Optimal sensor scheduling for hybrid estimation

In this paper, we consider a sensor scheduling problem for a class of hybrid systems named as the Stochastic Linear Hybrid System (SLHS). We propose an algorithm which selects one (or a group of) sensor at each time from a set of sensors. Then, the hybrid estimation algorithm computes the estimates of the continuous state and the discrete state of the SLHS based on the observation from the selected sensors. As the sensor scheduling algorithm is designed such that a Bayesian decision risk is minimized, the true discrete state can be better identified. At the same time, the continuous state estimation performance of the proposed algorithm is better than that of other hybrid estimation algorithms using only predetermined sensors. Finally, our algorithm is validated though an illustrative target tracking example.