There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.startPage | 116742 | - |
dc.citation.title | EXPERT SYSTEMS WITH APPLICATIONS | - |
dc.citation.volume | 198 | - |
dc.contributor.author | Kim, Minwoo | - |
dc.contributor.author | Kim, Jongyun | - |
dc.contributor.author | Jung, Minjae | - |
dc.contributor.author | Oh, Hyondong | - |
dc.date.accessioned | 2023-12-21T14:07:02Z | - |
dc.date.available | 2023-12-21T14:07:02Z | - |
dc.date.created | 2022-05-26 | - |
dc.date.issued | 2022-07 | - |
dc.description.abstract | This paper proposes an obstacle avoidance strategy for small multi-rotor drones with a monocular camera using deep reinforcement learning. The proposed method is composed of two steps: depth estimation and navigation decision making. For the depth estimation step, a pre-trained depth estimation algorithm based on the convolutional neural network is used. On the navigation decision making step, a dueling double deep Q-network is employed with a well-designed reward function. The network is trained using the robot operating system and Gazebo simulation environment. To validate the performance and robustness of the proposed approach, simulations and real experiments have been carried out using a Parrot Bebop2 drone in various complex indoor environments. We demonstrate that the proposed algorithm successfully travels along the narrow corridors with the texture free walls, people, and boxes. | - |
dc.identifier.bibliographicCitation | EXPERT SYSTEMS WITH APPLICATIONS, v.198, pp.116742 | - |
dc.identifier.doi | 10.1016/j.eswa.2022.116742 | - |
dc.identifier.issn | 0957-4174 | - |
dc.identifier.scopusid | 2-s2.0-85126279548 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/58580 | - |
dc.identifier.url | https://www.sciencedirect.com/science/article/pii/S0957417422002111?via%3Dihub | - |
dc.identifier.wosid | 000792157000003 | - |
dc.language | 영어 | - |
dc.publisher | PERGAMON-ELSEVIER SCIENCE LTD | - |
dc.title | Towards monocular vision-based autonomous flight through deep reinforcement learning | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic; Operations Research & Management Science | - |
dc.relation.journalResearchArea | Computer Science; Engineering; Operations Research & Management Science | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Obstacle avoidance | - |
dc.subject.keywordAuthor | Depth estimation | - |
dc.subject.keywordAuthor | Vision-based | - |
dc.subject.keywordAuthor | Deep reinforcement learning | - |
dc.subject.keywordAuthor | Q-learning | - |
dc.subject.keywordAuthor | Navigation decision making | - |
dc.subject.keywordPlus | OBSTACLE AVOIDANCE | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.