Planiranje robotskih trajektorij operacije prenosa izdelka z umetno inteligenco

diplomsko delo Visokošolskega strokovnega študijskega programa I. stopnje Strojništvo - Projektno aplikativni program

Marko Chris Physicos (Author), Miha Pipan (Mentor), Niko Herakovič (Co-mentor)

Abstract

V sklopu diplomske naloge smo preučevali možnost uporabe jezikovnih modelov umetne inteligence, kot je ChatGPT, za zaznavanje lokacije in orientacije objektov na slikah, ki smo jih kasneje uporabili kot osnovo za pridobivanje trajektorij za izvedbo operacijo prenašanja izdelkov na odlagalno mesto. Najprej smo pregledali teoretične osnove umetne inteligence, strojnega vida, delovanje API-ja (vmesnika uporabniškega programa) ter opisali robota Dobop Magician, s katerim smo izvajali operacije prenašanja izdelkov, nato pa smo izvedli eksperimentalne teste, s katerimi smo želeli preveriti, ali je s pomočjo umetne inteligence, v našem primeru modela ChatGPT, mogoče uspešno locirati predmete na slikah in ali je dovolj natančna za uporabo teh podatkov za nadaljnjo uporabo oziroma ali robot sploh zadene želeno tarčo. Da smo lahko to izvedli, smo morali najprej povezati robota s programom preko API. Na koncu smo naredili test natančnosti sistema, in ugotovili, da je sistem zadovoljivo natančen, vedno prime in odloži izdelke, vendar ga je potrebno predhodno dobro kalibrirati.

Keywords

diplomske naloge;detekcija objektov;strojni vid;planiranje trajektorij;umetna inteligenca;roboti;

Data

Language:	Slovenian
Year of publishing:	2025
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FS - Faculty of Mechanical Engineering
Publisher:	[M. C. Physicos]
UDC:	004.896:007.52(043.2)
COBISS:	248625923
Views:	71
Downloads:	6
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	Planning robotic trajectories for product transfer operations with artificial intelligence
Secondary abstract:	As part of our thesis, we explored the possibility of using artificial intelligence language models, such as ChatGPT, to detect the location and orientation of objects in images, which we later used as a basis for obtaining trajectories for performing product transfer operations to the disposal site. First, we reviewed the theoretical foundations of artificial intelligence, machine vision, and API (Application Programming Interface) operation, and described Dobop Magician, which we used to perform product transfer operations. We then conducted experimental tests to verify whether artificial intelligence, in our case the ChatGPT model, can successfully locate objects in images and whether it is accurate enough to use this data for further use, or whether the robot can even hit the desired target. To do this, we first had to connect the robot to the program via API. Finally, we tested the accuracy of the system and found that it is satisfactorily accurate, always pick and place the products correctly, but it needs to be calibrated well beforehand.
Secondary keywords:	thesis;object detection;machine vision;planning trajectories;artificial intelligence;robots;
Type (COBISS):	Bachelor thesis/paper
Study programme:	0
Thesis comment:	Univ. v Ljubljani, Fak. za strojništvo
Pages:	XX, 47 str.
ID:	27338323