Upravljanje bespilotnom letjelicom za pronalazak objekta na temelju semantike prostora

master's thesis

• Title (english): UAV Control for Object Search Based on Environment Semantics
• Author: Ivan Gusić
• Mentor: Tamara Petrović (mentor)
• Committee member: Tamara Petrović (predsjednik povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Committee member: Frano Petric (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-19, Croatia

Abstract

U ovom radu razvijena je metoda koja uz pomoć autonomne bespilotne letjelice pretražuje zatvoreni prostor manje površine, poput stana ili ureda s ciljem pronalaska zadanog predmeta. Autonomna bespilotna letjelica, opremljena kamerom, pomoću YOLO algoritma detektira objekte u prostoru. Detektiranim objektima estimira se lokacija te se na temelju detektiranih objekata gradi semantička mapa prostora. U daljnjem detaljnom pretraživanju u obzir se uzima semantika prepoznatih objekata kako bi se skratilo vrijeme pretrage. Metoda je testirana u simulatoru i njena je učinkovitost pokazana na nekoliko scenarija.

Abstract (english)

In this paper, a method was developed that, with the help of an autonomous drone, searches an enclosed space of a smaller area, such as an apartment or office, with the aim of finding a given object. An autonomous drone, equipped with a camera, detects objects in space using the YOLO algorithm. The location of the detected objects is estimated, and a semantic map of the space is built based on them. In the further detailed search, the semantics of the recognized objects are taken into account to shorten the search time. The method was tested in a simulator and its effectiveness was demonstrated in several scenarios.

• Keywords: autonomna bespilotna letjelica; YOLO; pretraga prostora; oktalno stablo; Crazyflie; ROS2
• Keywords (english): autonomous UAV; YOLO; space search; octree; Crazyflie; ROS2
• Language: croatian
• URN:NBN: urn:nbn:hr:168:567080
• 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: Closed access
• Created on: 2024-10-12 20:45:23