Tracking aggregate vs. individual gaze behaviors during a robot-led tour simplifies overall engagement estimates

As an early behavioral study of what non-verbal features a robot tourguide could use to analyze a crowd, personalize an interaction and maintain high levels of engagement, we analyze participant gaze statistics in response to a robot tour guide´s deictic gestures. There were thirty-seven participants overall, split into nine groups of three to five people each. In groups with the lowest engagement levels aggregate gaze response to the robot´s pointing gesture involved the fewest total glance shifts, least time spent looking at indicated object and no intra-participant gaze. Our diverse participants had overlapping engagement ratings within their group, and we found that a robot that tracks group rather than individual analytics could capture less noisy and often stronger trends relating gaze features to self-reported engagement scores. Thus we have found indications that aggregate group analysis captures more salient and accurate assessments of overall humans-robot interactions, even with lower resolution features.