Early therapeutic intervention programs help children diagnosed with Autism Spectrum Disorder (ASD) to improve their socio-emotional and functional skills. To relieve the children’s caregivers while ensuring that the children are adequately supported in their training exercises, new technologies may offer suitable solutions. This study investigates the potential of a robotic learning assistant which is planned to monitor the children’s state of engagement and to intervene with appropriate motivational nudges when necessary. To analyze stakeholder requirements, interviews with parents as well as therapists of children with ASD were conducted. Besides a general positive attitude towards the usage of new technologies, we received some important insights for the design of the robot and its interaction with the children. One strongly accentuated aspect was the robot’s adequate and context-specific communication behavior, which we plan to address via an AI-based engagement detection system. Further aspects comprise for instance customizability, adaptability, and variability of the robot’s behavior, which should further be not too distracting while still being highly predictable.

SummaryIn the evaluation of discrimination performance in closed set tests, it is important to know what proportion of correct results may possibly be explained by chance. The present paper describes a statistical model for the calculation of confidence limits which appears suitable for standardization of the different methods of appraisal used throughout the world. It utilizes the matching model and Poisson distribution and, as an example, it is applied to discrimination performance tests of cochlear implant wearers.