Algoritmi za istodobnu lokalizaciju i kartiranje nepoznatih prostora

undergraduate thesis

• Title (english): Simultaneous Localization and Mapping
• Author: Juraj Dukić Hrvoić
• Mentor: Vladimir Čeperić (mentor)
• Committee member: Vladimir Čeperić (predsjednik povjerenstva)
• Committee member: Ivan Grubišić (član povjerenstva)
• Committee member: Josip Renić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-09-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Algoritmi za istodobnu lokalizaciju i kartiranje nepoznatih prostora rad je u kojem se iznose povijesne činjenice o pojavi i potrebi za rješavanjem problema SLAM-a, opisuju osnove i razvoj problematike navedenih algoritama te najpopularnija ponuđena rješenja istih. Prikazuje se implementacija SLAM algoritma na robota u svrhu snalaženja u nepoznatom prostoru uz korištenje Kalmanovog filtra, analiziraju se utjecaji promjene parametara iz okoline na konačni rezultat te se, naposljetku, komentiraju prednosti i nedostaci EKF-SLAM-a. Opisani su koraci lokalizacije i mapiranja pomoću Kalmanova filtra. Zaključuje se da s većim brojem orijentira, kraćim vremenom uzorkovanja te većim rasponom senzora sustav preciznije prati svoj položaj i gibanje u prostoru.

Abstract (english)

Algorithms for simultaneous localization and mapping of unknown spaces is a paper in which the historical facts about the emergence and the urge to solve the problem of SLAM. The paper describes the basics and development of the problems of these algorithms as well as the most popular solutions. The implementation of the SLAM algorithm on an agent for the purpose of navigating an unknown space using a Kalman filter is presented. The effects of changes in environmental parameters on the final result have been analyzed. Finally, the advantages and disadvantages of EKF-SLAM were stated. Also, the localization and mapping steps using Kalman filters are described. It is concluded that with a larger number of landmarks, shorter sampling time and a larger range of sensors, the agent can localize itself and monitor its movement in the environment more accurately.

• Keywords: SLAM; EKF-SLAM; robotika; implementacija; odometrija; orijentir; senzor
• Keywords (english): SLAM; EKF-SLAM; robotics; implementation; odometry; landmark; sensor
• Language: croatian
• URN:NBN: urn:nbn:hr:168:421927
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 12:09:38