Award

In military operations, it is vital that commanders have a high-level of situational awareness to manage risk and make effective decisions. Historically, the limitation of situational awareness has been the availability of data. However, in today's data-saturated battlefield, the challenge has shifted to efficiently harnessing the torrent of source data to construct an accurate picture of the battlespace. For a typical Maritime Operations Center (MOC), the Common Operational Picture (COP) is the visual representation of the collective situational awareness. As the Navy develops the Maritime Tactical Command and Control (MTC2) system, the NavyÆs next generation command and control platform, it is paramount that the underlying data management and analytics can effectively leverage the deluge of multi-modal geospatial and non-geospatial data. To meet these challenges, the Machina Cognita Technologies (MCT) team (MCT, University at Buffalo, and Voyager Search) proposes to develop the Multi-modal Evidential Deduction for Upgraded Situational Awareness (MEDUSA) engine. The system will streamline the data management pipeline, leverage Machine Learning (ML) algorithms to drive accurate and targeted analytics, and create and integrate enhanced data layers and geospatial visualizations. Overall, the MEDUSA system will lead to increased situational awareness and enhanced geospatial analytics to accelerate and support kill chain requirements. The MEDUSA system will be designed to be an end-to-end data enhancement and visualization system supporting analysis for kill chain requirements. It will ingest multi-model COP source data, generate enhanced predictive data layers, and output real-time geographic visualizations to aid in threat analysis and environmental assessment. The efficiencies gained from a streamlined prediction analysis will lead to a clear and rapidly understandable operational picture providing increased situational awareness. MEDUSA will be composed of four primary components: a data correlation and entity disambiguation engine, semantic state space and entity embedding models, geospatial analytics algorithms, and an enhanced visualization tool. MEDUSA will expand and expedite the available data behind each entity displayed on the COP through an entity disambiguation step. By providing a single correlated view of the known information pertaining to each entity, MEDUSA will be able to help expedite the kill chain process. MEDUSA will then utilize semantic embedding space algorithms to encapsulate both the world state information as well as entity state information to enable analysis of the entire situation by deep learning-powered geospatial analytics algorithms. Next, MEDUSA will provide a collection of geospatial analytics algorithms to empower visualizations providing commanders with rapid, enhanced situational awareness. Finally, the MEDUSA system will provide semantically filterable and mission-specific data layers and visualizations.