Determining proper input dimensions based on noise additivity should be done inside the TransitionModel and MeasurementModel.
A more drastic solution would rework the transforms to take in TransitionModel/MeasurementModel directly. This would mean that apply() would no longer have to take the function handle as input, and the StateSpaceInference._time_update() would have to be modified accordingly.
The following lines appear in every single filter class
These just serve to determine which input dimensionality should be supplied to the transforms, which happens next, for example:
Determining proper input dimensions based on noise additivity should be done inside the
TransitionModel
andMeasurementModel
.A more drastic solution would rework the transforms to take in
TransitionModel
/MeasurementModel
directly. This would mean thatapply()
would no longer have to take the function handle as input, and theStateSpaceInference._time_update()
would have to be modified accordingly.