How to add new knowledge to already trained deep learning models applied to semantic localization
Date
06/19/201906/19/2019
Author
Cruz, Edmanuel
Rangel, José Carlos
Gomez Donoso, Francisco
Cazorla, Miguel
Metadata
Show full item recordAbstract
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.
Collections
Related items
Showing items related by title, author, creator and subject.
-
A System for Mobile Learning: A Need in a Moving World
Castillo, Aris; Clunie T., Clifton; de Clunie, Gisela; Rodríguez, Kexy (07/04/2013)This paper presents MLEA, a mobile learning application that brings together functionalities of Android devices, Moodle LMS and needs of Mobile learning system users. The application is an answer to young adult learners ... -
MLEA: a solution for users of android in UTP Virtual
de Clunie, Gisela T.; Crespo, Sergio; Castillo, Aris; Braz, Lucas; Serrao, Tássia; Rangel, Norman; Riley, Jeanette; de Barraza, Olinda; Rodríguez, Kexy (05/25/2011)This paper describes a design of an educational platform for a mobile learning architecture, which is a state of the art topic in distance education. The product will allow users to interact in an efficient, flexible, and ... -
Finding Ways to Bring Education to Everyone in Panama Through Mobile Learning
Castillo, Aris; Clunie, Gisela (2013-07-05)This paper presents the main features developed for a mobile learning application to expand the possibilities of learning for students from rural areas or those constrained by schedule and location to attend school. The ...