Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Autonomous Drone Navigation in the hallway using Convolution Neural Network

실내 복도환경에서의 컨벌루션 신경망을 이용한 드론의 자율주행 연구

  • Jo, Jeong Won (School of Computer Inf. & Comm., Kunsan National University) ;
  • Lee, Min Hye (School of Computer Inf. & Comm., Kunsan National University) ;
  • Nam, Kwang Woo (School of Computer Inf. & Comm., Kunsan National University) ;
  • Lee, Chang Woo (School of Computer Inf. & Comm., Kunsan National University)
  • Received : 2019.06.11
  • Accepted : 2019.07.08
  • Published : 2019.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Autonomous driving of drone indoor must move along a narrow path and overcome other factors such as lighting, topographic characteristics, obstacles. In addition, it is difficult to operate the drone in the hallway because of insufficient texture and the lack of its diversity comparing with the complicated environment. In this paper, we study an autonomous drone navigation using Convolution Neural Network(CNN) in indoor environment. The proposed method receives an image from the front camera of the drone and then steers the drone by predicting the next path based on the image. As a result of a total of 38 autonomous drone navigation tests, it was confirmed that a drone was successfully navigating in the indoor environment by the proposed method without hitting the walls or doors in the hallway.

실내 자율 주행은 실외 환경에서의 자율 주행과는 다른 환경적인 요소가 주어진다. 폐쇄된 환경에서 좁은 길을 따라 주행해야 하며, 불규칙한 조명, 계단과 같은 지형의 특성, 바닥에 산재한 장애물 등 실외 환경과 다른 요소를 극복해야 한다. 또한 실내 복도에서의 주행은 텍스처가 유사하거나 다양성이 적은 환경의 경우 복잡한 환경에 비해 인식에 어려움이 있다. 본 논문에서는 다양성이 적은 실내 복도환경에서의 컨벌루션 신경망(CNN)을 이용한 자율 주행 드론을 연구한다. 설계한 신경망은 드론의 전면 카메라로부터 이미지를 받아온 후, 그 이미지를 바탕으로 다음 경로를 예측하여 드론을 조향한다. 총 38번의 주행 테스트 결과, 복도 주변의 벽이나 문에 부딪히지 않고 직선 구간을 완주하여 다양성이 적은 실내 환경에서의 주행 성능을 확인할 수 있었다.

Keywords

References

  1. S. W. Lim, S. M. Cho, G. M. Park, "Integrated Video Analytics for Drone Captured Video", Journal of Broadcast Engineering, vol. 24, no. 2, March, 2019.
  2. H. D. Yoo, "Drone-delivery Using Autonomous Mobility: An Innovative Approach to Future Last-mile Delivery Problems", in Proceeding of 2018 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Thailand, 2018
  3. N. Smolyanskiy, A. Kamenev, J. Smith, S. Birchfield, "Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awareness", in Proceeding of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems(IROS), pp.4241-4247, 2017
  4. A. Giusti, J. Guzzi, D. C. Ciresan, F.- L. He, J. P. Rodriguez, F. Fontana, M. Faessler, C. Forster, J. Schmidhuber, G. Di Caro, D. Scaramuzza, L. M. Gambardella. "A machine learning approach to visual perception of forest trails for mobile robot", 2015
  5. Dhiraj Gandhi, Lerrel Pinto and Abhinav Gupta, "Learning to Fly by Crashing", in Proceeding of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Canada, 2017
  6. K. He, X. Zhang, S. Ren, J. Sun, "Deep Residual Learning for Image Recognition", in Proceeding of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), USA, 2016
  7. D. W. Kim, W. J. Kang, Y. P. Koo, J. H. Bang, K. H. Son, Hostallero David,, S. E. Yoon, H. H. Yeo, J. H. Ha, N. S. Seo, D. S. Han, Y. Yi, "AI-Based Drone Object Tracking System: Design and Implementation", Journal of Korea Institute of Communication and Information Sciences, vol. 42, No. 12, pp. 2391-2401, December, 2017 https://doi.org/10.7840/kics.2017.42.12.2391
  8. H. J. Lee, S. S. Hwang, "Obstacle Avoidance Algorithm for Indoor Autonomous Drone Using IR Sensor and Forward Image Information", Journal of Institute of Control, Robotics and Systems, vol.23, no. 9, pp. 803-809, September, 2017 https://doi.org/10.5302/J.ICROS.2017.17.0076
  9. J. Y. Yang, "Development of Reinforcement Learningbased Obstacle Avoidance toward Autonomous Mobile Robots for an Industrial Environment", Journal of the Korea Contents Association, vol. 19, no. 3, pp. 72-79, March, 2019. https://doi.org/10.5392/JKCA.2019.19.03.072
  10. A. R. Song, Y. G. Kim, "Deep Learning-based Hyper -spectral Image Classification with Application to Environmental Geographic Information Systems", Journal of the Korean Society of Remote Sensing, vol. 33, no. 6-2, pp. 1061-1073, December, 2017.
  11. pypi, afg984 [Internet], Available: https://pypi.org/project/pyardrone
  12. OpenCV [Internet], Available: https://opencv.org/
  13. tensorflow [Internet], Available: https://www.tensorflow.org/?hl=ko
  14. Parrot [Internet], Available https://www.parrot.com/global/drones/parrot-ardrone-20-elite-edition#parrot-ardrone-20-elite-edition