Estimiranje trajektorije vozila Kalmanovim filtrom za generiranje logičkih scenarija

master's thesis

• Title (english): Vehicle Trajectory Estimation with the Kalman filter for Generating Logical Scenarios
• Author: Pavle Pavičić
• Mentor: Ivan Marković (mentor)
• Committee member: Ivan Marković (predsjednik povjerenstva)
• Committee member: Marija Seder (član povjerenstva)
• Committee member: Ivan Petrović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Cilj ove teze je istražiti estimaciju stanja vozila korištenjem Kalmanovog filtra s različitim modelima vozila. Estimirani parametri koji se obrađuju u ovom istraživanju su: putanja vozila, masa i međuosovinski razmak. Budući da se autonomna vozila brzo razvijaju, ove vrste procjena mogu naći primjenu u brojnim sustavima poput sustava automatskog kočenja (skraćeno: ABS) koji koristi precizne vrijednosti mase i duljine vozila. Također, procjena stanja vozila u velikoj mjeri može pomoći u stvaranju simulacije logičkih scenarija prometa koji se koriste za daljnji razvoj autonomnih sustava vozila. Skupovi podataka korišteni tijekom istraživanja generirani su putem programa ASM ModelDesk, dok su obrada signala, razvoj modela i proračun parametara postignuti kroz program MATLAB i programski jezik Python.

Abstract (english)

This thesis aims to explore estimation of vehicle’s states by using Kalman filter with different vehicle models. The parameters estimated for this research are vehicle trajectory, mass and wheel base. Since autonomous vehicles are rapidly developing, these types of estimations can find use in numerous vehicle systems such as automatic braking system (abbreviated as: ABS) which needs accurate vehicle mass and vehicle length value. Also, estimation of vehicle’s states can largely help in generation of simulated logical traffic scenarios used for further development of autonomous vehicle systems. Datasets used for this research are generated via program ASM ModelDesk, while signal processing, model development and parameter calculation were achieved through MATLAB program and Python programming language.

• Keywords: Kalmanov filtar; estimacija parametara; autonomna vožnja; mateamtički model dinamike vozila; logički scenarij prometa
• Keywords (english): Kalman filter; parameter estimation; autonomous driving; vehicle dynamics model; logical traffic scenario
• Language: english
• URN:NBN: urn:nbn:hr:168:515897
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 15:48:26