Diversive Curiosity in Robots and Action Selection Method for Obtaining Unexperienced Sensory Information

  • Toma Morisawa
  • Ikuo Mizuuchi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 302)


Humans can acquire new knowledge by themselves, and robots are also expected to have such ability by introducing curiosity. In previous researches, curiosity is expressed as just a judging system that decides whether the robot continues looking over a specific environment. In this paper we define curiosity as a direction in the multidimensional sensory space, and propose an action selection method based on the curiosity vector. The system estimates the relation between action and resulting sensory changes using the stored observed data. It selects an action so as to obtain the desired sensory information, based on the curiosity vector. This paper also describes experiments in which a wheeled mobile robot moves toward an unknown area and a humanoid discovers actions to obtain unexperienced sensory information.


Curiosity Relation between action and sensory changes Action selection Behavior generation Novelty of sensory information 


  1. 1.
    Ichimura, A., Mizuuchi, I.: Reaching hidden objects based on memory of environmental states and robot s movement and manipulation. In: Proceedings of 16th International Conference on Advanced Robotics (ICAR2013). (2013)Google Scholar
  2. 2.
    Simsek, Ö., Barto, A.G.: An intrisic reward mechanism for efficient exploration. In: Proceedings of the 23rd International Conference on Machine Learning. (2004) 127–130.Google Scholar
  3. 3.
    Schmidhuber, J.: Adaptive confidence and adaptive curiosity. Technical report, Institut fur Informatik Technische Universitat Munchen (1991).Google Scholar
  4. 4.
    Berlyne, D.E.: Conflict, arousal, and curiosity. McGraw-Hill (1960).Google Scholar
  5. 5.
    ves Oudeyer, P.Y., Kaplan, F.: Intelligent adaptive curiosity: a source of self-development. In: Lund University Cognitive Studies. (2004) 127–130.Google Scholar
  6. 6.
    Shimo, N., Pang, S., Horio, K., Kasabov, N., Tamukoh, H., Koga, T., Sonoh, S., Isogai, H., Yamakawa, T.: Effective and adaptive learning based on diversive/specific curiosity. In: Proceedings of 4th International Conference on Brain-Inspired Information Technology. (2007).Google Scholar
  7. 7.
    Berlyne, D.E.: A Theory Of Human Curiosity. British Journal of Psychology 45(3) (1954) 180–191.Google Scholar
  8. 8.
    Morita, M., Ishikawa, M.: Brain-inspired emergence of behaviors based on the desire for existence by reinforcement learning. In: Proceedings of the 15th international conference on Advances in neuro-information processing. (2008) 763–770.Google Scholar
  9. 9.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(11) (1998) 1254–1259.Google Scholar
  10. 10.
    Oliva, A., Torralba, A.: Modeling the shape of the scene: a holistic representation of the spatial envelope. International Journal of Computer Vision 42(3) (2001) 145–175.Google Scholar
  11. 11.
    Oliva, A., Torralba, A. In: Building the gist of a scene: the role of global image features in recognition. Volume 155. (2006) 23–36.Google Scholar
  12. 12.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323(9) (1986) 533–536.Google Scholar
  13. 13.
    Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach (3rd Edition). Prentice Hall (2009).Google Scholar
  14. 14.
    McQueen, J.: Some methods for classification and analysis of multivariate observations. In. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability. (1967).Google Scholar
  15. 15.
    Bellman, R.E.: Dynamic Programming. Princeton University Press (1957).Google Scholar
  16. 16.
    Minato, T., Asada, M.: Towards selective attention: Generating image features by learning a visuo-motor map. Robotics and Autonomous Systems 45 (2003) 211–221.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Tokyo University of Agriculture and TechnologyTokyoJapan

Personalised recommendations