Quick learning of cause-effects relevant for robot action

In this work we propose a new paradigm for the rapid learning of cause-effect relations relevant for task execution. Learning occurs automatically from action experiences by means of a novel constructive learning approach designed for applications where there is no previous knowledge of the task or...

ver descrição completa

Detalhes bibliográficos
Autores: Agostini, Alejandro Gabriel, Wörgötter, Florentin, Torras, Carme|||0000-0002-2933-398X
Formato: informe técnico
Fecha de publicación:2010
País:España
Recursos:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/12364
Acesso em linha:https://hdl.handle.net/2117/12364
Access Level:acceso abierto
Palavra-chave:Machine learning
learning (artificial intelligence) service robots.
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_f9e54b3d04ecd47ea6e5eca0b40bffb1
oai_identifier_str oai:upcommons.upc.edu:2117/12364
network_acronym_str ES
network_name_str España
repository_id_str
spelling Quick learning of cause-effects relevant for robot actionAgostini, Alejandro GabrielWörgötter, FlorentinTorras, Carme|||0000-0002-2933-398XMachine learninglearning (artificial intelligence) service robots.Aprenentatge automàticClassificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticIn this work we propose a new paradigm for the rapid learning of cause-effect relations relevant for task execution. Learning occurs automatically from action experiences by means of a novel constructive learning approach designed for applications where there is no previous knowledge of the task or world model, examples are provided on-line during run time, and the number of examples is small compared to the number of incoming experiences. These limitations pose obstacles for the existing constructive learning methods, where on-line learning is either not considered, a significant amount of prior knowledge has to be provided, or a large number of experiences or training streams are required. The system is implemented and evaluated in a humanoid robot platform using a decision-making framework that integrates a planner, the proposed learning mechanism, and a human teacher that supports the planner in the action selection. Results demonstrate the feasibility of the system for decision making in robotic applications.20102010-01-0120112011-04-13reporthttp://purl.org/coar/resource_type/c_93fcAOhttp://purl.org/coar/version/c_b1a7d7d4d402bcceinfo:eu-repo/semantics/reportapplication/pdfhttps://hdl.handle.net/2117/12364reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 3.0 Spainhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/123642026-05-27T15:37:01Z
dc.title.none.fl_str_mv Quick learning of cause-effects relevant for robot action
title Quick learning of cause-effects relevant for robot action
spellingShingle Quick learning of cause-effects relevant for robot action
Agostini, Alejandro Gabriel
Machine learning
learning (artificial intelligence) service robots.
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Quick learning of cause-effects relevant for robot action
title_full Quick learning of cause-effects relevant for robot action
title_fullStr Quick learning of cause-effects relevant for robot action
title_full_unstemmed Quick learning of cause-effects relevant for robot action
title_sort Quick learning of cause-effects relevant for robot action
dc.creator.none.fl_str_mv Agostini, Alejandro Gabriel
Wörgötter, Florentin
Torras, Carme|||0000-0002-2933-398X
author Agostini, Alejandro Gabriel
author_facet Agostini, Alejandro Gabriel
Wörgötter, Florentin
Torras, Carme|||0000-0002-2933-398X
author_role author
author2 Wörgötter, Florentin
Torras, Carme|||0000-0002-2933-398X
author2_role author
author
dc.subject.none.fl_str_mv Machine learning
learning (artificial intelligence) service robots.
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Machine learning
learning (artificial intelligence) service robots.
Aprenentatge automàtic
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description In this work we propose a new paradigm for the rapid learning of cause-effect relations relevant for task execution. Learning occurs automatically from action experiences by means of a novel constructive learning approach designed for applications where there is no previous knowledge of the task or world model, examples are provided on-line during run time, and the number of examples is small compared to the number of incoming experiences. These limitations pose obstacles for the existing constructive learning methods, where on-line learning is either not considered, a significant amount of prior knowledge has to be provided, or a large number of experiences or training streams are required. The system is implemented and evaluated in a humanoid robot platform using a decision-making framework that integrates a planner, the proposed learning mechanism, and a human teacher that supports the planner in the action selection. Results demonstrate the feasibility of the system for decision making in robotic applications.
publishDate 2010
dc.date.none.fl_str_mv 2010
2010-01-01
2011
2011-04-13
dc.type.none.fl_str_mv report
http://purl.org/coar/resource_type/c_93fc
AO
http://purl.org/coar/version/c_b1a7d7d4d402bcce
dc.type.openaire.fl_str_mv info:eu-repo/semantics/report
format report
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/12364
url https://hdl.handle.net/2117/12364
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425135537094656
score 15,228081

Registos relacionados