Associate Professor
Faculty of Engineering, Information and Systems
Division of Intelligent Interaction Technologies
University of Tsukuba

Professional Activities (Current)

ACM/IEEE International Conference on Human-Robot Interaction (HRI), Program Committee Member
ACM/IEEE International Conference on Human-Robot Interaction (HRI), Steering Committee Member
The 23rd IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN 2014), Special Program Co-Chairs

Research Interests

Since 2003, we have been working on the studies of human-robot interaction (HRI). Particularly, we have strong interests on utilizing robotics technologies to enrich childhood education. Our studies involve wide range of areas from scientific investigation to the development of robot hardware/software.

Keywords: human-robot interaction (HRI), social robotics, social ICT, entertainment robots, childhood education, development and learning, telepresence robots, support for persons with developmental disorders, and robot ethics.

Care-Receiving Robot Project

In contrast to conventional teaching agents (including robots) that were designed to play the role of human teachers or caregivers, we propose the opposite scenario in which robots receive instruction or care from children. We hypothesize that by using this care-receiving robot, we may construct a new educational framework whose goal is to promote children's spontaneous learning by teaching through their teaching the robot. We conduct field experiments to test this hypothesis and develop useful robots that enrich childhood education.

Child-Operated Telepresence Robot Project

This project explores the use of child-operated telepresence robot systems for the purpose of facilitating international communication between distant classrooms. In particular, it has been revealed that young children who could not communicate well with speakers of different languages over conventional video conference services could establish and maintain communication using the telepresence robot system developed by this project. We also conducted an international field trial that connected remote classrooms between Australia and Japan.

Socialization between Toddlers and Robots at a Nursery School

Between 2004 - 2007, we conducted a long-term field study at an Early Childhood Education Center in San Diego, CA in which immersed a small humanoid robot into a classroom of children between 10 to 24 months old. The original goal was to explore the use cases of educational robot applications; however, through this exploratory field study, we could also observe the socialization process between the children and the robot and find lots of interesting clues for making an engaging robot. This study is widely recognized as a representative study of child-robot interaction.

Lifelong Reinforcement Learning

This was my MSc - Ph.D research whose goal was to expand the basic framework of reinforcement learning so that it could deal with a continuous, lifelong learning scenario in which the agent (robot) was given multiple (infinite) learning tasks one by one. The agent was supposed to utilize its past learning experience to solve the current task effectively. This problem was formulated by introducing the distribution of MDPs (Markov Decision Processes) and then a reinforcement learning algorithm was derived.

Other Publications