Masinõppe mudelite treenimise simulatsioonid autonoomsetele sõidukitele
Files
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Masinõppe mudelite treenimine autonoomsete sõidukite jaoks nõuab palju andmeid, mille käsitsi märgendamine on aeganõudev. Simulatsioonid aitavad seda protsessi automatiseerida. Käesolev töö koostab ülevaate 12-st internetiotsingu abil leitud simulatsioonist ja analüüsib neid lähtuvalt nende sobivusest maastikul liikuvatele sõidukitele (säilitades võimaluse liikuda ka linnakeskkonnas).
Training machine learning models for autonomous vehicles requires a lot of data which is time consuming and tedious to label manually. Simulated virtual environments help to automate this process. In this work these virtual environments are called simulations. The goal of this thesis is to survey the most suitable simulations for off-road vehicles (while not discarding the urban option). Only the simulations which provide labeled output data, are included in this work. The chosen 12 simulations are surveyed based on the information found online. The simulations are then analyzed based on the predefined features and categorized according to their suitability for training machine learning models for off-road vehicles. The results are shown in a table for comparison. The main purpose of this work is to map the seemingly large landscape of simulations and give a compact picture of the situation.
Training machine learning models for autonomous vehicles requires a lot of data which is time consuming and tedious to label manually. Simulated virtual environments help to automate this process. In this work these virtual environments are called simulations. The goal of this thesis is to survey the most suitable simulations for off-road vehicles (while not discarding the urban option). Only the simulations which provide labeled output data, are included in this work. The chosen 12 simulations are surveyed based on the information found online. The simulations are then analyzed based on the predefined features and categorized according to their suitability for training machine learning models for off-road vehicles. The results are shown in a table for comparison. The main purpose of this work is to map the seemingly large landscape of simulations and give a compact picture of the situation.