A neural network model for a 5-thruster unmanned underwater vehicle

Author

Simbulan, K.B. ; David, K.K. ; Vicerra, Ryan Rhay ; Atienza, Rowel ; Dadios, Elmer

Author_Institution

De La Salle Univ., Manila, Philippines

fYear

2012

fDate

19-22 Nov. 2012

Firstpage

1

Lastpage

6

Abstract

Unmanned underwater vehicles (UUVs) are mostly used for safe underwater explorations and researches. UUVs are subject to different parameters that changes over time. Such parameters are not considered in kinematic modelling of vehicles. As such, a dynamic modelling of underwater vehicles is necessary. This study proposes a dynamic model that is utilizing Artificial Neural Network (ANN), for a 5-thruster underwater vehicle design. The training data for the ANN model is gathered by empirical methods. The dynamic model is represented by UUV variables: thrusters input voltages and resulting velocity vector. The results of the neural network showed accuracy and reliability due to the low Mean Square Error (MSE) and satisfactory regression plots.

Keywords

mean square error methods; mobile robots; neurocontrollers; remotely operated vehicles; telerobotics; underwater vehicles; 5-thruster unmanned underwater vehicle; ANN; MSE; UUV; artificial neural network; dynamic model; input voltages; kinematic modelling; mean square error; neural network model; velocity vector; Artificial neural networks; Data models; Mathematical model; Training data; Underwater vehicles; Vehicle dynamics; Artificial Neural Network; Dynamic model; Intelligent systems; Unmanned underwater vehicle (UUV);

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 2012 - 2012 IEEE Region 10 Conference

Conference_Location

Cebu

ISSN

2159-3442

Print_ISBN

978-1-4673-4823-2

Electronic_ISBN

2159-3442

Type

conf

DOI

10.1109/TENCON.2012.6412181

Filename

6412181