A system for controlling the behaviors of an interactive human-like agent, and executing them in real-time, is presented. It relies on an underlying model of continuous behavior, as well as a discrete scheduling mechanism for changing behavior over time. A multiprocessing framework executes the behaviors and renders the motion of the agents in real-time. Finally we discuss the current state of our implementation and some areas of future work.
John P. Granieri, Welton Becket, Barry D. Reich, J