Generation of Obligation and Prohibition Dilemmas Using Knowledge Models

Abstract

Under the project MacCoy Critical, we would like to train individuals, in virtual environments, to handle critical situations such as dilemmas. These latter refer to situations where there is no "good" solution. In other words, situations that lead to negative consequences whichever choice is made. Our objective is to develop a S cenario Orchestration S ystem that generates dilemma situations dynamically without having to write them be forehand. The approach consists in using Knowledge Models to extract necessary properties for dilemmas to emerge. In this article we present this approach and expose a proof of concept of the generation process.

Towards an AI Assistant for Power Grid Operators

“…Because of confidentiality issues, it is often hard to share real-world data on decision-making problems. Thus, we should aim at developing synthetic but realistic environments from which to extract representative and relevant scenarios, for example by drawing inspiration from road safety decision-making assessment frameworks [109]. Moreover, synthetic and realistic environments for sequential decision-making have recently been developed for power grids [110,92,93] and could be interactively further studied with grid2viz [111] and grid2grame [112] study tools.…”