PROJECT TITLE :
Non-myopic sensor scheduling to track multiple reactive targets
This study addresses the sensor scheduling drawback of selecting and assigning sensors dynamically for multi-target tracking. The authors goal is to trade off the tracking accuracy and the interception risk during a period of your time. The interception risk is incurred by the actual fact that the emission energy originating from a sensor will be intercepted by the target throughout the tracking mission. To react to sensor emission, the targets are ready to switch between dynamic models. This non-myopic sensor scheduling downside is formulated as a partially observable Markov call process, where the one-step reward is constructed by combining the tracking error with the interception probability and the knowledge state is tracked by the interacting multiple model extended Kalman filtering. A novel sampling approach using the unscented transformation is proposed for long-term reward approximation. Numerical simulations illustrate the validity of the proposed scheduling scheme.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here