Agents’ interaction in virtual storytelling

Marc Cavazza, Fred Charles, Steven Mead

Research output: Chapter in Book/Report/Conference proceedingConference contribution

230 Downloads (Pure)


In this paper the authors describe a fully implemented prototype for interactive storytelling using the Unreal™ engine. Using a sit-com like scenario as an example of how the dynamic interactions between agents and/or the user dramatise the emerging story. Hierarchical Task Networks (HTNs) are formalised using AND/OR graphs, which are used to describe the many possible variations of the story at a sub-goal level, and the set of all behaviours (from a narrative perspective) of the primary actors at a terminal action level. The authors introduce real-time variant of the heuristic search algorithm AO✻ that has been implemented to provide a mechanism for planning (and re-planning) and discuss how the chosen heuristic evaluation function is used to describe narrative concepts. They provide early results of several examples of how the same basic plot can have many differing story instantiations as a result of the dynamic interaction within the virtual set and the personalities of the primary characters, and detail the steps required in the plan generation.
Original languageEnglish
Title of host publicationIntelligent Virtual Agents
PublisherSpringer Berlin
ISBN (Print)9783540425700
Publication statusPublished - 2001
Event3rd International Conference on Intelligent Virtual Agents - Madrid, Spain
Duration: 10 Sept 200111 Sept 2001
Conference number: 3rd

Publication series

NameLecture notes in computer science


Conference3rd International Conference on Intelligent Virtual Agents
Abbreviated titleIVA 2001

Bibliographical note

Author can archive post-print (ie final draft post-refereeing). For full details see [Accessed 08/06/2010]


Dive into the research topics of 'Agents’ interaction in virtual storytelling'. Together they form a unique fingerprint.

Cite this