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 proceedingArticle in proceedingResearchpeer-review

36 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 languageEnglish
Title of host publication9th 2023 International Conference on Control, Decision and Information Technologies, CoDIT 2023
Number of pages6
PublisherIEEE
Publication dateOct 2023
Pages1343 - 1348
Article number10284278
ISBN (Print)979-8-3503-1141-9
ISBN (Electronic)979-8-3503-1140-2
DOIs
Publication statusPublished - Oct 2023
Event9th International Conference on Control, Decision and Information Technologies (CoDIT) - Rome, Italy
Duration: 3 Jul 20236 Jul 2023
https://codit2023.com/

Conference

Conference9th International Conference on Control, Decision and Information Technologies (CoDIT)
Country/TerritoryItaly
CityRome
Period03/07/202306/07/2023
Internet address
SeriesInternational Conference on Control, Decision and Information Technologies (CoDIT)
ISSN2576-3555

Keywords

  • Visual Servoing Convolutional Neural Network Estimation Kalman filter

Fingerprint

Dive into the research topics of 'Efficient UAV Autonomous Navigation with CNNs'. Together they form a unique fingerprint.

Cite this