AAAI-2004 Intelligent Systems Demonstrator Proposal Intelligent Agents for Coalition Search and Rescue Task Support Austin Tate, Jeff Dalton, Clauirton de Siebra, Stuart Aitken AIAI, University of Edinburgh, Edinburgh EH8 9LE, UK Jeffrey M. Bradshaw and Andrzej Uszok IHMC, 40 S. Alcaniz, Pensacola, FL 32501, USA Demonstrator: Austin Tate Demonstration Materials: http://www.aiai.ed.ac.uk/project/cosar-ts/demo/isd/ Demonstration Storyboard/Screen Video (8 minutes): http://www.aiai.ed.ac.uk/project/cosar-ts/demo/isd/movies/ Shockwave (.html and .swf) Quicktime (.mov) Windows AVI with TSCC codec (.avi) Hardware and Software Requirements: The live demonstration can be run from a laptop with an internet connection. We will provide our own laptop. A large monitor or LCD projector and screen would be useful to replay this to attendees. AAAI would need to provide this. Web Services at AIAI, CMU and BBN are used in the full demonstration. Surrogates for each of these is available if any service is down. We can run locally if an internet connection is not available. An 8 minute screen recording of the demonstration is available as backup. An audio annotated version of this can be used to repeat the demonstration continuosly when the display stand is not manned. Summary: COSAR-TS is a DARPA DAML-program project to provide advanced capabilities linking models of organizational structures, policies, and doctrines with intelligent task support software. The work enables software and human agents to cooperate using a common shared intelligible model of tasks, processes, organizational structure, capabilities, agent status and presence, secure communication and access policies, authorities, and obligations. Preexisting ontologies (such as those provided in the OWL and OWL-S work) and tools (such as the CMU Matchmaker, CMU Notification Agent and BBN SONAT Elements of National Power Knowledge Base) are reused within the work - showing the value of semantically represented and shared models. The CoSAR-TS demonstrator is set in a realistic Coalition Search and Rescue scenario and aims to show the value of linking research at AIAI on I-X Task Support with IHMC work on KAoS Agent Domain and Policy Management concepts. OWL representations, and OWL-S descriptions of agents and services are utilized.