RT info:eu-repo/semantics/conferenceObject
T1 Learning Fuzzy Reactive Behaviors in Autonomous Robots
A1 Matellán Olivera, Vicente
A1 Molina, José Manuel
A1 Sánz, Javier
A1 Fernández Llamas, Camino
A2 Arquitectura y Tecnologia de Computadores
K1 Informática
K1 Robótica
K1 Robots autónomos
K1 Fuzzy
K1 Aprendizaje
AB This paper is concerned with the learning of basic behaviors in autonomous robots. In this way, we present a method for the adaptation of basic reactive behaviors implemented as fuzzycontrollers applying a genetic algorithm to the evolution of the fuzzy rule system. In this sense, weshow our experiments in the evolution of control rules based on symbolic concepts represented aslinguistic labels. The rules will be formulated in a fuzzy way and in order to test the rules obtainedin each generation of the genetic algorithm a real robot has been used. The individual with the bestperformance is chosen to generate a new population: the elite strategy. All the new individuals weretested in the same real environment. In conclusion, the individuals of the last generation offer a setof rules that provides better performance than the ones designed by a non-expert designer
YR 2012
FD 2012-10-11
LK http://hdl.handle.net/10612/1907
UL http://hdl.handle.net/10612/1907
NO IV European Workshop on Learning Robots, 1995, Karlsruhe (Alemania)
DS BULERIA. Repositorio Institucional de la Universidad de León
RD 27-abr-2024