주성분 분석 기반 법선 벡터 추정을 통한 드론 착륙 지점 탐지 기법 연구
PCA-Based Detection of Drone Landing Sites Using Normal Vector Estimation
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 논문에서는 드론의 하드웨어 제한 사항을 고려하여 단순하고 효율적인 드론 착륙 지점을 탐지하기 위해 주성분 분석을 기반으로 한 알고리즘을 제안한다. 제안한 알고리즘은 포인트 클라우드 데이터를 활용하여 주성분 분석 기반 법선 벡터 추정을 통해 착륙 지점을 도출하며 자원이 제한된 시스템에서도 적용 가능함을 증명한다. 드론에서취득한 데이터를 통해 드론 착륙 지점 도출 가능성에 대해 실험적으로 검증하였으며 이전 연구에서 제시한 알고리즘보다 빠르고 신뢰성 있게 안전한 착륙 지점을 식별할 수 있음을 확인하였다. 본 논문에서 제안한 방법은 효율성과 정확성을 보장하며 드론처럼 하드웨어 자원이 제한된 시스템에서 효과적으로 적용되리라 기대된다.
Abstract
This study proposes a principal component analysis (PCA)-based algorithm for the detection of drone landing sites, designed to be both simple and efficient while considering the hardware limitations inherent in drones. The algorithm utilizes point cloud data (PCD) to identify potential landing sites through PCA-based normal vector estimation, demonstrating its applicability even in resource-constrained systems. Experimental validation, utilizing data acquired from drones, confirmed that the proposed method identified safe landing sites more rapidly and reliably than algorithms presented in previous studies. The proposed approach ensures both efficiency and accuracy, rendering it a promising solution for resource-limited systems, such as drones.
참고문헌 (15)
- F. Ahmed, "Recent Advances in Unmanned Aerial Vehicles : A Review", Arabian Journal for Science and Engineering, 47(4), pp.11~22 (2022)
- T. Benarbia, "A Literature Review of Drone-Based Package Delivery Logistics Systems and Their Implementation Feasibility", Sustainability, 14(1), pp.360~ (2022)
- "Ministry of Land, Infrastructure and Transport, Advanced Aviation Division" (2024)[URL]
- L. Xin, "Vision-Based Autonomous Landing for the UAV : A Review", Aerospace, 9(11), pp.634~ (2022)
- H. H. Kang, "Precise Drone Landing System Using Aruco Make", The Journal of Korean Institute of Communication and Information Sciences, 47(1), pp.145~150 (2022)
- J. Springer, "Autonomous Drone Landing with Fiducial Markers and a Gimbal-Mounted Camera for Active Tracking", Sixth IEEE International Conference on Robotic Computing (IRC), pp.243~247 (2022)
- N. Q. Truong, "Deep Learning-Based Super-Resolution Reconstruction and Marker Detection for Drone Landing", IEEE Access, 10, pp.61639~61655 (2019)
- S. Lee, "Safe Landing of Drone Using AI-based Obstacle Avoidance", International Journal of Mechanical Engineering and Robotics Research, 9(11), pp.1495~1501 (2020)
- Z. Xue, "Vision Based Drone Obstacle Avoidance by Deep Reinforcement Learning", AI, 2(3), pp.366~380 (2021)
- R. Mukhamediev, "Review of Artificial Intelligence and Machine Learning Technologies : Classification, Restrictions, Opportunities and Challenges", Mathematics, 10(15), pp.2552~ (2022)
- L. Stumberg, "From Monocular SLAM to Autonomous Drone Exploration", 2017 European Conference on Mobile Robots (ECMR)
- H. Wang, "F-LOAM : Fast LiDAR Odometry and Mapping", 2021 IEEE, ~
- D-H. Ahn, "2D Indoor Map Building Scheme Using Ultrasonic Module", The Journal of Korean Institute of Communication and Information Sciences, 41(8), pp.986~994 (2016)
- R. Mur-Artal, "ORB-SLAM2 : An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras", IEEE Transactions on Robotics, 33(5), pp.1255~1262 (2017)
- M. C. Seo, "Obstacle Detection and Safe Landing Site Selection for Delivery Drones at Delivery Destinations without Prior Information", Journal of Auto-Vehicle Safety Association, 16(2), pp.20~26 (2024)