This is a by-invitation-only DARPA-sponsored workshop, to be held on April 27-28, 2004 at SRI International's Washington DC office ( Some travel money may be available for invitees.

The purpose of the workshop is to discuss ways in which computer systems can be made to be aware of themselves, and what forms of self-awareness will be useful for systems with various functions. The workshop will focus on engineering and architectural issues rather than philosophical discussions.

If you wish to be invited, send email to the workshop co-chairs, with a one-or-two-page statement of your interests and background relevant to this workshop; please indicate how you might contribute to the proposed workshop themes, and/or what alternative themes you think should be addressed. Send requests for invitation by February 1, 2004; the participation decisions will be announced by February 15, 2004. Proposed workshop themes are:

Discussion: A system could be said to be aware of many aspects of itself, ranging from simple physical properties such as the state of a battery or the system's spatio-temporal location, up to higher mental properties such as the system's own intentions, desires, knowledge or goals, and its role or 'location' in a community.

The recursion implicit in the use of 'self' places various kinds of stress on conventional ideas and formalisms for knowledge representation and use, and may require new architectural ideas. Contributions to the workshop should address technical issues which arise specifically from some well-motivated form of self-awareness.

As Ron Brachman (DARPA-IPTO) has put it:

A truly cognitive system would be able to ... explain what it was doing and why it was doing it. It would be reflective enough to know when it was heading down a blind alley or when it needed to ask for information that it simply couldn't get to by further reasoning. And using these capabilities, a cognitive system would be robust in the face of surprises. It would be able to cope much more maturely with unanticipated circumstances than any current machine can.

Some relevant writings include:





Perlis:   (and enter search word ``self'')

Program committee: Vinay Chaudhri (co-chair,, John McCarthy (co-chair,, Patrick Hayes, David Israel, Leora Morgenstern, Donald Perlis, and Carolyn Talcott.

Selene Makarios 2003-10-23