Modular creation of neuronal networks for autonomous robot control

Mostrar todas las versiones(2)

In general, complex control tasks can be solved by dividing them into simpler ones which are easier to handle. Several authors have developed different solutions that combine Layer Evolution techniques with Evolving Neural Networks, giving rise to controllers made up by several networks. In this typ...

Descripción completa

Detalles Bibliográficos
Autores principales: Osella Massa, Germán Leandro, Vinuesa, Hernán Luis, Lanzarini, Laura Cristina
Formato: Articulo
Lenguaje:Inglés
Publicado: 2007
Materias:
Ciencias Informáticas
Evolutionary Neural Networks
Evolutionary robotics
Modular evolution
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/82974
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-82974
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
Evolutionary Neural Networks
Evolutionary robotics
Modular evolution
spellingShingle Ciencias Informáticas
Evolutionary Neural Networks
Evolutionary robotics
Modular evolution
Osella Massa, Germán Leandro
Vinuesa, Hernán Luis
Lanzarini, Laura Cristina
Modular creation of neuronal networks for autonomous robot control
topic_facet Ciencias Informáticas
Evolutionary Neural Networks
Evolutionary robotics
Modular evolution
description In general, complex control tasks can be solved by dividing them into simpler ones which are easier to handle. Several authors have developed different solutions that combine Layer Evolution techniques with Evolving Neural Networks, giving rise to controllers made up by several networks. In this type of solution, the selection of the module to be used in each case is not an easy problem to solve. This paper is focused on a new evolutionary mechanism that allows combining modules which solve the different parts of a problem, giving place to a single recurrent neural network. In this way, simple modules which are trained independently of the problem to solve are used. The communication among them is established by evolution, which gives rise to a single neural network representing the expected solution. The proposed method in this paper has been used to solve the problem of obstacle evasion and target reaching using a Khepera II robot. The tests carried out, both in the simulated environment and over the real robot, have yielded really successful results.
format Articulo
Articulo
author Osella Massa, Germán Leandro
Vinuesa, Hernán Luis
Lanzarini, Laura Cristina
author_facet Osella Massa, Germán Leandro
Vinuesa, Hernán Luis
Lanzarini, Laura Cristina
author_sort Osella Massa, Germán Leandro
title Modular creation of neuronal networks for autonomous robot control
title_short Modular creation of neuronal networks for autonomous robot control
title_full Modular creation of neuronal networks for autonomous robot control
title_fullStr Modular creation of neuronal networks for autonomous robot control
title_full_unstemmed Modular creation of neuronal networks for autonomous robot control
title_sort modular creation of neuronal networks for autonomous robot control
publishDate 2007
url http://sedici.unlp.edu.ar/handle/10915/82974
work_keys_str_mv AT osellamassagermanleandro modularcreationofneuronalnetworksforautonomousrobotcontrol
AT vinuesahernanluis modularcreationofneuronalnetworksforautonomousrobotcontrol
AT lanzarinilauracristina modularcreationofneuronalnetworksforautonomousrobotcontrol
bdutipo_str Repositorios
_version_ 1764820488121483268

Ejemplares similares