UAV Visual Servoing Navigation in Sparsely Populated Environments

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

206 Downloads (Pure)

Abstract

This paper presents a novel approach based on deep neu-
ral networks for autonomous navigation of a quad-copter UAV in a
sparsely populated environment. Images from the video camera mounted
on the UAV are split, emulating a compounded eye, and processed by
deep neural networks that calculate the probability that each image con-
tains a wind turbine object. Then, these probabilities are used as inputs
to a vision servoing system that controls the drone's navigation move-
ments. Our experiments show that our approach produces relatively sta-
ble movements in the UAV, allowing it to nd and navigate autonomously
towards a wind turbine.
OriginalsprogEngelsk
Titel15th European Workshop on Advanced Control and Diagnosis
Antal sider15
ForlagSpringer
Publikationsdato17 jun. 2022
Sider1257-1272
ISBN (Elektronisk)978-3-030-85318-1
DOI
StatusUdgivet - 17 jun. 2022
Begivenhed15th European Workshop on Advanced Control and Diagnosis - Bologna, Italien
Varighed: 21 nov. 201922 nov. 2019
https://eventi.unibo.it/acd2019

Konference

Konference15th European Workshop on Advanced Control and Diagnosis
Land/OmrådeItalien
ByBologna
Periode21/11/201922/11/2019
Internetadresse
NavnLecture Notes in Control and Information Sciences - Proceedings
ISSN2522-5383

Fingeraftryk

Dyk ned i forskningsemnerne om 'UAV Visual Servoing Navigation in Sparsely Populated Environments'. Sammen danner de et unikt fingeraftryk.

Citationsformater