Takeo Igarashi

Interaction techniques for understanding and control of data-driven inteligent information systems

Grant No.：JPMJCR17A1

Research Director

Takeo Igarashi

Collaborator

Yonghao Yue
Taichi Kin	Specially Appointed Associate Professor The University of Tokyo Hospital The University of Tokyo
Issei Sato	Professor Graduate School of Information Science and Technology The University of Tokyo

Outline

Data-driven intelligent information processing technologies such as machine learning are growing rapidly. In this research, we develop interaction technologies to support the user to understand and control such data-driven intelligent information processing systems in preparation and annotation of training data, execution of learning, and use of the learning result in applications.

Takayuki Kanda

Human-Robot Interaction for Symbiotic Robots in a Public Space in a City.

Grant No.：JPMJCR17A2

Research Director

Takayuki Kanda

Outline

Since artificial intelligence and robotics technologies have recently grown fast, it is expected that diverse human works will be eventually replaced by artificial intelligence and robots. However, although many works expected to be automated in reality also play the role of bringing safety feelings to our society, the robots today are yet far from providing such safety feelings. They even fail to be morally considered. This project aims to solve this problem by providing moral interaction capability to robots, and realize a symbiotic society between people and robots.

Hideki Koike

A study on skill acquisition mechanism and development of skill transfer systems

Grant No.：JPMJCR17A3

Research Director

Hideki Koike

Collaborator

Shinichi Furuya	Research Director Tokyo Research Sony Computer Science Laboratories, Inc.
Jun Rekimoto	Professor Interfaculty Initiative in Information Studies The University of Tokyo

Outline

This research develops a technology base of skill acquisition/transfer system which copies skills from one person and pastes them to the other. To understand skill acquisition mechanism, we analyse person who have high skills in various fields and abstract an essence of the skills. At the same time, we develop real-time visual/audio/haptic feedback systems of the skills using computer vision/augmented reality/robitics/artificial intelligence technologies.

Ichiro Tsuda

An exploration of the principle of emerging interactions in spatiotemporal diversity

Grant No.：JPMJCR17A4

Research Director

Ichiro Tsuda

Collaborator

Takashi Ikeda	Associate Professor Research Center for Child Mental Development Kanazawa University
Yuji Kawai	Associate Professor Institute for Open and Transdisciplinary Research Initiatives Osaka University

Outline

We aim to construct an artificial system that produces functional differentiation via interactions with complex environment in order to adapt itself quickly to the environment. For this purpose, we develop a principle of self-organization with constraints which produces functional differentiation, and explore collective intelligence in humans and primates. We conduct the research via analyses of interactions between brain areas, individuals and groups, respectively. The research results are expected to contribute to the development of order-made medical treatments, the design of interacting robots, in particular, with humans, and the creation of new format of community based on collective intelligence.

Atsushi Nakazawa

Computational and cognitive neuroscientific approaches for understanding the tender care

Grant No.：JPMJCR17A5

Research Director

Atsushi Nakazawa

Collaborator

Ryo Kurazume	Professor Graduate School and Faculty of Information Science and Electrical Engineering Kyushu University
Wataru Sato	Team Leader Information R&D and Strategy Headquarters Riken
Miwako Honda	Director Division of Health economics and geriatric research Tokyo Medical Center

Outline

This project analyzes the skill of the “tender care” and finds the essential elements and models in the care through the computational and cognitive neuroscientific approaches, such as the use of a) wearable and environmental sensing and b) the brain imaging and facial electromyography. On top of these findings, we develop a system that helps learning the tender care skills through quantifying the learners’ behaviors. In the end, we evaluate the effectiveness of the system in actual care scenes.