KalmanPosterior¶

class probnum.filtsmooth.KalmanPosterior(locations, state_rvs, gauss_filter)¶

Bases: probnum.filtsmooth.filtsmoothposterior.FiltSmoothPosterior

Posterior Distribution after (Extended/Unscented) Kalman Filtering/Smoothing

Parameters:	locations (array_like) – Locations / Times of the discrete-time estimates. state_rvs (`list` of `RandomVariable`) – Estimated states (in the state-space model view) of the discrete-time estimates. gauss_filter (`GaussFiltSmooth`) – Filter/smoother used to compute the discrete-time estimates.

Attributes Summary

`locations`	Locations / times of the discrete observations
`state_rvs`	Discrete-time posterior state estimates

Methods Summary

__call__(t[, smoothed]) Evaluate the time-continuous posterior at location t

Attributes Documentation

locations¶

Locations / times of the discrete observations

Type:	`np.ndarray`

state_rvs¶

Discrete-time posterior state estimates

Type:	`list` of `RandomVariable`

Methods Documentation

__call__(t, smoothed=True)[source]¶

Evaluate the time-continuous posterior at location t

Algorithm: 1. Find closest t_prev and t_next, with t_prev < t < t_next 2. Predict from t_prev to t 3. (if smoothed=True) Predict from t to t_next 4. (if smoothed=True) Smooth from t_next to t 5. Return random variable for time t

Parameters:	t (float) – Location, or time, at which to evaluate the posterior. smoothed (bool, optional) – If `True` (default) perform smooth interpolation. If `False` perform a prediction from the previous location, without smoothing.
Returns:	Estimate of the states at time `t`.
Return type:	`RandomVariable`