Recognition of Gestural Behaviors Expressed by Humanoid Robotic Platforms for Teaching Affect Recognition to Children with Autism - A Healthy Subjects Pilot Study

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that is characterized by impaired social interactions and restricted, repetitive behaviors. Children who are considered to be within the spectrum tend to lack the social interaction, facial processing, and emotion recognition and implementation skills that typically developing children possess. These impairments inhibit positive social interactions, relationship building, and effective communication, which could potentially lead to distress and frustration for the child. This study focuses on developing a system to teach five of the six universal emotions. Therefore, we created an emotional gesture set to be performed on a pair of humanoid robot platforms, the NAO and the Mini Darwin. As a step towards reaching that goal of teaching and assessing children with ASD, we conducted a pilot study with able-bodied adults to validate that the gesture set created was easily recognizable. In this pilot study, we asked 137 able-bodied adult participants to watch the system perform gestures that associated to emotions. Then, we asked them to identify the emotion that the system was attempting to portray. Gestures achieved recognition rates ranging in values, with a maximum rate of 96% for sadness and a minimum rate of 57% for happiness.