Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View
An operational planning procedure for a time-critical maritime unmanned aerial vehicle (UAV) search mission is introduced and evaluated. The mission is the fast identification of a target vessel. The triggering report only contains information regarding the category and displacement of a vessel carr...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2022-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9923756/ |
_version_ | 1811247044721901568 |
---|---|
author | Geraldo Mulato De Lima Filho Angelo Passaro Guilherme Moura Delfino Leandro De Santana Herman Monsuur |
author_facet | Geraldo Mulato De Lima Filho Angelo Passaro Guilherme Moura Delfino Leandro De Santana Herman Monsuur |
author_sort | Geraldo Mulato De Lima Filho |
collection | DOAJ |
description | An operational planning procedure for a time-critical maritime unmanned aerial vehicle (UAV) search mission is introduced and evaluated. The mission is the fast identification of a target vessel. The triggering report only contains information regarding the category and displacement of a vessel carrying out a prohibited activity, resembling operational situations. A neural network trained to classify vessels is combined with vessel clustering to reduce waypoints in the flight plan. The UAV’s onboard sensors provide input for the neural network regarding each vessel in the search area, resulting in a prioritization of vessels to be visited. As the accuracy of the classification and the possibilities for clustering depend on several operational factors as well as on the UAV’s sensor degradation, we investigate three methodologies to identify which planning procedure to use in various operational situations. The results show that our robust and agile approach can help a UAV find the unknown target vessel as soon as possible. |
first_indexed | 2024-04-12T15:02:33Z |
format | Article |
id | doaj.art-bbbcf7f3bb4d4066b5b1f9886f8a4a05 |
institution | Directory Open Access Journal |
issn | 2169-3536 |
language | English |
last_indexed | 2024-04-12T15:02:33Z |
publishDate | 2022-01-01 |
publisher | IEEE |
record_format | Article |
series | IEEE Access |
spelling | doaj.art-bbbcf7f3bb4d4066b5b1f9886f8a4a052022-12-22T03:28:02ZengIEEEIEEE Access2169-35362022-01-011011174911175810.1109/ACCESS.2022.32156469923756Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational ViewGeraldo Mulato De Lima Filho0https://orcid.org/0000-0002-5157-6865Angelo Passaro1https://orcid.org/0000-0002-2421-0657Guilherme Moura Delfino2https://orcid.org/0000-0002-0935-4791Leandro De Santana3https://orcid.org/0000-0003-3235-544XHerman Monsuur4https://orcid.org/0000-0001-8905-6585Postgraduate Program in Space Science and Technologies, Aeronautics Institute of Technology, São José dos Campos, BrazilPostgraduate Program in Space Science and Technologies, Aeronautics Institute of Technology, São José dos Campos, BrazilPostgraduate Program in Space Science and Technologies, Aeronautics Institute of Technology, São José dos Campos, BrazilDepartment of Thermal and Fluid Engineering of the University of Twente, University of Twente, Enschede, AE, The NetherlandsFaculty of Military Sciences, Netherlands Defence Academy, Den Helder, AC, The NetherlandsAn operational planning procedure for a time-critical maritime unmanned aerial vehicle (UAV) search mission is introduced and evaluated. The mission is the fast identification of a target vessel. The triggering report only contains information regarding the category and displacement of a vessel carrying out a prohibited activity, resembling operational situations. A neural network trained to classify vessels is combined with vessel clustering to reduce waypoints in the flight plan. The UAV’s onboard sensors provide input for the neural network regarding each vessel in the search area, resulting in a prioritization of vessels to be visited. As the accuracy of the classification and the possibilities for clustering depend on several operational factors as well as on the UAV’s sensor degradation, we investigate three methodologies to identify which planning procedure to use in various operational situations. The results show that our robust and agile approach can help a UAV find the unknown target vessel as soon as possible.https://ieeexplore.ieee.org/document/9923756/Artificial intelligenceoptimization methodsunmanned aerial vehicles (UAV)decision support systems |
spellingShingle | Geraldo Mulato De Lima Filho Angelo Passaro Guilherme Moura Delfino Leandro De Santana Herman Monsuur Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View IEEE Access Artificial intelligence optimization methods unmanned aerial vehicles (UAV) decision support systems |
title | Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View |
title_full | Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View |
title_fullStr | Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View |
title_full_unstemmed | Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View |
title_short | Time-Critical Maritime UAV Mission Planning Using a Neural Network: An Operational View |
title_sort | time critical maritime uav mission planning using a neural network an operational view |
topic | Artificial intelligence optimization methods unmanned aerial vehicles (UAV) decision support systems |
url | https://ieeexplore.ieee.org/document/9923756/ |
work_keys_str_mv | AT geraldomulatodelimafilho timecriticalmaritimeuavmissionplanningusinganeuralnetworkanoperationalview AT angelopassaro timecriticalmaritimeuavmissionplanningusinganeuralnetworkanoperationalview AT guilhermemouradelfino timecriticalmaritimeuavmissionplanningusinganeuralnetworkanoperationalview AT leandrodesantana timecriticalmaritimeuavmissionplanningusinganeuralnetworkanoperationalview AT hermanmonsuur timecriticalmaritimeuavmissionplanningusinganeuralnetworkanoperationalview |