Improving underwater vehicle navigation state estimation using locally weighted projection regression

Georgios Fagogenis, David Flynn, David Michael Lane

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Navigation is instrumental in the successful deployment of Autonomous Underwater Vehicles (AUVs). Sensor hardware is installed on AUVs to support navigational accuracy. Sensors, however, may fail during deployment, thereby jeopardizing the mission. This work proposes a solution, based on an adaptive dynamic model, to accurately predict the navigation of the AUV. A hydrodynamic model, derived from simple laws of physics, is integrated with a powerful non-parametric regression method. The incremental regression method, namely the Locally Weighted Projection Regression (LWPR), is used to compensate for un-modeled dynamics, as well as for possible changes in the operating conditions of the vehicle. The augmented hydrodynamic model is used within an Extended Kalman Filter, to provide optimal estimations of the AUV's position and orientation. Experimental results demonstrate an overall improvement in the prediction of the vehicle's acceleration and velocity.
Original languageEnglish
Title of host publicationRobotics and Automation (ICRA), 2014 IEEE International Conference on
PublisherIEEE
Pages6549-6554
DOIs
Publication statusPublished - 31 May 2014

Fingerprint

Autonomous underwater vehicles
State estimation
Navigation
Hydrodynamics
Sensors
Extended Kalman filters
Dynamic models
Physics
Hardware

Cite this

Fagogenis, G., Flynn, D., & Lane, D. M. (2014). Improving underwater vehicle navigation state estimation using locally weighted projection regression. In Robotics and Automation (ICRA), 2014 IEEE International Conference on (pp. 6549-6554). IEEE. https://doi.org/10.1109/ICRA.2014.6907825
Fagogenis, Georgios ; Flynn, David ; Lane, David Michael. / Improving underwater vehicle navigation state estimation using locally weighted projection regression. Robotics and Automation (ICRA), 2014 IEEE International Conference on. IEEE, 2014. pp. 6549-6554
@inproceedings{7af5851a20a745cab00a614ac039a6e0,
title = "Improving underwater vehicle navigation state estimation using locally weighted projection regression",
abstract = "Navigation is instrumental in the successful deployment of Autonomous Underwater Vehicles (AUVs). Sensor hardware is installed on AUVs to support navigational accuracy. Sensors, however, may fail during deployment, thereby jeopardizing the mission. This work proposes a solution, based on an adaptive dynamic model, to accurately predict the navigation of the AUV. A hydrodynamic model, derived from simple laws of physics, is integrated with a powerful non-parametric regression method. The incremental regression method, namely the Locally Weighted Projection Regression (LWPR), is used to compensate for un-modeled dynamics, as well as for possible changes in the operating conditions of the vehicle. The augmented hydrodynamic model is used within an Extended Kalman Filter, to provide optimal estimations of the AUV's position and orientation. Experimental results demonstrate an overall improvement in the prediction of the vehicle's acceleration and velocity.",
author = "Georgios Fagogenis and David Flynn and Lane, {David Michael}",
year = "2014",
month = "5",
day = "31",
doi = "10.1109/ICRA.2014.6907825",
language = "English",
pages = "6549--6554",
booktitle = "Robotics and Automation (ICRA), 2014 IEEE International Conference on",
publisher = "IEEE",
address = "United States",

}

Fagogenis, G, Flynn, D & Lane, DM 2014, Improving underwater vehicle navigation state estimation using locally weighted projection regression. in Robotics and Automation (ICRA), 2014 IEEE International Conference on. IEEE, pp. 6549-6554. https://doi.org/10.1109/ICRA.2014.6907825

Improving underwater vehicle navigation state estimation using locally weighted projection regression. / Fagogenis, Georgios; Flynn, David; Lane, David Michael.

Robotics and Automation (ICRA), 2014 IEEE International Conference on. IEEE, 2014. p. 6549-6554.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Improving underwater vehicle navigation state estimation using locally weighted projection regression

AU - Fagogenis, Georgios

AU - Flynn, David

AU - Lane, David Michael

PY - 2014/5/31

Y1 - 2014/5/31

N2 - Navigation is instrumental in the successful deployment of Autonomous Underwater Vehicles (AUVs). Sensor hardware is installed on AUVs to support navigational accuracy. Sensors, however, may fail during deployment, thereby jeopardizing the mission. This work proposes a solution, based on an adaptive dynamic model, to accurately predict the navigation of the AUV. A hydrodynamic model, derived from simple laws of physics, is integrated with a powerful non-parametric regression method. The incremental regression method, namely the Locally Weighted Projection Regression (LWPR), is used to compensate for un-modeled dynamics, as well as for possible changes in the operating conditions of the vehicle. The augmented hydrodynamic model is used within an Extended Kalman Filter, to provide optimal estimations of the AUV's position and orientation. Experimental results demonstrate an overall improvement in the prediction of the vehicle's acceleration and velocity.

AB - Navigation is instrumental in the successful deployment of Autonomous Underwater Vehicles (AUVs). Sensor hardware is installed on AUVs to support navigational accuracy. Sensors, however, may fail during deployment, thereby jeopardizing the mission. This work proposes a solution, based on an adaptive dynamic model, to accurately predict the navigation of the AUV. A hydrodynamic model, derived from simple laws of physics, is integrated with a powerful non-parametric regression method. The incremental regression method, namely the Locally Weighted Projection Regression (LWPR), is used to compensate for un-modeled dynamics, as well as for possible changes in the operating conditions of the vehicle. The augmented hydrodynamic model is used within an Extended Kalman Filter, to provide optimal estimations of the AUV's position and orientation. Experimental results demonstrate an overall improvement in the prediction of the vehicle's acceleration and velocity.

U2 - 10.1109/ICRA.2014.6907825

DO - 10.1109/ICRA.2014.6907825

M3 - Conference contribution

SP - 6549

EP - 6554

BT - Robotics and Automation (ICRA), 2014 IEEE International Conference on

PB - IEEE

ER -

Fagogenis G, Flynn D, Lane DM. Improving underwater vehicle navigation state estimation using locally weighted projection regression. In Robotics and Automation (ICRA), 2014 IEEE International Conference on. IEEE. 2014. p. 6549-6554 https://doi.org/10.1109/ICRA.2014.6907825