Oz Project Overview

Dusk in Cairo. You are walking down a dusty street, on your way to a museum. You wish to discover the origin of a symbol found in a book belonging to your father the archeologist. Your father had told you, before he died, that this book contained his life's work. Suddenly, you hear footsteps. A man grabs the shoulder of your leather jacket. He says he is Horace, a friend of your father's, and if you come with him, he can help you. You stop in Cafe Tut -- he is charming and surprisingly knowledgeable about your father. You absorb his every word, until you suddenly get an eerie feeling. Horace is asking strange questions about the book. Your father's book. You then notice a suspicious gun-like bulge in his suit jacket. You slowly get up, mentioning the restroom, and then bolt out of the cafe, barely evading Horace's hands as you jump into the nearest taxi. ``Quick, get me to the museum,'' you scream over the sound of the screeching tires. You relax as you see Horace getting smaller though the rear window of the cab. ``Yes, Sir,'' the gold-toothed cabbie replies with a smile, heading quickly in the wrong direction.

This is a description of what a short segment of Interactive Drama should be like. You find yourself immersed in a fantasy world with exciting characters and the possibility of many adventures. Although you control your own direction by choosing each action you take, you are confident that your experience will be good, because a master interactive-storyteller subtly controls your destiny.

We use the phrase ``interactive drama'' to mean the presentation by computers of rich, highly interactive worlds, inhabited by dynamic and complex characters, and shaped by aesthetically pleasing stories. People interacting with these worlds will be called ``interactors.'' A similar notion, which has influenced our work, has been presented by Laurel (Laurel 89, Laurel 91).

``Highly interactive'' is an important phrase of our description. The word ``interactive'' distinguishes our work from conventional media, while ``highly interactive'' indicates the interactor is choosing what to do, say, and think at all times, in contrast to other interactive media such as hypertext, where the interactor is given only a small number of fixed choices. If our example had been a conventional story, the author alone would decide exactly what happens to the protagonist. In interactive drama, the interactor is the protagonist and determines the action.

Likewise, the term ``drama'' is important. Even though the interactor is choosing what to do, say, and think, there is a destiny, created by the author of the interactive drama. This destiny is not an exact sequence of actions and events, but is subtly shaped by the system, which embodies dramatic theory and principle, in order to create a cathartic experience.

Oz is a computer system we are developing that allows authors to create and present interactive dramas (Bates 92). Figure 1 shows the Oz system architecture. The architecture includes a simulated physical world, several characters, an interactor, a theory of presentation, and a drama manager. A model of each character's body and of the interactor's body are in the physical world. Outside the physical world, a model of mind controls each character's actions. The interactor's actions are controlled by the interactor. Sensory information is passed from the physical world to the interactor through an interface controlled by a theory of presentation. As shown, the drama manager influences the characters' minds, the physical world, and the presentation theory.

Oz has three primary research foci: characters, presentation, and drama. As in traditional media, each of these areas is important for creating a rich dramatic experience. In our research on characters we study how to create computer controlled agents that appear reactive, goal directed, emotional, moderately intelligent, and capable of using natural language (Bates et al. 91, Bates et al. 92, Reilly & Bates 92). Currently, the project has two different presentation models: textual and animated. The textual system uses text as the input and output medium. The world and characters are described through text, and the interactor's actions are entered to the computer through text. In the animated system, the world and characters are presented graphically. Humans interact with the system physically, through sonar sensors and a mouse. In the future of both systems, people may interact through sounds and speech. For the most part, our presentation research deals with how to generate English narrative text (Kantrowitz 90, Kantrowitz & Bates 92). We also study how the state of a story can affect the best way to describe a scene (Smith & Bates 89). The work on drama has to do with how we can represent and control an interactive story with the computer (Bates 90).

References (For a complete list of Oz papers, see our publications page.)

Bates, J. (1990). Computational Drama in Oz. In Working Notes of the AAAI-90 Workshop on Interactive Fiction and Synthetic Realities, Boston, MA.

Bates, J. (1992). Virtual Reality, Art, and Entertainment. PRESENCE: Teleoperators and Virtual Environments, 1(1):133-138.

Bates, J., Loyall, A. B., Reilly, W. S. (1991). Broad Agents. In Proceedings AAAI Spring Symposium on Integrated Intelligent Architectures, Stanford, CA. Available in SIGART Bulletin, Volume 2, Number 4, August 1991, pp. 38-40.

Bates, J., Loyall, A. B., Reilly, W. S. (1992). An Architecture for Action, Emotion, and Social Behavior. In Proceedings of the Fourth European Workshop on Modeling Autonomous Agents in a Multi-Agent World,, S.Martino al Camino, Italy.

Kantrowitz, M. (1990). Natural Language Text Generation in the Oz Interactive Fiction Project. Technical Report CMU-CS-90-158, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA.

Kantrowitz, M. and Bates, J. (1992). Natural Language Text Generation in the Oz Interactive Fiction Project. In Dale, R., Hovy, E., Rosner, D., and Stock, O., editors, Aspects of Automated Natural Language Generation, Volume 587 of Lecture Notes in Artificial Intelligence, pp. 13-28. Springer-Verlag. (This is the Proceedings of the Sixth International Workshop on Natural Language Generation, Trento, Italy, April 1992.) Also appeared as Technical Report CMU-CS-92-107, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, April 1992.

Laurel, B. (1986). Toward the Design of a Computer-Based Interactive Fantasy System. Ph.D. Thesis, Drama Department, Ohio State University.

Laurel, B. (1991). Computers as Theater. Addison-Wesley Publishing Company, Reading, MA.

Reilly, W. S., and Bates, J. (1992). Building Emotional Agents. Technical Report CMU-CS-92-143, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA.

Smith, S. and Bates, J. (1989). Toward a Theory of Narrative for Interactive Fiction. Technical Report CMU-CS-89-121, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA.

Maintained by: