prikaz prve stranice dokumenta Autonomna vozila
  Download
PDF 18.35 MB
master's thesis
Autonomna vozila
2021. urn:nbn:hr:126:701039
Pribisalić, Iva
Josip Juraj Strossmayer University of Osijek
Department of Mathematics
Chair of Applied Mathematics
Applied Mathematics Research Group

Cite this document

Pribisalić, I. (2021). Autonomna vozila (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:701039

Pribisalić, Iva. "Autonomna vozila." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2021. https://urn.nsk.hr/urn:nbn:hr:126:701039

Pribisalić, Iva. "Autonomna vozila." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2021. https://urn.nsk.hr/urn:nbn:hr:126:701039

Pribisalić, I. (2021). 'Autonomna vozila', Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 24 January 2023, https://urn.nsk.hr/urn:nbn:hr:126:701039

Pribisalić I. Autonomna vozila [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2021 [cited 2023 January 24] Available at: https://urn.nsk.hr/urn:nbn:hr:126:701039

I. Pribisalić, "Autonomna vozila", Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:126:701039

Please login to the repository to save this object to your list.
Metadata
TitleAutonomna vozila
Title (english)Autonomous Vehicles
AuthorIva Pribisalić
MentorDarija Marković (mentor)
Committee memberDomagoj Matijević (predsjednik povjerenstva)
Committee memberDarija Marković (član povjerenstva)
Committee memberDomagoj Ševerdija (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
(Chair of Applied Mathematics)
(Applied Mathematics Research Group)
Osijek
Defense date and country2021-09-16, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Mathematical Logic and Accounting
Abstract
Cilj ovog rada je upoznati se s autonomnim vozilima. Nakon povijesnog pregleda razvoja autonomnih vozila, objašnjen je proces kojim vozila postižu autonomiju. Sve započinje radom senzora koji skeniraju okolinu i detektiraju objekte. Neki od poznatijih senzora koji se koriste su radar, lidar, kamera, GPS, IMU te ultrazvučni i odometrijski senzori. Na osnovu podataka koje daju senzori, potrebno je stvoriti percepciju okoline. To se postiže lokalizacijom i mapiranjem te detektiranjem objekata. Problem detektiranja objekata rješava se metodama poput histograma orijentiranih gradijenata, transformacije značajke invarijantne skale, maksimalno stabilnim ekstremnim regijama, metode potpornih vektora, slučajnih šuma i umjetnih neuronskih mreža. Nakon što je vozilo svjesno svoje okoline, treba planirati kako doći do svog odredišta. Najpoznatiji algoritmi koji se koriste za pronalazak najkraće rute su Dijkstrin i A* algoritam. Osim toga, vozilo treba moći predvidjeti kako će se drugi objekti u prometu ponašati. Nakon što su odluke donesene, proslijeđuju se kontroli vozila koja te odluke prevodi u naredbe za aktuator. Aktuator konačno upravlja vozilom prema donesenim odlukama. Vozila dodatno koriste V2X komunikaciju kako bi komunicirala s drugim vozilima, mobitelima, stanicama i drugim objektima. To poboljšava percepiju vozila jer ima uvid u situacije izvan dometa njegovih senzora. Među najpoznatijim autonomnim vozilima svakako su Tesla i Waymo. Tesla je autonomno vozilo razine 2, a Waymo razine 4 automatiziranosti i u skladu s time imaju određene funkcionalnosti. Toyota je razvila autonomne autobuse razine 4 automatiziranosti za olimpijske i paraolimpijske igre u Tokiju 2020. godine. Na kraju je ukratko navedeno što možemo očekivati u budućnosti kada je riječ o autonomnim vozilima.
Abstract (english)
The goal of this paper is to learn about autonomous vehicles. We will begin with the definition and history of autonomous vehicles and move on to the autonomy process. Sensors are the basic of vehicle autonomy. This is how vehicle gets information about the environment. Some of the most popular sensors include lidar, radar, camera, GPS, IMU, ultrasonic and odometry sensors. Vehicle perception is created based on the data from sensors with the use of localization, mapping and object detection. Object detection problem is solved using methods such as histogram of oriented gradients, scale-invariant feature transformation, maximally stable extremal regions, support vector machine, random forest and artificial neural networks. After perception, planning takes place. Vehicle must plan how to get to it’s destination and this is accomplished by finding the shortest path using Dijkstra’s or A* algorithm. When traveling to chosen location, vehicle should be able to predict how will other objects behave.. All decisions that were made are forwarded to the vehicle control. Decisions are translated into commands for the actuators which finally manage mechanical motion. Vehicles use V2X communication to exchange information with other vehicles, mobile phones etc. This is how vehicle becomes more aware of the environment.Tesla and Waymo are among the most famous autonomous vehicles nowadays. Tesla is level 2 and Waymo is level 4 automation. Each has certain functionalities based on the automation level. Toyota developed level 4 automation bus for olympic and paralympic games in Tokyo 2020. Finally, the paper summarizes what we can expect in the future when it comes to autonomous vehicles
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:701039
Study programmeTitle: Mathematics; specializations in: Financial and Statistical Mathematics, Mathematics and Computer Science, Industrial and Applied Mathematics
Course: Financial and Statistical Mathematics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-09-21 07:55:32