Marie A. Bienkowski
In this paper, we report on our past and continuing cxperiences in applying an AI generative planning system to the problem of generating crisis action operations plans in a military domain. We describe the application, the System for Operational Crisis Action Planning (SOCAP). and the lessons we learned creating it. We also report on the applied research we performed to address the lessons learned from the use of SOCAP in the second Integrated Feasibility Demonstration (IFD-2). This research involved integrating the generative planner with several complementary technologies that were available in the Planning Initiative: a temporal reasoner, a case-based reasoner, and the capacity analysis component of a scheduling system. We discuss both the unique characteristics of each Technology Information Experiment (TIE) and the general features that contributed to the success of each one. Finally, we present current work on the application of SOCAP to providing feasibility estimations of air campaign plans. scheduled for demonstration in IFD-4.