Trajectory correction based on shape peculiarity in direct teaching manipulator

详细信息    查看全文

• 作者：Taeyong Choi (1)
  Chanhun Park (1)
  Hyunmin Do (1)
  Dongil Park (1)
  Jinho Kyung (1)
  Gwangjo Chung (1)
  
• 关键词：Direct teaching manipulator ; feature point extraction ; human ; robot cooperation ; trajectory correction
• 刊名：International Journal of Control, Automation and Systems
• 出版年：2013
• 出版时间：October 2013
• 年：2013
• 卷：11
• 期：5
• 页码：1009-1017
• 全文大小：2267KB
• 参考文献：1. Y. F. Yong, J. A. Gleave, J. L. Green, and M. C. Bonney, 鈥淥ff-line programming of robots,鈥? / Handbook of Industrial Robotics, S. Y. Nof, Ed. Wiley, 1985, pp. 366鈥?80.
  2. Y. Shamash, Y. Yang, and Z. Roth, 鈥淭eaching a robot,鈥? / International Encyclopedia of robotics: Applications and Automation, R. C. Dorf, Ed., Wiley, 1988, pp. 1689鈥?701. CrossRef
  3. C. H. Park, J. H. Kyung, D. I. Park, K. T. Park, D. H. Kim, and D. G. Gweon, 鈥淒irect teaching algorithm for a manipulator in a constraint condition using the teaching force shaping method,鈥? / Advanced Robotics, vol. 24, no. 8鈥?, pp. 1365鈥?384, 2010. CrossRef
  4. S. Jeong, Y. Nakabo, T. Ogure, and Y. Yamada, 鈥淒evelopment of a direct teaching system for a cooperative cell-production robot considering safety and operability,鈥? / Proc. IEEE Int. Conf. Intelligent Robots and Systems, pp. 5339鈥?344, October 2009.
  5. Y. Maeda, T. Ushioda, and S. Makita, 鈥淓asy robot programming for industrial manipulators by manual volume sweeping,鈥? / Proc. IEEE Int. Conf. Robotics and Automation, pp. 2234鈥?239, May 2008.
  6. A. Stopp, S. Horstmann, S. Kristensen, and F. Lohnert, 鈥淭oward interactive learning for manufacturing assistants,鈥? / IEEE Trans. on Industrial Electronics, vol. 50, no. 4, pp. 705鈥?07, 2003. CrossRef
  7. G. Grunwald, G. Schreiber, A. Albu-Schaffer, and G. Hirzinger, 鈥淧rogramming by touch: the different way of human-robot interaction,鈥? / IEEE Trans. on Industrial Electronics, vol. 50, no. 4, pp. 659鈥?66, 2003. CrossRef
  8. S. Cho and S. Jo, 鈥淚ncremental motion learning through kinesthetic teaching and new motion production from learned motions by a humanoid robot,鈥? / International Journal of Control, Automation, and Systems, vol. 10, no. 1, pp. 126鈥?35, 2012. CrossRef
  9. D. I. Park, C. H. Park, and J. H. Kyung, 鈥淪ignal processing of direct teaching data for human-robot cooperation,鈥? / Proc. Int. Symposium on Industrial Electronics, pp. 1956鈥?960, 2010.
  10. T. C. Phung, Y. S. Ihn, J. C. Koo, and H. R. Choi, 鈥淎n enhanced edge tracking method using a low resolution tactile sensor,鈥? / International Journal of Control, Automation, and Systems, vol. 8, no. 2, pp. 462鈥?67, 2010. CrossRef
  11. T. M. Sezgin and R. Davis, 鈥淪ketch interpretation using multiscale models of temporal patterns,鈥? / IEEE Journal of Computer Graphics and Applications, vol. 27, no. 1, pp. 28鈥?7, 2007. CrossRef
  12. K. Yang, Z. Li, and J. Ye, 鈥淔reely-drawn sketches interpretation using SVMs-chain modeling,鈥? / Engineering Application of Artificial Intelligence, vol. 25, no. 2, pp. 392鈥?03, 2012. CrossRef
  13. S. Liu and H. Asada, 鈥淎daptive control of deburring robots based on human demonstration data,鈥? / Proc. Int. Conf. on Industrial Electronics, Control, Instrumentation, and Automation, vol. 2, pp. 946鈥?52, November 1992 CrossRef
  14. U. Ramer, 鈥淎n iterative procedure for the polygonal approximation of plane curves,鈥? / Computer Graphics and Image Processing, vol. 1, no. 3, pp. 244鈥?56, 1972. CrossRef
  15. D. Douglas and T. Peucker, 鈥淎lgorithm for the reduction of the number of points required to represent a digitized line of its caricature,鈥? / The Canadian Cartographer, vol. 10, no. 2, pp. 112鈥?22, 1973. CrossRef
  16. J. Hershberger and J. Snoeyink, 鈥淪peeding up the Douglas-Peucker line-simplification algorithm,鈥? / Proc. 5th Symp. on Data Handling, pp. 134鈥?43, 1992.
  
• 作者单位：Taeyong Choi (1)
  Chanhun Park (1)
  Hyunmin Do (1)
  Dongil Park (1)
  Jinho Kyung (1)
  Gwangjo Chung (1)
  
  1. Department of Robotics and Mechatronics, Korea Institute of Machinery & Materials (KIMM), Daejeon, 305-343, Korea
  
• ISSN：2005-4092

文摘

Direct teaching of an industrial robot is a novel technique to easily teach manipulators. However, the human-hand generated teaching data can have significant noise errors ranging from low to high frequency. To use the teaching data, a post-processing method to correct the teaching trajectory is required. Currently there is no suitable way to correct the direct teaching trajectory other than conventional simple-line smoothing methods. Here, a novel shape-based trajectory correction method to rebuild the teaching data with the curvature and velocity information is proposed. The proposed method is tested on three real objects using a physical direct-teaching manipulator.