A spatial model of engagement for a social robot

Even if a socially interactive robot has perfect information about the location, pose, and movement of humans in the environment, it is unclear how this information should be used to enable the initiation, maintenance, and termination of social interactions. We review models that have been developed to describe social engagement based on spatial relationships and describe a system developed for use on a robotic receptionist. The system uses spatial information from a laser tracker and head pose information from a camera to classify people in a categorical model of engagement. The robot's behaviors are determined by the presence of people in these different levels. We evaluate the system using observational behavioral analysis of recorded interactions between the robot and humans. This analysis suggests improvements to the current system: namely, to put a stonger emphasis on movement in the estimation of social engagement and to vary the timing of interactive behaviors.