Mark Riedl
Assistant Professor
School of Interactive Computing
College of Computing
Georgia Institute of Technology

E-mail: riedlatccdotgatechdotedu
Phone: 404.385.2860
Fax: 404.894.9846

Address:
School of Interactive Computing
Georgia Institute of Technology
85 5th Street, NW
Atlanta, GA 30332
News Background Teaching Research Publications

News

(updated 03.26.2008)

  • Awarded Best Paper at INTETAIN'08 for: Toward Intelligent Support of Authoring Machinima Media Content: Story and Visualization.

Background

I received my Ph.D. degree in Computer Science at North Carolina State University (2004). From 2004-2007 I was a research scientist at the University of Southern California Institute for Creative Technologies. I joined the Georgia Tech School of Interactive Computing in December 2007 as an assistant professor.

Curriculum Vitae ("GT format") (updated 04.10.2008)

Teaching

Fall 2008

Research

My research involves artificial intelligence, storytelling, and entertainment computing. Narrative is a cognitive tool used by humans for communication, sense-making, entertainment, education, and training. The goal of my research is to discover new computational algorithms and models that can facilitate the development of intelligent computer systems that can reason about narrative in order to be better communicators, entertainers, and educators. Some of the topics that interest me are as follows:

  • Artificial intelligence
  • Narrative generation for education, training, and entertainment
  • Interactive narratives for education, training, and entertainment
  • Artificial intelligence for computer games and virtual worlds
  • Intelligent cinematography
  • Believable autonomous agents
  • Mixed-initiative problem-solving
  • Discourse generation

If you are interested in joining my research group, please contact me by email and make an appointment to talk with me.

A non-inclusive list of representative projects are described below.

Automated Story Director

IN-TALE screenshot

The goal of this research is to create a framework with which to create interactive narrative experiences. An intelligent experience manager reasons about the experiences of the interactive user -- the participant -- in a virtual world and intelligently determines how to manipulate the virtual world such that the participant's experiences conform to a particular set of given attributes (e.g., dramatic, thematic, pedagogical). The Automated Story Director is an intelligent experience manager. The Automated Story Director assumes that desired participant experience properties are encoded into a desired, exemplar narrative. The exemplar narrative is represented as a plan and is initially generated from a set of properties, or hand-authored. In the case where the interactive participant deviates significantly from the exemplar narrative, the exemplar narrative is re-generated to accommodate the participant.

The Automated Story Director is part of a larger framework that consists of a virtual world architecture and semi-autonomous character agents. The semi-autonomous character agents are AI agents that play the role of story world characters. The agents are semi-autonomous, meaning that they are able to act autonomously in most instances and to interact with the participant. Character agents also take directives from the Automated Story Director to ensure that their actions are contributing to the desired narrative experience.

Little Red Riding Hood

The Automated Story Director framework is instantiated in two prototype systems:

  • IN-TALE (Interactive Narrative - Tacit Adaptive Leader Experience): A proof-of-concept military leader training exercise focusing around situational, social, and cultural awareness
  • Little Red Riding Hood: An entertainment-based experience

Representative publications:

Contributors:

  • Andrew Stern, researcher, Procedural Arts, LLC (2005 - 2006)
  • Jason Alderman, intern, Georgia Institute of Technology (Summer 2005 and Summer 2006)
  • Don Dini, research programmer, now at Method in Mind, LLC (2005 - 2007)
  • Chirag Merchant, research programmer, Institute for Creative Technologies (2007 - 2008)

Narrative Generation

Fabulist

Fabulist is an architecture for automated story generation and presentation. The Fabulist architecture splits the narrative generation process into three-tiers: fabula generation, discourse generation, and media representation. The fabula generation process uses a planning approach to narrative generation. The Intent-Driven Partial Order Causal Link (IPOCL) planning algorithm simultaneously reasons about causality and character intentionality and motivation in order to produce narrative sequences that are causally coherent and have elements of character believability. Modifications to IPOCL account for personality and also ease authoring constraints.

Representative publications:

Analogical Story Domain Mapping

One way to generate stories is to include elements of previous stories, adapted to the new story world. This work looks at using techniques inspired by case-based planning to generate narratives based on existing story segments. We are exploring the use of analogical reasoners to automatically map story segements from their original domain to the domain of the new story world.

Representative publications:

Contributors:

  • Carlos Leon, intern, Universidad Complutense de Madrid (Summer 2007)
  • Neha Sugandh, special problem (Spring 2008 - present)

Cambot

Cambot is prototype application that can direct machinima movies. Given a script and a virtual set, it blocks the actors, places the virtual camera and edits the movie together.

For more information see the official Cambot website.

 

Representative publications:

Contributors:

  • David Elson, intern, Columbia University (Summer 2006)

Intellient Story Authoring Support

This project investigates how artificial inteligence can be brought to bear to build authoring tools that intelligently support the user's creative process of storywriting. This work has resulted in the development of a prototype plot outlining assistant, ReQUEST. This work has also explored the use of Cambot (see above) into a mixed-initiative framework.

Representative publications:

Contributors:

  • Jonathan Rowe, intern, North Carolina State University (Summer 2007)
  • Stacy Marsella, research scientist, USC Information Sciences Institute (Fall 2008 - present)
  • Peter Danenberg, graduate research assistant, USC Information Sciences Institute (Fall 2008 - present)
  • Brian O'Neil, special problem student (Summer 2008)

Recent Publications

Mark O. Riedl. Computationally Creative Search for Stories. Proceedings of the 3rd International Conference on Design Computing and Cognition, Atlanta, Georgia, 2008.

Mark O. Riedl, Andrew Stern, Don Dini, and Jason Alderman. Dynamic Experience Management in Virtual Worlds for Entertainment, Education, and Training. International Transactions on Systems Science and Applications, Special Issue on Agent Based Systems for Human Learning, vol. 4(2), 2008.

Mei Si, Stacy Marsella, and Mark O. Riedl. Interactive Drama Authoring with Plot and Character: An Intelligent System that Fosters Creativity. Proceedings of the AAAI Spring Symposium on Creative Intelligent Systems, Palo Alto, California, 2008.

Mark O. Riedl, Jonathan P. Rowe, and David K. Elson. Toward Intelligent Support of Authoring Machinima Media Content: Story and Visualization. Proceedings of the 2nd International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN), Playa del Carmen, Cancun Mexico, 2008. Awarded Best Paper.

Mark O. Riedl and Carlos Leon. Toward Vignette-Based Story Generation for Drama Management Systems. Proceedings of the 2nd International Conference on Intelligent Technologies for Interactive Entertainment (INTETAIN), Workshop on Integrating Technologies for Interactive Story, Playa del Carmen, Cancun Mexico, 2008.

David K. Elson and Mark O. Riedl. A Lightweight Intelligent Virtual Cinematography System for Machinima Production. Proceedings of the 3rd Annual Conference on Artificial Intelligence and Interactive Digital Entertainment, Palo Alto, California, 2007.

Selected Publications 1999-2006

Narrative Generation

Mark O. Riedl and R. Michael Young. Story Planning as Exploratory Creativity: Techniques for Expanding the Narrative Search Space. New Generation Computing, 24(3), 2006. (A shorter version appears in Proceedings of the 2005 IJCAI Workshop on Computational Creativity, Edinburgh, 2005.)

Mark O. Riedl and R. Michael Young. An Objective Character Believability Evaluation Procedure for Multi-Agent Story Generation Systems. Proceedings of the 5th International Working Conference on Intelligent Virtual Agents, Kos, Greece, 2005.

Mark O. Riedl. Narrative Generation: Balancing Plot and Character. Ph.D. Dissertation, Department of Computer Science, North Carolina State University, 2004.

Mark O. Riedl and R. Michael Young. An Intent-Driven Planner for Multi-Agent Story Generation. Proceedings of the 3rd International Joint Conference on Autonomous Agents and Multi Agent Systems, New York, 2004.

Mark O. Riedl and R. Michael Young. Character-Focused Narrative Planning for Execution in Virtual Worlds. Proceedings of the 2nd International Conference on Virtual Storytelling, Toulouse, France, 2003.

 

Interactive Narrative

Mark O. Riedl and Andrew Stern. Believable Agents and Intelligent Story Adaptation for Interactive Storytelling. Proceedings of the 3rd International Conference on Technologies for Interactive Digital Storytelling and Entertainment, Darmstadt, Germany, 2006. Awarded best paper.

Mark O. Riedl and Andrew Stern. Failing Believably: Toward Drama Management with Autonomous Actors in Interactive Narratives. Proceedings of the 3rd International Conference on Technologies for Interactive Digital Storytelling and Entertainment, Darmstadt, Germany, 2006.

Mark O. Riedl and Andrew Stern. Believable Agents and Intelligent Scenario Direction for Social and Cultural Leadership Training. Proceedings of the 15th Conference on Behavior Representation in Modeling and Simulation, Baltimore, Maryland, 2006. Awarded best paper.

Mark O. Riedl and R. Michael Young. From Linear Story Generation to Branching Story Graphs. IEEE Computer Graphics and Applications, 26(3), 2006. Featured article of Special Issue on Interactive Narrative. (A shorter version appears in Proceedings of the 1st Conference on Artificial Intelligence and Interactive Digital Entertainment, Marina del Rey, California, 2005.)

Mark O. Riedl, H. Chad Lane, Randall Hill, and William Swartout. Automated Story Direction and Intelligent Tutoring: Towards a Unifying Architecture. Proceedings of the 2005 AIED Workshop on Narrative Learning Environments, Amsterdam, 2005.

R. Michael Young, Mark O. Riedl, Mark Branly, Arnav Jhala, R.J. Martin, and C.J. Saretto. An Architecture for Integrating Plan-Based Behavior Generation with Interactive Game Environments. Journal of Game Development, vol. 1, 2004.

Mark O. Riedl, C.J. Saretto, and R. Michael Young. Managing Interaction Between Users and Agents in a Multi-Agent Storytelling Environment. Proceedings of the 2nd International Joint Conference on Autonomous Agents and Multi Agent Systems, Melbourne, Australia, 2003.

R. Michael Young and Mark O. Riedl. Towards an Architecture for Intelligent Control of Narrative in Interactive Virtual Worlds. Proceedings of the 2003 International Conference on Intelligent User Interfaces, Miami, Florida, 2003.

 

Game AI

Michael van Lent, Mark O. Riedl, Paul Carpenter, Ryan McAlinden, and Paul Brobst. Increasing Replayability with Deliberative and Reactive Planning. Proceedings of the 1st Conference on Artificial Intelligence and Interactive Digital Entertainment, Marina del Rey, California, 2005.

David B. Christian, Mark O. Riedl, R. Michael Young. Conversation Starters: Using Spatial Context to Initiate Dialogue in First Person Perspective Games. Proceedings of the 2002 AAAI Spring Symposium on Artificial Intelligence and Interactive Entertainment, Palo Alto, California, 2002.

 

Intelligent User Interfaces

Robert St. Amant, Mark O. Riedl, Frank E. Ritter, and Andrew Reifers. Image Processing in Cognitive Models with SegMan. Proceedings of the 11th International Conference on Human-Computer Interaction, Las Vegas, Nevada, 2005.

Mark O. Riedl and Robert St. Amant. Toward Automated Exploration of Interactive Systems. Proceedings of the 2002 Inernational Conference on Intelligent User Interfaces, San Francisco, California, 2002.

Robert St. Amant and Mark O. Riedl. A Perception/Action Substrate for Cognitive Modeling in HCI. International Journal of Human-Computer Studies, vol. 55(1), 2001.

Robert St. Amant, Christopher G. Healey, Mark O. Riedl, Sarat Kocherlakota, David A. Pegram, and Mika Torhola. Intelligent Visualization in a Planning Simulation. Proceedings of the 2001 International Conference on Intelligent User Interfaces, Santa Fe, New Mexico, 2001.

Mark O. Riedl. A Computational Model and Classification Framework for Social Navigation. Proceedings of the 2001 International Conference on Intelligent User Interfaces, Santa Fe, New Mexico, 2001.

David A. Pegram, Robert St. Amant, and Mark O. Riedl. An Approach to Visual Interaction in Mixed-Initiative Planning. Proceedings of the 1999 AAAI Workshop on Mixed-Initiative Intelligence, Orlando, Florida, 1999.