IDA: a cognitive agent architecture

Abstract

We describe an architecture for an intelligent distribution agent being designed for the Navy. This autonomous software agent will implement global workspace theory, a psychological theory of consciousness. As a result, it can be expected to react to novel and problematic situations in a more flexible, more human-like way than traditional AI systems. If successful, it will perform a function, namely billet assignment, heretofore reserved for humans. The architecture consists of a more abstract layer overlying a multi-agent system of small processors. The mechanisms implementing the architecture are quite varied and diverse, and are drawn mostly from the "new" AI.