Emotion recognition in a social robot for robot-assisted therapy to autistic treatment using deep learning

Abstract

The Autistic Spectrum Disorder (ASD) is a certain kind of condition characterized by difficulty in social communication, social relationship, and imagination. This condition mainly affects children. The earlier intervention in ASD can help the individual to improve the social skills through Autistic therapies. The robot-assisted therapy is an emerging field in which a special type of robot called social robot is used to interact with ASD individual. These robots have social and communicative skills that can influence the ASD individual. Understanding the emotional state of ASD individual will help in providing appropriate therapy to the individual. This paper discusses emotion recognition technique to be used in a social robot using deep learning techniques. This emotion recognition technique can work in real time to predict the behavior of ASD children.