Coherence and Relevance Monitoring and Adjustment (CARMA)

ABSTRACT:Maintaining the efficacy of military plans is difficult, yet critical. A plan may become irrelevant because the world has diverged from the plans assumptions; if there are changes to many related plans, they may become incoherent, unable to generate well-synchronized and coordinated operations. The Adaptive Planning process partly addresses this problem through cyclical, collaborative plan review and maintenance. However, to fully address this problem, the military needs a highly-automated and effective system that continuously maintains living plans in response to rapidly changing conditions. Charles River Analytics proposes to implement and evaluate a system for plan Coherence and Relevance Monitoring and Adjustment (CARMA) to provide an affordable, open, and extensible solution to help generate and maintain living plans. To create this system, we will develop: (1) a sophisticated catalog that represents plan elements (e.g., goals, assets, terrain) and their relationships (e.g., supported, supporting, and collateral) across time and space; (2) monitoring and analysis algorithms that can automatically guide Warfighters to adapt plans to changes that threaten plan coherence or relevance; and (3) an information extraction and routing service that grounds the living plan process in accurate, complete, and timely information.BENEFIT:The research performed under this effort will have immediate benefit to the Air Operations Center Weapon System (AOC WS) across multiple regional and functional AOCs. Specifically, it will increase the productivity of current planners as it allows them to attend to the most significant implications of changes in the operating environment, thereby increasing plan quality as planners spend more time thinking creatively and collaboratively. It will also improve force effectiveness as forces will go into battle with plans that achieve effective unity of effort. These benefits will apply across air, maritime, ground, and space domains. This research will also enhance our commercial AgentWorks software development kit for deploying hybrid computational reasoning into an enterprise.