KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Robot Arm for Service Using Deep Learning and Sensors

딥러닝과 센서를 이용한 서비스용 로봇 팔의 설계

  • 박명숙 (한경대학교 전기전자제어공학과) ;
  • 김규태 (한경대학교 전기전자제어공학과) ;
  • 구모세 (한경대학교 전기전자제어공학과) ;
  • 고영준 (한경대학교 전기전자제어공학과) ;
  • 김상훈 (한경대학교 ICT로봇기계공학부)
  • Received : 2021.12.28
  • Accepted : 2022.01.29
  • Published : 2022.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the application of artificial intelligence technology, robots can provide efficient services in real life. Unlike industrial manipulators that do simple repetitive work, this study presented design methods of 6 degree of freedom robot arm and intelligent object search and movement methods for use alone or in collaboration with no place restrictions in the service robot field and verified performance. Using a depth camera and deep learning in the ROS environment of the embedded board included in the robot arm, the robot arm detects objects and moves to the object area through inverse kinematics analysis. In addition, when contacting an object, it was possible to accurately hold and move the object through the analysis of the force sensor value. To verify the performance of the manufactured robot arm, experiments were conducted on accurate positioning of objects through deep learning and image processing, motor control, and object separation, and finally robot arm was tested to separate various cups commonly used in cafes to check whether they actually operate.

인공지능 기술의 적용으로 로봇이 실생활에서 효율성 높은 서비스를 제공할 수 있게 되었다. 본 연구에서는 단순 반복적 작업을 하는 산업용 매니퓰레이터와 달리 서비스 로봇 분야에서 장소의 제약 없이 단독으로 또는 협업하여 사용하기 위한 6자유도 로봇 팔의 설계방법과 지능적인 물체 검출 및 이동 방법을 제시하고 성능을 검증하였다. 로봇 팔에 포함된 임베디드 보드의 ROS 환경에서 깊이 카메라와 딥러닝을 이용하여 로봇팔은 물체를 검출하고, 역기구학 해석을 통해 물체 영역으로 이동한다. 또한 물체와 접촉 시 힘센서 값의 분석을 통해 물체를 정확히 잡고 이동하는 동작이 가능하게 하였다. 제작한 로봇 팔에 대한 성능검증을 위하여 딥러닝과 영상처리를 통한 물체의 정확한 위치 산출, 모터 제어 및 물체 분리에 대한 실험을 하였으며, 실제 동작 여부를 확인하기 위하여 카페에서 흔히 사용하는 다양한 컵들을 분리하는 실험을 수행하였다.

Keywords

Acknowledgement

이 논문은 2020년도 정부(교육부)의 재원으로 한국연구재단 기초연구사업의 지원을 받아 수행된 연구임(No.2020R1F1A1067496).

References

  1. M. Yang, E. Yang, R. C. Zante, M. Post, and X. Liu, "Collaborative mobile industrial manipulator: A review of system architecture and applications," In 2019 25th International Conference on Automation and Computing (ICAC), IEEE, pp.1-6, 2019.
  2. S. U. Jeon and B. J. Jeong, "Collaborative robot trends," in Proceedings of Korean Institute of Electrical Engineers, Vol.68, No.1, pp.22-26, 2019.
  3. Korea Institute for Robot Industry Advancement, "Robot Industry Policy and Trend," Sep. 2021.
  4. D. Belanche, L. V. Casalo, C. Flavian, and J. Schepers, "Service robot implementation: A theoretical framework and research agenda," The Service Industries Journal, Vol.40, No.3-4, pp.203-225, 2020. https://doi.org/10.1080/02642069.2019.1672666
  5. A. Roshanianfard and N. Noguchi, "Development of a 5DOF robotic arm (RAVebots-1) applied to heavy products harvesting," IFAC-PapersOnLine, Vol.49, No.16, pp.155-160, 2016. https://doi.org/10.1016/j.ifacol.2016.10.029
  6. J. I. Kang, H. S. Choi, B. H. Jun, D. H. Ji, J. Y. Oh, and J. Y. Kim, "Design and control of robot arm for inspection and rescue operations," Journal of Institute of Control, Robotics and Systems, Vol.22, No.11, pp.888-894, 2016. https://doi.org/10.5302/J.ICROS.2016.16.0161
  7. H. Kim, D. Park, T. Choi, H. Do, J. Kyung, and C. Park, "Design of high payload dual arm robot with replaceable forearm module for multiple tasks: Human rescue and object handling," The Journal of Korea Robotics Society, Vol.12, No.4, pp.441-447, 2017. https://doi.org/10.7746/jkros.2017.12.4.441
  8. J. S. Yoon, C. H. Kwak, Y. H. Kim W. H. Kim, and S. H. Ok, "Implementation of a table tennis robot using monocular camera-based 3D object recognition method and path planning for 6-Axis manipulator," The Journal of Korean Institute of Information Technology, Vol.16, No.8, pp.35-44, 2018.
  9. S. Mori, K. Tanaka, S. Nishikawa, R. Niiyama, and Y. Kuniyoshi, "High-speed and lightweight humanoid robot arm for a skillful badminton robot," IEEE Robotics and Automation Letters, Vol.3, No.3, pp.1727-1734, 2018. https://doi.org/10.1109/lra.2018.2803207
  10. W. Wang, P. Wang, Y. Zhao, Y. Zhu and J. Zhao, "Kinematics and workspace analysis of a robotic arm for medical delivery robots," In E3S Web of Conferences, Vol.257, EDP Sciences, 2021.
  11. K. Lee, S. Naa, J. Park, K. Ann, and C. Lee, "Development of a dual-arm service robot using stereo vision and 6-Axis manipulators," The Journal of Korean Society of Manufacturing Technology Engineers, Vol.27, No.3, pp.271-277, 2018. https://doi.org/10.7735/ksmte.2018.27.3.271
  12. D. Ko, J. Lee, J. Kim, B. Park, and C. Lee, "Integration of mobile robot and manipulator using the ROS," The Journal of Korean Society of Manufacturing Technology Engineers, Vol.29, No.3, pp.182-188, 2020. https://doi.org/10.7735/ksmte.2020.29.3.182
  13. Y. Chunxin, S. Chumkamon, and E. Hayashi, "Robot assisting water serving to disabilities by voice control," In Proceedings of International Conference on Artificial Life & Robotics, Vol.26, pp.457-460, 2021.
  14. K. T. Kim, M. S. Koo, Y. J. Ko, M. S. Park, and S. H. Kim, "The design of 6-axis robot arm with intelligent object detection and object movement function," Proceedings of the Korea Information Processing Society Conference, Nov. 04, pp.417-420, 2021.
  15. J. H. Ha, Y. D. Joo, D. H. Kim, J. Y. Kim, and H. S. Choi, "A study on design, experiment control of the waterproof robot arm," Journal of the Korean Society of Marine Engineering, Vol.38, No.6, pp.648-657, 2014. https://doi.org/10.5916/jkosme.2014.38.6.648
  16. I. Sucan and S. Chitta, MoveIt, [Internet], https://moveit.ros.org/.
  17. GAZEBO [Internet], http://gazebosim.org/.
  18. J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," in Computer Vision and Pattern Recognition, Berlin/Heidelberg, Germany: Springer, pp.1804-2767, 2018.
  19. YOLO: Real-Time Object Detection [Internet], https://pjreddie.com/darknet/yolo/.
  20. YOLO ROS: Real-Time Object Detection for ROS [Internet], https://github.com/leggedrobotics/darknet_ros.
  21. darknet_ros_3d [Internet], https://github.com/IntelligentRoboticsLabs/gb_visual_detection_3d.