Bayesian Filtering Library Generated from SVN r
BackwardFilter< StateVar > Class Template Referenceabstract

Virtual Baseclass representing all bayesian backward filters. More...

#include <backwardfilter.h>

Inheritance diagram for BackwardFilter< StateVar >:
ParticleSmoother< StateVar >

Public Member Functions

 BackwardFilter (Pdf< StateVar > *prior)
 Constructor.
 
 BackwardFilter (const BackwardFilter< StateVar > &filt)
 copy constructor
 
virtual ~BackwardFilter ()
 destructor
 
virtual void Reset (Pdf< StateVar > *prior)
 Reset Filter.
 
virtual bool Update (SystemModel< StateVar > *const sysmodel, const StateVar &u, Pdf< StateVar > *const filtered_post)
 Full Update (system with inputs)
 
virtual bool Update (SystemModel< StateVar > *const sysmodel, Pdf< StateVar > *const filtered_post)
 Full Update (system without inputs)
 
virtual Pdf< StateVar > * PostGet ()
 Get Posterior density.
 
int TimeStepGet () const
 Get current time.
 

Protected Member Functions

virtual bool UpdateInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, Pdf< StateVar > *const filtered_post)=0
 Actual implementation of Update, varies along filters.
 

Protected Attributes

Pdf< StateVar > * _prior
 prior Pdf
 
Pdf< StateVar > * _post
 Pointer to the Posterior Pdf.
 
int _timestep
 Represents the current timestep of the filter.
 

Detailed Description

template<typename StateVar>
class BFL::BackwardFilter< StateVar >

Virtual Baseclass representing all bayesian backward filters.

This is the virtual baseclass representing all simularities between Bayesian backward filters. One class of smoothers corresponds to a forward pass (with a classical Bayesian filter) and a backward pass (with a backward Bayesian filter) The backward filters related with these smoothers are related to a System Model (they don't need a measurement model!(for as far I see now))

This class is the base class for a rauch tung striebel backward filter, a backward particle filters, ...

See also
Pdf SystemModel ConditionalPdf

StateVar represents the form of the states and inputs

Definition at line 59 of file backwardfilter.h.

Constructor & Destructor Documentation

◆ BackwardFilter()

template<typename StateVar >
BackwardFilter ( Pdf< StateVar > * prior)

Constructor.

Precondition
you created the prior
Parameters
priorpointer to the prior Pdf

◆ ~BackwardFilter()

template<typename SVar >
~BackwardFilter ( )
virtual

destructor

Definition at line 32 of file backwardfilter.h.

Member Function Documentation

◆ PostGet()

template<typename SVar >
Pdf< SVar > * PostGet ( )
virtual

Get Posterior density.

Get the current Posterior density

Returns
a pointer to the current posterior

Definition at line 65 of file backwardfilter.h.

◆ Reset()

template<typename StateVar >
void Reset ( Pdf< StateVar > * prior)
virtual

Reset Filter.

Definition at line 39 of file backwardfilter.h.

◆ TimeStepGet()

template<typename SVar >
int TimeStepGet ( ) const

Get current time.

Get the current time of the filter

Returns
the current timestep

Definition at line 46 of file backwardfilter.h.

◆ Update() [1/2]

template<typename StateVar >
virtual bool Update ( SystemModel< StateVar > *const sysmodel,
const StateVar & u,
Pdf< StateVar > *const filtered_post )
virtual

Full Update (system with inputs)

Parameters
sysmodelpointer to the system model to use for update
uinput to the system
filtered_postfiltered posterior

◆ Update() [2/2]

template<typename StateVar >
virtual bool Update ( SystemModel< StateVar > *const sysmodel,
Pdf< StateVar > *const filtered_post )
virtual

Full Update (system without inputs)

Parameters
sysmodelpointer to the system model to use for update
filtered_postfiltered posterior

◆ UpdateInternal()

template<typename StateVar >
virtual bool UpdateInternal ( SystemModel< StateVar > *const sysmodel,
const StateVar & u,
Pdf< StateVar > *const filtered_post )
protectedpure virtual

Actual implementation of Update, varies along filters.

Parameters
sysmodelpointer to the used system model
uinput param for proposal density
filtered_postis the posterior obtained by filtering of the timestep you want to smooth

Implemented in ParticleSmoother< StateVar >.

Member Data Documentation

◆ _post

template<typename StateVar >
Pdf<StateVar>* _post
protected

Pointer to the Posterior Pdf.

The Posterior Pdf represents the subjective belief of the person applying the filter AFTER processing a backwards step.

Definition at line 69 of file backwardfilter.h.

◆ _prior

template<typename StateVar >
Pdf<StateVar>* _prior
protected

prior Pdf

Definition at line 64 of file backwardfilter.h.

◆ _timestep

template<typename StateVar >
int _timestep
protected

Represents the current timestep of the filter.

Definition at line 72 of file backwardfilter.h.


The documentation for this class was generated from the following file: