An Agent Architecture Potentially Capable of Robust Autonomy
Stan Franklin · 2001
Robust autonomy on the part of software agents re-quires, at least in part, the ability to deal intelligently with novel and unexpected situations. According to global workspace theory, dealing with such situations is one of the primary functions of consciousness in humans. Below we briefly describe two software agents that implement this psychological theory, and discuss their resulting potential for robust autonomy. Autonomous Agents Artificial intelligence pursues the twin goals of understand-ing human intelligence and of producing intelligent arti-facts. Designing, implementing and experimenting with autonomous agents (Franklin & Graesser 1997) furthers both these goals in a synergistic way. In particular, design-