Abstract

Here we describe briefly the architecture and mechanisms of a "conscious" software agent named IDA who is to act as a type of employment agent (Franklin in press). This agent is "conscious" in the sense of implementing the Global Workspace Theory of consciousness (Baars 1988, 1997). We go on to show how this architecture and these mechanisms allow IDA to deliberate much as we humans do and to make voluntary choices of actions (Franklin 2000). The technology described, if successful, should allow the automation of the work of many human information agents (Franklin 2001). The IDA model also makes, hopefully testable, hypotheses about how human action selection, deliberation and volition (Franklin & Graesser 2001 to appear).

IDA possesses the mechanisms prescribed for consciousness by Global Workspace Theory. Is she truly conscious in the sense of being sentient? IDA has no self, but we believe one can be added. IDA isn't self-conscious, but she could be. She could be made to report her "experiences." How would one support or deny the claim that IDA is truly conscious?

References

Baars, B. J. 1988. A Cognitive Theory of Consciousness. Cambridge: Cambridge University Press.

Baars, B. J. 1997. In the Theater of Consciousness. Oxford: Oxford University Press.

Franklin, S. 2000. Deliberation and Voluntary Action in 'Conscious' Software Agents. Neural Network World 10:505-521.

Franklin, S. 2001. Automating Human Information Agents. In Practical Applications of Intelligent Agents, ed. Z. Chen, and L. C. Jain. Berlin: Springer-Verlag.

Franklin, S. in press. Conscious Software: A Computational View of Mind. In Soft ComputingAgents: New Trends for Designing Autonomous Systems, ed. V. Loia, and S. Sessa. Berlin: Springer (Physica-Verlag).

Franklin, S., and A. Graesser; 2001 to appear. Modeling Cognition with Software Agents. CogSci2001; Cognitive Science Society; Edinburgh, Scotland; August 1-4, 2001.