Humanoid Robot Assisted Training for Facial Expressions Recognition Based on Affective Feedback

Abstract

Different studies explore the use of electronic screen media to train specific social skills, since they provide visual elements which are well accepted by children with ASD. However, even if children have high levels of attention to the screen, this might also reduce the possibilities of interacting with others. The challenge lays on finding ways to encourage and motivate the child to keep learning and share the experience with others. For this reason, we propose a feasible framework composed of three technologies: a tablet to train facial expressions recognition, a humanoid robot as reinforcer, and a wearable device to quantify smiles. We did a feasibility test with adults not only to verify the machine response, but also to obtain qualitative data regarding the interaction with the robot. In this study we analyze the importance and the synergistic effect of combining screen media with the robot embodiment and affective computing technologies.