mrpt::bayes::CParticleFilter::TParticleFilterOptions Struct Reference

The configuration of a particle filter. More...

#include <mrpt/bayes/CParticleFilter.h>

Inheritance diagram for mrpt::bayes::CParticleFilter::TParticleFilterOptions:

List of all members.

Public Member Functions
	TParticleFilterOptions ()
	Initilization of default parameters.
void	loadFromConfigFile (const mrpt::utils::CConfigFileBase &source, const std::string &section)
	See mrpt::utils::CLoadableOptions.
void	dumpToTextStream (mrpt::utils::CStream &out) const
	See mrpt::utils::CLoadableOptions.
Public Attributes
bool	adaptiveSampleSize
	A flag that indicates whether the CParticleFilterCapable object should perform adative sample size (default=false).
double	BETA
	The resampling of particles will be performed when ESS (in range [0,1]) < BETA (default is 0.5).
unsigned int	sampleSize
	The initial number of particles in the filter (it can change only if adaptiveSampleSize=true) (default=1).
unsigned int	pfAuxFilterOptimal_MaximumSearchSamples
	In the algorithm "CParticleFilter::pfAuxiliaryPFOptimal", the number of samples for searching the maximum likelihood value (see papers!) (default=100).
double	powFactor
	An optional step to "smooth" dramatic changes in the observation model to affect the variance of the particle weights, eg weight*=likelihood^powFactor (default=1 = no effects).
TParticleFilterAlgorithm	PF_algorithm
	The PF algorithm to use (default=pfStandardProposal) See TParticleFilterAlgorithm for the posibilities.
TParticleResamplingAlgorithm	resamplingMethod
	The resampling algorithm to use (default=prMultinomial).
double	max_loglikelihood_dyn_range
	Only for PF_algorithm=pfAuxiliaryPFOptimal: If a given particle has a max_likelihood (from the a-priori estimate) below the maximum from all the samples - max_loglikelihood_dyn_range, then the particle is directly discarded.

---

Detailed Description

The configuration of a particle filter.

Definition at line 103 of file CParticleFilter.h.

---

Constructor & Destructor Documentation

mrpt::bayes::CParticleFilter::TParticleFilterOptions::TParticleFilterOptions

(

)

Initilization of default parameters.

---

Member Function Documentation

void mrpt::bayes::CParticleFilter::TParticleFilterOptions::dumpToTextStream

(

mrpt::utils::CStream &

out

)

const [virtual]

See mrpt::utils::CLoadableOptions.

Implements mrpt::utils::CLoadableOptions.

void mrpt::bayes::CParticleFilter::TParticleFilterOptions::loadFromConfigFile	(	const mrpt::utils::CConfigFileBase &	source,
		const std::string &	section
	)			[virtual]

See mrpt::utils::CLoadableOptions.

Implements mrpt::utils::CLoadableOptions.

---

Member Data Documentation

bool mrpt::bayes::CParticleFilter::TParticleFilterOptions::adaptiveSampleSize

A flag that indicates whether the CParticleFilterCapable object should perform adative sample size (default=false).

Definition at line 122 of file CParticleFilter.h.

double mrpt::bayes::CParticleFilter::TParticleFilterOptions::BETA

The resampling of particles will be performed when ESS (in range [0,1]) < BETA (default is 0.5).

Definition at line 126 of file CParticleFilter.h.

double mrpt::bayes::CParticleFilter::TParticleFilterOptions::max_loglikelihood_dyn_range

Only for PF_algorithm=pfAuxiliaryPFOptimal: If a given particle has a max_likelihood (from the a-priori estimate) below the maximum from all the samples - max_loglikelihood_dyn_range, then the particle is directly discarded.

This is done to assure that the rejection sampling doesn't get stuck in an infinite loop trying to get an acceptable sample. Default = 15 (in logarithmic likelihood)

Definition at line 153 of file CParticleFilter.h.

TParticleFilterAlgorithm mrpt::bayes::CParticleFilter::TParticleFilterOptions::PF_algorithm

The PF algorithm to use (default=pfStandardProposal) See TParticleFilterAlgorithm for the posibilities.

Definition at line 142 of file CParticleFilter.h.

unsigned int mrpt::bayes::CParticleFilter::TParticleFilterOptions::pfAuxFilterOptimal_MaximumSearchSamples

In the algorithm "CParticleFilter::pfAuxiliaryPFOptimal", the number of samples for searching the maximum likelihood value (see papers!) (default=100).

Definition at line 134 of file CParticleFilter.h.

double mrpt::bayes::CParticleFilter::TParticleFilterOptions::powFactor

An optional step to "smooth" dramatic changes in the observation model to affect the variance of the particle weights, eg weight*=likelihood^powFactor (default=1 = no effects).

Definition at line 138 of file CParticleFilter.h.

TParticleResamplingAlgorithm mrpt::bayes::CParticleFilter::TParticleFilterOptions::resamplingMethod

The resampling algorithm to use (default=prMultinomial).

Definition at line 146 of file CParticleFilter.h.

unsigned int mrpt::bayes::CParticleFilter::TParticleFilterOptions::sampleSize

The initial number of particles in the filter (it can change only if adaptiveSampleSize=true) (default=1).

Definition at line 130 of file CParticleFilter.h.