Distributed Satellite Resource Management for Space Superiority

Emerging sensor concepts for extending the Space Surveillance Network will significantly increase the number and types of sensors available for maintaining the space catalog. Concurrently the same time the space situational awareness problem is becoming become exponentially more difficult (e.g., thousands of targets, smaller satellites, a proliferation of debris). To exploit fully these new sensing capabilities, it is necessary to develop resource management algorithms capable of computing near-optimal tasking decisions in real time for thousands of targets and dozens of sensors, and be responsive to changes in sensor performance capabilities versus different target types and operating conditions. To develop such a multi-sensor resource manager Parietal Systems, Inc. (PSI) has developed innovative multi-armed bandit algorithms in Phase I to compute efficient far-sighted solutions of the sensor allocation and scheduling problem for target search and classification. In Phase II PSI will extend these algorithms to integrate tracking with search and classification and to operate in a distributed decision-making environment with multiple users sharing common sensor assets. The effort will evaluate algorithm performance tradeoffs for different operating conditions, and demonstrate the algorithms in an closed loop evaluation system. BENEFIT: The research will produce real-time multi-sensor management algorithms that can be used for tasking the Space Surveillance Network. The sensor management algorithms will thus benefit the development new multi-sensor systems for military and security applications, but also the development of commercial multi-sensor fusion systems for detection and classification (biosurveillance monitoring, medical diagnosis, cargo inspection, inspection of infrastructure, etc.).