How to add new knowledge to already trained deep learning models applied to semantic localization

The capacity of a robot to automatically adapt to new environments is crucial, especially in social robotics. Often, when these robots are deployed in home or office environments, they tend to fail because they lack the ability to adapt to new and continuously changing scenarios. In order to accompl...

Ful tanımlama

Kaydedildi:
Detaylı Bibliyografya
Yazar: Cruz, Edmanuel (author)
Diğer Yazarlar: Rangel, José Carlos (author), Gomez Donoso, Francisco (author), Cazorla, Miguel (author)
Materyal Türü: article
Dil:İngilizce
Baskı/Yayın Bilgisi: 2020
Konular:
Online Erişim:https://link.springer.com/article/10.1007/s10489-019-01517-1
https://ridda2.utp.ac.pa/handle/123456789/9445
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!
_version_ 1869652471282925568
author Cruz, Edmanuel
author2 Rangel, José Carlos
Gomez Donoso, Francisco
Cazorla, Miguel
author2_role author
author
author
author_browse Cazorla, Miguel
Cruz, Edmanuel
Gomez Donoso, Francisco
Rangel, José Carlos
author_facet Cruz, Edmanuel
Rangel, José Carlos
Gomez Donoso, Francisco
Cazorla, Miguel
author_role author
collection Repositorio Institucional de documento digitales de acceso abierto de la UTP
dc.creator.none.fl_str_mv Cruz, Edmanuel
Rangel, José Carlos
Gomez Donoso, Francisco
Cazorla, Miguel
dc.date.none.fl_str_mv 06/19/2019
06/19/2019
2020-01-02T21:25:41Z
2020-01-02T21:25:41Z
2020-01-02T21:25:41Z
2020-01-02T21:25:41Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv https://link.springer.com/article/10.1007/s10489-019-01517-1
https://ridda2.utp.ac.pa/handle/123456789/9445
https://ridda2.utp.ac.pa/handle/123456789/9445
dc.language.none.fl_str_mv eng
eng
dc.rights.none.fl_str_mv info:eu-repo/semantics/embargoedAccess
dc.source.none.fl_str_mv reponame:Repositorio Institucional de documento digitales de acceso abierto de la UTP
instname:Universidad Tecnológica de Panamá
instacron:U Tecnológica de Panamá
dc.subject.none.fl_str_mv Semantic localization
Deep learning
Retraining strategies
Machine learning
Semantic localization
Deep learning
Retraining strategies
Machine learning
dc.title.none.fl_str_mv How to add new knowledge to already trained deep learning models applied to semantic localization
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
description The capacity of a robot to automatically adapt to new environments is crucial, especially in social robotics. Often, when these robots are deployed in home or office environments, they tend to fail because they lack the ability to adapt to new and continuously changing scenarios. In order to accomplish this task, robots must obtain new information from the environment, and then add it to their already learned knowledge. Deep learning techniques are often used to tackle this problem successfully. However, these approaches, complete retraining of the models, which is highly time-consuming. In this work, several strategies are tested to find the best way to include new knowledge in an already learned model in a deep learning pipeline, putting the spotlight on the time spent for this training. We tackle the localization problem in the long term with a deep learning approach and testing several retraining strategies. The results of the experiments are discussed and, finally, the best approach is deployed on a Pepper robot.
eu_rights_str_mv embargoedAccess
format article
id lrtest_9a2af4c0c89d0bd89ca3fa4dec21c467
instacron_str U Tecnológica de Panamá
institution U Tecnológica de Panamá
instname_str Universidad Tecnológica de Panamá
language eng
network_acronym_str lrtest
network_name_str lr
oai_identifier_str oai:ridda2.utp.ac.pa:123456789/9445
publishDate 2020
publishDateSort 2020
reponame_str Repositorio Institucional de documento digitales de acceso abierto de la UTP
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling How to add new knowledge to already trained deep learning models applied to semantic localizationCruz, EdmanuelRangel, José CarlosGomez Donoso, FranciscoCazorla, MiguelSemantic localizationDeep learningRetraining strategiesMachine learningSemantic localizationDeep learningRetraining strategiesMachine learningThe capacity of a robot to automatically adapt to new environments is crucial, especially in social robotics. Often, when these robots are deployed in home or office environments, they tend to fail because they lack the ability to adapt to new and continuously changing scenarios. In order to accomplish this task, robots must obtain new information from the environment, and then add it to their already learned knowledge. Deep learning techniques are often used to tackle this problem successfully. However, these approaches, complete retraining of the models, which is highly time-consuming. In this work, several strategies are tested to find the best way to include new knowledge in an already learned model in a deep learning pipeline, putting the spotlight on the time spent for this training. We tackle the localization problem in the long term with a deep learning approach and testing several retraining strategies. The results of the experiments are discussed and, finally, the best approach is deployed on a Pepper robot.The capacity of a robot to automatically adapt to new environments is crucial, especially in social robotics. Often, when these robots are deployed in home or office environments, they tend to fail because they lack the ability to adapt to new and continuously changing scenarios. In order to accomplish this task, robots must obtain new information from the environment, and then add it to their already learned knowledge. Deep learning techniques are often used to tackle this problem successfully. However, these approaches, complete retraining of the models, which is highly time-consuming. In this work, several strategies are tested to find the best way to include new knowledge in an already learned model in a deep learning pipeline, putting the spotlight on the time spent for this training. We tackle the localization problem in the long term with a deep learning approach and testing several retraining strategies. The results of the experiments are discussed and, finally, the best approach is deployed on a Pepper robot.2020-01-02T21:25:41Z2020-01-02T21:25:41Z2020-01-02T21:25:41Z2020-01-02T21:25:41Z06/19/201906/19/2019info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://link.springer.com/article/10.1007/s10489-019-01517-1https://ridda2.utp.ac.pa/handle/123456789/9445https://ridda2.utp.ac.pa/handle/123456789/9445engenginfo:eu-repo/semantics/embargoedAccessreponame:Repositorio Institucional de documento digitales de acceso abierto de la UTPinstname:Universidad Tecnológica de Panamáinstacron:U Tecnológica de Panamáoai:ridda2.utp.ac.pa:123456789/94452021-07-06T15:35:10Z
spellingShingle How to add new knowledge to already trained deep learning models applied to semantic localization
Cruz, Edmanuel
Semantic localization
Deep learning
Retraining strategies
Machine learning
Semantic localization
Deep learning
Retraining strategies
Machine learning
status_str publishedVersion
title How to add new knowledge to already trained deep learning models applied to semantic localization
title_full How to add new knowledge to already trained deep learning models applied to semantic localization
title_fullStr How to add new knowledge to already trained deep learning models applied to semantic localization
title_full_unstemmed How to add new knowledge to already trained deep learning models applied to semantic localization
title_short How to add new knowledge to already trained deep learning models applied to semantic localization
title_sort How to add new knowledge to already trained deep learning models applied to semantic localization
topic Semantic localization
Deep learning
Retraining strategies
Machine learning
Semantic localization
Deep learning
Retraining strategies
Machine learning
url https://link.springer.com/article/10.1007/s10489-019-01517-1
https://ridda2.utp.ac.pa/handle/123456789/9445