Gaze Estimation for Human-Robot Interaction: Analysis Using the NICO Platform

This is mainly because of the importance of the gaze as a social non-verbal cue for interaction [3]. It drives many different social cognitive mechanisms (such as joint attention, intention prediction, and task coordination) and provides an explainable behaviour for others [4,5]. Affective states are also represented in the gaze behaviour [6]. The ability to perceive and understand the social cues affects the effectiveness and efficiency of the whole interaction experience. Gaze understanding and following is one of the earliest behavior mechanisms developed by infants to engage in different social communication scenarios [7]. Therefore, achieving high accuracy in gaze estimation is a key enabler to reach a seamless Human-Robot interaction task. Despite the significant progress of gaze estimation methodologies, these methods remain not fully evaluated in real human-robot interaction scenarios. In this paper we present an applied evaluation for the latest gaze estimation methods in a standard HRI scenario, specifically when the human and the robot are engaged in a shared task space (e.g., table surface).