prikaz prve stranice dokumenta Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net
  Download
PDF 2.4 MB
master's thesis
Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. urn:nbn:hr:200:768537
Stipić, Nikola
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

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Stipić, N. (2022). Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net (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:200:768537

Stipić, Nikola. "Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net." 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:200:768537

Stipić, Nikola. "Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net." 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:200:768537

Stipić, N. (2022). 'Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 15 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:768537

Stipić N. Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2022 [cited 2025 January 15] Available at: https://urn.nsk.hr/urn:nbn:hr:200:768537

N. Stipić, "Robotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net", 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:200:768537

Metadata
TitleRobotska manipulacija korištenjem računalnog vida i neuronske mreže Dex-Net
Title (english)Robot manipulation using computer vision and Dex-Net neural network
AuthorNikola Stipić
MentorRobert Cupec (mentor)
MentorPetra Pejić (sumentor)
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 country2022-10-04, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom diplomskom radu, eksperimentalno su ispitane mogućnosti primjene neuronske mreže Dex-Net, koja određuje prikladno mjesto na površini predmeta za hvatanje od strane robota na osnovu fizičkih obilježja objekta koristeći računalni vid, s primjenom u robotskoj manipulaciji. Sva programska podrška izvedena je u sustavu ROS te primijenjena u stvarnom okruženju. Robotski sustav korišten u eksperimentalnoj fazi ovog rada sastoji se od UR5 robotskog manipulatora, Intel RealSense L515 kamere, Robotiq hvataljke s 3 prsta te osobnog prijenosnog računala.
Abstract (english)
In this thesis, the possibilities of using the neural network Dex-Net, which determines suitable grasps based on the physical characteristics of the object using computer vision, with application in robotic manipulation, were experimentally investigated. All software was implemented using ROS and was applied in a real environment. Robotic system used in the experimental phase of this thesis consists of a UR5 robotic manipulator, an Intel RealSense L515 camera, a Robotiq 3-finger gripper and a personal laptop.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:768537
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 on2022-12-22 11:55:24