Highly accurate markerless localization of mobile robots in indoor industrial environments

doctoral thesis

• Title (croatian): Lokalizacija visoke točnosti mobilnih robota u zatvorenim industrijskim okruženjima bez korištenja markera
• Author: Goran Vasiljević
• Mentor: Zdenko Kovačić (mentor)
• Committee member: Zdenko Kovačić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Control and Computer Engineering); Zagreb
• Defense date and country: 2017, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Automation and Robotics
• Universal decimal classification (UDC): 621.3 - Electrical engineering

Abstract

The topic of this PhD thesis is the precise localization of mobile robots in industrial environments based on laser range scanning and without installed markers. During the research, new localization methods were developed to achieve the accuracy required within specific industrial applications that had previously been achieved only by markers. Two methods for localization using a laser range scanner were investigated, with the first method improving the accuracy of the existing AMCL-based methods, and the other achieving improved accuracy by fusing data from laser scanners placed at different height levels of the mobile robot (industrial forklift). New methods have been implemented on a real autonomous forklift using ROS (Robot Operating System) and their performance validated in realistic industrial conditions. Robustness of algorithms has been tested under conditions of fast and slow changes in the environment as well as resistance to possible accumulation of errors during long-term robot movement.

Abstract (croatian)

Tema doktorskog rada je precizna lokalizacija mobilnih robota u industrijskim okruženjima temeljena na laserskim senzorima udaljenosti bez korištenja markera. Tijekom istraživanja razvijene su nove metode lokalizacije kojima se postiže točnost koja se zahtijeva u specifičnim industrijskim aplikacijama, koju je ranije bilo moguće postići samo uz pomoć markera. Istražene su dvije metode lokalizacije koje koriste laserski senzor udaljenosti, pri čemu prva metoda poboljšava točnost postojećih metoda temeljenih na AMCL algoritmu, a druga metoda poboljšava točnost fuzijom podataka s laserskih senzora udaljenosti postavljenih na različite visine mobilnog robota. Nove metode su implementirane na pravom autonomnom viličaru koristeći ROS (robotski operacijski sustav), te je validiran njihov učinak u realističnim industrijskim uvjetima. Robusnost algoritama je testirana pod uvjetima brzih i sporih promjena u okolini, zajedno s otpornošću na moguću akumulaciju pogreške tijekom dugotrajnog gibanja robota.

• Keywords: mobile robot localization; autonomous forklift; industrial environments; markerless localization; long term autonomy
• Keywords (english): lokalizacija mobilnog robota; autonomni viličari; industrijsko okruženje; lokalizacija bez korištenja markera; dugotrajna autonomija
• Language: english
• URN:NBN: urn:nbn:hr:168:836814
• Study programme: Title: Electrical Engineering and Computing; Study programme type: university; Study level: postgraduate; Academic / professional title: Doktor znanosti elektrotehnike i računarstva (Doktor znanosti elektrotehnike i računarstva)
• Type of resource: Text
• Extent: 104 str. ; 30 cm.
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-04-04 12:29:31