MAP moving horizon state estimation with binary measurements
It provides a computationally tractable MAP estimation method for systems with binary measurements, which is important for applications like sensor networks with threshold sensors.
The paper develops a moving horizon MAP state estimator for discrete-time systems with binary measurements, showing that for linear systems with log-concave noise, the estimator solves a convex optimization problem at each step. Simulations on diffusion field estimation demonstrate effectiveness.
The paper addresses state estimation for discrete-time systems with binary (threshold) measurements by following a Maximum A posteriori Probability (MAP) approach and exploiting a Moving Horizon (MH) approximation of the MAP cost-function. It is shown that, for a linear system and noise distributions with log-concave probability density function, the proposed MH-MAP state estimator involves the solution, at each sampling interval, of a convex optimization problem. Application of the MH-MAP estimator to dynamic estimation of a diffusion field given pointwise-in-time-and-space binary measurements of the field is also illustrated and, finally, simulation results relative to this application are shown to demonstrate the effectiveness of the proposed approach.