Engagement Evaluation for Autism Intervention by Robots Based on Dynamic Bayesian Network and Expert Elicitation

Robots as therapy tools have been researched in intervention for children with autism. During the interaction between robots and autistic children, engagement is an important metric which can be used to express whether robot's behavior is suited to the current context. The evaluation of engagement is a key prerequisite to improve the autonomous ability of robots in intervention. In this paper, we propose a new model to evaluate the engagement of children with autism. The proposed model is developed based on the dynamic Bayesian network, and the parameters of the model are obtained by fuzzy logic and expert elicitation. After determining the input features and the classification of engagement, the topology of the model is established. Afterward, experts' opinions are collected based on linguistic variables. Based on triangular fuzzy number, the parameterization of the model is realized by fuzzification, aggregation, and defuzzification. Finally, the model is validated by experiment. The result demonstrates that proposed model satisfies the actual demands and the result of engagement classification can provide the input condition for the decision making of the robot.