Affiliations: Facultad de Física e Inteligencia Artificial, Universidad Veracruzana Sebastián Camacho 5, Col. Centro, Xalapa, Veracruz, México
Note: [] Corresponding author: F. Montes-González, Facultad de Física e Inteligencia Artificial, Universidad Veracruzana Sebastián Camacho 5, Col. Centro, Xalapa, Veracruz, México. Tel.: +522288172957; Fax.: +52288172855, Email: fmontes@uv.mx
Abstract: The use of effective central selection provides flexibility in design by offering modularity and extensibility. In earlier papers we have focused on the development of a simple centralized selection mechanism. Our current goal is to integrate evolutionary methods in the design of non-sequential behaviours and the tuning of specific parameters of the selection model. The foraging behaviour of an animal robot (animat) has been modelled in order to integrate the sensory information from the robot to perform selection that is nearly optimized by the use of genetic algorithms. In this paper we present how selection through optimization finally arranges the pattern of presented behaviours for the foraging task. Hence, the execution of specific parts in a behavioural pattern may be ruled out by the tuning of these parameters. Furthermore, the intensive use of colour segmentation from a colour camera for locating a cylinder sets a burden on the calculations carried out by the genetic algorithm.
