Keepon is a small creature-like robot designed to interact with children by directing attention and expressing emotion. Keepon’s minimal design makes its behaviors easy to understand, resulting in interactions that are enjoyable and comfortable—particularly important in our research on human social development.

Keepon has soft rubber skin, cameras in its eyes, and a microphone in its nose:

Keepon has four degrees of freedom. Attention is directed by turning +/-180° and nodding +/-40°, while emotion is expressed by rocking side-to-side +/-25° and bobbing up to 15mm:

Keepon has been used since 2003 in research on social development and communication. We have studied behaviors such as eye-contact, joint attention, touching, emotion, and imitation between Keepon and children of different ages and levels of social development. In the case of children with autism and other developmental disorders, we have had encouraging results with the use of Keepon as a tool for therapists, pediatricians, and parents to observe, study, and facilitate social interactions.

• H. Kozima, C. Nakagawa.
  Interactive robots as facilitators of children’s social development.
  Mobile Robots: Toward New Applications, pp. 269-286, 2006.
• H. Kozima, C. Nakagawa, Y. Yasuda.
  Children-robot interaction: a pilot study in autism therapy.
  Progress in Brain Research, Vol. 164, pp. 385-400, 2007.
• H. Kozima, M.P. Michalowski, C. Nakagawa.
  Keepon: A Playful Robot for Research, Therapy, and Entertainment.
  International Journal of Social Robotics, Vol. 1, 2008.

Rhythmic human-robot social interaction

Human social behavior shares much in common with dance. Our speech, as well as the movement of our body, head, and hands, is periodic and rhythmic. Social scientists such as William S. Condon and Adam Kendon have identified interactional synchrony as a phenomenon that plays an important role in the regulation and coordination of movements, vocalizations, and other social cues. We have been developing technology to allow robots like Keepon to synchronize with these social rhythms in their interactions. We believe that rhythmic synchrony is as important for establishing engagement, rapport, and comfort between a robot and a person as it is between people.

We are using Max/MSP from Cycling ’74 to design our architecture for rhythmic social interaction. While we are focusing on dance-oriented play as a domain for developing and evaluating our technologies, the technologies and methods for perceiving, modeling, and generating rhythmic behaviors will be useful in less constrained interactions.

• M.P. Michalowski, H. Kozima.
  Methodological issues in facilitating rhythmic play with robots.
  Proceedings of RO-MAN 2007, August, 2007.
• M.P. Michalowski, S. Sabanovic, H. Kozima.
  A dancing robot for rhythmic social interaction.
  Proceedings of HRI 2007, March, 2007.
• M.P. Michalowski, S. Sabanovic, P. Michel.
  Roillo: Creating a social robot for playrooms.
  Proceedings of RO-MAN 2006, September, 2006.