DOI QR코드

DOI QR Code

Development of Path-Finding System for Humanoid Robots Based on Image Pattern Recognition

패턴 인식 알고리즘 기반 휴머노이드 경로 시스템 개발

  • 박현 (연세대학교 전산학과 정보통신망 연구실) ;
  • 은진혁 (연세대학교) ;
  • 박혜련 (연세대학교) ;
  • 석정봉 (연세대학교 컴퓨터정보통신공학부)
  • Received : 2012.03.31
  • Accepted : 2012.09.13
  • Published : 2012.10.30

Abstract

In this paper, we develop a pattern recognition algorithm applied to a humanoid robot which is exploited as a guide for visually handicapped persons to find a desired path to their destinations. Behavior primitives of a humanoid robot are defined, and Canny's edge detection algorithm is employed to extract the pattern and color of the paving blocks that especially devised for visually handicapped persons. Based on these, an efficient path finding algorithm is developed and implemented on a humanoid robot, running on an embedded linux operating system equipped with a video camera. The performance of our algorithm is experimentally examined in terms of the response time and the pattern recognition ratio. In order to validate our algorithm in various realistic environments, the experiments are repeatedly performed by changing the tilt of paving blocks and the brightness in surrounding area. The results show that our algorithm performs sufficiently well to be exploited as a path finding system for visually handicapped persons.

본 논문에서는 패턴 인식 알고리즘을 기반으로 인간 형태를 가진 휴머노이드 로봇의 보행 동작을 제어하는 경로 인식 시스템을 개발하였다. 휴머노이드 로봇이 효과적인 작업 수행을 할 수 있도록 행동 프리미티브를 정의 하였으며, Canny 에지 검출 알고리즘을 적용한 보도 블록의 패턴 및 색상 추출, 이를 기반으로 한 이동 방향을 인식하는 알고리즘 제안하고, 리눅스 운영체제와 영상 카메라가 장착된 소형 휴머노이드 임베디드 시스템에 구현하였다. 제안 알고리즘의 성능 실험을 휴머노이드 로봇의 동작 속도 및 인식율에 관점에서 수행하였으며, 다양한 현실 환경을 반영하기 위해 경사도 및 조도 변화를 적용하였다. 실험 결과 제안 알고리즘은 다양한 환경에서 시각 장애인의 길안내 도우미 로봇으로서 적절한 수준에서 반응함을 확인하였다.

Keywords

References

  1. Su-Hee Noh, Doo-Young Na and Yong-Tae Kim, "Walking Stabilization Using Locomoti on Primitive for Humanoid Robots," Korean Institute of Intelligent Systems(KIIS) Spring Conference 2009, Vol. 19, No. 1, pp. 125-1 26, Korea, 2009.
  2. Y. Sakagami, R. Watanabe, C. Aoyarna, S. Matsunaga, N. Higaki and K. Fujimura, "The inteligent ASIMO : System overvier and integration," in Proc. 2002 IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems, pp. 2478-2483, Lausanne, Switzerland, Oct. 2002.
  3. Riezenman, M.J, "Robots stand on own two feet," Spectrum IEEE, 39(8), pp. 24-25, Aug. 2002.
  4. Su-Hee Noh, and Yong-Tae Kim, "Behavior Planning for Humanoid Robot Using Behavi or Primitive," J. KIIS 2009, Vol 19, No 1, pp. 108-114, 2009.
  5. Jung-Shik Kong, and Jin-Geol Kim, "A Study on the Joint Controller for a Humanoid Robot based on Genetic Algorithm," J. KIIS 2007, Vol 17, No 5, pp. 640-647, 2007. https://doi.org/10.5391/JKIIS.2007.17.5.640
  6. K. Hauser, T. Bretl, and J-C Latombe, "Using motion primitives in proba-bilistic sample-based planning for humanoid robots," Workshop on the Algorithmic Foundations of Robotics(WAFR), pp. 1-16, 2006.
  7. J. Kuffner, K. Nishiwaki, S. Kagami, M. Inaba and H. Inoue, "Motion planning for humanoid robots," International Symposium on Robotic Research, pp. 1-9, 2003.
  8. Joong-Yeub Lee, "Blinded Use of Smart Walk Guide System Design," J. Digital Interaction Design, Vol.10, No.1, pp. 193-203, 2011.
  9. Jin-Hee Lee, Sukhyun Lim, Eun-Seok Lee, and Byeong-Seok Shin, "An Outdoor Navigation System for the Visually Impaired Persons incorporating GPS and Ultrasonic Sensors," J. Korean Institute of Information Scientists and Engineers, Vol. 36, No. 6, pp. 462- 470, 2009.
  10. Sang-Il Hahn, Jong-Su Kim, Jin-Woo Ahn, and Hyung-Tai Cha, "Information System for Blind People using Smartphone," in Proc. KIIS Spring Conf 2010, Vol. 20, No. 1, pp. 63-66, Korea, 2010.
  11. J. Canny, "A computational approach to edge detection," IEEE Transactions on patten analysis and machine intellgence, Vol Pami-8. No 6, pp. 679-698, November, 1986. https://doi.org/10.1109/TPAMI.1986.4767851
  12. Raised block regulations(Korea National Institute for Special Education), Retrieved June., 1, 2012, from http://edu.knise.kr/jsp/lesionsee/facility/facility_braille.jsp?main=4&sub=8.
  13. H-MF-17AI Robot(Hibus), Retrieved June., 1, 2012, from http://edu.hybus.net/goods/goods_detail.asp?idx=38&ctg_code=01-5&intPageSize=12&schword=&page=1&goods_company=&sort=.
  14. Yong-Tae Kim, and Han-jeong Kim, "Motion Planning for Legged Robots Using Locomotion Primitives in the 3D Workspace," J. Korea Robotics Society, Vol. 2, No. 3, pp. 275-281, 2007.