Tilt Riders: Improvisational Agents Who Know What the Scene Is about

The creation of autonomous agents for interactive narrative requires a heavy authorial effort, especially when the authors are concerned about integrating all possible story states in the agents behaviors. In this paper, we consider that the autonomous agents lack of narrative perspective over the action prevents them from successfully dealing with unpredicted story states. To deal with this problem we propose a conceptual model of story development for autonomous agents that endows narrative control to them. The proposed model is supported by our cognitive research with improvisational theatre actors and improvisational theatre theory.