Sensor Fusion Dynamic Scenario Descriptor

For Phase II, Radiance proposes to advance our design, implementation and testing of multi-sensor (RF/IR/Vis), multi-platform data fusion algorithms, advancing the state-of-the-art in Rao-Blackwellised Particle Filters in a dynamic Bayesian network framework. This effort supports the development of a multi-sensor, multi-geometry picture of threat scenarios, supporting C2BMCs requirement for a single integrated picture of the battlespace. Our algorithms provide an approach to improve tracking performance by simultaneously fusing metric and physical attributes. They adapt as sensor attribute data are added to the network, and adapt with changes in operational environments and threats, offering the potential to enhance performance and reduce risk for MDA C2BMC, and RF/EOIR sensor elements. For Phase I we researched, implemented, and tested the Dynamic Scenario Descriptor (DySD) simulation. Our Proof-of-Principle demonstrated the feasibility and utility of our approach. For Phase II we propose to advance this technology and continue DySD development. We will explore physics between target attributes, mapping linear and nonlinear spaces, and expand the number of network nodes. We will test and evaluate Phase II DySD with complex and diverse threats and sensors, and provide software demonstrations. We will identify and target technology insertion options, and advance our Commercialization Strategy.