Finding the Place: How to Train and Use Convolutional Neural Networks for a Dynamically Learning Robot

 

Authors

Cruz, Edmanuel; Rangel, José Carlos; Gomez Donoso, Francisco; Bauer, Zuria; Cazorla, Miguel; García Rodríguez, José

Format

Article

Status

publishedVersion

Description

For a robot, the ability to adapt his knowledge automatically and customize its behavior is a key feature. Furthermore, a robot should be able to carry out its tasks at a long-term basis, performing it seamlessly in presence of changes in their surroundings. To do that, it is essential that the robot dynamically learn from their environment, but to perform a fully retraining of a deep learning architecture when the model needs new knowledge is a highly time consuming task. This work focus on exploring several strategies to include new data to an already learned model, applied to the semantic localization problem focusing in the accuracy of the final model and their training time. Exhaustive experimentation is carried out and each result is discussed consequently.
For a robot, the ability to adapt his knowledge automatically and customize its behavior is a key feature. Furthermore, a robot should be able to carry out its tasks at a long-term basis, performing it seamlessly in presence of changes in their surroundings. To do that, it is essential that the robot dynamically learn from their environment, but to perform a fully retraining of a deep learning architecture when the model needs new knowledge is a highly time consuming task. This work focus on exploring several strategies to include new data to an already learned model, applied to the semantic localization problem focusing in the accuracy of the final model and their training time. Exhaustive experimentation is carried out and each result is discussed consequently.

Publication Year

2019

Language

eng

Topic

Robots
Semantics
Training
Feature extraction
Computer architecture
Task analysis
Visualization
Robots
Semantics
Training
Feature extraction
Computer architecture
Task analysis
Visualization

Repository

RI de Documento Digitales de Acceso Abierto de la UTP

Get full text

https://ieeexplore.ieee.org/abstract/document/8489469/keywords#keywords
https://ridda2.utp.ac.pa/handle/123456789/9438

Rights

embargoedAccess

License