Fuzija podataka radar-IMU-kamera sustava za estimaciju vlastitog gibanja

master's thesis

• Title (english): Radar-IMU-camera system data fusion for ego-motion estimation
• Author: Vlaho-Josip Štironja
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Petrović (član povjerenstva)
• Committee member: Marija Seder (član povjerenstva)
• Committee member: Juraj Peršić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Poznavanje vlastitog gibanja ključan je zadatak svakog autonomnog mobilnog robota. U tu svrhu, uobičajeno se koriste senzori poput kamera, inercijalnih mjernih jedinica (IMU) i lidara. Potaknuta nedavnim razvojem, nova istraživanja počela su koristiti i radare pri estimaciji vlastitog gibanja zbog njihove robusnosti na vremenske uvjete. Različiti tipovi senzori mjere različita fizikalna svojstva okoline ili unutarnjih stanja. Stoga se njihova ograničenja i uvjeti rada bitno razlikuju. Fuzijom različitih senzora povećava se robusnost sustava te se proširuju dozvoljeni uvjeti rada. U diplomskom radu potrebno je potrebno estimirati vlastito gibanje fuzijom radara, kamere i IMU-a. U tu svrhu potrebno je prikupiti novi skup podataka kojim je moguće provesti fuziju te analizirati njenu točnost.

Abstract (english)

Knowledge of ego-motion is a key task for all autonomous mobile robots. For that purpose, one usually uses sensors like cameras, inertial measurement units (IMU), and lidars. Given recent developments, novel research is also targeting radars for ego-motion estimation due to their robustness to environmental conditions. Different sensors measure different physical properties of the environment or inner system states. Thus their limitations and the extent of operating conditions can differ substantially. By fusing different sensors, we can increase the system's robustness and extend operating conditions. The goal of this thesis is to estimate the ego-motion of a sensor platform by fusing radar, camera, and IMU data. To that end, novel dataset collection will be required through which fusion can be carried out and accuracy analyzed.

• Keywords: Radar; Kamera; Inercijalna mjerna jedinica; Fuzija senzora; Kalmanov filtar; Estimacija stanja
• Keywords (english): Radar; Camera; Inertial measurement unit; Sensor fusion; Kalman filtar; State estimation
• Language: english
• URN:NBN: urn:nbn:hr:168:912632
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 16:19:28