Evolucija kretanja dvonožnog modela korištenjem neuronskih mreža

undergraduate thesis

• Title (english): Movement Evolution of Biped Model using Neural Networks
• Author: Dino Grgić
• Mentor: Željka Mihajlović (mentor)
• Committee member: Željka Mihajlović (predsjednik povjerenstva)
• Committee member: Hrvoje Nuić (član povjerenstva)
• Committee member: Juraj Fulir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj završni rad implementira učenje hodanja bipedalnog modela uz pomoć neuronskih mreža. Modeli robota i simulacija hoda odrađena je uz pomoć programskog paketa za simulaciju robota Webots. Učenje hoda izvršeno je aproksimacijom funkcija koje opisuju kut zglobova modela robota kroz vrijeme provodeći funkcijsku regresiju.

Abstract (english)

This final work implements learning of walk movement for the bipedal model using neural
networks. Robot model and simulation is implemented with Webots programming package for
robot simulation. Learning of walk movement is done by approximating functions that describe
the angle of model joints throughout time with functional regression.

• Keywords: simulacija kretanja bipedalnog modela; neuronske mreže; fukcijska regresija; Webots; Keras
• Keywords (english): bipedal model movement simulation; neural networks; functional regression; Webots; Keras
• Language: croatian
• URN:NBN: urn:nbn:hr:168:981623
• 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: 2023-01-14 20:30:36