A two-layered approach to communicative artifacts


A key issue in social intelligence design is the realization of artifacts that can fluently communicate with people. Thus, we proposed a two-layered approach to enhance a robot’s capacity of involvement and engagement. The upper layer flexibly controls social interaction by dynamic Bayesian networks (DBN) representing social interaction patterns. The lower layer improves the robustness of the system by detecting rhythmic and repetitive gestures. We designed a listener robot that can follow and record humans’ explanation on how to assemble and/or disassemble a bicycle. The implementation of this system is described by assembling the key algorithms presented in this paper.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5


  1. Aikawa M (2000) Techniques of human relation—psychology of social skills, In: Saiensu-Sha (ed)Selection of social psychology, No. 20, (in Japanese)

  2. Hatakeyama M (2004) Human–robot interaction based on interaction schema, Master Thesis, University of Tokyo, Japan (in Japanese)

  3. Kipp M (2004) Gesture generation by imitation: from human behavior to computer character animation, Boca Raton, Dissertation

  4. Matsusaka Y, Fujie S, Kobayashi T (2001) Modeling of conversational strategy for the robot participating in the group conversation, In: Proceedings International Speech Communication Association (ISCA)-EUROSPEECH2001, pp 2173–2176

  5. Okamoto M, Nakano I Y, Nishida T (2004) Toward enhancing user involvement via empathy channel in human-computer interface design, In: Proceedings of international workshop on intelligent media technology for communicative intelligence (IMTfCI 2004), Warsaw, September, pp 129–132

  6. Ogasawara Y, Okamoto M, Nakano IY, Nishida T (2005) Establishing natural communication environment between a human and a listener robot, In: Proceedings of social intelligence and interaction in animals, robots and agent (AISB 2005), conversational informatics for supporting social intelligence and interaction: situational and environmental information enforcing involvement in conversation, England, April, pp 42–51

  7. Reeves B, Nass C (1996) The media equation: how people treat computers, television, and new media like real people and places, CSLI Publications

  8. Tajima T, Xu Y, Nishida T (2004) Entrainment based human-agent interaction, In: Proceedings of 2004 IEEE Conf. on Robotics, Automation and Mechatronics (RAM2004), Singapore, pp 1042–1047

  9. Tarasenko K, Nishida T (2006) Dynamic Bayesian Networks for modelling of alignment and mutual adaptation with communicative robots, In: Proceedins of workshop of social intelligence design (SID2006), pp 39–46

  10. Tomasello M (1999) The cultural origins of human cognition, Harvard University Press, Cambridge

  11. Watanabe T, Ogawa H (2001) InterRobot for human interaction and communication support. In: Proceedings of world multi-conference on systems, cybernetics and informatics (SCI2001) pp 466–471

Download references

Author information



Corresponding author

Correspondence to Yong Xu.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Xu, Y., Hiramatsu, T., Tarasenko, K. et al. A two-layered approach to communicative artifacts. AI & Soc 22, 185–196 (2007). https://doi.org/10.1007/s00146-007-0131-4

Download citation


  • Humanoid Robot
  • Joint Attention
  • Communication Mode
  • User Involvement
  • Front Wheel