Plan Critiquing and Look-Ahead Constraint Reasoning for Active Templates

摘要

The primary objective of this program was to develop knowledge-based Active Templates technology to help Special Operations Forces (SOF) planning staff quickly build robust and agile plans, and then monitor their execution. To this end, we conducted research and development in four major areas. First, we developed a SOF knowledge representation language and example scenario for representing mission plans and constraints on those plans. Second, we developed a template-based natural language user interface to allow mission planners to input mission plan details in a format that is understandable to both the machine and human operator. Third, we designed a branch plan specification environment with a plan critiquer and look-ahead constraint reasoner, and demonstrated the feasibility of these designs by developing a temporal constraint reasoner. Finally, we developed and transitioned to operational use adaptive planning software that supports collaborative mission planning and orders production. We conclude that although successful, many areas for further research and development still exist in all four areas including further research in plan representations to support reasoning over branch plans, implementing the branch plan environment designs, and enhancing the adaptive planning software to interface with additional support tools including a knowledge base for reasoning over the plan.