ParticleFilter Class Template Reference

Virtual Class representing all particle filters. More...

#include <particlefilter.h>

Inheritance diagram for ParticleFilter:

Filter ASIRFilter BootstrapFilter Optimalimportancefilter

List of all members.

Public Member Functions

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

Protected Member Functions

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.
virtual bool ProposalStepInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Proposal step.
virtual bool UpdateWeightsInternal (SystemModel< StateVar > *const sysmodel, const StateVar &u, MeasurementModel< MeasVar, StateVar > *const measmodel, const MeasVar &z, const StateVar &s)
 Update Weights.
virtual bool DynamicResampleStep ()
 Resample if necessary.
virtual bool StaticResampleStep ()
 Resample if wanted.
virtual bool Resample ()
 Actual Resampling happens here;.

Protected Attributes

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

Virtual Class representing all particle filters.

This is a virtual class representing the family of all particle filters. Particle filters are filters in which the Posterior density is represented by a set of particles (aka (weighted) samples). In other words, the posterior density is a Monte Carlo Pdf (class MCPdf)

However, the updating of the Posterior density can still be done in several ways, that's why the System and Measurement update members are still pure virtual functions.

This class is the base class for all sorts of particle filters.

Todo:
: Actually all particle filters represented by this class are of the "Sequential importance sampling methods" type. Typical of those methods is the so called Proposal density. In theory it would be possible to create Filters using a recursive version of other Monte Carlo methods (eg. MCMC methods), although I am not aware of any of these (due to the increased complexity).
See also:
MCPdf

Sample

WeightedSample

Bug:
Resampling is not implemented generically enough yet. There's only the possibility to choose between static period resampling and dynamic resampling as proposed by Jun Liu. The correct way of implementing this would be to create a virtual function that has to be implemented by the user, but this creates more hassle for the user (a different particle filter for each scheme).

Definition at line 159 of file particlefilter.h.


Constructor & Destructor Documentation

ParticleFilter ( MCPdf< SV > *  prior,
ConditionalPdf< SV, SV > *  proposal,
int  resampleperiod = 0,
double  resamplethreshold = 0,
int  resamplescheme = DEFAULT_RS 
) [inline]

Constructor.

Precondition:
you created the necessary models and the prior
Parameters:
prior pointer to the Monte Carlo Pdf prior density
proposal pointer to the proposal density to use
resampleperiod fixed resampling period (if desired)
resamplethreshold threshold used when dynamic resampling
resamplescheme resampling scheme, see header file for different defines and their meaning
Bug:
prior should be of type pdf and not mcpdf. See also notes with implementation
Bug:
let the user implement her/his own resamplescheme

Definition at line 912 of file particlefilter.h.

ParticleFilter ( MCPdf< SV > *  prior,
MCPdf< SV > *  post,
ConditionalPdf< SV, SV > *  proposal,
int  resampleperiod = 0,
double  resamplethreshold = 0,
int  resamplescheme = DEFAULT_RS 
) [inline]

Constructor.

Precondition:
you created the necessary models and the prior
Parameters:
prior pointer to the Monte Carlo Pdf prior density
post pointer to the Monte Carlo Pdf post density
proposal pointer to the proposal density to use
resampleperiod fixed resampling period (if desired)
resamplethreshold threshold used when dynamic resampling
resamplescheme resampling scheme, see header file for different defines and their meaning
Bug:
prior should be of type pdf and not mcpdf. See also notes with implementation
Bug:
let the user implement her/his own resamplescheme

Definition at line 957 of file particlefilter.h.

ParticleFilter ( const ParticleFilter< SV, MV > &  filt  )  [inline]

Copy Constructor.

Bug:
implementation probably contains a bug

Definition at line 1006 of file particlefilter.h.


Member Function Documentation

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

Actual implementation of Update, varies along filters.

Parameters:
sysmodel pointer to the used system model
u input param for proposal density
measmodel pointer to the used measurementmodel
z measurement param for proposal density
s sensor param for proposal density

Implements Filter.

bool ProposalStepInternal ( SystemModel< SV > *const   sysmodel,
const SV &  u,
MeasurementModel< MV, SV > *const   measmodel,
const MV &  z,
const SV &  s 
) [inline, protected, virtual]

Proposal step.

Implementation of proposal step

Parameters:
sysmodel pointer to the used system model
u input param for proposal density
measmodel pointer to the used measurementmodel
z measurement param for proposal density
s sensor param for proposal density
Bug:
Make sampling method variable. See implementation.

Reimplemented in EKParticleFilter.

Definition at line 1028 of file particlefilter.h.

bool UpdateWeightsInternal ( SystemModel< SV > *const   sysmodel,
const SV &  u,
MeasurementModel< MV, SV > *const   measmodel,
const MV &  z,
const SV &  s 
) [inline, protected, virtual]

Update Weights.

Parameters:
sysmodel pointer to the used system model
u input param for proposal density
measmodel pointer to the used measurementmodel
z measurement param for proposal density
s sensor param for proposal density

Definition at line 1084 of file particlefilter.h.

bool DynamicResampleStep (  )  [inline, protected, virtual]

Resample if necessary.

Bug:
let the user implement her/his own resamplescheme

Definition at line 1155 of file particlefilter.h.

bool StaticResampleStep (  )  [inline, protected, virtual]

Resample if wanted.

Bug:
let the user implement her/his own resamplescheme

Definition at line 1191 of file particlefilter.h.

void ProposalSet ( ConditionalPdf< SV, SV > *const   cpdf  )  [inline, virtual]

Set the proposal density.

Parameters:
cpdf the 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

Definition at line 1016 of file particlefilter.h.

ConditionalPdf< SV, SV > * ProposalGet (  )  [inline]

Get a pointer to the proposal density.

Returns:
a pointer to the proposal density

Definition at line 1022 of file particlefilter.h.

MCPdf< SV > * PostGet (  )  [inline, virtual]

Get Posterior density.

Get the current Posterior density

Returns:
a pointer to the current posterior

Reimplemented from Filter.

Definition at line 1273 of file particlefilter.h.

bool Update ( SystemModel< SVar > *const   sysmodel,
const SVar &  u,
MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z,
const SVar &  s 
) [inline, virtual, inherited]

Full Update (system with inputs/sensing params).

Parameters:
sysmodel pointer to the system model to use for update
u input to the system
measmodel pointer to the measurement model to use for update
z measurement
s "sensing parameter"

Definition at line 276 of file filter.h.

bool Update ( SystemModel< SVar > *const   sysmodel,
MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z,
const SVar &  s 
) [inline, virtual, inherited]

Full Update (system without inputs, with sensing params).

Parameters:
sysmodel pointer to the system model to use for update
measmodel pointer to the measurement model to use for update
z measurement
s "sensing parameter"

Definition at line 286 of file filter.h.

bool Update ( SystemModel< SVar > *const   sysmodel,
MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z 
) [inline, virtual, inherited]

Full Update (system without inputs/sensing params).

Parameters:
sysmodel pointer to the system model to use for update
measmodel pointer to the measurement model to use for update
z measurement

Definition at line 296 of file filter.h.

bool Update ( SystemModel< SVar > *const   sysmodel,
const SVar &  u,
MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z 
) [inline, virtual, inherited]

Full Update (system with inputs, without sensing params).

Parameters:
sysmodel pointer to the system model to use for update
u input to the system
measmodel pointer to the measurement model to use for update
z measurement

Definition at line 305 of file filter.h.

bool Update ( SystemModel< SVar > *const   sysmodel,
const SVar &  u 
) [inline, virtual, inherited]

System Update (system with inputs).

Parameters:
sysmodel pointer to the system model to use for update
u input to the system

Definition at line 315 of file filter.h.

bool Update ( SystemModel< SVar > *const   sysmodel  )  [inline, virtual, inherited]

System Update (system without inputs).

Parameters:
sysmodel pointer to the system model to use for update

Definition at line 323 of file filter.h.

bool Update ( MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z,
const SVar &  s 
) [inline, virtual, inherited]

Measurement Update (system with "sensing params").

Parameters:
measmodel pointer to the measurement model to use for update
z measurement
s "sensing parameter"

Definition at line 330 of file filter.h.

bool Update ( MeasurementModel< MVar, SVar > *const   measmodel,
const MVar &  z 
) [inline, virtual, inherited]

Measurement Update (system without "sensing params").

Parameters:
measmodel pointer to the measurement model to use for update
z measurement

Definition at line 339 of file filter.h.

int TimeStepGet (  )  const [inline, inherited]

Get current time.

Get the current time of the filter

Returns:
the current timestep

Definition at line 270 of file filter.h.


Member Data Documentation

ConditionalPdf<StateVar,StateVar>* _proposal [protected]

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.

int _resamplePeriod [protected]

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.

Pdf<StateVar>* _post [protected, inherited]

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.

int _timestep [protected, inherited]

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:

Generated on Mon Mar 30 05:43:59 2009 for Bayesian Filtering Library by  doxygen 1.5.5