Efficient UAV Autonomous Navigation with CNNs

Kamil Mikolaj; Martin Lauersen; Tomer Tchelet; Daniel Ortiz Arroyo; Petar  Durdevic

doi:10.1109/CoDIT58514.2023.10284278

Efficient UAV Autonomous Navigation with CNNs

Kamil Mikolaj, Martin Lauersen, Tomer Tchelet, Daniel Ortiz Arroyo, Petar Durdevic

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

24 Downloads (Pure)

Abstract

This paper presents a novel approach to the navi-
gation of Unmanned Aerial Vehicles (UAV) for the autonomous
inspection of wind turbines. Firstly, a Single Shot Detector
(SSD) network is trained to detect wind turbines and their
subcomponents. Then, an optimized template matching algorithm
is used to estimate the distance between the UAV and the wind
turbine, using as the template, the SSD bounding box prediction
on the left image of a stereo camera. Lastly, an Extended Kalman
Filter (EKF) estimates the position of the wind turbine’s hub. The
EKF is designed to compensate for CNN’s latency while sending
setpoints to the controller of the UAV

Original language	English
Title of host publication	9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023
Number of pages	6
Publisher	IEEE
Publication date	Oct 2023
Pages	1343 - 1348
Article number	10284278
ISBN (Print)	979-8-3503-1141-9
ISBN (Electronic)	979-8-3503-1140-2
DOIs	https://doi.org/10.1109/CoDIT58514.2023.10284278
Publication status	Published - Oct 2023
Event	9th International Conference on Control, Decision and Information Technologies (CoDIT) - Rome, Italy Duration: 3 Jul 2023 → 6 Jul 2023 https://codit2023.com/

Conference

Conference	9th International Conference on Control, Decision and Information Technologies (CoDIT)
Country/Territory	Italy
City	Rome
Period	03/07/2023 → 06/07/2023
Internet address	https://codit2023.com/

Series	International Conference on Control, Decision and Information Technologies (CoDIT)
ISSN	2576-3555

Keywords

Visual Servoing Convolutional Neural Network Estimation Kalman filter

Access to Document

10.1109/CoDIT58514.2023.10284278

EfficientNavigationCNN_CODIT23Accepted author manuscript, 3.02 MB

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

@inproceedings{b6b2ec6764cf496988b8e7bcc37b4c7e,

title = "Efficient UAV Autonomous Navigation with CNNs",

abstract = "This paper presents a novel approach to the navi-gation of Unmanned Aerial Vehicles (UAV) for the autonomousinspection of wind turbines. Firstly, a Single Shot Detector(SSD) network is trained to detect wind turbines and theirsubcomponents. Then, an optimized template matching algorithmis used to estimate the distance between the UAV and the windturbine, using as the template, the SSD bounding box predictionon the left image of a stereo camera. Lastly, an Extended KalmanFilter (EKF) estimates the position of the wind turbine{\textquoteright}s hub. TheEKF is designed to compensate for CNN{\textquoteright}s latency while sendingsetpoints to the controller of the UAV",

keywords = "Visual Servoing Convolutional Neural Network Estimation Kalman filter",

author = "Kamil Mikolaj and Martin Lauersen and Tomer Tchelet and {Ortiz Arroyo}, Daniel and Petar Durdevic",

year = "2023",

month = oct,

doi = "10.1109/CoDIT58514.2023.10284278",

language = "English",

isbn = "979-8-3503-1141-9",

series = "International Conference on Control, Decision and Information Technologies (CoDIT)",

pages = "1343 -- 1348",

booktitle = "9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023",

publisher = "IEEE",

address = "United States",

note = "9th International Conference on Control, Decision and Information Technologies (CoDIT) , CoDIT 2023 ; Conference date: 03-07-2023 Through 06-07-2023",

url = "https://codit2023.com/",

}

Mikolaj, K, Lauersen, M, Tchelet, T, Ortiz Arroyo, D & Durdevic, P 2023, Efficient UAV Autonomous Navigation with CNNs. in 9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023., 10284278, IEEE, International Conference on Control, Decision and Information Technologies (CoDIT), pp. 1343 - 1348, 9th International Conference on Control, Decision and Information Technologies (CoDIT) , Rome, Italy, 03/07/2023. https://doi.org/10.1109/CoDIT58514.2023.10284278

Efficient UAV Autonomous Navigation with CNNs. / Mikolaj, Kamil; Lauersen, Martin; Tchelet, Tomer et al.
9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023. IEEE, 2023. p. 1343 - 1348 10284278 (International Conference on Control, Decision and Information Technologies (CoDIT)).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Efficient UAV Autonomous Navigation with CNNs

AU - Mikolaj, Kamil

AU - Lauersen, Martin

AU - Tchelet, Tomer

AU - Ortiz Arroyo, Daniel

AU - Durdevic, Petar

PY - 2023/10

Y1 - 2023/10

N2 - This paper presents a novel approach to the navi-gation of Unmanned Aerial Vehicles (UAV) for the autonomousinspection of wind turbines. Firstly, a Single Shot Detector(SSD) network is trained to detect wind turbines and theirsubcomponents. Then, an optimized template matching algorithmis used to estimate the distance between the UAV and the windturbine, using as the template, the SSD bounding box predictionon the left image of a stereo camera. Lastly, an Extended KalmanFilter (EKF) estimates the position of the wind turbine’s hub. TheEKF is designed to compensate for CNN’s latency while sendingsetpoints to the controller of the UAV

AB - This paper presents a novel approach to the navi-gation of Unmanned Aerial Vehicles (UAV) for the autonomousinspection of wind turbines. Firstly, a Single Shot Detector(SSD) network is trained to detect wind turbines and theirsubcomponents. Then, an optimized template matching algorithmis used to estimate the distance between the UAV and the windturbine, using as the template, the SSD bounding box predictionon the left image of a stereo camera. Lastly, an Extended KalmanFilter (EKF) estimates the position of the wind turbine’s hub. TheEKF is designed to compensate for CNN’s latency while sendingsetpoints to the controller of the UAV

KW - Visual Servoing Convolutional Neural Network Estimation Kalman filter

UR - http://www.scopus.com/inward/record.url?scp=85177470671&partnerID=8YFLogxK

U2 - 10.1109/CoDIT58514.2023.10284278

DO - 10.1109/CoDIT58514.2023.10284278

M3 - Article in proceeding

SN - 979-8-3503-1141-9

T3 - International Conference on Control, Decision and Information Technologies (CoDIT)

SP - 1343

EP - 1348

BT - 9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023

PB - IEEE

T2 - 9th International Conference on Control, Decision and Information Technologies (CoDIT)

Y2 - 3 July 2023 through 6 July 2023

ER -

Mikolaj K, Lauersen M, Tchelet T, Ortiz Arroyo D , Durdevic P. Efficient UAV Autonomous Navigation with CNNs. In 9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023. IEEE. 2023. p. 1343 - 1348. 10284278. (International Conference on Control, Decision and Information Technologies (CoDIT)). doi: 10.1109/CoDIT58514.2023.10284278

Efficient UAV Autonomous Navigation with CNNs

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this