Long-term human-robot interactions have been widely researched; however, there is a lack of methods to evaluate people’s perception and engagement with those systems. Questionnaires and interviews may be biased and decrease human involvement. Hence, a recent study investigates the possibility of using gaze patterns as a suitable metric.
During the experiment, participants wearing eye-tracking glasses got involved in an interactive session with a robot and self-reported their perception and engagement with it. The results show that mutual gaze towards a robot was a negative predictor of uncanniness during a social chat.
During joint tasks, which involved tangible artifacts, the best predictor of involvement was the gaze focused on the object of shared attention and not on the robot itself. These findings show that the gaze can be used as an indicator of people’s perception of robots.
Over the past years, extensive research has been dedicated to developing robust platforms and data-driven dialogue models to support long-term human-robot interactions. However, little is known about how people’s perception of robots and engagement with them develop over time and how these can be accurately assessed through implicit and continuous measurement techniques. In this paper,