Precision landing of multirotor drones using computer vision

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60162694%3AG43__%2F26%3A00566210" target="_blank" >RIV/60162694:G43__/26:00566210 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.eeict.cz/download" target="_blank" >https://www.eeict.cz/download</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Precision landing of multirotor drones using computer vision

Popis výsledku v původním jazyce

Precision landing is the last and most crucial stage in navigation, and autonomous precision landing Unmanned Aerial Vehicles (UAVs) have many potential applications across a variety of industries. Until recently, most designs relied on the Global Positioning System (GPS) and Inertial Navigation Systems (INS) with sensors such as 3-axis accelerometers, gyroscopes, and magnetometers. However, the accuracy of GPS data is often insufficient, necessitating the use of more precise sensors. In this study, a high-precision landing solution that employs a camera and ArUco markers as the landing platform is proposed. Once the markers are detected through image processing, the relative position between the markers and the drone is calculated. Using the Micro Air Vehicle Communication (MAVLink) protocol, the NVIDIA Jetson Nano board communicates with the flight controller to manage the drone’s position, enabling it to fly to the marker’s location and land precisely. The algorithm’s efficacy was tested and confirmed in both the Robot Operating System (ROS)/Gazebo simulation environment and real-world experiments.

Název v anglickém jazyce

Precision landing of multirotor drones using computer vision

Popis výsledku anglicky

Precision landing is the last and most crucial stage in navigation, and autonomous precision landing Unmanned Aerial Vehicles (UAVs) have many potential applications across a variety of industries. Until recently, most designs relied on the Global Positioning System (GPS) and Inertial Navigation Systems (INS) with sensors such as 3-axis accelerometers, gyroscopes, and magnetometers. However, the accuracy of GPS data is often insufficient, necessitating the use of more precise sensors. In this study, a high-precision landing solution that employs a camera and ArUco markers as the landing platform is proposed. Once the markers are detected through image processing, the relative position between the markers and the drone is calculated. Using the Micro Air Vehicle Communication (MAVLink) protocol, the NVIDIA Jetson Nano board communicates with the flight controller to manage the drone’s position, enabling it to fly to the marker’s location and land precisely. The algorithm’s efficacy was tested and confirmed in both the Robot Operating System (ROS)/Gazebo simulation environment and real-world experiments.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20204 - Robotics and automatic control

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings II of the Conference Student EEICT

ISBN

978-80-214-6153-6

ISSN

—

e-ISSN

2788-1334

Počet stran výsledku

4

Strana od-do

156-159

Název nakladatele

Brno University of Technology

Místo vydání

Brno

Místo konání akce

Brno, Czech Republic

Datum konání akce

25. 4. 2023

Typ akce podle státní příslušnosti

CST - Celostátní akce

Kód UT WoS článku

—