Continuous evolution of neural modules for autonomous robot controllers

In recent years, research on techniques for developing controllers for autonomous robots has been conducted. Evolutionary Algorithms are among the most popular tools used in this type of problem, mostly for its capacity to adapt to the environment. Nevertheless, they are usually applied to produce a...

Descripción completa

Detalles Bibliográficos
Autores principales:	Vinuesa, Hernán Luis, Osella Massa, Germán Leandro, Corbalán, Leonardo César, Lanzarini, Laura Cristina
Formato:	Objeto de conferencia
Lenguaje:	Inglés
Publicado:	2007
Materias:	Ciencias Informáticas Informática modular evolution evolutionary algorithms Neural nets Algorithms evolución de módulos neuronales algoritmos evolutivos
Acceso en línea:	http://sedici.unlp.edu.ar/handle/10915/23177
Aporte de:	SEDICI (UNLP) de Universidad Nacional de La Plata

id	I19-R120-10915-23177
record_format	dspace
institution	Universidad Nacional de La Plata
institution_str	I-19
repository_str	R-120
collection	SEDICI (UNLP)
language	Inglés
topic	Ciencias Informáticas Informática modular evolution evolutionary algorithms Neural nets Algorithms evolución de módulos neuronales algoritmos evolutivos
spellingShingle	Ciencias Informáticas Informática modular evolution evolutionary algorithms Neural nets Algorithms evolución de módulos neuronales algoritmos evolutivos Vinuesa, Hernán Luis Osella Massa, Germán Leandro Corbalán, Leonardo César Lanzarini, Laura Cristina Continuous evolution of neural modules for autonomous robot controllers
topic_facet	Ciencias Informáticas Informática modular evolution evolutionary algorithms Neural nets Algorithms evolución de módulos neuronales algoritmos evolutivos
description	In recent years, research on techniques for developing controllers for autonomous robots has been conducted. Evolutionary Algorithms are among the most popular tools used in this type of problem, mostly for its capacity to adapt to the environment. Nevertheless, they are usually applied to produce a controller that will not continue its adjustment after concluding this process. This causes trouble to a controller when it is used in a dynamic environment. In this paper, the combination of a state-of-the-art modular neuro-evolution algorithm with a specific evolutionary algorithm is proposed. The former method is used to generate the controller while the later is used to adjust it during its operation. As a result, an adaptable controller based on a minimal topology neural network is obtained. The method proposed was tested in a goal-reach problem with satisfying results. Finally, conclusions are presented.
format	Objeto de conferencia Objeto de conferencia
author	Vinuesa, Hernán Luis Osella Massa, Germán Leandro Corbalán, Leonardo César Lanzarini, Laura Cristina
author_facet	Vinuesa, Hernán Luis Osella Massa, Germán Leandro Corbalán, Leonardo César Lanzarini, Laura Cristina
author_sort	Vinuesa, Hernán Luis
title	Continuous evolution of neural modules for autonomous robot controllers
title_short	Continuous evolution of neural modules for autonomous robot controllers
title_full	Continuous evolution of neural modules for autonomous robot controllers
title_fullStr	Continuous evolution of neural modules for autonomous robot controllers
title_full_unstemmed	Continuous evolution of neural modules for autonomous robot controllers
title_sort	continuous evolution of neural modules for autonomous robot controllers
publishDate	2007
url	http://sedici.unlp.edu.ar/handle/10915/23177
work_keys_str_mv	AT vinuesahernanluis continuousevolutionofneuralmodulesforautonomousrobotcontrollers AT osellamassagermanleandro continuousevolutionofneuralmodulesforautonomousrobotcontrollers AT corbalanleonardocesar continuousevolutionofneuralmodulesforautonomousrobotcontrollers AT lanzarinilauracristina continuousevolutionofneuralmodulesforautonomousrobotcontrollers
bdutipo_str	Repositorios
_version_	1764820465743822849

Continuous evolution of neural modules for autonomous robot controllers

Ejemplares similares