Metoda pretraživanja prostora zasnovana na RRT algoritmu i potencijalnim poljima

undergraduate thesis

• Title (english): Potential field and RRT based exploration algorithm
• Author: Krešimir Topolovec
• Mentor: Matko Orsag (mentor)
• Committee member: Matko Orsag (predsjednik povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Committee member: Antun Ivanović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2017-09-20, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U uvodnim poglavljima rada je ukratko opisan RRT algoritam i osnove po-
tencijalnih polja. Iznesene su temeljne jednadžbe s objašnjenjima kao temelj za
razumijevanje implementacije. Pokazano je kako, koristeći potencijalna polja i
RRT izgraditi algoritam koji u konačnom vremenu rješava problem pronalaska
puta prema cilju unutar prostora s preprekama. Praktični dio rada uključuje razvoj
algoritma koji kombinira potencijalna polja i RRT algoritam u svrhu kretanja
letjelice prema zadanom cilju izbjegavajući pritom prepreke. Algoritam je imple-
mentiran u ROS okruženju, u jeziku C++ te je isproban na modelu bespilotne
letjelice u Gazebo simulatoru i vizualiziran u RVizu. Nakon uspješno provedenih
simulacija predložena su eventualna poboljšanja algoritma.

Abstract (english)

The introductory chapters of the paper briefly describe the RRT algorithm and the basics of potential fields. Basic equations with explanations are presented as a basis for understanding the implementation. It was shown how to construct an algorithm that solves the problem of finding a path to a goal within a space with obstacles. The practical part of the work involves the development of an algorithm that combines the potential fields and the RRT algorithm for the purpose of moving the aircraft to the desired goal while avoiding the obstacles. The algorithm was implemented in the ROS environment, in C ++ language and tested on the model of unmanned aircraft in the Gazebo simulator and visualized in RViz.

• Keywords: potencijalna; polja; planiranje; trajektorije; RRT; algoritam; ROS; Gazebo; C++
• Keywords (english): potential; fields; trajectory; planning; RRT; algorithm; ROS; Gazebo; C++
• Language: croatian
• URN:NBN: urn:nbn:hr:168:881969
• Study programme: Title: Computing; 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-14 01:39:03