For this research project, we use “Geminoids”, androids built to very closely resemble specific human “models”, as a platform for research toward understanding humans; our goal is to apply methods from engineering, cognitive science, and neuroscience to investigate various research topics.

In addition, using a teleoperation system created for this project, we explore not just how people conversing with the robot are affected, but also how the robot’s operator is affected.

In this research, we developed Geminoid HI-2, modeled on Dr. Ishiguro, and Geminoid F, an android closely resembling a specific female model. Currently, at ATR, using these androids, we are investigating the capability of such an android to socially influence people, and what operators experience when conversing using a Geminoid.

This work is supported by Grant-in Aid for Scientific Research (S), KAKENHI(25220004) and KAKENHI(20220002).

This project develops a cybernetic avatar (CA) that is rich in hospitality for users and is controlled by remote control, autonomous operation, free operation, etc., and a human-centered CA society where anyone can experience various social activities. In this laboratory, we engage in research and development on technology for manipulating CA, and physiological and brain science research on the effects of CA on the body of operators and users.

This research is supported by JST, Moonshot Research and Development Program.

In the near future, various home appliances and robots will act autonomously and will have intentions and desires. As they have intentions and desires, they will be able to establish relationships with humans in which they understand each other's intentions and desires by using natural language to interact with each other. This kind of world is a society in which humans and intelligent robots and information media coexist in the next stage of the information society. In order to create an academic field that realizes this new symbiotic society, we will engage in research and development with four research groups: (1)Dialogue engagement and rapport research. (2)Communication understanding and generation research. (3)Behavioral decision model estimation research. (4)Human-machine social norms research

This work is supported by Grant-in Aid for Scientific Research on Innovative Areas.

This research engages in the development of Symbiotic Human-Robot Interaction, and its goal is to develop autonomous social robots that can communicate with multiple humans via various communicative means as humans use them. In order to achieve the goal, it is necessary to develop certain devices and technologies: (a) surface skin material and internal structure for safe interaction with humans, (b) robust and flexible speech recognition technology, (c) functions of autonomous context- and task-sensitive communication on the basis of a hierarchical model consisting of desire, intention, and behavior including speech acts, and (d) functions of using multiple communicative means to communicate with multiple persons in social contexts.

This research is supported by JST, ERATO.

For this research initiative, we seek to create a teleoperated android the size of a cellular phone (i.e., a “Geminoid Cell Phone”) which can be used to convey a person’s “presence” anywhere, at any time. Through this innovation, users will be able to transmit their presence to a remote location in such a way that their conversation partners feel as if they were conversing face to face.

This Geminoid Cell Phone constitutes a new information medium which supports natural interactions between humans and their environment, joining the ranks of personal computers and cell phones. Work in this project will involve the development of core cellular phone functions, capability for recognizing a user’s motions, sensors and actuators to be place on the robot, as well as integration of the above to achieve smooth communication using the Geminoid Cell Phone.

The developed system will also be evaluated by conducting experiments involving remote conversations with one or two cell phone robots.

This research is supported by JST, CREST.