By Costa, S.; Soares, F.; Pereira, A.P.; Santos, C.; Hiolle, A.
IEEE ICDL-EPIROB 2014 - 4th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
In this paper we present a child-robot interaction pilot study, focusing on recognizing and labelling emotions displayed by a humanoid robot. ZECA (Zeno Engaging Children with Autism) has a special skin covering its face which allows the display of facial expressions representing five emotions: joy, sadness, fear, anger, and surprise. These facial expressions were used in two different game scenarios, involving imitation and storytelling activities. The goal of these scenarios is to help the child acquire knowledge about different emotions and to improve their skill in recognizing them. The results show that these scenarios are appropriate for the goal established for this study, and positive behaviours concerning non-verbal communication were observed. This exploratory study demonstrated the possible positive outcomes this child-robot interaction can produce and highlighted the issues regarding data collection and their analysis that will inform future studies.