Evolutionary robots with on-line self-organization and behavioral fitness


We address two issues in Evolutionary Robotics, namely the genetic encoding and the performance criterion, also known as the fitness function. For the first aspect, we suggest to encode mechanisms for parameter self-organization, instead of the parameters themselves as in conventional approaches. We argue that the suggested encoding generates systems that can solve more complex tasks and are more robust to unpredictable sources of change. We support our arguments with a set of experiments on evolutionary neural controllers for physical robots and compare them to conventional encoding. In addition, we show that when also the genetic encoding is left free to evolve, artificial evolution will select to exploit mechanisms of self-organization. For the second aspect, we shall discuss the role of the performance criterion, als known as fitness function, and suggest Fitness Space as a framework to conceive fitness functions in Evolutionary Robotics. Fitness Space can be used as a guide to design fitness functions as well as to compare different experiments in Evolutionary Robotics.

DOI: 10.1016/S0893-6080(00)00032-0

Extracted Key Phrases

14 Figures and Tables

Citations per Year

225 Citations

Semantic Scholar estimates that this publication has 225 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Floreano2000EvolutionaryRW, title={Evolutionary robots with on-line self-organization and behavioral fitness}, author={Dario Floreano and Joseba Urzelai}, journal={Neural networks : the official journal of the International Neural Network Society}, year={2000}, volume={13 4-5}, pages={431-43} }