prikaz prve stranice dokumenta Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom
Access restricted to authenticated users
master's thesis
Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom
2021. urn:nbn:hr:179:193072
Pučić, Josip
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Pučić, J. (2021). Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom (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:179:193072

Pučić, Josip. "Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:193072

Pučić, Josip. "Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2021. https://urn.nsk.hr/urn:nbn:hr:179:193072

Pučić, J. (2021). 'Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 15 November 2024, https://urn.nsk.hr/urn:nbn:hr:179:193072

Pučić J. Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2021 [cited 2024 November 15] Available at: https://urn.nsk.hr/urn:nbn:hr:179:193072

J. Pučić, "Integracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom", 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:179:193072

Please login to the repository to save this object to your list.
Metadata
TitleIntegracija NVIDIA Jetson AGX Xavier platforme s mobilnom robotskom bazom
Title (english)Integration of NVIDIA Jetson Xavier AGX platform with a mobile robot
AuthorJosip Pučić
MentorJosip Musić (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2021-09-23, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U radu je obrađena integracija NVIDIA Jetson Xavier AGX modula sa mobilnim robotom korištenjem robotskog operacijskog sustava. Opisan je postupak instalacije operativnog sustava Jetpack za Xaviera, te konfiguracija ROS-a za Jetpack. Razrađeni su osnovni koncepti mobilnih robota, ROS-a, navigacije i umjetne inteligencije s osvrtom na primjene u radu. Pri tome je cilj rada omogućiti mobilnom robotu da prepozna čovjeka u svojoj okolini i kreće se do njega. Prepoznavanje čovjeka realizirano je korištenjem Microsoft KinectV2 dubinske kamere i Darknet_ROS paketa za detekciju objekata na slici temeljenom na YOLOv3 algoritmu. Korištenjem dubinske kamere dobiva se udaljenost detektirane osobe od robota, a to omogućava da se čovjek lokalizira u prostoru relativno u odnosu na robota. Korištene su OpenCV metode obrade slike zbog ne poklapanja dubinske slike i slike u boji. Za navigaciju robota korišten je ROS-ov navigacijski skup. Realizirani sustav je ostvario traženu funkcionalnost.
Abstract (english)
The thesis explains the process of integrating the NVIDIA Jetson Xavier AGX module with a mobile robot using a robot operating system. The process of installing the Jetpack operating system for Xavier and the ROS configuration for Jetpack is explained. The basic concepts of mobile robots, ROS, navigation, and artificial intelligence have been covered with references to the applications in the thesis. The thesis aims to enable a mobile robot to recognize a human in its environment and move towards it. Human recognition was realized using a Microsoft KinectV2 depth camera and Darknet_ROS package to detect objects in an image based on the YOLOv3 algorithm. Using a depth camera, the distance of the detected person from the robot was obtained and this allowed localization of the person in the environment. OpenCV image processing methods were used due to the inconsistency of depth images and color images. The ROS navigation stack was used to navigate the robot. The developed system performed per set goals.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:193072
Study programmeTitle: Electronics and Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva (magistar/magistra inženjer/inženjerka elektronike i računalnog inženjerstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2022-07-07 07:26:58