Vision-based HRV Measurement for HRI Study

The purpose of this study is to enable a robot to estimate the emotional state of a person based on autonomic nervous activity toward human-robot `emotional' interaction. In this paper, an RGB camera is used as a non-contact vision-based technique in order to measure heart rate variability (HRV) which reflects the activity of the autonomic nervous system. The preliminary experiment was conducted to confirm whether HRV of subjects who were stationary could be accurately measured by analyzing the heartbeat interval (R-R interval) from the signal obtained by the camera. The result showed that HRV of a subject was fluctuated during seeing images evoking emotion. The subsequent experiment was conducted to investigate the influence of body motion by utterance on the measurement, and the mental state of subjects when talking with the robot was examined. As a result, it was confirmed that the measurement of HRV using the RGB camera has a potential to be able to non-invasively estimate the mental state of a user interacting with a robot.