An Adaptive Learning Game for Autistic Children using Reinforcement Learning and Fuzzy Logic

This paper presents an adapted serious game for rating the social ability in children with autism spectrum disorder (ASD). The required measurements are obtained by challenges of the proposed serious game. The proposed serious game uses the reinforcement learning concepts for being adaptive. It is based upon fuzzy logic to evaluate the social ability level of the children with ASD. The game adapts itself to the level of the autistic patient by reducing or increasing the challenges in the game via an intelligent agent during the play time. This task is accomplished by making more elements and reshaping them to a variety of real world shapes and re-designing their motions and speed. If the autistic patient's communication level grows during the playtime, the challenges of game may become harder to make a dynamic procedure for evaluation. At each step or state, using fuzzy logic, the level of the player is estimated based on some attributes such as the average of the distances between the fixed points gazed by the player or the number of the correct answers selected by the player divided by the number of the questioned objects. This paper offers the usage of dynamic AI difficulty system proposing a concept to enhance the conversation skills in the autistic children. The proposed game is tested by participation of 3 autistic children. Each one of them play the game in 5 turns. The results obtained display that the method is useful in a long time period.