Lokalizacija i navigacija mobilnog robota za dekontaminaciju

master's thesis

• Title (english): Localization and navigation of a mobile robot for decontamination
• Author: Dino Smirčić
• Mentor: Matko Orsag (mentor)
• Committee member: Matko Orsag (član povjerenstva)
• Committee member: Frano Petric (član povjerenstva)
• Committee member: Marko Car (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2025-02-21, Croatia

Abstract

Cilj ovoga rada bio je osmisliti algoritme za samostalno upravljanje robota u poznatim i nepoznatim okruženjima. Korišteni su LiDAR (Light Detection and Ranging) i Intel Realnsense depth kamera za stvaranje mape za navigaciju prostorom. Modeliran je nosač za LiDAR i kameru koji se dizajnirao po mjeri za mobilnog robota. Platforma koja se koristila je Scout Agilex Scout 2.0 mini, a algoritmi su napisani u programskom alatu ROS2. Za prepoznavanje prepreka u okruženju korišten je algoritam YOLOv8.... More Osmišljen je algoritam za prepoznavanje i označavanje prepreka u trodimenzionalnom prostoru kako bi se označila područja u kojima je robotu zabranjeno kretanje. Provedena su ispitivanja navigacije robota u otvorenom i zatvorenom prostoru s pomičnim i nepomičnim preprekama u kojima je robot uspio doći do zadanog cilja. Less

Abstract (english)

The goal of this thesis was to design and implement algorithms for autonomous robot navigation. LiDAR (Light Detection and Ranging) and Intel Realsense depth camera technology were used to accomplish this. A mount was designed and modeled for the purpose of connecting both sensors into a fixed frame. Scout Agilex 2.0 mini was used as a mobile base. The algorithms were written in Python as ROS2 packages. A ROS2 3D segmentation package was designed for marking obstacles for collision avoidance... More in real-world scenarios. Tests were put in place in both open and closed spaces with both static and moving obstacles in which the robot accomplished reaching its goal. Less

• Keywords: lokalizacija; navigacija; autonomija; segmentacija slike; prepoznavanje predmeta; depth kamera; LiDAR; SLAM
• Keywords (english): localization; navigation; autonomy; image segmentation; object detection; depth camera; LiDAR; SLAM
• Language: croatian
• URN:NBN: urn:nbn:hr:168:452837
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2025-03-12 11:18:22