Browse > Article
http://dx.doi.org/10.12673/jant.2021.25.6.485

Vision-based Obstacle State Estimation and Collision Prediction using LSM and CPA for UAV Autonomous Landing  

Seongbong Lee (Department of Aeronautical Systems Engineering, Hanseo University)
Cheonman Park (Department of Aeronautical Systems Engineering, Hanseo University)
Hyeji Kim (Department of Aeronautical Systems Engineering, Hanseo University)
Dongjin Lee (Department of Aeronautical Systems Engineering, Hanseo University)
Publication Information
Journal of Advanced Navigation Technology / v.25, no.6, 2021 , pp. 485-492 More about this Journal
Abstract
Vision-based autonomous precision landing technology for UAVs requires precise position estimation and landing guidance technology. Also, for safe landing, it must be designed to determine the safety of the landing point against ground obstacles and to guide the landing only when the safety is ensured. In this paper, we proposes vision-based navigation, and algorithms for determining the safety of landing point to perform autonomous precision landings. To perform vision-based navigation, CNN technology is used to detect landing pad and the detection information is used to derive an integrated navigation solution. In addition, design and apply Kalman filters to improve position estimation performance. In order to determine the safety of the landing point, we perform the obstacle detection and position estimation in the same manner, and estimate the speed of the obstacle using LSM. The collision or not with the obstacle is determined based on the CPA calculated by using the estimated state of the obstacle. Finally, we perform flight test to verify the proposed algorithm.
Keywords
Autonomous Precision Landing; Collision Prediction; Closest Point of Approach; Least-Squares Method; State Estimation;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Oh, S. M., Johnson, E. "Relative motion estimation for vision-based formation flight using unscented Kalman filter," In AIAA guidance, navigation and control conference and exhibit, August. 2007.
2 J. S. Kim, Driving environment modeling techniqure using CNN-based object detection ans SLAM, Master dissertation, Soonchunhyang University, Asan, Dec. 2020.
3 M. J. Go, Detecting vehicles that are illegally driving on road shoulders using Faster R-CNN, Master dissertation, Yonsei University, Seoul, Jun. 2017.
4 H. Yu, R. Hong, X. Huang and Z. Wang, "Obstacle Detection with Deep Convolutional Neural Network," in 2013 Sixth International Symposium on Computational Intelligence and Design, Hangzhou, pp. 265-268, Oct. 2013.
5 S. W. Jung, J. M. Koo, K. Y. Jung, H. J. Kim, and H. Myung, "Vision-based Autonomous Landing System of an Unmanned Aerial Vehicle on a Moving Vehicle," The Journal of Korea Robotics Society, Vol. 11, No. 4, pp. 262-269, Nov. 2016.   DOI
6 G. B. Kim, S. H. Song, and K. J. Yoon, "Design and Fabrication of Multi-rotor system for Vision based Autonomous Landing," The Journal of the Institute of Internet, Broadcasting and Communication, Vol. 12, No. 6, pp. 141-146, Dec. 2012.   DOI
7 Mac, Thi Thoa, Cosmin Copot, and Clara M. Ionescu. "Detection and Estimation of Moving obstacles for a UAV," IFAC-PapersOnLine 52.1 pp.22-27, 2019.   DOI
8 P. Misans, and M. Terauds, "CW doppler radar based land vehicle speed measurement algorithm using zero crossing and least squares method," in 2012 13th Biennial Baltic Electronics Conference, Tallinn, pp. 161-164, Oct. 2012.
9 C. Jiang, S. Chen, Y. Chen, J. Shen, D. Liu and Y. Bo, "Superior Position Estimation Based on Optimization in GNSS," IEEE Communications Letters, Vol. 25, No. 2, pp. 479-483, Feb. 2021.   DOI
10 S. H. Lee, J. M. Song, and J. S. Bae, "Vision-based Navigation for VTOL Unmanned Aerial Vehicle Landing," The Journal of the Korea Institute of Military Science and Technology, Vol. 18, No. 3, pp. 226-233, Jun. 2015.   DOI
11 H. J. Choi, Reactive Collision Avoidance of Unmanned Aerial Vehicles Using Vision Sensors, Ph.D. dissertation, Seoul National University, Seoul, Jul. 2014.
12 J. Y. Hwang, S. Y. Lee, H. K. Kim, H. J. Lee, and D. G. Hong, "Development of Collision Prediction Model for Pedestrian Protection," in The Korean Society Of Automotive Engineers 2014 Conference Proceedingsdings, Busan, pp. 745-746, May. 2014.