SBIR-STTR Award

Our proposed Defensive Engagement System (DES) is designed to provide the submarine decision maker with automated actions, decision aids, and workflow cues to maximize the effectiveness of defensive actions when they are required. The DES encompasses automated defensive payload assignments, automated and optimized presets, evasion planning with options, rapid counter fire capability, and other defensive actions aids to provide enhanced situational awareness. The DES is designed to operate as a background function so that it is always engaged and current plans and recommendations can be reviewed during the watch routine. Our DES is also designed as both a forward fit and back fit capability. Leveraging our Combat System of the Future architecture, the forward fit application is designed as a service for a Service Oriented Architecture (SOA) implementation. For the back fit requirements, a translation layer will be used to provide similar functionality for current architecture configurations. The proposed DES, takes a layered defensive strategy by providing sensor cueing for early assessments of transients or other energy detections of interest. With the sensor to display approach, defensive aids and recommendations can provide the best available guidance on the required accelerated defensive decision time line.

Keywords:
Submarine Evasion, Submarine Evasion, Automation, Counterfire, Defensive Decision Aids, Countermeasures

Providing tactical cueing information to support accelerated situational understanding as an aid for the platform watch team, is the objective of this Phase II SBIR. With the greater availability of information from advanced sensors, third party information, and autonomous vehicles, the watch team can become overloaded and either miss or not properly assimilate the data available at any given point in time. Using a mission driven and decision centered design process, our research and associated innovative experimentation will temporally identify and properly characterize the watch team information needs. This provides the foundation for applying predictive analytics through machine learning, deep learning, and artificial intelligence (AI), significantly increasing a watch team’s ability to handle greater complexity and uncertainty. Utilizing and properly combining the appropriate tactical information, environmental variables, and historical data can also serve to measure and track evolving tactical risks. This information, when compared with risks perceived by the watch team, can lead to alternative considerations otherwise potentially missed. In addition, providing timely tactical cues can and should increase the platform’s safety as well as effectiveness for successfully completing routine and non-routine evolutions. Capturing and incorporating fleet expertise as tactical cues will also serve to provide continuous watch team training.