Control of a mobile sensor for multi-target tracking using multi-target/object Multi-Bernoulli filter

In multi-object stochastic systems, the issue of sensor control is a theoretically and computationally challenging problem. In this paper, we present a novel random finite set (RFS) approach to the multi-target sensor management problem. Our approach is based on a partially observed Markov decision process (POMDP) where the reward function is a measure of information gain. The multi-target state is modelled as Multi-Bernoulli RFS, and the Multi-Bernoulli filter is used in conjunction with two different reward functions: maximizing the expected Rényi divergence between the predicted and updated densities, and minimizing the expected cardinality variance. Numerical studies and discussions are presented with range only measurements.