dc.contributor.author | Ellingsen, Nikolai Kjærem | |
dc.date.accessioned | 2020-10-15T10:28:16Z | |
dc.date.available | 2020-10-15T10:28:16Z | |
dc.date.issued | 2020 | |
dc.identifier.citation | Ellingsen, N. K. (2020) Imitation Accelerated Q-learning on a Simulated Formula Student Driverless Racecar (Master's thesis). University of Agder, Grimstad | en_US |
dc.identifier.uri | https://hdl.handle.net/11250/2683037 | |
dc.description | Master's thesis in Information- and communication technology (IKT590) | en_US |
dc.description.abstract | In the international Formula Student competition, only a handful compete in the driverless category. Most of them using expensive hardware such as LIDAR’s. By leveraging reinforcement learning, a cheaper camera based system can be created .In order to train this system a simulator based on a fork of Microsoft’s AirSim by Formula Technion was used. A virtual replica of a Formula Student car designed for 2020 by Align Racing UiA, functioned as the test vehicle. In order to decrease the required training time, a pre-trained imitation learning network was used. This was implemented into a Deep Q-Learning network in four different methods. The most successful method was able to accelerate the learning process by 36%. | en_US |
dc.language.iso | eng | en_US |
dc.publisher | University of Agder | en_US |
dc.rights | Attribution-NonCommercial-NoDerivatives 4.0 Internasjonal | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/deed.no | * |
dc.subject | IKT590 | en_US |
dc.title | Imitation Accelerated Q-learning on a Simulated Formula Student Driverless Racecar | en_US |
dc.type | Master thesis | en_US |
dc.rights.holder | © 2020 Nikolai Kjærem Ellingsen | en_US |
dc.subject.nsi | VDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550 | en_US |
dc.source.pagenumber | 41 | en_US |