딥러닝 기반 자율주행 계단 등반 물품운송 로봇 개발

Development of Stair Climbing Robot for Delivery Based on Deep Learning

  • 문기일 (한국기술교육대학교 메카트로닉스공학부) ;
  • 이승현 (한국기술교육대학교 메카트로닉스공학부) ;
  • 추정필 (한국기술교육대학교 메카트로닉스공학부) ;
  • 오연우 (한국기술교육대학교 메카트로닉스공학부) ;
  • 이상순 (한국기술교육대학교 메카트로닉스공학부)
  • Mun, Gi-Il (School of Mechatronics Engineering, Korea University of Technology and Education) ;
  • Lee, Seung-Hyeon (School of Mechatronics Engineering, Korea University of Technology and Education) ;
  • Choo, Jeong-Pil (School of Mechatronics Engineering, Korea University of Technology and Education) ;
  • Oh, Yeon-U (School of Mechatronics Engineering, Korea University of Technology and Education) ;
  • Lee, Sang-Soon (School of Mechatronics Engineering, Korea University of Technology and Education)
  • 투고 : 2022.12.02
  • 심사 : 2022.12.16
  • 발행 : 2022.12.31

초록

This paper deals with the development of a deep-learning-based robot that recognizes various types of stairs and performs a mission to go up to the target floor. The overall motion sequence of the robot is performed based on the ROS robot operating system, and it is possible to detect the shape of the stairs required to implement the motion sequence through rapid object recognition through YOLOv4 and Cuda acceleration calculations. Using the ROS operating system installed in Jetson Nano, a system was built to support communication between Arduino DUE and OpenCM 9.04 with heterogeneous hardware and to control the movement of the robot by aligning the received sensors and data. In addition, the web server for robot control was manufactured as ROS web server, and flow chart and basic ROS communication were designed to enable control through computer and smartphone through message passing.

키워드

과제정보

본 연구는 한국기술교육대학교의 지원에 의해 이루어졌음.

참고문헌

  1. H.G. Lee and S. S. Lee," Development of Unmanned Cleaning Robot for Photovoltaic Panels", Journal of Semiconductor & Display Technology, Vol.18, No.3, pp.144-149, 2019.
  2. S.P. Park, S. Lee, H. Lee and S. S. Lee," Development of Unmanned Cleaning Robot for Floating Photovoltaic Panels", Journal of Semiconductor & Display Technology, Vol.19, No.3, pp.130-135, 2020.
  3. G.G. Park, J.Y. Kim, J.Y. Keum and S. S. Lee, "Development of Runway Cleaning Robot Based on Deep Learning", Journal of Semiconductor & Display Technology, Vol.20, No.3, pp.140-145, 2021.
  4. D.G. Choi, S.W. Lee, D.Y. Jang, N.S. Kim, H.S. Hong, J.W. Kim Jong-won, "Development of Driving Mechanism Using Locker Bogie and Caterpillar", Proceedings of the Korean Society of Precision Engineers Conference, pp. 425-426. 2011.
  5. J. W. Park, P.K. Kim, J. W. Kim, C.G. Hong, "Methodology of generating automatic gun detection model using YOLOv4", Journal of the Korean Society of Information Sciences, pp. 1325-1327, 2020.
  6. H. Liu, K. Fan, Q. Ouyang, N. Li N, "Real-Time Small Drones Detection Based on Pruned YOLOv4", Sensors. Vol. 21, p. 3374. 2021 https://doi.org/10.3390/s21103374
  7. Y.W.Yao and S. W. Jing. "Surface Defect Detection of Aircraft Flared Duct Based on Improved YOLOv4 Algorithm" 4th International Conference on Signal Processing and Machine Learning, pp. 26-32, 2021.
  8. B. Dang Ba, S.J. Baek, A.H. Kim, Y.R. Choi, J.H. Lim, J.W. Kim, "Development of ROS-based simulator for wheelchair-type service robot", Journal of the Korean Institute of Intelligent Systems, Vol. 30, pp. 214-219, 2020. https://doi.org/10.5391/jkiis.2020.30.3.214
  9. J. W. Han, S. H. Lee, S. S. Lee, Y. E. Cho, and C. G. Lee, "A Technique for Accurate Module Execution Time Analysis of ROS Networks", Proceedings of the Korean Society of Information Sciences, pp. 1468-1470, 2020.