prikaz prve stranice dokumenta Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida
  Download
PDF 1.56 MB
undergraduate thesis
Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2022. urn:nbn:hr:200:556095
Bošnjak, Andrej
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

Bošnjak, A. (2022). Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida (Undergraduate 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:200:556095

Bošnjak, Andrej. "Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida." Undergraduate 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:200:556095

Bošnjak, Andrej. "Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida." Undergraduate 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:200:556095

Bošnjak, A. (2022). 'Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 08 June 2024, https://urn.nsk.hr/urn:nbn:hr:200:556095

Bošnjak A. Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2022 [cited 2024 June 08] Available at: https://urn.nsk.hr/urn:nbn:hr:200:556095

A. Bošnjak, "Hvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida", Undergraduate 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:200:556095

Metadata
TitleHvatanje pravokutnih predmeta robotskom rukom pomoću računalnog vida
Title (english)Grasping rectangular objects with a robotic arm using computer vision
AuthorAndrej Bošnjak
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 country2022-09-21, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Opisan je sustav za detekciju pravokutnih predmeta te njihovo hvatanje i pomicanje robotskom rukom. Sustav uključuje robotsku ruku UR5, hvataljku Robotiq 3 finger gripper i RGB-D kameru Intel RealSense LiDAR Camera L515 te algoritam za prepoznavanje pravokutnih objekata razvijen u C++ biblioteci Robot Vision Library i programsko rješenje za manipulaciju robota napisano u programskom jeziku Python. Svi dijelovi sustava su povezani unutar ROS okvira. Na slici snimljenoj kamerom prepoznaje se pravokutni predmet i određuje se njegovo središte u koordinatnom sustavu kamere. Kako bi robot uhvatio predmet, pomiče se u točku dobivenu transformacijom točke središta u koordinatni sustav baze robota te se hvataljka zakreće dok se prsti hvataljke ne poravnaju sa stranicama predmeta. Tada hvataljka hvata predmet i podiže ga. Nakon pomicanja robot se vraća u početni položaj. Rezultati testiranja su prikazani tablicama, gdje je opisana uspješnost svakog koraka u izvedbi programa.
Abstract (english)
A system for detection of rectangular objects, their grasping and movement with a robotic arm is described. The system includes a UR5 robotic arm, a Robotiq 3 finger gripper, an Intel RealSense LiDAR Camera L515 RGB-D camera, as well as an algorithm for detection of rectangular objects developed in the C++ library Robot Vision Library and a programming solution for robot manipulation written in the Python programming language. All parts of the system are connected within the ROS framework. In the image captured by the camera, a rectangular object is detected and its center is determined in the camera's coordinate system. In order for the robot to grasp the object, it moves to the point obtained from transforming the center point into the base coordinate system, and the gripper is rotated until its fingers are aligned with the sides of the object. Then the gripper grasps the object and lifts it. After moving, the robot comes back to its starting position. The testing results are shown in tables, where the success of each step in the program's execution is described.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:556095
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2022-10-11 12:47:29