Believability through Context Using 'knowledge in the world' to create intelligent characters

摘要

Intelligent characters are presently quite limited. How useful and how believable they are depends on the extent to which they are integrated into a specific environment for a particular set of tasks. This tight integration of character and context is an inadequate approach in the rapidly-expanding realm of large, diverse, structurally homogeneous but disparate virtual environments, of which the Web is only the most obvious example. By separating a character's core features, which are invariable, from its knowledge of and abilities in any specific environment, and embedding this latter information as annotations in the environment itself, we can significantly improve the character's believability, its utility, and its reusability across a variety of domains. This paper describes an agent architecture that can interaet with an annotated virtual environment, together with a structure for representing information in and about these environments. We also present an example applying this approach to intelligent characters in a complex virtual world.