No abstract

No abstract

Automated story generation is a desired feature in games and interactive media because it can control how a virtual world evolves so that it can be adapted to the players' choices. In order to have variety and quality in the generated stories, previous works have relied on simulation-based storytelling, in which a story is generated as their characters, represented as agents, try to achieve their goals. One challenge of this approach is to make the agents act more like human characters and less like omniscient intelligent beings. In this article, we present a perception model for simulation-based story generation that introduces errors into characters' knowledge, (mis)leading them to nonoptimal, but still coherent, believable actions. The perception is executed using a description of the virtual world's elements using physical characteristics, and a pattern matching process that associates combinations of physical characteristics with predefined combinations of attributes, which are allowed to be wrong, and consequently may result in non-perfect interpretations of the world. We developed a story generation system from the proposed model and tested it with a version of the Little Red Riding Hood story, famous for its perception failure. Our results show interesting variations for the traditional known ending.

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.

No abstract