Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex
Autor(a) principal: | |
---|---|
Data de Publicação: | 2014 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Journal on Interactive Systems |
Texto Completo: | https://sol.sbc.org.br/journals/index.php/jis/article/view/723 |
Resumo: | In this work, we propose a technique for generation of emergent navigation behavior in autonomous agents which are able to move at the environment using their own vision. In order to achieve this, we apply the Continuous Time Recurrent Artificial Neural Network and the genetic encoding proposed in [1] and [2]. However, we use a new sensorial description, which consists of captured images by a virtual camera, evolving an artificial visual cortex. The experiments show that the agents are able to navigate at the environment and to find the exit, in a non-programmed way and whithout requiring agent’s reprogrammation, using only the visual data passed to the neural network. This technique has the flexibility of being applied in various environments, without displaying a biased forced behavior as a result of a behavioral modeling, as in other techniques. |
id |
SBC-3_c6c8e2692d0a4db4b2e5aa4fad2fd796 |
---|---|
oai_identifier_str |
oai:ojs2.sol.sbc.org.br:article/723 |
network_acronym_str |
SBC-3 |
network_name_str |
Journal on Interactive Systems |
repository_id_str |
|
spelling |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual CortexIn this work, we propose a technique for generation of emergent navigation behavior in autonomous agents which are able to move at the environment using their own vision. In order to achieve this, we apply the Continuous Time Recurrent Artificial Neural Network and the genetic encoding proposed in [1] and [2]. However, we use a new sensorial description, which consists of captured images by a virtual camera, evolving an artificial visual cortex. The experiments show that the agents are able to navigate at the environment and to find the exit, in a non-programmed way and whithout requiring agent’s reprogrammation, using only the visual data passed to the neural network. This technique has the flexibility of being applied in various environments, without displaying a biased forced behavior as a result of a behavioral modeling, as in other techniques.Nenhum resumo disponívelBrazilian Computer Society2014-12-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://sol.sbc.org.br/journals/index.php/jis/article/view/72310.5753/jis.2014.723Journal of Interactive Systems; v. 5 n. 3 (2014)Journal on Interactive Systems; Vol. 5 No. 3 (2014)2763-7719reponame:Journal on Interactive Systemsinstname:Sociedade Brasileira de Computação (SBC)instacron:SBCenghttps://sol.sbc.org.br/journals/index.php/jis/article/view/723/717Carneiro, Lílian de OliveiraCavalcante-Neto, JoaquimVidal, CretoNogueira, YuriVila Nova, Arnaldoinfo:eu-repo/semantics/openAccess2020-09-05T16:09:12Zoai:ojs2.sol.sbc.org.br:article/723Revistahttps://sol.sbc.org.br/journals/index.php/jis/ONGhttps://sol.sbc.org.br/journals/index.php/jis/oaijis@sbc.org.br2763-77192763-7719opendoar:2020-09-05T16:09:12Journal on Interactive Systems - Sociedade Brasileira de Computação (SBC)false |
dc.title.none.fl_str_mv |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
title |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
spellingShingle |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex Carneiro, Lílian de Oliveira |
title_short |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
title_full |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
title_fullStr |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
title_full_unstemmed |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
title_sort |
Emergent Navigation Behavior of Autonomous Virtual Agents Endowed with an Evolved Visual Cortex |
author |
Carneiro, Lílian de Oliveira |
author_facet |
Carneiro, Lílian de Oliveira Cavalcante-Neto, Joaquim Vidal, Creto Nogueira, Yuri Vila Nova, Arnaldo |
author_role |
author |
author2 |
Cavalcante-Neto, Joaquim Vidal, Creto Nogueira, Yuri Vila Nova, Arnaldo |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Carneiro, Lílian de Oliveira Cavalcante-Neto, Joaquim Vidal, Creto Nogueira, Yuri Vila Nova, Arnaldo |
description |
In this work, we propose a technique for generation of emergent navigation behavior in autonomous agents which are able to move at the environment using their own vision. In order to achieve this, we apply the Continuous Time Recurrent Artificial Neural Network and the genetic encoding proposed in [1] and [2]. However, we use a new sensorial description, which consists of captured images by a virtual camera, evolving an artificial visual cortex. The experiments show that the agents are able to navigate at the environment and to find the exit, in a non-programmed way and whithout requiring agent’s reprogrammation, using only the visual data passed to the neural network. This technique has the flexibility of being applied in various environments, without displaying a biased forced behavior as a result of a behavioral modeling, as in other techniques. |
publishDate |
2014 |
dc.date.none.fl_str_mv |
2014-12-30 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://sol.sbc.org.br/journals/index.php/jis/article/view/723 10.5753/jis.2014.723 |
url |
https://sol.sbc.org.br/journals/index.php/jis/article/view/723 |
identifier_str_mv |
10.5753/jis.2014.723 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
https://sol.sbc.org.br/journals/index.php/jis/article/view/723/717 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Brazilian Computer Society |
publisher.none.fl_str_mv |
Brazilian Computer Society |
dc.source.none.fl_str_mv |
Journal of Interactive Systems; v. 5 n. 3 (2014) Journal on Interactive Systems; Vol. 5 No. 3 (2014) 2763-7719 reponame:Journal on Interactive Systems instname:Sociedade Brasileira de Computação (SBC) instacron:SBC |
instname_str |
Sociedade Brasileira de Computação (SBC) |
instacron_str |
SBC |
institution |
SBC |
reponame_str |
Journal on Interactive Systems |
collection |
Journal on Interactive Systems |
repository.name.fl_str_mv |
Journal on Interactive Systems - Sociedade Brasileira de Computação (SBC) |
repository.mail.fl_str_mv |
jis@sbc.org.br |
_version_ |
1796797411062972416 |