Bayesian Filtering Library Generated from SVN r
Public Member Functions | Protected Member Functions | Protected Attributes | List of all members
Optimalimportancefilter< StateVar, MeasVar > Class Template Reference

Particular particle filter: Proposal PDF = Optimal Importance function. More...

#include <optimalimportancefilter.h>

Inheritance diagram for Optimalimportancefilter< StateVar, MeasVar >:
ParticleFilter< StateVar, MeasVar > Filter< StateVar, MeasVar >

Public Member Functions

 OptimalImportanceFilter (MCPdf< StateVar > *prior, int resampleperiod=0, double resamplethreshold=0, int resamplescheme=DEFAULT_RS)
 Constructor. More...
 
virtual ~OptimalImportanceFilter ()
 Destructor.
 
 OptimalImportanceFilter (const OptimalImportanceFilter< StateVar, MeasVar > &filt)
 Copy constructor.
 
virtual void Update (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Full Update (system with inputs/sensing params) More...
 
virtual void Update (SystemModel< StateVar > *const sysmodel, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Full Update (system without inputs, with sensing params) More...
 
virtual void Update (SystemModel< StateVar > *const sysmodel, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z)
 Full Update (system without inputs/sensing params) More...
 
virtual void Update (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z)
 Full Update (system with inputs, without sensing params) More...
 
virtual void Update (SystemModel< StateVar > *const sysmodel, const StateVar &u)
 Only sysupdate. More...
 
virtual void Update (SystemModel< StateVar > *const sysmodel)
 System Update (system without inputs) More...
 
virtual void Update (MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Only measupdate. More...
 
virtual void Update (MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z)
 Measurement Update (system without "sensing params") More...
 
virtual void ProposalSet (ConditionalPdf< StateVar, StateVar > *const cpdf)
 Set the proposal density. More...
 
ConditionalPdf< StateVar, StateVar > * ProposalGet ()
 Get a pointer to the proposal density. More...
 
virtual MCPdf< StateVar > * PostGet ()
 Get Posterior density. More...
 
virtual void Reset (Pdf< StateVar > *prior)
 Reset Filter.
 
int TimeStepGet () const
 Get current time. More...
 

Protected Member Functions

virtual void ConstructProposal (SystemModel< StateVar > *const sysmodel, MeasurementModel< MeasVar, StateVar > *const measmodel)
 Construct Optimal importance density from a sys and meas. model. More...
 
virtual bool UpdateInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Actual implementation of Update, varies along filters. More...
 
virtual bool ProposalStepInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Proposal step. More...
 
virtual bool UpdateWeightsInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Update Weights. More...
 
virtual bool DynamicResampleStep ()
 Resample if necessary. More...
 
virtual bool StaticResampleStep ()
 Resample if wanted. More...
 
virtual bool Resample ()
 Actual Resampling happens here;. More...
 

Protected Attributes

ConditionalPdf< StateVar, StateVar > * _proposal
 Pointer to the Proposal Density. More...
 
WeightedSample< StateVar > _sample
 While updating use sample<StateVar> More...
 
vector< WeightedSample< StateVar > > _old_samples
 While updating store list of old samples. More...
 
vector< WeightedSample< StateVar > > _new_samples
 While updating store list of new samples. More...
 
vector< Sample< StateVar > > _new_samples_unweighted
 While resampling. More...
 
vector< WeightedSample< StateVar > >::iterator _os_it
 Iterator for old list of samples. More...
 
vector< WeightedSample< StateVar > >::iterator _ns_it
 Iterator for new list of samples. More...
 
int _resamplePeriod
 Number of timestep between resampling from the Posterior Pdf. More...
 
double _resampleThreshold
 Threshold used when dynamic resampling. More...
 
int _resampleScheme
 Which resample algorithm (see top of particle.h for #defines) More...
 
bool _dynamicResampling
 Dynamic resampling or fixed period resampling? More...
 
bool _proposal_depends_on_meas
 Proposal depends on last measurement? More...
 
bool _created_post
 created own post More...
 
Pdf< StateVar > * _prior
 prior Pdf More...
 
Pdf< StateVar > * _post
 Pointer to the Posterior Pdf. More...
 
int _timestep
 Represents the current timestep of the filter. More...
 

Detailed Description

template<typename StateVar, typename MeasVar>
class BFL::Optimalimportancefilter< StateVar, MeasVar >

Particular particle filter: Proposal PDF = Optimal Importance function.

This is one (simple) particular implementation of a particle filter, in which the proposal density is equal to the pdf $ P(x_k | x_{k-1}, z_k) $. Note that this pdf can only be easily (analytically) determined for a limited class of models! The current implementation focusses on systems with a linear measurement model.

See also
@Article{         doucet98bis,
author =       {Doucet, Arnaud and Godsill, Simon and Andrieu, Christophe},
title =        {On Sequential Monte Carlo Sampling Methods for
                Bayesian Filtering},
journal =      {Statistics and Computing},
year =         {2000},
volume =       {10},
number =       {3},
pages =        {197--208},
}

for a more thorough discussion about all these issues and the possible suboptimal alternatives in case one is not able to sample from the optimal importance function.

Definition at line 67 of file optimalimportancefilter.h.

Member Function Documentation

◆ ConstructProposal()

virtual void ConstructProposal ( SystemModel< StateVar > *const  sysmodel,
MeasurementModel< MeasVar, StateVar > *const  measmodel 
)
protectedvirtual

Construct Optimal importance density from a sys and meas. model.

Parameters
sysmodelsystem model to use
measmodelmeasurement model to use for proposal construction

◆ DynamicResampleStep()

virtual bool DynamicResampleStep ( )
protectedvirtualinherited

Resample if necessary.

Bug:
let the user implement her/his own resamplescheme

◆ OptimalImportanceFilter()

OptimalImportanceFilter ( MCPdf< StateVar > *  prior,
int  resampleperiod = 0,
double  resamplethreshold = 0,
int  resamplescheme = DEFAULT_RS 
)

Constructor.

Precondition
you created the necessary models and the prior
Parameters
priorpointer to the Monte Carlo Pdf prior density
resampleperiodfixed resampling period (if desired)
resamplethresholdthreshold used when dynamic resampling
resampleschemeresampling scheme, see header file for different defines and their meaning

◆ PostGet()

virtual MCPdf< StateVar > * PostGet ( )
virtualinherited

Get Posterior density.

Get the current Posterior density

Returns
a pointer to the current posterior

Reimplemented from Filter< StateVar, MeasVar >.

◆ ProposalGet()

ConditionalPdf< StateVar, StateVar > * ProposalGet ( )
inherited

Get a pointer to the proposal density.

Returns
a pointer to the proposal density

◆ ProposalSet()

virtual void ProposalSet ( ConditionalPdf< StateVar, StateVar > *const  cpdf)
virtualinherited

Set the proposal density.

Parameters
cpdfthe new proposal density. The order of the conditional arguments is fixed and should be: x (state), u (input), z (measurement), s (sensor param). Off course all of them are optional

◆ ProposalStepInternal()

virtual bool ProposalStepInternal ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
protectedvirtualinherited

Proposal step.

Implementation of proposal step

Parameters
sysmodelpointer to the used system model
uinput param for proposal density
measmodelpointer to the used measurementmodel
zmeasurement param for proposal density
ssensor param for proposal density
Bug:
Make sampling method variable. See implementation.

Reimplemented in EKParticleFilter.

◆ Resample()

virtual bool Resample ( )
protectedvirtualinherited

Actual Resampling happens here;.

Reimplemented in EKParticleFilter.

◆ StaticResampleStep()

virtual bool StaticResampleStep ( )
protectedvirtualinherited

Resample if wanted.

Bug:
let the user implement her/his own resamplescheme

◆ TimeStepGet()

int TimeStepGet ( ) const
inherited

Get current time.

Get the current time of the filter

Returns
the current timestep

◆ Update() [1/8]

virtual void Update ( MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z 
)
virtual

Measurement Update (system without "sensing params")

Parameters
measmodelpointer to the measurement model to use for update
zmeasurement

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [2/8]

virtual void Update ( MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
virtual

Only measupdate.

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [3/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel)
virtual

System Update (system without inputs)

Parameters
sysmodelpointer to the system model to use for update

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [4/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u 
)
virtual

Only sysupdate.

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [5/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z 
)
virtual

Full Update (system with inputs, without sensing params)

Parameters
sysmodelpointer to the system model to use for update
uinput to the system
measmodelpointer to the measurement model to use for update
zmeasurement

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [6/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
virtual

Full Update (system with inputs/sensing params)

Parameters
sysmodelpointer to the system model to use for update
uinput to the system
measmodelpointer to the measurement model to use for update
zmeasurement
s"sensing parameter"

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [7/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z 
)
virtual

Full Update (system without inputs/sensing params)

Parameters
sysmodelpointer to the system model to use for update
measmodelpointer to the measurement model to use for update
zmeasurement

Reimplemented from Filter< StateVar, MeasVar >.

◆ Update() [8/8]

virtual void Update ( SystemModel< StateVar > *const  sysmodel,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
virtual

Full Update (system without inputs, with sensing params)

Parameters
sysmodelpointer to the system model to use for update
measmodelpointer to the measurement model to use for update
zmeasurement
s"sensing parameter"

Reimplemented from Filter< StateVar, MeasVar >.

◆ UpdateInternal()

virtual bool UpdateInternal ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
protectedvirtualinherited

Actual implementation of Update, varies along filters.

Parameters
sysmodelpointer to the used system model
uinput param for proposal density
measmodelpointer to the used measurementmodel
zmeasurement param for proposal density
ssensor param for proposal density

Implements Filter< StateVar, MeasVar >.

Reimplemented in EKParticleFilter, ASIRFilter< StateVar, MeasVar >, and BootstrapFilter< StateVar, MeasVar >.

◆ UpdateWeightsInternal()

virtual bool UpdateWeightsInternal ( SystemModel< StateVar > *const  sysmodel,
const StateVar &  u,
MeasurementModel< MeasVar, StateVar > *const  measmodel,
const MeasVar &  z,
const StateVar &  s 
)
protectedvirtualinherited

Update Weights.

Parameters
sysmodelpointer to the used system model
uinput param for proposal density
measmodelpointer to the used measurementmodel
zmeasurement param for proposal density
ssensor param for proposal density

Member Data Documentation

◆ _created_post

bool _created_post
protectedinherited

created own post

Definition at line 208 of file particlefilter.h.

◆ _dynamicResampling

bool _dynamicResampling
protectedinherited

Dynamic resampling or fixed period resampling?

Definition at line 202 of file particlefilter.h.

◆ _new_samples

vector<WeightedSample<StateVar> > _new_samples
protectedinherited

While updating store list of new samples.

Definition at line 181 of file particlefilter.h.

◆ _new_samples_unweighted

vector<Sample<StateVar> > _new_samples_unweighted
protectedinherited

While resampling.

Definition at line 183 of file particlefilter.h.

◆ _ns_it

vector<WeightedSample<StateVar>>::iterator _ns_it
protectedinherited

Iterator for new list of samples.

Definition at line 187 of file particlefilter.h.

◆ _old_samples

vector<WeightedSample<StateVar> > _old_samples
protectedinherited

While updating store list of old samples.

Definition at line 179 of file particlefilter.h.

◆ _os_it

vector<WeightedSample<StateVar>>::iterator _os_it
protectedinherited

Iterator for old list of samples.

Definition at line 185 of file particlefilter.h.

◆ _post

Pdf<StateVar>* _post
protectedinherited

Pointer to the Posterior Pdf.

The Posterior Pdf represents the subjective belief of the person applying the filter AFTER processing inputs and measurements. A filter does not maintain the beliefs at all timesteps t, since this leads to non-constant (or ever growing if you prefer) memory requirements. However, it is possible, to copy the Posterior density at all timesteps in your application by means of the PostGet() member function

See also
PostGet()

Definition at line 95 of file filter.h.

◆ _prior

Pdf<StateVar>* _prior
protectedinherited

prior Pdf

Definition at line 82 of file filter.h.

◆ _proposal

ConditionalPdf<StateVar,StateVar>* _proposal
protectedinherited

Pointer to the Proposal Density.

Every particle filter (or more correct: every Sequential Importance Sampling method) uses a proposal density to do the forward sampling step

Definition at line 174 of file particlefilter.h.

◆ _proposal_depends_on_meas

bool _proposal_depends_on_meas
protectedinherited

Proposal depends on last measurement?

Definition at line 205 of file particlefilter.h.

◆ _resamplePeriod

int _resamplePeriod
protectedinherited

Number of timestep between resampling from the Posterior Pdf.

By choosing this period, one can avoid numerical instability (aka Degeneration of the particle filter

Definition at line 193 of file particlefilter.h.

◆ _resampleScheme

int _resampleScheme
protectedinherited

Which resample algorithm (see top of particle.h for #defines)

Definition at line 199 of file particlefilter.h.

◆ _resampleThreshold

double _resampleThreshold
protectedinherited

Threshold used when dynamic resampling.

Definition at line 196 of file particlefilter.h.

◆ _sample

WeightedSample<StateVar> _sample
protectedinherited

While updating use sample<StateVar>

Definition at line 177 of file particlefilter.h.

◆ _timestep

int _timestep
protectedinherited

Represents the current timestep of the filter.

Todo:
Check wether this really belongs here

Definition at line 100 of file filter.h.


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