Various Ways to Compute the Continuous-Discrete Extended Kalman Filter

Abstract

The Extended Kalman Filter (EKF) is a very popular tool dealing with state estimation. Its continuous-discrete version (CD-EKF) estimates the state trajectory of continuous-time nonlinear models, whose internal state is described by a stochastic differential equation and which is observed through a noisy nonlinear form of the sampled state. The prediction step of the CD-EKF leads to solve a differential equation that cannot be generally solved in a closed form. This technical note presents an overview of the numerical methods, including recent works, usually implemented to approximate this filter. Comparisons of theses methods on two different nonlinear models are finally presented. The first one is the Van der Pol oscillator which is widely used as a benchmark. The second one is a neuronal population model. This more original model is used to simulate EEG activity of the cortex. Experiments showed better stability properties of implementations for which the positivity of the prediction matrix is guaranteed.