Building Intelligent Synthetic Characters for Computer Games

John E. Laird

Professor of Electrical Engineering and Computer Science, University of Michigan

Newell-Simon Hall 1305 (Michael Mauldin Auditorium)

Synthetic characters in computer games usually fall short of human players, struggling to exhibit even a modicum of intelligence. However, progress is being made. Characters in recent games have progressed to include limited forms of situation-based reasoning, communication, and cooperation. The continued improvement in the intelligence of synthetic characters should lead to significant improvements in game play as well as new gaming experiences. Our work in developing characters for computer games using the Soar architecture tries to push even further to human-like behavior. In this talk, I’ll review our research on Soar, an architecture for building AI systems and psychological models of human behavior. I’ll also briefly describe our development of TacAir-Soar, a real-time expert system that flies U.S. military air missions in simulation, and that is used for training in the U.S. Air Force. Our experience building TacAir-Soar is now being applied to building human-like synthetic characters for computer games, specifically Quake II. The Soar Quakebot creates and uses internal maps of its environment and attempts to anticipate the actions of opponents via internal projective modeling. Two hypotheses underlying this talk are that AI architectures such as Soar can greatly improve the cognitive capabilities of synthetic characters and speed development using modest computational resources; and that computer games provide a challenging (and cool) environment for research in AI.

Speaker's Bio

John E. Laird is a Professor of Electrical Engineering and Computer Science at the University of Michigan and Associate Chair of the Computer Science and Engineering Division. He received his Ph.D. in Computer Science from Carnegie Mellon University in 1983. His research interests spring from a desire to understand the nature of the architecture underlying artificial and natural intelligence. He is one of the original developers of the Soar architecture and leads its continued development and evolution. He has done research in problem solving, learning, problem solving, cognitive modeling, and interactive knowledge-rich agents. From 1992–1997, he led the development of TacAir-Soar, a real-time expert system that simulates military pilots and is used in training in large-scale distributed simulations. He is a founder of Soar Technology, which continues to develop TacAir-Soar and related software for the military. Most recently his research has broaden to include creating human-like AI systems in computer games. He was an organizer of two symposia on AI and computer games and has been a presenter at the last three Computer Game Developers Conferences.

Upcoming Events