Journal of Aerospace System Engineering (항공우주시스템공학회지)

The Society for Aerospace System Engineering (항공우주시스템공학회)
권호 표지
DOI QR코드

DOI QR Code

Drone-mounted fruit recognition algorithm and harvesting mechanism for automatic fruit harvesting

자동 과일 수확을 위한 드론 탑재형 과일 인식 알고리즘 및 수확 메커니즘

  • Joo, Kiyoung (Smart Air Mobility, Korea Aerospace University) ;
  • Hwang, Bohyun (Department of Aerospace and mechanical engineering, Korea Aerospace University) ;
  • Lee, Sangmin (Smart Air Mobility, Korea Aerospace University) ;
  • Kim, Byungkyu (Smart Air Mobility, Korea Aerospace University) ;
  • Baek, Joong-Hwan (School of Electronics and Information Engineering, Korea Aerospace University)
  • 주기영 (한국항공대학교 스마트 항공 모빌리티 학과) ;
  • 황보현 (한국항공대학교 항공우주 및 기계공학부) ;
  • 이상민 (한국항공대학교 스마트 항공 모빌리티 학과) ;
  • 김병규 (한국항공대학교 스마트 항공 모빌리티 학과) ;
  • 백중환 (한국항공대학교 항공전자정보공학과)
  • Received : 2021.12.15
  • Accepted : 2022.02.04
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The role of drones has been expanded to various fields such as agriculture, construction, and logistics. In particular, agriculture drones are emerging as an effective alternative to solve the problem of labor shortage and reduce the input cost. In this study therefore, we proposed the fruit recognition algorithm and harvesting mechanism for fruit harvesting drone system that can safely harvest fruits at high positions. In the fruit recognition algorithm, we employ "You-Only-Look-Once" which is a deep learning-based object detection algorithm and verify its feasibility by establishing a virtual simulation environment. In addition, we propose the fruit harvesting mechanism which can be operated by a single driving motor. The rotational motion of the motor is converted into a linear motion by the scotch yoke, and the opened gripper moves forward, grips a fruit and rotates it for harvesting. The feasibility of the proposed mechanism is verified by performing Multi-body dynamics analysis.

최근 드론의 역할은 농업∙건설∙물류등의 다양한 영역으로 확대되고 있으며 특히 농업인구가 고령화되는 현 상황에 따라 드론은 노동력 부족 문제를 해결할 효과적인 대안으로 떠오르고 있다. 이에 본 논문에서는 농업 현장에서의 부족한 노동력을 보완하고 높은 위치의 과일도 안전하게 수확할 수 있는 드론 탑재형 과일수확 시스템을 제안한다. 과일수확 시스템은 과일인식 알고리즘과 과일수확 메커니즘으로 구성되어 있다. 과일인식 알고리즘은 딥러닝 기반의 객체탐지 알고리즘인 You Only Look Once를 사용하였고, 가상 시뮬레이션 환경을 구축하여 가능성을 검증하였다. 또한, 하나의 모터로 구동이 가능한 과일수확 메커니즘을 제안하였다. 모터의 회전운동을 기반으로 Scotch yoke을 구동시켜 선형운동으로 변환하여 gripper가 전개된 상태에서 과실에 접근 후 과실을 잡고 돌려 수확하는 메커니즘이다. 제안된 메커니즘에 대한 다물체동역학 해석을 수행하여 구동 가능성을 검증하였다.

Keywords

Acknowledgement

이 논문은 2020년도 한국항공대학교 교비지원 연구비와 한국연구재단의 4단계 두뇌한국21 사업(과제번호 : 5199990714521)의 지원을 받아 작성되었습니다.

References

  1. S. Jung, N.V. Sy, T. An, and B. Kim, "Design and test of cable based airborne capture mechanism for drone," Journal of Aerospace System Engineering, vol.14, No.3, pp. 10-16, 2020 https://doi.org/10.20910/JASE.2020.14.3.10
  2. J.Kim, "Mid to Long Term R&D Direction of UAV for Disaster & Public Safety," Journal of Aerospace System Engineering, vol.14, No.5, pp. 83-90, 2020 https://doi.org/10.20910/JASE.2020.14.5.83
  3. M. A. Khan, B. A. Alvi, and A. Safi, and I. U. Khan, "Drones for good in smart cities: a review," Proc. Int. Conf. Elect., Electron., Comput., Commun., Mech. Comput., pp. 1-6, January 2018.
  4. Y. H. Lee, S. J. Bae, W. Jung, J. Y. Cho, S. H. Hong, W. S. Nam, and J. Y. Kim, "Performance Evaluation Method for Facility Inspection and Diagnostic Technologies," Journal of the Society of Disaster Information, vol.16, pp 178-191, 2020. https://doi.org/10.15683/KOSDI.2020.3.31.178
  5. I. Bruns, "Drones for power line inspections," Retrieved December, Vol.1, 2020.
  6. Z. Zhang, C. Igathinathane, J. Li, H. Cen, Y. Lu, and P. Flores, "Technology progress in mechanical harvest of fresh market apples," Computers and Electronics in Agriculture, vol.175, pp 105606, 2020. https://doi.org/10.1016/j.compag.2020.105606
  7. W. Jia, Y. Zhang, J. Lian, Y. Zheng, D. Zhao, and C. Li, "Apple harvesting robot under information technology: A review," International Journal of Advanced Robotic Systems, vol.17, pp 1729881420925310, 2020.
  8. Tevel (tevel-tech.com)
  9. R. Joseph and A Farhadi. "YOLOv3: An Incremental Improvement." ArXiv. abs/1804.02767, 2018.
  10. N. Hani, P. Roy, and V. Isler, "MinneApple: A Benchmark Dataset for Apple Detection and Segmentation," IEEE Robotics and Automation Letters, pp. 1-1, 2020.
  11. S. Lee, and B. Kim. "Deep Learning based Real-time Fruit Detection System for Harvesting UAV," Proc. Conf. SASE., November 2021.
  12. K. Joo, B. Hwang, and B. Kim. "Development of Drone mechanism for fruit harvesting," Proc. Conf. SASE., November 2021.
  13. P. S. Valsange, "Design of helical coil compression spring: A review," International Journal of Engineering Research and Applications, vol.2, pp 513-522, 2012.
  14. M. Taktak, "Dynamic optimization design of a cylindrical helical spring," Applied acoustics, vol.77, pp 178-183, 2014. https://doi.org/10.1016/j.apacoust.2013.08.001