Published in Proceedings of the 2001 IEEE Aerospace Conference: Big Sky, MT, Volume 6, March 10, 2001, pages 2813-2820. DOI: http://www.dx.doi.org/10.1109/AERO.2001.931301.
© 2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Agent-based, decision-support systems provide human decision-makers with a means of solving complex problems through collaboration with heterogeneous collections of both human and computer-based expert agents. Over the past decade the Collaborative Agent Design (CAD) Research Center has developed several proof-of-concept and production-oriented agent-based, decision-support systems for both commercial and Department of Defense applications. These applications range in domain from engineering design to tactical command and control. While diverse in application, each of these systems is predicated on the same set of fundamental principles derived from years of experience in this area. Primary among these principles are the notions of high-level representation, human/computer collaborative partnership, and the development of tools as opposed to predefined solutions. The CAD Research Center has formalized this philosophy into an architectural framework together with a suite of development and execution tools. Collectively, these components are known as the ICDM (Integrated Cooperative Decision Model) framework.