Recognition and identification of residents' behaviors and environments using robots for Biofication of Living Spaces

In rapidly aging society, the number of elderly people living alone increases drastically. The elderly people tend to be more and more independent in their own homes. Thus it is an urgent necessity to make these homes comfortable to them to assist in providing safe and comfortable lives. "Biofication of Living Spaces" is proposed with the concept of creating safe and pleasant living environments. It implies learning from biological systems, and applying to living spaces to have features such as high adaptability and excellent tolerance to environmental changes. As a first step towards realizing "Biofied Spaces", a system for acquisition and storing information must be developed. This system is similar to the five human senses. The information acquired includes environmental information such as temperature, humidity, human behavior, psychological state and location of furniture. This study addresses human behavior among them as it is the most important factor in design of a living space. The sensors to acquire these data are supposed to mount on robots. The developed technique for identification of human behaviors is validated utilizing several experimental tests. The experiments suggest the way that does not require the contact between a sensor and a human body. In conclusion, this study leads to recommendations to achieve identification of human behaviors for biofication of living spaces.