Controlling Narrative Generation with Planning Trajectories: The Role of Constraints

  • Authors:
  • Julie Porteous;Marc Cavazza

  • Affiliations:
  • School of Computing, Teesside University, United Kingdom;School of Computing, Teesside University, United Kingdom

  • Venue:
  • ICIDS '09 Proceedings of the 2nd Joint International Conference on Interactive Digital Storytelling: Interactive Storytelling
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

AI planning has featured in a number of Interactive Storytelling prototypes: since narratives can be naturally modelled as a sequence of actions it is possible to exploit state of the art planners in the task of narrative generation. However the characteristics of a "good" plan, such as optimality, aren't necessarily the same as those of a "good" narrative, where errors and convoluted sequences may offer more reader interest, so some narrative structuring is required. We have looked at injecting narrative control into plan generation through the use of PDDL3.0 state trajectory constraints which enable us to express narrative control information within the planning representation. As part of this we have developed an approach to planning with trajectory constraints. The approach decomposes the problem into a set of smaller subproblems using the temporal orderings described by the constraints and then solves them incrementally. In this paper we outline our method and present results that illustrate the potential of the approach.