK
fDate :
6/24/1905 12:00:00 AM
Abstract :
The twin fitness landscape properties of neutrality and ruggedness are crucial to the dynamics of evolutionary optimisation. In this paper, we investigate the interplay between these two properties in a complex evolutionary robotics fitness landscape, through the introduction of four robot controller architecture models; the GasNet, uniform, dispersed and plexus models. We show that, in isolation, neither added neutrality or decreased ruggedness (coupling) in the models produces increase in the speed of evolution. However, both effects in conjunction produce a significant increase in the speed of evolution
Keywords :
evolutionary computation; intelligent control; neural net architecture; neurocontrollers; optimal control; robots; GasNet model; dispersed model; dynamics; evolution rate; evolutionary optimisation; evolutionary robotics; model coupling; neutrality; plexus model; robot controller architecture models; robot fitness landscapes; ruggedness; uniform model; Artificial neural networks; Genetics; Orbital robotics; Organisms; Robot control; Robust stability; Robustness; Signal design;
Conference_Titel :
Evolutionary Computation, 2002. CEC '02. Proceedings of the 2002 Congress on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7282-4
DOI :
10.1109/CEC.2002.1004439
