Robotic framework with multi-modal perception for physio-musical interactive therapy for children with autism

The rapid increase in the population of children with autism spectrum disorder (ASD) in the United States has revealed urgent needs for therapeutic accessibility for children with ASD in the domain of emotion and social interaction. There have been a number of approaches with robotic therapeutic systems [1,2] with intriguing approaches and results. However, the spectral diversity of ASD is so wide that we still need to push forward research to provide parameterized therapeutic tools and frameworks. We focus on the recent studies that reveal strong relevance in premotor cortex among neural domains for music, emotion, and motor behaviors [3,4]. We hypothesize that musical interaction and physical activities can provide a new therapeutic domain for effective development in the children's emotion and social interaction. To investigate this challenging problem, we propose to develop autonomous interaction methods for robots to effectively stimulate the emotional and social interactivity of children. The objectives of this collaborative effort are to promote emotional and social engagement with children with autism as well as provide parametrized metrics for clinicians and parents for prolonged and quantifiable clinical settings.