How to add new knowledge to already trained deep learning models applied to semantic localization
Empreu sempre aquest identificador per citar o enllaçar aquest ítem
http://hdl.handle.net/10045/101373
Títol: | How to add new knowledge to already trained deep learning models applied to semantic localization |
---|---|
Autors: | Cruz, Edmanuel | Rangel, José Carlos | Gomez-Donoso, Francisco | Cazorla, Miguel |
Grups d'investigació o GITE: | Robótica y Visión Tridimensional (RoViT) |
Centre, Departament o Servei: | Universidad de Alicante. Departamento de Ciencia de la Computación e Inteligencia Artificial | Universidad de Alicante. Instituto Universitario de Investigación Informática |
Paraules clau: | Semantic localization | Deep learning | Retraining strategies | Machine learning |
Àrees de coneixement: | Ciencia de la Computación e Inteligencia Artificial |
Data de publicació: | de gener-2020 |
Editor: | Springer Nature |
Citació bibliogràfica: | Applied Intelligence. 2020, 50: 14-28. doi:10.1007/s10489-019-01517-1 |
Resum: | 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. |
Patrocinadors: | This work has been supported by the Spanish Government TIN2016-76515R Grant, supported with Feder funds. Edmanuel Cruz is funded by a Panamenian grant for PhD studies IFARHU & SENACYT 270-2016-207. Jose Carlos Rangel was supported by the National System of Research (SNI) of the SENACYT of Panama. This work has also been supported by a Spanish grant for PhD studies ACIF/2017/243. Thanks also to Nvidia for the generous donation of a Titan Xp and a Quadro P6000. |
URI: | http://hdl.handle.net/10045/101373 |
ISSN: | 0924-669X (Print) | 1573-7497 (Online) |
DOI: | 10.1007/s10489-019-01517-1 |
Idioma: | eng |
Tipus: | info:eu-repo/semantics/article |
Drets: | © Springer Science+Business Media, LLC, part of Springer Nature 2019 |
Revisió científica: | si |
Versió de l'editor: | https://doi.org/10.1007/s10489-019-01517-1 |
Apareix a la col·lecció: | INV - RoViT - Artículos de Revistas |
Arxius per aquest ítem:
Arxiu | Descripció | Tamany | Format | |
---|---|---|---|---|
2020_Cruz_etal_ApplIntell_final.pdf | Versión final (acceso restringido) | 1,74 MB | Adobe PDF | Obrir Sol·licitar una còpia |
Tots els documents dipositats a RUA estan protegits per drets d'autors. Alguns drets reservats.