Adaptive Tasking of Radar and Optical Sensors

Today's battlefield environment contains large number of sensors onboard multiple platforms. This set of sensors types includes SAR, EO/IR, GMTI, AMTI, HSI, MSI, and video and for each sensor type there may be multiple modalities. In an attempt to maximize sensor performance, today's sensors employ either very simplistic tasking approaches or require an operator to manually change sensor tasking operations. As such, the sensors become less effective as the sensing environments deviates from the assumed conditions. In order to improve the overall system capability, this effort examines a genetic algorithm approach to solving the adaptive sensor tasking problem. The genetic algorithm approach is a method for intelligently searching a large solution space with the added benefit that it is highly parallelizable and easily incorporates prior solution information. This Phase I effort will develop an objective function that accurately models the adaptive sensor tasking problem, develop a genetic algorithm solution for this problem, and provide a proof-of-concept demonstration of this capability.