Distributed Decentralized Fusion for Developing a Common Undersea Scene

Naval C4ISR systems are inherently distributed, relying on a variety of platforms and sensors to supply various aspects of the littoral battlespace. The ASW and MCM commanders require an accurate and timely scene that is developed within a network-centricinfrastructure, with the ultimate goal of maintaining a consistent portrayal of the battlespace among dispersed warfighters. Critical issues that hinder development of a consistent undersea picture across distributed C2 nodes include shared sensor dataacross multiple platforms, bandwidth constraints in exchanging information, interfacing with legacy systems, registration errors, and communication latencies.Multi-platform, decentralized tracking has the potential to outperform centralized tracking approaches in the real world. We leverage our experience in multi-source hierarchical tracking and fusion to develop baseline algorithms that include an efficientapproach to distributed multi-hypothesis tracking, cutting edge nonlinear filtering, mixed detection-level and track-level processing, and a recursive approach to track fusion that supports real-time processing. New capabilities to be developed include:adaptive tracklet formation algorithms that reflect target dynamics, target interaction, network loading, and real time demands; network-centric data association algorithms that preserve ambiguities to downstream decision-making processes; effectivetracklet processing algorithms that account for correlation, sensor measurements, and context data; and bias estimation and compensation algorithms. The proposed technology will help support network-centric multi-sensor multi-target tracking capabilitiesfor ASW and MCM C4ISR systems in developing a common undersea picture. Commercial and military applications include border and maritime surveillance and reconnaissance, and law enforcement for smuggling and other illegal activities.