There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 411 | - |
dc.citation.number | 6 | - |
dc.citation.startPage | 399 | - |
dc.citation.title | 제어·로봇·시스템학회 논문지 | - |
dc.citation.volume | 26 | - |
dc.contributor.author | 김민우 | - |
dc.contributor.author | 김종윤 | - |
dc.contributor.author | 정민재 | - |
dc.contributor.author | 오현동 | - |
dc.date.accessioned | 2023-12-21T17:37:15Z | - |
dc.date.available | 2023-12-21T17:37:15Z | - |
dc.date.created | 2022-12-29 | - |
dc.date.issued | 2020-05 | - |
dc.description.abstract | Collision avoidance of drones in a complex environment, especially in an indoor environment, is a challenging task. This paperdevelops an obstacle avoidance system for small multi-rotor drones based on a deep reinforcement learning algorithm using only amonocular camera. The proposed method comprises two steps: depth estimation and navigation decision-making. For the depth estimationstep, a pre-trained depth estimation algorithm based on a CNN (Convolutional Neural Network) is used. In the navigation decision-makingstep, a dueling double deep Q-network is employed. The entire training procedure is performed in a Gazebo simulation environment usinga robot operating system. To validate the robustness of the proposed approach, various simulations and experiments are conducted using aParrot Bebop2 drone in an indoor corridor. We demonstrate that the proposed algorithm successfully navigates through a narrow corridorcomprising a texture-free wall, people, and boxes. A supplementary video clip of the experiments can be found at https://youtu.be/oSQHCsvuE-8. | - |
dc.identifier.bibliographicCitation | 제어·로봇·시스템학회 논문지, v.26, no.6, pp.399 - 411 | - |
dc.identifier.doi | 10.5302/j.icros.2020.20.0014 | - |
dc.identifier.issn | 1976-5622 | - |
dc.identifier.scopusid | 2-s2.0-85086765810 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/60510 | - |
dc.language | 한국어 | - |
dc.publisher | 제어·로봇·시스템학회 | - |
dc.title.alternative | Collision Avoidance for a Small Drone with a Monocular Camera Using Deep Reinforcement Learning in an Indoor Environment | - |
dc.title | 단안 카메라와 심층강화학습을 이용한소형 무인기 실내 충돌 회피 시스템 | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.identifier.kciid | ART002592839 | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | kci | - |
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.