engleski

Challenges of using humanoid robots in the assessement of autism spectrum disorder

The diagnosis of autism spectrum disorder, which is usually given during the preschool period, depends on the education and experience of human evaluators. Research has shown that inter-rater reliability can be very low, even among experienced clinicians. The ongoing collaboration between the researchers from the Faculty of Electrical Engineering and Computing and Faculty of Education and Rehabilitation Sciences (University of Zagreb, Croatia) initiated the use of humanoid robots in the process of ASD assessment. The goal of the project is the development of a robot-based diagnostic protocol and testing of its verification in clinical settings. The expected benefit of using the robot is twofold: the robot always performs its actions in a predictable and consistent way, and it can use its sensors to catch aspects of a child's behavior that a human examiner might miss. In this poster we describe four tasks from the widely accepted ADOS protocol, that have been adapted to make them suitable for the Aldebaran Nao humanoid robot. These tasks include evaluating the child's response to being called by name, symbolic and functional imitation, joint attention task and assessing the child's ability to simultaneously communicate on multiple channels. We present the results of clinical trials of the proposed robot assisted protocol, performed on a population of typically developing preschool children and preschool children with ASD. The obtained results indicate that the use of robots in ASD assessment is a promising approach, but much work remains to be done before they become useful diagnosic tools.

assessment; preschool; autism

nije evidentirano