No abstract

No abstract

In this paper, state estimation is considered for discrete-time nonlinear systems with uncertain observations and sensor failure. We focus on the multi-sensor case where sensors may fail independently of each other at different rates. The local unbiased minimum variance estimator is developed for this case. An illustrative example is included to show the performance of the proposed approach. I. MODELThe problem of random sensor failure has received a lot of attention over the years. Several solutions have been proposed, e.g. [1-5] to name a few. It was only recently that the results have been extended to the case of the multiple sensors that may fail independently [6]. Due to the importance of nonlinear system models, in this work, we are presenting an extension of [6] to the case of nonlinear systems. Reference [6] also treats stochastic robustness and resilience (for linear models) which are not discussed here. Consider the dynamical system and the measurement model ( )

No abstract

No abstract