Putting AI in Entertainment: An AI Authoring Tool for Simulation and Games

摘要

For the past couple of years, a small group of people at Stottler Henke Associates, an Artificial Intelligence (AI) consulting company, have been working on techniques to write better AI behavior for simulations and games. They are focusing on a visual authoring tool that provides a way to quickly synthesize complex behavior, and are building a corresponding AI engine to run with a simulation or game. For game development uses, they see their tool making the AI understandable to game designers and end users, as well as improving developers' productivity. This work also will be useful for simulation developers and for analysts, operators, and instructors. Here, they explain some of their tool's features and how the AI engine processes the resulting content. On the basis of their tests with the popular simulation games Half-Life and Civilization 2, the authors made four major extensions to increase the efficacy and expressiveness of their BrainFrame visual language: global and local variables, interrupt transitions, shared blackboards, and polymorphic indexing of behaviors.