Incremental learning of skills in a task-parameterized Gaussian Mixture Model

The final publication is available at link.springer.com

Detalles Bibliográficos
Autores: Hoyos, Jose, Prieto, Flavio, Alenyà Ribas, Guillem|||0000-0002-6018-154X, Torras, Carme|||0000-0002-2933-398X
Tipo de recurso: artículo
Fecha de publicación:2016
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/102402
Acceso en línea:https://hdl.handle.net/2117/102402
https://dx.doi.org/10.1007/s10846-015-0290-3
Access Level:acceso abierto
Palabra clave:Programming by demonstration
Robot learning
Incremental learning
ROBOTS
cooperative systems
learning (artificial intelligence)
uncertainty handling
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
id ES_7b7feae1c6a210e55e9cbca1fbd0bf3f
oai_identifier_str oai:upcommons.upc.edu:2117/102402
network_acronym_str ES
network_name_str España
repository_id_str
spelling Incremental learning of skills in a task-parameterized Gaussian Mixture ModelHoyos, JosePrieto, FlavioAlenyà Ribas, Guillem|||0000-0002-6018-154XTorras, Carme|||0000-0002-2933-398XProgramming by demonstrationRobot learningIncremental learningROBOTScooperative systemslearning (artificial intelligence)uncertainty handlingClassificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)Àrees temàtiques de la UPC::Informàtica::RobòticaThe final publication is available at link.springer.comProgramming by demonstration techniques facilitate the programming of robots. Some of them allow the generalization of tasks through parameters, although they require new training when trajectories different from the ones used to estimate the model need to be added. One of the ways to re-train a robot is by incremental learning, which supplies additional information of the task and does not require teaching the whole task again. The present study proposes three techniques to add trajectories to a previously estimated task-parameterized Gaussian mixture model. The first technique estimates a new model by accumulating the new trajectory and the set of trajectories generated using the previous model. The second technique permits adding to the parameters of the existent model those obtained for the new trajectories. The third one updates the model parameters by running a modified version of the Expectation-Maximization algorithm, with the information of the new trajectories. The techniques were evaluated in a simulated task and a real one, and they showed better performance than that of the existent model.Peer Reviewed20162016-01-0120172017-03-13journal articlehttp://purl.org/coar/resource_type/c_6501AMhttp://purl.org/coar/version/c_ab4af688f83e57aainfo:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/102402https://dx.doi.org/10.1007/s10846-015-0290-3reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)Inglésengopen accesshttp://purl.org/coar/access_right/c_abf2info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/1024022026-05-27T15:37:01Z
dc.title.none.fl_str_mv Incremental learning of skills in a task-parameterized Gaussian Mixture Model
title Incremental learning of skills in a task-parameterized Gaussian Mixture Model
spellingShingle Incremental learning of skills in a task-parameterized Gaussian Mixture Model
Hoyos, Jose
Programming by demonstration
Robot learning
Incremental learning
ROBOTS
cooperative systems
learning (artificial intelligence)
uncertainty handling
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
title_short Incremental learning of skills in a task-parameterized Gaussian Mixture Model
title_full Incremental learning of skills in a task-parameterized Gaussian Mixture Model
title_fullStr Incremental learning of skills in a task-parameterized Gaussian Mixture Model
title_full_unstemmed Incremental learning of skills in a task-parameterized Gaussian Mixture Model
title_sort Incremental learning of skills in a task-parameterized Gaussian Mixture Model
dc.creator.none.fl_str_mv Hoyos, Jose
Prieto, Flavio
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author Hoyos, Jose
author_facet Hoyos, Jose
Prieto, Flavio
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author_role author
author2 Prieto, Flavio
Alenyà Ribas, Guillem|||0000-0002-6018-154X
Torras, Carme|||0000-0002-2933-398X
author2_role author
author
author
dc.subject.none.fl_str_mv Programming by demonstration
Robot learning
Incremental learning
ROBOTS
cooperative systems
learning (artificial intelligence)
uncertainty handling
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
topic Programming by demonstration
Robot learning
Incremental learning
ROBOTS
cooperative systems
learning (artificial intelligence)
uncertainty handling
Classificació INSPEC::Cybernetics::Artificial intelligence::Learning (artificial intelligence)
Àrees temàtiques de la UPC::Informàtica::Robòtica
description The final publication is available at link.springer.com
publishDate 2016
dc.date.none.fl_str_mv 2016
2016-01-01
2017
2017-03-13
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
AM
http://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/102402
https://dx.doi.org/10.1007/s10846-015-0290-3
url https://hdl.handle.net/2117/102402
https://dx.doi.org/10.1007/s10846-015-0290-3
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
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
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_ 1869411519617302528
score 15,300724

Similares en LA Referencia