magistrsko delo
Klemen Pevec (Author), Janez Perš (Mentor)

Abstract

Moderni brezpilotni letalski sistemi ze zanašajo na globalne pozicijske sisteme za opravljanje avtonomnih misij in vračanje na točko vzleta ob izgubi brezžične povezave z operaterjem. Sprejem signala GPS je lahko moten ali onemogočen zaradi mnogih naravnih, namernih in elektromagnetnih razlogov, kar onemogoči prej omenjene sisteme. Namen našega dela je bil raziskati možnosti lokalizacije brezpilotnih sistemov v tem primeru. Za ta namen smo na podlagi teorije avtonomnih mobilnih sistemov, računalniškega vida in vgradnih sistemov predlagali pet metod lokalizacije brez signala GPS: inercialna odometrija, odometrija z modelom kvadrokopterja, dva pristopa vizualne odometrije in pristop z algoritmom SLAM. Delovanje vseh petih metod smo preverili na dveh podatkovnih zbirkah, ki smo ju posneli s pomočjo testnega kvadrokopterja in zajema podatkov senzorjev na njem. Kvalitativno oceno delovanja smo podali s pomočjo več metrik, ki opisujejo natančnost in uporabnost predlaganih metod. Ugotovili smo, da je vseh pet metod razen inercialne odometrije, ki ni dovolj natančna, primernih za praktično rabo v primeru odsotnosti GPS signala. Najboljše sta delovali metodi z optično odometrijo, ki pa zahtevata dobro oceno višine od tal. Odometrija z modelom kvadrokopterja je dosegla zadovoljive rezultate, vendar ne deluje dobro v vetrovnih razmerah. Ugotovili smo še, da vse metode razen SLAM delujejo na vgradnih sistemih z omejenimi sistemskimi sredstvi.

Keywords

brezpilotni letalniki;kvadrokopterji;lokalizacija;odometrija;SLAM;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FE - Faculty of Electrical Engineering
Publisher: [K. Pevec]
UDC: 004:629.014.9(043.3)
COBISS: 110711555 Link will open in a new window
Views: 125
Downloads: 33
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Localization of an Unmanned Aerial Vehicle in the Event of a Global Positioning System Failure
Secondary abstract: Modern unmanned aerial vehicles rely on the global positioning system to carry out autonomous missions and return to launch if the control link is lost. GPS reception can be jammed or lost due to several natural, intentional, and electromagnetic causes, which disables autonomous systems. The purpose of this paper was to research localization options of unmanned aerial vehicles in those scenarios. Based on the theory of autonomous mobile systems, computer vision, and embedded systems, we proposed five localization methods without GPS reception: inertial odometry, odometry with quadcopter model, two approaches with visual odometry, and using SLAM. We have tested the performance of all five methods on two datasets, that we obtained using a test quadcopter platform and data captured by its sensors. We have used multiple metrics to evaluate the accuracy, precision, and usability of the proposed methods. We have concluded that all five methods are suitable for real-life use in the case of GPS signal absence, except for inertial odometry, which is not accurate enough. Optical odometry methods performed the best, but they require good ground-camera distance measurement. Odometry with quadcopter model worked well but does not give accurate estimates in windy environments. All methods except SLAM are appropriate for use on embedded systems with limited resources.
Secondary keywords: Unmanned Aircraft System;Quadcopter;Localization;Odometry;SLAM;
Type (COBISS): Master's thesis/paper
Study programme: 1000316
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za elektrotehniko
Pages: XXI, 97 str.
ID: 15523695