Modelling User Experience in Human-Robot Interactions

In human-human interaction, the participants’ multimodal behaviour has impact on the interaction as a whole, and similarly in spoken human-robot interactive situations, the interlocutors’ multimodal signals seem to correlate with the user’s assessment of the interaction. We explored in more detail how some aspects of multimodal behaviour (gazing, facial expressions, body posture) can predict the user’s experience and impressions of the robot’s behaviour (responsiveness, expressiveness, interface, usability, overall impression). The results indicate that the user’s assessment concerning the evaluation categories Interface and Usability, and to some extent the categories Expressiveness and Overall correlate with their behaviour in a statistically significant manner. The work contributes to our understanding of how the interlocutors’ engagement and active participation relate to their assessment of the success of communication, and points towards automating evaluation of human-robot interactions.