Primjena NEAT algoritma za navigaciju mobilnog robota

undergraduate thesis

• Title (english): Application of the NEAT algorithm for mobile robot navigation
• Author: Vita Gajdek
• Mentor: Petar Ćurković (mentor)
• Committee member: Vladimir Milić (član povjerenstva)
• Committee member: Petar Ćurković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2024-09-26, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing; Artificial Intelligence

Abstract

Tehnološki napredak u posljednjih nekoliko desetljeća uvelike se oslanja na postignuća ostvarena u strojnom učenju. Danas je gotovo nemoguće zamisliti modernu tehnologiju koja ne koristi umjetne neuronske mreže. Težnja za optimizacijom inteligentnih sustava potaknula je i razvoj evolucijskog računarstva inspiriranog principima prirodne evolucije.
U ovom će se radu objasniti mehanizmi evolucijskih algoritama čijom se primjenom nastoji poboljšati put do rješenja kompleksnih zadataka. Cilj rada je analizirati NEAT (engl. NeuroEvolution of Augmenting Topologies) algoritam i osvrnuti se na njegovu implementaciju u području mobilne robotike.
Korištenjem biblioteke neat-python u programskom jeziku python implementirat će se NEAT algoritam u svrhu navigacije mobilnih robota. Analizirat će se rezultati simulacije te će se dati prijedlozi za daljnji rad.

Abstract (english)

Advancements in technology in the last few decades stem from the achievements in the field of machine learning. It is almost impossible to imagine modern day technology that isn't using artificial neural networks. Evolutionary computation has gained significant interest due to the constant strive for optimization of intelligent systems.
This study elaborates on the concepts of evolutionary algorithms that are aimed to improve problem solving processes of more complex tasks. The goal is to analize NEAT (NeuroEvolution of Augmenting Topologies) algorithm in the context of mobile robotics.
Furthermore, the NEAT algorithm will be implemented in Python using neat-python library in order to simulate a controller of a mobile robot. The simulation results shall be analized for multiple cases.

• Keywords: evolucijski algoritmi; neuroevolucija; NEAT; mobilna robotika; python
• Keywords (english): evolutionary algorithms; neuroevolution; NEAT; mobile robotics; python
• Language: croatian
• URN:NBN: urn:nbn:hr:235:704585
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2024-09-25 16:12:16