Thesis Details

Aplikace posilovaného učení při řízení modelu vozidla

Bachelor's Thesis Student: Maslowski Petr Academic Year: 2018/2019 Supervisor: Šůstek Martin, Ing.
English title
Vehicle Control via Reinforcement Learning
Language
Czech
Abstract

The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.

Keywords

Reinforcement learning, machine learning, neural networks, convolution neural networks, DQN, autonomous vehicle control, simulated driving, CARLA simulator

Department
Degree Programme
Information Technology
Files
Status
defended, grade A
Date
13 June 2019
Reviewer
Committee
Zbořil František, doc. Ing., Ph.D. (DITS FIT BUT), předseda
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Grézl František, Ing., Ph.D. (DCGM FIT BUT), člen
Hliněná Dana, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Strnadel Josef, Ing., Ph.D. (DCSY FIT BUT), člen
Citation
MASLOWSKI, Petr. Aplikace posilovaného učení při řízení modelu vozidla. Brno, 2019. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2019-06-13. Supervised by Šůstek Martin. Available from: https://www.fit.vut.cz/study/thesis/22043/
BibTeX
@bachelorsthesis{FITBT22043,
    author = "Petr Maslowski",
    type = "Bachelor's thesis",
    title = "Aplikace posilovan\'{e}ho u\v{c}en\'{i} p\v{r}i \v{r}\'{i}zen\'{i} modelu vozidla",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2019,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/22043/"
}
Back to top