Real-time dynamic coordinate and parameter estimation with lattice-based non-linear probabilistic filters

摘要

A real-time method for dynamic state quantity determination initially comprises a prediction of an a priori probability density function (PDF) for a state variable vector as a function of a last a posteriori PDF and a nonlinear stochastic process equation characterizing the state variable vector. Then a measured value vector is generated, which has observations about the state variable vector as measuring signals. The measured value vector and the a priori PDF are converted into a measurement density function and discretized on a Cartesian grid, in particular a thin grid. Iteratively, the a priori PDF is tracked step by step taking into account an affine linear transformation of the grating of the measurement density function. After each iterative tracking step, an updated a posteriori PDF is estimated as the product of the a priori PDF on the affine linear transformed grid having a weighting coefficient formed from the relationship between the measurement density function on the non-transformed grid and the tracked measurement density function.