ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion

Barak Or; Itzik Klein

doi:10.1109/UT49729.2023.10103449

ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Inertial and Doppler velocity log sensors are commonly used to provide the navigation solution for autonomous underwater vehicles (AUV). To this end, a nonlinear filter is adopted for the fusion task. The filter's process noise covariance matrix is critical for filter accuracy and robustness. While this matrix varies over time during the AUV mission, the filter assumes a constant matrix. Several models and learning approaches in the literature suggest tuning the process noise covariance during operation. In this work, we propose ProNet, a hybrid, adaptive process, noise estimation approach for a velocity-aided navigation filter. ProNet requires only the inertial sensor reading to regress the process noise covariance. Once learned, it is fed into the model-based navigation filter, resulting in a hybrid filter. Simulation results show the benefits of our approach compared to other models and learning adaptive approaches.

Original language	English
Title of host publication	2023 IEEE International Symposium on Underwater Technology, UT 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350331752
DOIs	https://doi.org/10.1109/UT49729.2023.10103449
State	Published - 2023
Event	2023 IEEE International Symposium on Underwater Technology, UT 2023 - Tokyo, Japan Duration: 6 Mar 2023 → 9 Mar 2023

Publication series

Name	2023 IEEE International Symposium on Underwater Technology, UT 2023

Conference

Conference	2023 IEEE International Symposium on Underwater Technology, UT 2023
Country/Territory	Japan
City	Tokyo
Period	6/03/23 → 9/03/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Autonomous underwater vehicles
Deep Neural Network
Doppler Velocity Log
Extended Kalman Filter
Inertial Measurement Unit
Inertial Navigation System

ASJC Scopus subject areas

Oceanography
Automotive Engineering
Acoustics and Ultrasonics
Instrumentation

Access to Document

10.1109/UT49729.2023.10103449

Cite this

@inproceedings{10b7e4050eb4406bb272879807934850,

title = "ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion",

abstract = "Inertial and Doppler velocity log sensors are commonly used to provide the navigation solution for autonomous underwater vehicles (AUV). To this end, a nonlinear filter is adopted for the fusion task. The filter's process noise covariance matrix is critical for filter accuracy and robustness. While this matrix varies over time during the AUV mission, the filter assumes a constant matrix. Several models and learning approaches in the literature suggest tuning the process noise covariance during operation. In this work, we propose ProNet, a hybrid, adaptive process, noise estimation approach for a velocity-aided navigation filter. ProNet requires only the inertial sensor reading to regress the process noise covariance. Once learned, it is fed into the model-based navigation filter, resulting in a hybrid filter. Simulation results show the benefits of our approach compared to other models and learning adaptive approaches.",

keywords = "Autonomous underwater vehicles, Deep Neural Network, Doppler Velocity Log, Extended Kalman Filter, Inertial Measurement Unit, Inertial Navigation System",

author = "Barak Or and Itzik Klein",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Symposium on Underwater Technology, UT 2023 ; Conference date: 06-03-2023 Through 09-03-2023",

year = "2023",

doi = "10.1109/UT49729.2023.10103449",

language = "English",

series = "2023 IEEE International Symposium on Underwater Technology, UT 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 IEEE International Symposium on Underwater Technology, UT 2023",

address = "United States",

}

Or, B & Klein, I 2023, ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion. in 2023 IEEE International Symposium on Underwater Technology, UT 2023. 2023 IEEE International Symposium on Underwater Technology, UT 2023, Institute of Electrical and Electronics Engineers Inc., 2023 IEEE International Symposium on Underwater Technology, UT 2023, Tokyo, Japan, 6/03/23. https://doi.org/10.1109/UT49729.2023.10103449

ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion. / Or, Barak; Klein, Itzik.
2023 IEEE International Symposium on Underwater Technology, UT 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 IEEE International Symposium on Underwater Technology, UT 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - ProNet

T2 - 2023 IEEE International Symposium on Underwater Technology, UT 2023

AU - Or, Barak

AU - Klein, Itzik

PY - 2023

Y1 - 2023

N2 - Inertial and Doppler velocity log sensors are commonly used to provide the navigation solution for autonomous underwater vehicles (AUV). To this end, a nonlinear filter is adopted for the fusion task. The filter's process noise covariance matrix is critical for filter accuracy and robustness. While this matrix varies over time during the AUV mission, the filter assumes a constant matrix. Several models and learning approaches in the literature suggest tuning the process noise covariance during operation. In this work, we propose ProNet, a hybrid, adaptive process, noise estimation approach for a velocity-aided navigation filter. ProNet requires only the inertial sensor reading to regress the process noise covariance. Once learned, it is fed into the model-based navigation filter, resulting in a hybrid filter. Simulation results show the benefits of our approach compared to other models and learning adaptive approaches.

AB - Inertial and Doppler velocity log sensors are commonly used to provide the navigation solution for autonomous underwater vehicles (AUV). To this end, a nonlinear filter is adopted for the fusion task. The filter's process noise covariance matrix is critical for filter accuracy and robustness. While this matrix varies over time during the AUV mission, the filter assumes a constant matrix. Several models and learning approaches in the literature suggest tuning the process noise covariance during operation. In this work, we propose ProNet, a hybrid, adaptive process, noise estimation approach for a velocity-aided navigation filter. ProNet requires only the inertial sensor reading to regress the process noise covariance. Once learned, it is fed into the model-based navigation filter, resulting in a hybrid filter. Simulation results show the benefits of our approach compared to other models and learning adaptive approaches.

KW - Autonomous underwater vehicles

KW - Deep Neural Network

KW - Doppler Velocity Log

KW - Extended Kalman Filter

KW - Inertial Measurement Unit

KW - Inertial Navigation System

UR - http://www.scopus.com/inward/record.url?scp=85159335180&partnerID=8YFLogxK

U2 - 10.1109/UT49729.2023.10103449

DO - 10.1109/UT49729.2023.10103449

M3 - Conference contribution

AN - SCOPUS:85159335180

T3 - 2023 IEEE International Symposium on Underwater Technology, UT 2023

BT - 2023 IEEE International Symposium on Underwater Technology, UT 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 6 March 2023 through 9 March 2023

ER -

ProNet: Adaptive Process Noise Estimation for INS/DVL Fusion

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this