prikaz prve stranice dokumenta Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom
  Download
PDF 6.66 MB
master's thesis
Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom
2023. urn:nbn:hr:200:639403
Vulić, Lukrecia
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

Vulić, L. (2023). Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom (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:200:639403

Vulić, Lukrecia. "Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:639403

Vulić, Lukrecia. "Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:639403

Vulić, L. (2023). 'Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 20 April 2024, https://urn.nsk.hr/urn:nbn:hr:200:639403

Vulić L. Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2024 April 20] Available at: https://urn.nsk.hr/urn:nbn:hr:200:639403

L. Vulić, "Otvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:639403

Please login to the repository to save this object to your list.
Metadata
TitleOtvaranje ormara robotskom rukom pomoću računalnog vida i upravljanja silom
Title (english)Opening Cabinets by a Robot Arm Using Computer Vision and Force Control
AuthorLukrecia Vulić
MentorRobert Cupec (mentor)
MentorValentin Šimundić (sumentor)
Committee memberRobert Cupec (predsjednik povjerenstva)
Committee memberEmmanuel Karlo Nyarko (član povjerenstva)
Committee memberPetra Pejić (član povjerenstva)
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 country2023-08-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom diplomskom radu obraden je problem detekcije i otvaranja vrata robotskim manipulatorom uz primjenu raˇcunalnog vida. Detekcija i izgradnja modela vrata obavljena je na temelju sekvence RGB-D slika kojima je prikazana ljudska demonstracija otvaranja vrata. Za postupak otvaranja vrata, na temelju prethodno izraˇcunatih toˇcaka putanje, koristilo se hibridno upravljanje silom i pozicijom. Robotski sustav sastojao se od UR5 robotskog manipulatora, robotskog alata Robotiq 3-Finger Adaptive Robot Gripper, Intel RealSense LiDAR Camera L515 kamere i senzora sile FT 300-S. Za programiranje robotskog sustava koriˇsteni su razvojni alati ROS Noetic i Docker. Eksperimentalnom analizom utvrdila se uspjeˇsnost izvodenja algoritama za detekciju i izgradnju modela vrata i algoritma za otvaranje vrata robotskom rukom uz upravljanje silom. U 60.86% pokusa uspjeˇsno su izvedena oba algoritma, u 21.74% pogreˇsno je izgraden model vrata te je u ovim sluˇcajevima nemogu´ce odrediti uspjeˇsnost algoritma za otvaranje vrata. U preostalih 17.39% sluˇcajeva nije bilo mogu´ce utvrditi uspjeˇsnost niti jednog algoritma, zbog aktiviranja sigurnosnih mjera uzrokovanih loˇsim poloˇzajem manipulatora.
Abstract (english)
This master thesis addresses the problem of door detection and opening using a robotic manipulator with the application of computer vision. The detection and construction of the door model were based on a sequence of RGB-D images showing a human demonstration of door opening. Hybrid force-position control was used to open the door using the previously calculated path points. The robotic system consisted of a UR5 robotic manipulator, a Robotiq 3-finger adaptive robotic gripper, the L515 Intel RealSense LiDAR camera, and FT 300-S force sensor. The development tools ROS Noetic and Docker were used to programme the robotic system. Experimental analysis was performed to evaluate the performance of the door detection, model construction, and force control opening algorithms. Both algorithms were successfully executed in 60.86% of the experiments, while in 21.74% of the cases the door model was inaccurately constructe making it impossible to determine the success of the door opening algorithm. In the remaining 17.39% of cases, the success of neither algorithm could be determined because security measures were activated due to the poor positioning of the manipulator.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:639403
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 on2023-09-18 09:47:46