prikaz prve stranice dokumenta Robotska paletizacija primjenom računalnog vida
  Download
PDF 8.96 MB
master's thesis
Robotska paletizacija primjenom računalnog vida
2022. urn:nbn:hr:200:741070
Rekić, Tomislav
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

Rekić, T. (2022). Robotska paletizacija primjenom računalnog vida (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:741070

Rekić, Tomislav. "Robotska paletizacija primjenom računalnog vida." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:741070

Rekić, Tomislav. "Robotska paletizacija primjenom računalnog vida." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. https://urn.nsk.hr/urn:nbn:hr:200:741070

Rekić, T. (2022). 'Robotska paletizacija primjenom računalnog vida', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 16 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:741070

Rekić T. Robotska paletizacija primjenom računalnog vida [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2022 [cited 2024 April 16] Available at: https://urn.nsk.hr/urn:nbn:hr:200:741070

T. Rekić, "Robotska paletizacija primjenom računalnog vida", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:200:741070

Please login to the repository to save this object to your list.
Metadata
TitleRobotska paletizacija primjenom računalnog vida
Title (english)Robotic palletization using computer vision
AuthorTomislav Rekić
MentorRobert Cupec (mentor)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2022-09-26, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovome radu predstavljen je sustav za robotsku paletizaciju primjenom algoritama raˇcunalnog vida. Rad je nastao u suradnji s tvrtkom Protostar Labs d.o.o. Koriˇsteni robotski sustav sastoji se od robotske ruke UR5, od robotske ˇsake Robotiq 3-Finger, od LIDAR kamere Intel RealSense, od ROS-a, simulatora Gazebo i od biblioteke Open3D za rad s oblacima toˇcaka. Za rad sustava koriste se algoritmi RANSAC, DBSCAN i ICP. Zada´ca je ovog robotskog sustava detektirati nadolaze´ce objekte na radnoj povrˇsini, izraˇcunati njihovu poziciju, uhvatiti ih i odloˇziti na za to predvideno mjesto. Provedeni pokusi o ovome radu pokazali su da ovaj sustav robotske paletizacije nije adekvatan za uporabu u industriji. Iako je u ˇcetvrtom pokusu pokazano da je najve´ca pogreˇska sustava 8 mm, prisutna je sistemska pogreˇska izmedu dva algoritma detekcije u prosjeku od 23 mm. Robotska ruka UR5, robotska ˇsaka Robotiq 3-Finger i pravilno kalibrirana LIDAR kamera L515 su se pokazali dovoljno dobrim te nisu znatno pridonijeli pogreˇsci koja je u ovome radu zabiljeˇzena.
Abstract (english)
In this thesis, a system for robot palletization using computer vision algorithms is presented. The thesis was written in cooperation with the company Protostar Labs d.o.o. The robotic system used for this thesis consists of the UR5 robot arm, the Robotiq 3-Finger gripper, the Intel RealSense LiDAR camera, ROS, Gazebo simulator, and the Open3D library used for working with point clouds. Algorithms RANSAC, DBSCAN, and ICP are used in this system. The purpose of this robotic system is to detect incoming objects in the work area, calculate their position, grab them, and release them at the specified location. The experiments conducted in this thesis have shown that this robotic palletization system is inadequate for industrial use. Although the results of the fourth experiment showed that the largest error in object placement was only eight millimeters, there is a consistent difference between the two detection algorithms which averages 23 millimeters. The UR5 robotic arm, the Robotiq 3-Finger gripper, and the properly calibrated L515 LiDAR camera proved to be good enough and haven’t contributed in any meaningful way to the error in object placement noted in this thesis.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:741070
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-10-18 13:08:03