We study the emergence of intelligent behavior of a simple mobile robot. Robot control system is realized by mechanisms based on neural networks and evolutionary algorithms. The evolutionary algorithm is responsible for the adaptation of a neural network parameters based on the robot's performance in a simulated environment. In experiments, we demonstrate the performance of evolutionary algorithm on selected problems, namely maze exploration and discrimination of walls and cylinders. A comparison of different networks architectures is presented and discussed. © Springer Science+Business Media B.V. 2009.
CITATION STYLE
Neruda, R., Slušný, S., & Vidnerová, P. (2009). Behavior emergence in autonomous robot control by means of evolutionary neural networks. In Lecture Notes in Electrical Engineering (Vol. 14 LNEE, pp. 235–247). https://doi.org/10.1007/978-1-4020-8919-0_17
Mendeley helps you to discover research relevant for your work.