Supporting the Adaptive Generation of Learning Game Scenarios with a Model-Driven Engineering Framework.

Learning games are promising methods for autism therapy. In this context, our research project aims to propose an "escape-room" game for helping children with Autistic Syndrome Disorder (ASD) to learn visual performance skills. Given the specific needs of the intended players, the generation of learning scenarios has to be adaptive. For that, our proposal relies on Model Driven Engineering techniques to deal with dynamic scenarization instead of implementing fixed configurations of scenarios. Our approach proposes to express the game description components and child profiles as models from which adapted scenarios can be automatically generated by means of model transformations. In addition, an iterative co-design process based on rapid prototyping is introduced. It allows ASD experts to take part in the design activity and get fast feedback.