Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.

Sonraí bibleagrafaíochta
Príomhchruthaitheoirí:	Issa, Razin Bin, Rahman, Md. Saferi, Das, Modhumonty, Barua, Monika
Rannpháirtithe:	Alam, Md. Golam Rabiul
Formáid:	Tráchtas
Teanga:	en_US
Foilsithe / Cruthaithe:	Brac University 2020
Ábhair:	Reinforcement Learning Autonomous Vehicle Faster R-CNN Double Deep Q Learning
Rochtain ar líne:	http://hdl.handle.net/10361/14048

id	10361-14048
record_format	dspace
spelling	10361-140482022-01-26T10:18:28Z Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track Issa, Razin Bin Rahman, Md. Saferi Das, Modhumonty Barua, Monika Alam, Md. Golam Rabiul Rhaman, Md. Khalilur Department of Computer Science and Engineering, Brac University Reinforcement Learning Autonomous Vehicle Faster R-CNN Double Deep Q Learning This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019. Cataloged from PDF version of thesis. Includes bibliographical references (pages 43-46). This research focuses on autonomous traversal of land vehicles through exploring undiscovered tracks and overcoming environmental barriers. Most of the existing systems can only operate and traverse in a distinctive mapped model especially in a known area. However, the proposed system which is trained by Deep Reinforcement Learning can learn by itself to operate autonomously in extreme conditions. The dynamic double deep Q-learning (DDQN) model enables the proposed system not to be confined only to known environments. The ambient environmental obstacles are identified through Faster R-CNN for smooth movement of the autonomous vehicle. The exploration and exploitation strategies of DDQN enables the autonomous agent to learn proper decisions for various dynamic environments and tracks. The proposed model is tested in a gaming environment. It shows the overall effectiveness in traversing of autonomous land vehicles in comparison to the existing models. The goal is to integrate Deep Reinforcement learning and Faster R-CNN to make the system effective to traverse through undiscovered paths by detecting obstacles. Razin Bin Issa Md. Saferi Rahman Modhumonty Das Monika Barua B. Computer Science 2020-10-07T05:30:24Z 2020-10-07T05:30:24Z 2019 2019-12 Thesis ID: 16101214 ID: 16101011 ID: 16101204 ID: 16101262 http://hdl.handle.net/10361/14048 en_US Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 48 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	en_US
topic	Reinforcement Learning Autonomous Vehicle Faster R-CNN Double Deep Q Learning
spellingShingle	Reinforcement Learning Autonomous Vehicle Faster R-CNN Double Deep Q Learning Issa, Razin Bin Rahman, Md. Saferi Das, Modhumonty Barua, Monika Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.
author2	Alam, Md. Golam Rabiul
author_facet	Alam, Md. Golam Rabiul Issa, Razin Bin Rahman, Md. Saferi Das, Modhumonty Barua, Monika
format	Thesis
author	Issa, Razin Bin Rahman, Md. Saferi Das, Modhumonty Barua, Monika
author_sort	Issa, Razin Bin
title	Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
title_short	Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
title_full	Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
title_fullStr	Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
title_full_unstemmed	Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
title_sort	reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track
publisher	Brac University
publishDate	2020
url	http://hdl.handle.net/10361/14048
work_keys_str_mv	AT issarazinbin reinforcementlearningbasedautonomousvehicleforexplorationandexploitationofundiscoveredtrack AT rahmanmdsaferi reinforcementlearningbasedautonomousvehicleforexplorationandexploitationofundiscoveredtrack AT dasmodhumonty reinforcementlearningbasedautonomousvehicleforexplorationandexploitationofundiscoveredtrack AT baruamonika reinforcementlearningbasedautonomousvehicleforexplorationandexploitationofundiscoveredtrack
_version_	1814308888912068608

Reinforcement learning based autonomous vehicle for exploration and exploitation of undiscovered track

Míreanna comhchosúla