Underwater Target Motion Analysis with Dynamic Sensor Selection in Multi-Sensor Environment

The objective of our work is to track an underwater target moving in 3D space using a multi-sensor network of passive sonobuoys spread over the sea surface. All the buoys are equipped with passive SONAR that measures the bearing and elevation angles of the target. The tracker is located remotely from the sensors, and the measurements from the sonobuoys are sent to a common central tracker for further processing. But due to some physical constraints, it is not always possible to send the data from all the sensors together. To select a set of sensors, we have designed a cost function by utilizing the Fisher information matrix (FIM) of the estimated target states. The optimum solution for this cost function gives the desired sensor subset. The measurements obtained from these selected sensors are used to perform the target state estimation using various non-linear estimators. The performances of these estimators are compared in terms of root mean square (RMSE) error of target states and percentage track divergence.