Evolving brain structures for robot control
Frank Pasemann, Ulrich Steinmetz, Martin Hülse, and Bruno Lara
Contact the author: Please use for correspondence this email.
Submission date: 04. Apr. 2001
published in: 6th International Work Conference on Artificial and Natural Neural Networks / J. Mira (ed.)
Berlin ; Heidelberg ; New York ; Barcelona ; Hong Kong ; London : Springer, 2001. - P. 410 - 417
(Lecture notes in computer science ; 2085)
Download full preprint: PDF (309 kB), PS ziped (246 kB)
To study the relevance of recurrent neural network structures for the behavior of autonomous agents a series of experiments with miniature robots is performed. A special evolutionary algorithm is used to generate networks of different sizes and architectures. Solutions for obstacle avoidance and phototropic behavior are presented. Networks are evolved with the help of simulated robots, and the results are validated with the use of physical robots.