Automated dilemmas generation in simulations
Résumé
Our ultimate purpose is to train individuals, in virtual environments, to handle critical situations. One of these critical situations are dilemmas. They refer to situations that lead to negative consequences whichever is the choice made by the protagonist. In critical contexts, it is crucial to know how to handle this kind of situations in order to prevent disastrous consequences from happening. Thus, people need to be exposed to various training situations in which they put in play and develop the appropriate skills. However, in complex domains, it is difficult-sometimes impossible-to write all the possible training scenarios. To address this problem, an automated generation approach is considered. In this article, we present KOBA, a scenario engine that automatically generates dilemma situations without having to write them beforehand. This engine uses knowledge models to extract the necessary properties for dilemmas to emerge. In this article, we present this approach and expose a proof of concept of the generation process.
Origine : Fichiers produits par l'(les) auteur(s)
Loading...