Upravljanje gibanjem mobilnoga robota praćenjem točke nedogleda

master's thesis

• Title (english): Mobile robot motion control by vanishing point tracking
• Author: Dario Kuvačić
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Marković (predsjednik povjerenstva)
• Committee member: Ivan Petrović (član povjerenstva)
• Committee member: Marija Seder (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Autonomno upravljanje je vrlo aktivna tema u moderno doba, te predstavlja znatni skok u intustriji. Jednostavni zadatak upravljanja robota sa diferencijalnim pogonom pomoću svog okruženja sadrži brojne tehničke prepreke. U radu gledamo problem perspektive, tehnike obrade slike, te moguća rješenja za automatsku detekciju točke beskonačnosti. Algoritam detekcije točke beskonačnosti je sam od sebe koristan u brojnim primjenama, te predloženo rješenje je testirano u stvarnom okruženju te komentirane su prednosti i mane. Ukupni algoritam radi na edukacijskom robotu Turtlebot, uz Robotski operacijski sustav (ROS). Gledamo rad Ros-a, postavljanje node-a, komunikacijska struktura, te simulacijsko okruženje. Konačno simuliramo robota, te pratimo njegov simulirani rad, te komentiramo njegov rad, poteškoće rada sa simulacijom, prednosti i mane algoritma kao moguća poboljšanja.

Abstract (english)

Autonomous management is a very active topic in modern times, and represents a significant leap in the industry. The simple task of controlling a differential-driven robot using its environment contains a number of technical obstacles. In this paper, we look at the problem of perspective, image processing techniques, and possible solutions for automatic infinity point detection. The vanishing point detection algorithm is in itself useful in a number of applications, and the proposed solution has been tested in a real environment and the advantages and disadvantages have been commented on. The overall algorithm runs on the Turtlebot educational robot, in addition to the Robotic Operating System (ROS). We look at Ros’s work, node setup, communication structure, and simulation environment. Finally, we simulate the robot, and monitor its simulated operation, and comment on its operation, the difficulties of working with the simulation, the advantages and disadvantages of the algorithm as possible improvements.

• Keywords: ROS; Gazebo; Računalni vid; Python; OpenCV; Robotika; Diferencijalni pogon; Turtlebot
• Keywords (english): ROS; Gazebo; Computer vision; Python; OpenCV; Robotics; Diferential drive; Turtlebot
• Language: croatian
• URN:NBN: urn:nbn:hr:168:240106
• 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 12:51:30