Optimizacija putanje robota primjenom genetskih algoritama

master's thesis

• Title (english): Robot path optimization using genetic algorithms
• Author: Stjepan Krstičević
• Mentor: Lana Horvat Dmitrović (mentor)
• Committee member: Lana Horvat Dmitrović (predsjednik povjerenstva)
• Committee member: Ana Žgaljić Keko (član povjerenstva)
• Committee member: Mario Bukal (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rješavanje problema optimizacije putanje robota jedan je od temeljnih zadataka interdisciplinarnog znanstvenog područja robotike. Jedna od tehnika koja se koristi za rješavanje tog problema je optimizacija putanje genetskim algoritmima. Genetski algoritmi, kao vrsta evolucijskog algoritma, koriste postupke selekcije, mutacije i križanja u svrhu pretraživanja prostora stanja i pronalaska optimalnog puta. Kako je izmjena genetskog materijala slučajan proces koji u sebi sadrži određenu dozu nepravilnosti, implementacijom kaosa dolazimo do novog oblika genetskog algoritma. U ovom radu prikazuje se implementacija tradicionalnog i kaotičnog genetskog algoritma u svrhu rješavanja problema optimizacije putanje robota kao i analiza kvalitete rješenja i brzine programa ta dva algoritma.

Abstract (english)

Solving the robot trajectory optimization problem is one of the fundamental tasks in the interdisciplinary scientific field of robotics. One of the techniques used to solve this problem is path optimization using genetic algorithms. Genetic algorithms, as a type of evolutionary algorithm, use selection, mutation, and crossover procedures to search for state space and find the optimal pathway. As the change of genetic material is a random process that contains a certain dose of irregularities, the implementation of chaos leads to a new form of genetic algorithm. This paper presents the implementation of a traditional and chaotic genetic algorithm in order to solve the problem of robot path optimization as well as the analysis of the solution quality and program speed of these two algorithms.

• Keywords: genetski algoritam; teorija kaosa; križanje; funkcija dobrote; putanja robota; optimizacija; usmjereni aciklički graf
• Keywords (english): genetic algorithm; chaos theory; crossover; fitness function; robot trajectory; optimization; directed acyclic graph
• Language: croatian
• URN:NBN: urn:nbn:hr:168:948146
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:14:11