Design and Validation of MOMDP Models for Child–Robot Interaction Within Tasks of Robot-Assisted ASD Diagnostic Protocol

The existing procedures for autism spectrum disorder diagnosis are time-consuming and challenging both for evaluators and children being evaluated. Occurrence of low agreement rates between different clinicians when evaluating a child suggests that there exists a need for a more objective approach to diagnostics. To that end, we developed a robot-assisted ASD diagnostic protocol. In this work the focus is on robot reasoning for tasks of the protocol. We propose the mixed observability Markov decision process models for tasks which infer information about the state of a child based on observations of child’s behavior. In order to formulate observation probabilities of task models, ASD experts are surveyed and their knowledge is encoded in the observation probabilities of task models. Expert knowledge also allowed for implementation of child behavioral models which are used to validate and tune developed models. Following the successful validation through simulations of child–robot interaction using child behavioral models, task models are validated through experimental sessions with six typically developing children and eight children with ASD. Results obtained through experiments show that the robot is capable of correctly identifying the behavior of the child within the diagnostic tasks.