Social robot in diagnosis of autism among preschool children

Current research on autism raises an important methodological issue concerning reliable measurement tools to diagnose abnormal social interactions within autistic children. Here we presents proposal of a interdisciplinary approach combining psychology and robotics yielding Human-Robot interaction to recognize autism symptoms based on a pre-schoolers' play with the social robot (`Touch me' and `Dance with me'). The observational measures combined with competent raters technique indicated abnormal interaction patterns in children with autism during interactive games with NAO robot. Our research, by linking psychological and engineering perspectives provides promising preliminary results on application of robot to study autism based on HRI and results in collection of user's requirements and evaluation's criteria for a robot design.