magistrsko delo
Klemen Zaponšek (Author), Simon Klančnik (Mentor), Aleš Hace (Mentor), Rok Pučko (Co-mentor)

Abstract

Magistrska naloga predstavlja uporabo strojnega vida v avtomatiziranih robotskih procesih. S pomočjo tega imajo roboti možnost vizualnega zaznavanja objektov, simbolov, karakterjev, barv in to delo lahko opravljajo hitro in neizčrpno. Tako lahko roboti samodejno in dinamično manipulirajo z objekti, s katerimi so predhodno manipulirali po točno določenem zaporedju in trajektorijah. Cilj naloge je izdelava preprostega in prilagodljivega sistema 2D stojnega vida, ki robotu s preprosto primi in spusti aplikacijo, pošilja informacije o zaznanem objektu, preko katerih nato robot prosto ležeč objekt v prostoru zgrabi in ga loči v predviden zalogovnik. Pri nalogi sta bila uporabljena kolaborativna robota podjetja Universal robot z oznako UR3 in UR5. Za namen zajema in obdelave slike ter komunikacije z robotskima sistemoma pa je bil uporabljen programski paket LabVIEW z Vision Assistant in Vision Acquisition dodatkom. Uporabljeni sta še industrijski kameri podjetja Basler različnih dimenzij. Od tega je bila večja kamera vpeta fiksno v prostoru, manjša pa na vrhu robotske roke. Za primerjavo se je uporabila tudi enostavna USB endoskopska kamera, ki je bila zaradi majhnih dimenzij prav tako pritrjena na vrhu robotske roke. V tem se boste seznanili z navodili za izdelavo robotske aplikacije s strojnim vidom v programskem paketu LabVIEW.

Keywords

strojni vid;robotski sistemi;kolaborativni robot;detekcija orientacije;industrijska kamera;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FS - Faculty of Mechanical Engineering
Publisher: [K. Zaponšek]
UDC: 004.93:007.52(043.2)
COBISS: 99446275 Link will open in a new window
Views: 490
Downloads: 224
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Robotical manipulation of objects in space using 2d machine vision
Secondary abstract: The master's thesis presents the use of machine vision in automated robotic processes. With this, robots can visually perceive objects, symbols, characters, colours, as well as perform this work quickly and inexhaustibly. Robots can thus automatically and dynamically manipulate objects that have previously been manipulated in a specific sequence and trajectories. The aim of the thesis is to create a simple and flexible 2D machine vision system that sends the information about the detected object to the robot in a simple pick-and-place application, through which the robot then grabs a free-lying object in space and separates it into the intended storage. Collaborative robots from the company Universal robot, marked UR3 and UR5, were used in the task. The LabVIEW software package with Vision Assistant and Vision Acquisition add-ons was used for capturing and processing images and communicating with robotic systems, as well as Basler industrial cameras of various dimensions. Of these, a larger camera was mounted fixed in space and a smaller one on the top of the robotic arm. A simple USB endoscopic camera, which was also attached to the top of the robotic arm due to its small dimensions, was also used for comparison. This work gives you an insight into the instructions for creating a robotic application with the machine vision in the LabVIEW software package.
Secondary keywords: machine vision;robotic systems;collaborative robot;orientation detection;LabVIEW;industrial camera;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za strojništvo
Pages: XI, 69 str.
ID: 12993762