A Bayesian method for integrated multitarget tracking and sensor management
Chris Kreucher, Keith D. Kastella, Alfred O. Hero · 2003
Abstract- This paper presents an integrated method for target tracking and sensor management, applied to the problem of tracking multiple ground targets. We use a multiple target tracking methodology based on re-cursive estimation of a Joint Multitarget Probability Density (JMPD) which is implemented using particle filtering methods. This Bayesian method for tracking multiple targets allows nonlinear, non- Gaussian target motion and measurement-to-state coupling. The sen-sor management scheme is predicated on maximizing the expected Rinyi Information Divergence between the current JMPD and the JMPD after a measurement has been made. The Rinyi Information Divergence, a gen-eralization of the Kullback-Leibler Distance, provides a way to measure the dissimilarity between two den-sities. Sensor management then proceeds by evaluat-ing the expected information gain for each of the pos-sible measurement decisions, and selecting to make the measurement that maximizes the expected information gain.