Evaluation of Connectives Acquisition in a Humanoid Robot Using Direct Physical Feedback

  • Dai Hasegawa
  • Rafal Rzepka
  • Kenji Araki
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4830)


In this paper, we propose a method where humanoid robot acquires meanings of grammatical connectives using direct physical feedback from human. Our system acquired 70% connectives of all connectives taught by subjects. It can be also said that robot partially learned the concept of time.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Araki, K., Tochinai, K.: Effectiveness of Natural Language Processing Method Using Inductive Learning. In: IASTED International Conference on Artificial Intelligence and Soft Computing, pp. 295–300 (2001)Google Scholar
  2. 2.
    Fukui, H., Araki, K., Tochinai, K.: The Method of Acquisition of Corresponding Relation between Language and Act Using Inductive Learning with Genetic Algorithm (in Japanease). Journal of Infomation Processing Society of Japan 45(10), 2428–2437 (2004)Google Scholar
  3. 3.
    Fernald, A., Hurtado, N.: Name in frames: infants interpret words in sentence frames faster than words in isolation. Developmental Science 9(3), 33–44 (2006)CrossRefGoogle Scholar
  4. 4.
    Brooks, R.A.: Intelligence without representation. Artificial Intelligence 47, 139–159 (1991)CrossRefGoogle Scholar
  5. 5.
    Kanda, T., Ishiguro, H., Ono, T., Imai, M., Nakatsu, R.: An evaluation on interaction between humans and an autonomous robot Robovie (in Japanease). Journal of Robotics Society of Japan 20(3), 315–323 (2002)Google Scholar
  6. 6.
    Kondo Kagaku Co. Ltd.
  7. 7.
    MeCab: Yet Another Part-of-Speech and Morphological Analyzer:

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Dai Hasegawa
    • 1
  • Rafal Rzepka
    • 1
  • Kenji Araki
    • 1
  1. 1.Graduate School of Information Science and Technology, Hokkaido University, SapporoJapan

Personalised recommendations