Advertisement

Learning Robot Behaviour and Skills Based on Human Demonstration and Advice: The Machine Learning Paradigm

  • R. Dillmann
  • O. Rogalla
  • M. Ehrenmann
  • R. Zöliner
  • M. Bordegoni

Abstract

Service robots require easy programming methods allowing the unexperienced human user to easily integrate motion and perception skills or complex problem solving strategies. To achieve this goal, robots should learn from operators how and what to do considering hard- and software constraints. Various approaches modelling the man-machine skill transfer have been proposed. Systems following the Programming by Demonstration (PbD) paradigm that were developed within the last decade are getting closer to this goal. However, most of these systems lack the possibility for the user to supervise and influence the process of program generation after the initial demonstration was performed. In this paper a principle learning methodology is discussed, which allows to transfer human skills and to supervise the learning process including subsymbolic and symbolic task knowledge. Here, several existing approaches will be discussed and compared to each other. Moreover, a system approach is presented, integrating the overall process of skill transfer from a human to a robotic manipulation system. One major goal is to modify information gained by the demonstration in that way that different target systems are supported. The resulting PbD-system yields towards a hybrid learning approach in robotics to support natural programming based on human demonstrations and user advice.

Keywords

Target System Service Robot Manipulation Task Skill Transfer User Demonstration 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    E. W. Aboaf, S. M. Drucker, and C. G. Atkeson. Task-level robot learning: Juggling a tennis ball more accurately. In IEEE International Conference on Robotics and Automation, volume 3, pages 1290–1295, Scottsdale, 1989.Google Scholar
  2. [2]
    H. Asada and S. Liu. Transfer of human skills to neural net robot controllers. In IEEE International Conference on Robotics and Automation, pages 2442–2448, Sacramento, 1991.Google Scholar
  3. [3]
    H. Friedrich, J. Holle, and R. Dillmann. Interactive generation of flexible robot programs. In IEEE International Conference on Robotics and Automation, Leuven, B, 1998. submitted.Google Scholar
  4. [4]
    Sing Bang Kang and Katsushi Ikeuchi. Toward automatic robot instruction from perception — mapping human grasps to manipulator grasps. IEEE Transactions on Robotics and Automation, 13 (1), February 1997.Google Scholar
  5. [5]
    M. Kaiser. Interaktive Akquisition elementarer Roboterfähigkeiten. PhD thesis, Universität Karlsruhe, Fakultät für Informatik, 1996. Erschienen im Infix-Verlag, St. Augustin (DISKI 153 ).Google Scholar
  6. [6]
    R. Koeppe and G. Hirzinger. Learning compliant motions by task-demonstration in virtual environments. In Fourth International Symposium on Experimental Robotics, 1995.Google Scholar
  7. [7]
    Y. Kuniyoshi, M. Inaba, and H. Inoue. Learning by watching: Extracting reusable task knowledge from visual observation of human performance. IEEE Transactions on Robotics and Automation, 10 (6): 799–822, 1994.CrossRefGoogle Scholar
  8. [8]
    A. I. Cypher. Watch what I do — Programming by Demonstration. MIT Press, Cambridge, Massachusetts, 1993.Google Scholar
  9. [9]
    Friedrich H., editor. Proceedings of the Programming by Demonstration Workshop at the International Conference on Machine Learning. Tahoe City, California, July 1995.Google Scholar
  10. [10]
    L. A. Hermens and J. C. Schlimmer. A machine-learning apprentice for the completion of repetitive forms. IEEE Expert, pages 28–33, Februar 1994.Google Scholar
  11. [11]
    A. M. Segre. Machine Learning of Robot Assembly Plans. Kluwer Academic Publishers, 1989.Google Scholar
  12. [12]
    M. Inaba and H. Inoue. Robotics Research 5, chapter Vision based robot programming, pages 129–136. MIT Press, Cambridge, MA, USA, 1990.Google Scholar
  13. [13]
    S. B. Kang. Robot Instruction by Human Demonstration. PhD thesis, Carnegie Mellon University, Pittsburgh, PA, 1994.Google Scholar
  14. [14]
    C. P. Tung and A. C. Kak. Automatic learning of assembly tasks using a dataglove system. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’95), volume 1, pages 1–8, Pittsburgh, PA, USA, Aug. 5–9 1995.Google Scholar
  15. [15]
    Sing Bing Kang and Katsushi Ikeuchi. Determination of motion breakpoints in a task sequence from human hand motion. In Proceedings of the IEEE International Conference on Robotics and Automation (ICORA ‘84), volume 1, pages 551–556, San Diego, CA, USA, 1994.Google Scholar
  16. [16]
    S. K. Tso and K. P. Liu. Visual programming for capturing of human manipulation skill. In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 42–48, Yokohama, 1993.Google Scholar
  17. [17]
    A. Ude and R. Dillmann. Robot motion specification: A vision-based approach. Surveys on Mathematics for Industry, 5, 1995.Google Scholar
  18. [18]
    K. Ikeuchi, M. Kawade, and T. Suehiro. Assembly task recognition with planar, curved and mechanical contacts. In IEEE International Conference on Robotics and Automation, volume 2, pages 688–694, Atlanta, 1993.CrossRefGoogle Scholar
  19. [19]
    Y. Kuniyoshi, M. Inaba, and H. Inoue. Seeing, understanding, and doing human task. In IEEE International Conference on Robotics and Automation, pages 2 – 9, Nizza, 1992.Google Scholar
  20. [20]
    Makoto Kaneko. Scale-dependent grasps. In Eighth international symposium of Robotics Research, Hayama, Japan, October 1997.Google Scholar
  21. [21]
    Y-C. Lee, C. Hwang, and Y.-P. Shih. A combined approach to fuzzy model identification. IEEE Transactions on Systems, Man, and Cybernetics, 24 (5): 736–744, 1994.MathSciNetCrossRefGoogle Scholar
  22. [22]
    Katsushi Ikeuchi and Takashi Suehiro. Assembly task recognition using face-contact relations. In Proceedings of the IEEE International Conference on Robotics and Automation (ICORA’92), volume 3, pages 2171–2177, Nice, France, 1992.CrossRefGoogle Scholar
  23. [23]
    George V. Paul and Katsushi Ikeuchi. Modelling planar assembly tasks: Representation and recognition. In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS’95), volume 1, pages 17–22, Pittsburgh, PA, USA, Aug. 5–9 1995.Google Scholar
  24. [24]
    Katsushi Ikeuchi and Sing Bang Kang. Programming grasping tasks by human demonstration. Journal of the Robotics Society of Japan, 13 (5), July 1995.Google Scholar
  25. [25]
    Sing Bang Kang and Katsushi Ikeuchi Toward automatic robot instruction from perception — recognizing a grasp from observation. IEEE Transactions on Robotics and Automation, 9(4), August 1993.Google Scholar
  26. [26]
    J. Kreuziger and M. Hauser. The application of symbolic learning techniques in a robot manipulation system. In Workshop on Learning Robots, Vienna, March 1993.Google Scholar
  27. [27]
    Virtual Technologies Inc., Palo Alto, Kalifornien, USA. CyberGlove™ User’s Manual, Oktober 1995.Google Scholar
  28. [28]
    Polhemus, P.O. Box 560, Colchester, Vermont 05446, USA. 3SPACE™ FASTRAK™ User’s Manual, November 1993.Google Scholar
  29. [29]
    M. Ehrenmann, P. Steinhaus, and R. Dillmann. A multisensor system for observation of user actions in programing by demonstration. hi Proceedings of Multi Sensor Fusion and Integration (MFI), volume 1, Taipeh, Taiwan, August 1999.Google Scholar
  30. [30]
    O. Rogalla, M. Ehrenmann, and R. Dillmann. A sensor fusion approach for pbd. In Proceedings of the International Conference on Intelligent Robots and Systems (IROS), volume 1, Canada, 1998.Google Scholar
  31. [31]
    J. Gonzalez, N. Guil, P. Pérez, M. Ehrenmann, and R. Dillmann. An efficient image processing algorithm for high-level skill acquisition. In International Symposium on Assembly and Task Planning (ISATP), volume 1, pages 262–267, Porto, Portugal, July 1999.Google Scholar
  32. [32]
    M.R. Cutkosky. On grasp choice, grasp models, and the design of hands for manufacturing tasks. IEEE Trans. Robotics and Automation, 5 (3): 269–279, 1989.CrossRefGoogle Scholar
  33. [33]
    H. Friedrich, V. Grossmann, M. Ehrenmann, O. Ro-galla, R. Zöllner, and R. Dillmann. Towards cognitive elementary operators: Grasp classification using neural network classifiers. In TASTED International Conference on Intelligent Systems and Control (ISC), volume 1, page accepted, Santa Barbara, California, USA, Octubre 1999.Google Scholar
  34. [34]
    Andrew Blake and Michael Isard. Active Contours. Springer, 1998.CrossRefGoogle Scholar
  35. [35]
    M. Isard. A smoothing filter for condensation. In Lecture Notes in Computer Science. 1998.Google Scholar
  36. [36]
    T. Knieriemen. Autonome Mobile Roboter - Sensordateninterpretation und Weltmodellierung zur Navigation in unbekannter Umgebung, volume 80 of BI - Wissenschaftverlag. K.H. Böhling, U. Kulisch, H.Maurer, 1991.Google Scholar
  37. [37]
    H. Friedrich, R. Dillmann, and O. Rogalla. Interactive robot programming based on human demonstration and advice. Lecture Notes in Artificial Intelligence, 1999.Google Scholar
  38. [38]
    M. Lichon, M. Bordegoni, R. Buckingham, G. Frugoli, U. Cugini, and C. Rizzi. Experimental evaluation of artificial skill, in human skill acquisition for service robots. In Workshop at 10th IEEF_/RSJ IROS97.Google Scholar
  39. [39]
    P. Denti, P. Dragoni, G. Frugoli, and C. Rizzi. Soft-world: A system to simulate flexible products behaviour in industrial processes. In Proceeding ESS’96.Google Scholar

Copyright information

© Springer-Verlag London 2000

Authors and Affiliations

  • R. Dillmann
    • 1
  • O. Rogalla
    • 2
  • M. Ehrenmann
    • 3
  • R. Zöliner
    • 4
  • M. Bordegoni
    • 5
  1. 1.Institute for Process Control & RoboticsUniversity of KarlsruheKarlsruheGermany
  2. 2.Institute for Process Control & RoboticsUniversity of KarlsruheKarlsruheGermany
  3. 3.Institute for Process Control & RoboticsUniversity of KarlsruheKarlsruheGermany
  4. 4.Institute for Process Control & RoboticsUniversity of KarlsruheKarlsruheGermany
  5. 5.Dipartimento di Ingegneria IndustrialeUniversity of ParmaParmaItaly

Personalised recommendations