Optimiranje robotskih trajektorija primjenom biološki inspiriranih algoritama

Čehulić, Lovro (2018) Optimiranje robotskih trajektorija primjenom biološki inspiriranih algoritama. = Robot trajectory optimization based on bio-inspired algorithms. Master's thesis (Bologna) , Sveučilište u Zagrebu, Fakultet strojarstva i brodogradnje, UNSPECIFIED. Mentor: Ćurković, Petar.

[img]
Preview
Text
Čehulić_2018_diplomski.pdf - Published Version Jezik dokumenta:Croatian

Download (2MB) | Preview
[img] Text
Čehulić_Lovro_autorska_izjava_diplomski_2018.pdf - Published Version
Restricted to Repository staff only Jezik dokumenta:Croatian

Download (517kB)

Abstract (Croatian)

Tema ovog diplomskog rada je izrada modula za planiranje kretanja koji se temelji na biološki inspiriranim algoritmima. Planirane trajektorije smještene su u 2D i 3D prostoru. Prostor je okoliš koji je korisnik definirao ovisno o željenom broju i položaju prepreka. Provode se različite metode kako bi se ispitao njihov utjecaj na performanse i na razinu konvergencije algoritma. Pokazano je da svaka verzija algoritma ima svoje prednosti i nedostatke. Za svaku verziju algoritma provodi se temeljita statistička analiza, a rezultati su dokumentirani i prezentirani u radu.

Abstract

The subject matter of this master's thesis is a design of a motion planning module based on a biologically inspired algorithm. Planned trajectories are placed in both 2D and 3D space. Space is a user-defined environment which contains an arbitrary number of placed obstacles. Different methods are implemented to examine their impact on the performance and the level of convergence of the algorithm. It is shown that each instance of the algorithm has its benefits and shortcomings. A meticulous statistical analysis is performed for each version of the algorithm, and the results are documented and presented in the thesis.

Item Type: Thesis (Master's thesis (Bologna))
Uncontrolled Keywords: Evolucijski algoritmi; planiranje kretanja; umjetna inteligencija.
Keywords (Croatian): Evolutionary algorithms; motion planning; artificial intelligence.
Subjects: TECHNICAL SCIENCE > Mechanical Engineering
Divisions: 900 Department of Robotics and Production System Automation > 920 Chair of Manufacturing and Assembly System Planning
Date Deposited: 29 Nov 2018 10:44
Last Modified: 25 Oct 2019 11:25
URI: http://repozitorij.fsb.hr/id/eprint/8919

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year