Constrained Sensor Control for Labeled Multi-Bernoulli Filter Using Cauchy-Schwarz Divergence

Abstract

A constrained sensor control method is presented for multiobject tracking using labeled multi-Bernoulli filters. The proposed framework is based on a novel approximation of the Cauchy-Schwarz divergence between the labeled multi-Bernoulli prior and posterior densities, which does not need Monte Carlo sampling of random sets in the multiobject space. The void probability functional is also formulated for labeled multi-Bernoulli distributions and used within our proposed method to form a constrained sensor control solution. Numerical studies demonstrate that reasonably acceptable movements are decided for the controlled sensor by our sensor control method, with the advantage that the void probability constraint is formally considered as part of the sensor control optimization algorithm.