Using Small Humanoid Robots to Detect Autism in Toddlers

Autism Spectrum Disorder is a developmental disorder often characterized by limited social skills, repetitive behaviors, obsessions, and/or routines. Using the small humanoid robot NAO, we designed an interactive program to elicit common social cues from toddlers while in the presence of trained psychologists during standard toddler assessments. Our program will capture three different videos of the child-robot interaction and create algorithms to analyze the videos and flag autistic behavior to make diagnosis easier for clinicians. Our novel contributions will be automatic video processing and automatic behavior classification for clinicians to use with toddlers, validated on a large number of subjects and using a reproducible and portable robotic program for the NAO robot.

[1]  Vassilios Morellas,et al.  A computer vision approach for the assessment of autism-related behavioral markers , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[2]  Michael Murias,et al.  Early behavioral intervention is associated with normalized brain activity in young children with autism. , 2012, Journal of the American Academy of Child and Adolescent Psychiatry.

[3]  K. Dautenhahn,et al.  Towards interactive robots in autism therapy: background, motivation and challenges , 2004 .

[4]  Lauren M. Schmitt,et al.  The Clinical Use of Robots for Individuals with Autism Spectrum Disorders: A Critical Review. , 2012, Research in autism spectrum disorders.

[5]  Brian Scassellati,et al.  Quantitative metrics of social response for autism diagnosis , 2005, ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005..