prikaz prve stranice dokumenta Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža
Access restricted to authenticated users
master's thesis
Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. urn:nbn:hr:179:340076
Bralić, Andrej
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Bralić, A. (2021). Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:340076

Bralić, Andrej. "Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:340076

Bralić, Andrej. "Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:340076

Bralić, A. (2021). 'Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 19 January 2025, https://urn.nsk.hr/urn:nbn:hr:179:340076

Bralić A. Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2025 January 19] Available at: https://urn.nsk.hr/urn:nbn:hr:179:340076

A. Bralić, "Upravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:179:340076

Metadata
TitleUpravljanje modelom trkaćeg vozila korištenjem dubokih neuralnih mreža
Title (english)Racing car model control based on deep neural network
AuthorAndrej Bralić
MentorMirjana Bonković (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-07-23, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Basic Technical Sciences
Automatics
Abstract
Cilj ovog rada je predstaviti mogućnosti i rezultate upravljanja modelom trkaćeg automobila korištenjem duboke neuronske mreže. Sastavljen je Waveshare model trkaćeg automobila, PiRacer, te je podešeno odgovarajuće softversko okruženje kako bi se istrenirala duboka neuronska mreža zadužena za autonomnu kontrolu automobila. Rad opisuje hardverske dijelove automobila PiRacer, njihove karakteristike i način na koji su komponente ugrađene u upravljačku strukturu. Opisane su glavne karakteristike i funkcionalnosti duboke neuronske mreže, zajedno s postupkom treniranja modela i arhitekturom mreže. Eksperimentom je verificiran predloženi model mreže i predstavljeni su rezultati koji pokazuju učinkovitost primijenjene neuronske mreže.
Abstract (english)
The goal of the thesis is to present the possibilities and results related to racing car model control by using a deep neural network. A Waveshare model of a racing car, Pi Racer, is assembled and an appropriate software framework has been set up in order to train the deep neural network for racing car control. The thesis describes hardware parts of the PiRacer car, their characteristics, and the way the components are embedded into the control structure. The main characteristics and the functionality of the deep neural network are described together with the neural model training procedure and the network architecture. Experiments verified the proposed model of the network and presented results that demonstrate the efficacy of the applied neural network.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:340076
Study programmeTitle: Systems and Control
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka automatike i sustava (magistar/magistra inženjer/inženjerka automatike i sustava)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2021-11-23 11:25:32