Variance Based Trajectory Segmentation in Object-Centric Coordinates

  • Iori YanokuraEmail author
  • Masaki Murooka
  • Shunichi Nozawa
  • Kei Okada
  • Masayuki Inaba
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 867)


Human imitation is suggested as a useful method for humanoid robots achieving daily life tasks. When a person does demonstration such as housework many times, there is a property that the variance of the hand trajectory in object-centric coordinates becomes small at the stage of acting on the object. In this paper, we focused on human demonstration in object-centric coordinates, and proposed a task segmentation method and motion generation of a robot. In fact, we conducted a experiment (by taking a kettle and moving it to a cup) with the life-sized humanoid robot HRP-2.


Humanoid robot Imitation learning Task segmentation Motion generation Change point detection 


  1. 1.
    Furuta, Y., Wada, K., Murooka, M., Nozawa, S., Kakiuchi, Y., Okada, K., Inaba, M.: Transformable semantic map based navigation using autonomous deep learning object segmentation. In: IEEE-RAS International Conference on Humanoid Robots, pp. 614–620 (2016)Google Scholar
  2. 2.
    Nozawa, S., Kumagai, I., Kakiuchi, Y., Okada, K., Inaba, M.: Humanoid full-body controller adapting constraints in structured objects through updating task-level reference force. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3417–3424 (2012)Google Scholar
  3. 3.
    Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469–483 (2009)CrossRefGoogle Scholar
  4. 4.
    Kuniyoshi, Y., Yorozu, Y., Inaba, M., Inoue, H.: From visuo-motor self learning to early imitation – a neural architecture for humanoid learning. In: IEEE International Conference on Robotics and Automation, pp. 3132–3139 (2003)Google Scholar
  5. 5.
    Ross, S., Gordon, G.J., Bagnell, J.A.: No-regret reductions for imitation learning and structured prediction. In: International Conference on Artificial Intelligence and Statistics (2011)Google Scholar
  6. 6.
    Duan, Y., Andrychowicz, M., Stadie, B.C., Ho, J., Schneider, J., Sutskever, I., Abbeel, P., Zaremba, W.: One-shot imitation learning. arXiv, Vol. abs/1703.07326 (2017)Google Scholar
  7. 7.
    Maeda, G., Ewerton, M., Lioutikov, R., Amor, H.B., Peters, J., Neumann, G.: Learning interaction for collaborative tasks with probabilistic movement primitives. In: IEEE-RAS International Conference on Humanoid Robots, pp. 527–534 (2014)Google Scholar
  8. 8.
    Schneider, M., Ertel, W.: Robot learning by demonstration with local Gaussian process regression. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 255–260 (2010)Google Scholar
  9. 9.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26(1), 43–49 (1978)CrossRefGoogle Scholar
  10. 10.
    Fearnhead, P.: Exact and efficient bayesian inference for multiple changepoint problems. Stat. Comput. 16(2), 203–213 (2006)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Okada, K., Ogura, T., Haneda, A., Fujimoto, J., Gravot, F., Inaba, M.: Humanoid motion generation system on hrp2-jsk for daily life environment. In: IEEE International Conference on Mechatronics and Automation, pp. 1772–1777 (2005)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Iori Yanokura
    • 1
    Email author
  • Masaki Murooka
    • 1
  • Shunichi Nozawa
    • 1
  • Kei Okada
    • 1
  • Masayuki Inaba
    • 1
  1. 1.Graduate School of Information Science and TechnologyThe University of TokyoBunkyo-city, TokyoJapan

Personalised recommendations