home | research | classes | documents | bio and CV | consulting | contacting me

 My research focus is the creation of computational models of interactive narrative within virtual environments. My work builds on concepts from narrative theory, cognitive psychology, and computational linguistics, using techniques from artificial intelligence and computer science to construct a framework for the intelligent control of interactive virtual worlds. Much of my work is based on the use of planning and plan-based knowledge representations. Within that topic, my work touches on many areas:

• Hierarchical task network and causal link planning.
• Natural language discourse generation
• Cognitive models of narrative comprehension
• The role of narrative in learning within virtual worlds
• Intelligent user interfaces to support interactive plan authoring
• AI techniques in computer games

Recently, I’ve been looking at ways that games and intelligent technology can be used to engage students in computers and programming.

Examples of the work done in my group include:

• developing a service-oriented architecture providing access to planning and plan execution from conventional applications
• designing a game creation tool that makes building 3D games accessible to high school kids with little or no programming experience.
• extending discourse generation techniques to model temporal, causal and epistemic relationships between camera actions (e.g., shots and shot sequences) and the physical events that they film.
• developing algorithms for plan execution, monitoring and repair that proactively adapt the flow of a narrative around the actions of a user.
• constructing intelligent user interfaces for interactive story authoring, targeted at authors rather than information technologists.

and so much more.

Our work spans the range from concepts to theory to applications. Some of our work is conceptual: defining new representation schemes and exploring their expressive power. Some of it is theoretical and algorithmic: designing new plan adaptation algorithms and proving that they achieve certain properties. And some is applied: experimenting with our approaches in both virtual and real environments. Some of the applications that we are particularly interested in right now are: constructing narratives for effective learning of causal and temporal domain features, interactive story construction for literacy education, plan management in massively multi-player on-line worlds.

Some of the active funding sources for my work include:

• HI-FIVES: Using web-Based Gaming to Improve Student Comprehension of Information Technology in Science, from the National Science Foundation program on Information Technology Experiences for Students and Teachers
• Plan-Based Integration of Control and Coherence in Intelligent Exploratory Environments, a National Science Foundation Early Career Development (CAREER) award.
• Creating Effective Task Descriptions from Action Plans, from the National Science Foundation program on Human Language and Communication.

Currently, I direct the Liquid Narrative research group here at NC State University. The main research systems that we're working center around the Zocalo architecture for intelligent control of virtual environments and the development of computational models of interactive narrative for games, training simulations and educational applications.

Previously, I worked as a post-doctoral fellow helping to develop the RETSINA multi-agent architecture, as part of the Intelligent Software Agents group at Carnegie Mellon University's Robotics Institute.

Before joining CMU, I worked as a graduate student on problems of natural language discourse generation in the context of intelligent tutoring projects at the University of Pittsburgh's Learning Research and Development Center.