Perception simulation in social planning for emergent storytelling

The immersion level of a game is one of the main factors that affect its quality. The higher the immersion, the more connected to the game the player feels. To increase immersion, a number of games try to adapt the story to at least create the illusion that the player's actions and decisions are guiding it. However, this adaptation is often limited, since creating story variations to each of the player's actions would be infeasible. One possible solution, which has been studied in the storytelling area, is to allow the game itself to generate its story as it is being played. One of the main methods for generating stories is based on simulating virtual worlds inhabited with agents to impersonate their characters. Although stories frequently rely on their characters' misunderstandings and knowledge failures to develop interesting situations, most storytelling approaches available in the literature are based on correct and perfect reasoning. As such, they are less likely to make scenarios based on mistakes to emerge. In this paper we enhance a perception simulation method, that allows characters to make wrong but coherent choices, with a reasoning process that deals with uncertainty and the knowledge of the others. Our main goal is to develop story generation capacity in simulation based systems. As test scenario we recreated Little Red Riding Hood story world, with which our method generated coherent variations of the story, where characters made decisions based on perception without recurring to predefined scripts.