Reallocation and Cross-Domain Optimization using Relationally-Consistent Semantic Extensions (ReCOURSE)
Small Business Information
MA, Cambridge, MA, 02138-4555
AbstractABSTRACT: Real world uncertainties all but guarantee that execution will deviate from even carefully considered plans, and therefore any effective military command will assume that resources must be reallocated to achieve desired outcomes. Unfortunately, reallocation is typically a manual process that results in sub-optimal use of resources and force effectiveness. To provide a system that can dynamically reallocate resources across air, space, and cyber domains, Charles River Analytics proposes a Phase II effort to develop and evaluate a full-scope prototype for Reallocation and Cross-Domain Optimization using Relationally-Consistent Semantic Extensions (ReCOURSE). Our approach includes four primary components: (1) a semantically rich, logically grounded representational layer that can query, integrate and control data management, analysis, and definitional information technologies; (2) a computational inference layer that takes sensor data, quantitative metrics, and other types of information as input and uses it to output definitions, descriptions, analyses, and projections of world states; (3) an empirically informed efficacy-mining function that learns resource effectiveness based on operational data; and (4) a multi-objective optimization layer that generates options and tradeoffs between solutions. ReCOURSE will provide significant value to the Joint Forces Air Component Commander, specifically supporting analyzing/approving a recommended target list received from the Joint Targeting Board. BENEFIT: The research performed under this effort will have immediate benefit to Air Operations Center Weapon System(s) (AOC WS) that are assigned to multiple geographic and functional combatant commands. Additionally, advances in this area of plan analysis and maintenance could help in other military domains across air, maritime, ground, and space operations. This research will also have direct application to enhance our commercial EAToolkit product, a software development kit for optimization using evolutionary algorithms.
* information listed above is at the time of submission.