Detailed Description

Declares a class that represents a Rao-Blackwellized set of particles for solving the SLAM problem (This class is the base of RBPF-SLAM applications).

This class is used internally by the map building algorithm in "mrpt::slam::CMetricMapBuilderRBPF"

See also: mrpt::slam::CMetricMapBuilderRBPF

Definition at line 62 of file maps/CMultiMetricMapPDF.h.

#include <mrpt/maps/CMultiMetricMapPDF.h>

Inheritance diagram for mrpt::maps::CMultiMetricMapPDF:

Classes
struct	TPredictionParams
	The struct for passing extra simulation parameters to the prediction/update stage when running a particle filter. More...

Public Types
typedef CRBPFParticleData	CParticleDataContent
	This is the type inside the corresponding CParticleData class. More...

typedef CProbabilityParticle< CRBPFParticleData >	CParticleData
	Use this to refer to each element in the m_particles array. More...

typedef std::deque< CParticleData >	CParticleList
	Use this type to refer to the list of particles m_particles. More...

typedef double(*	TParticleProbabilityEvaluator) (const bayes::CParticleFilter::TParticleFilterOptions &PF_options, const CParticleFilterCapable obj, size_t index, const void action, const void *observation)
	A callback function type for evaluating the probability of m_particles of being selected, used in "fastDrawSample". More...

Public Member Functions
void *	operator new (size_t size)

void *	operator new[] (size_t size)

void	operator delete (void *ptr) throw ()

void	operator delete[] (void *ptr) throw ()

void	operator delete (void memory, void ptr) throw ()

void *	operator new (size_t size, const std::nothrow_t &) throw ()

void	operator delete (void *ptr, const std::nothrow_t &) throw ()

	CMultiMetricMapPDF (const bayes::CParticleFilter::TParticleFilterOptions &opts=bayes::CParticleFilter::TParticleFilterOptions(), const mrpt::maps::TSetOfMetricMapInitializers mapsInitializers=NULL, const TPredictionParams predictionOptions=NULL)
	Constructor. More...

void	clear (const mrpt::poses::CPose2D &initialPose)
	Clear all elements of the maps, and restore all paths to a single starting pose. More...

void	clear (const mrpt::poses::CPose3D &initialPose)

void	clear (const mrpt::maps::CSimpleMap &prevMap, const mrpt::poses::CPose3D &currentPose)
	Resets the map by loading an already-mapped map for past poses. More...

void	getEstimatedPosePDFAtTime (size_t timeStep, mrpt::poses::CPose3DPDFParticles &out_estimation) const
	Returns the estimate of the robot pose as a particles PDF for the instant of time "timeStep", from 0 to N-1. More...

void	getEstimatedPosePDF (mrpt::poses::CPose3DPDFParticles &out_estimation) const
	Returns the current estimate of the robot pose, as a particles PDF. More...

const CMultiMetricMap *	getAveragedMetricMapEstimation ()
	Returns the weighted averaged map based on the current best estimation. More...

const CMultiMetricMap *	getCurrentMostLikelyMetricMap () const
	Returns a pointer to the current most likely map (associated to the most likely particle) More...

size_t	getNumberOfObservationsInSimplemap () const
	Get the number of CSensoryFrame inserted into the internal member SFs. More...

bool	insertObservation (mrpt::obs::CSensoryFrame &sf)
	Insert an observation to the map, at each particle's pose and to each particle's metric map. More...

void	getPath (size_t i, std::deque< math::TPose3D > &out_path) const
	Return the path (in absolute coordinate poses) for the i'th particle. More...

double	getCurrentEntropyOfPaths ()
	Returns the current entropy of paths, computed as the average entropy of poses along the path, where entropy of each pose estimation is computed as the entropy of the gaussian approximation covariance. More...

double	getCurrentJointEntropy ()
	Returns the joint entropy estimation over paths and maps, acording to "Information Gain-based Exploration Using" by C. More...

void	updateSensoryFrameSequence ()
	Update the poses estimation of the member "SFs" according to the current path belief. More...

void	saveCurrentPathEstimationToTextFile (const std::string &fil)
	A logging utility: saves the current path estimation for each particle in a text file (a row per particle, each 3-column-entry is a set [x,y,phi], respectively). More...

virtual mxArray *	writeToMatlab () const
	Introduces a pure virtual method responsible for writing to a `mxArray` Matlab object, typically a MATLAB `struct` whose contents are documented in each derived class. More...

mrpt::utils::CObjectPtr	duplicateGetSmartPtr () const
	Returns a copy of the object, indepently of its class, as a smart pointer (the newly created object will exist as long as any copy of this smart pointer). More...

CObject *	clone () const
	Cloning interface for smart pointers. More...

void	clearParticles ()
	Free the memory of all the particles and reset the array "m_particles" to length zero. More...

void	writeParticlesToStream (STREAM &out) const
	Dumps the sequence of particles and their weights to a stream (requires T implementing CSerializable). More...

void	readParticlesFromStream (STREAM &in)
	Reads the sequence of particles and their weights from a stream (requires T implementing CSerializable). More...

void	getWeights (std::vector< double > &out_logWeights) const
	Returns a vector with the sequence of the logaritmic weights of all the samples. More...

const CParticleData *	getMostLikelyParticle () const
	Returns the particle with the highest weight. More...

const CMultiMetricMapPDF &	derived () const
	CRTP helper method. More...

CMultiMetricMapPDF &	derived ()
	CRTP helper method. More...

double	getW (size_t i) const MRPT_OVERRIDE
	Access to i'th particle (logarithm) weight, where first one is index 0. More...

void	setW (size_t i, double w) MRPT_OVERRIDE
	Modifies i'th particle (logarithm) weight, where first one is index 0. More...

size_t	particlesCount () const MRPT_OVERRIDE
	Get the m_particles count. More...

double	normalizeWeights (double *out_max_log_w=NULL) MRPT_OVERRIDE
	Normalize the (logarithmic) weights, such as the maximum weight is zero. More...

double	ESS () const MRPT_OVERRIDE
	Returns the normalized ESS (Estimated Sample Size), in the range [0,1]. More...

void	performSubstitution (const std::vector< size_t > &indx) MRPT_OVERRIDE
	Replaces the old particles by copies determined by the indexes in "indx", performing an efficient copy of the necesary particles only and allowing the number of particles to change. More...

void	prepareFastDrawSample (const bayes::CParticleFilter::TParticleFilterOptions &PF_options, TParticleProbabilityEvaluator partEvaluator=defaultEvaluator, const void action=NULL, const void observation=NULL) const
	Prepares data structures for calling fastDrawSample method next. More...

size_t	fastDrawSample (const bayes::CParticleFilter::TParticleFilterOptions &PF_options) const
	Draws a random sample from the particle filter, in such a way that each particle has a probability proportional to its weight (in the standard PF algorithm). More...

void	prediction_and_update (const mrpt::obs::CActionCollection action, const mrpt::obs::CSensoryFrame observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	Performs the prediction stage of the Particle Filter. More...

void	performResampling (const bayes::CParticleFilter::TParticleFilterOptions &PF_options, size_t out_particle_count=0)
	Performs a resample of the m_particles, using the method selected in the constructor. More...

bool	PF_SLAM_implementation_gatherActionsCheckBothActObs (const mrpt::obs::CActionCollection actions, const mrpt::obs::CSensoryFrame sf)
	Auxiliary method called by PF implementations: return true if we have both action & observation, otherwise, return false AND accumulate the odometry so when we have an observation we didn't lose a thing. More...

Virtual methods that the PF_implementations assume exist.
mrpt::math::TPose3D	getLastPose (const size_t i, bool &pose_is_valid) const MRPT_OVERRIDE
	Return the last robot pose in the i'th particle; pose_is_valid will be false if particle is a path and it's empty. More...

void	PF_SLAM_implementation_custom_update_particle_with_new_pose (CParticleDataContent *particleData, const mrpt::math::TPose3D &newPose) const MRPT_OVERRIDE

bool	PF_SLAM_implementation_doWeHaveValidObservations (const CParticleList &particles, const mrpt::obs::CSensoryFrame *sf) const MRPT_OVERRIDE

bool	PF_SLAM_implementation_skipRobotMovement () const MRPT_OVERRIDE
	Do not move the particles until the map is populated. More...

double	PF_SLAM_computeObservationLikelihoodForParticle (const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const size_t particleIndexForMap, const mrpt::obs::CSensoryFrame &observation, const mrpt::poses::CPose3D &x) const MRPT_OVERRIDE
	Evaluate the observation likelihood for one particle at a given location. More...

Virtual methods that the PF_implementations assume exist.
virtual void	PF_SLAM_implementation_custom_update_particle_with_new_pose (CRBPFParticleData *particleData, const mrpt::math::TPose3D &newPose) const=0

virtual void	PF_SLAM_implementation_replaceByNewParticleSet (typename mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList &old_particles, const std::vector< mrpt::math::TPose3D > &newParticles, const std::vector< double > &newParticlesWeight, const std::vector< size_t > &newParticlesDerivedFromIdx) const
	This is the default algorithm to efficiently replace one old set of samples by another new set. More...

virtual bool	PF_SLAM_implementation_doWeHaveValidObservations (const typename mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList &particles, const mrpt::obs::CSensoryFrame *sf) const

Static Public Member Functions
static void *	operator new (size_t size, void *ptr)

static double	defaultEvaluator (const bayes::CParticleFilter::TParticleFilterOptions &PF_options, const CParticleFilterCapable obj, size_t index, const void action, const void *observation)
	The default evaluator function, which simply returns the particle weight. More...

static void	computeResampling (CParticleFilter::TParticleResamplingAlgorithm method, const std::vector< double > &in_logWeights, std::vector< size_t > &out_indexes, size_t out_particle_count=0)
	A static method to perform the computation of the samples resulting from resampling a given set of particles, given their logarithmic weights, and a resampling method. More...

static void	log2linearWeights (const std::vector< double > &in_logWeights, std::vector< double > &out_linWeights)
	A static method to compute the linear, normalized (the sum the unity) weights from log-weights. More...

Public Attributes
mrpt::maps::CMultiMetricMapPDF::TPredictionParams	options

CParticleList	m_particles
	The array of particles. More...

Static Public Attributes
static const mrpt::utils::TRuntimeClassId	classCObject

RTTI stuff
static const mrpt::utils::TRuntimeClassId	classCSerializable

Protected Member Functions
void	prediction_and_update_pfStandardProposal (const mrpt::obs::CActionCollection action, const mrpt::obs::CSensoryFrame observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options) MRPT_OVERRIDE
	Performs the particle filter prediction/update stages for the algorithm "pfStandardProposal" (if not implemented in heritated class, it will raise a 'non-implemented' exception). More...

void	prediction_and_update_pfOptimalProposal (const mrpt::obs::CActionCollection action, const mrpt::obs::CSensoryFrame observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options) MRPT_OVERRIDE
	Performs the particle filter prediction/update stages for the algorithm "pfOptimalProposal" (if not implemented in heritated class, it will raise a 'non-implemented' exception). More...

void	prediction_and_update_pfAuxiliaryPFOptimal (const mrpt::obs::CActionCollection action, const mrpt::obs::CSensoryFrame observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options) MRPT_OVERRIDE
	Performs the particle filter prediction/update stages for the algorithm "pfAuxiliaryPFOptimal" (if not implemented in heritated class, it will raise a 'non-implemented' exception). More...

void	prediction_and_update_pfAuxiliaryPFStandard (const mrpt::obs::CActionCollection action, const mrpt::obs::CSensoryFrame observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options) MRPT_OVERRIDE
	Performs the particle filter prediction/update stages for the algorithm "pfAuxiliaryPFStandard" (if not implemented in heritated class, it will raise a 'non-implemented' exception). More...

CSerializable virtual methods
void	writeToStream (mrpt::utils::CStream &out, int *getVersion) const
	Introduces a pure virtual method responsible for writing to a CStream. More...

void	readFromStream (mrpt::utils::CStream &in, int version)
	Introduces a pure virtual method responsible for loading from a CStream This can not be used directly be users, instead use "stream >> object;" for reading it from a stream or "stream >> object_ptr;" if the class is unknown apriori. More...

The generic PF implementations for localization & SLAM.
void	PF_SLAM_implementation_pfAuxiliaryPFOptimal (const mrpt::obs::CActionCollection actions, const mrpt::obs::CSensoryFrame sf, const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const TKLDParams &KLD_options)
	A generic implementation of the PF method "prediction_and_update_pfAuxiliaryPFOptimal" (optimal sampling with rejection sampling approximation), common to both localization and mapping. More...

void	PF_SLAM_implementation_pfAuxiliaryPFStandard (const mrpt::obs::CActionCollection actions, const mrpt::obs::CSensoryFrame sf, const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const TKLDParams &KLD_options)
	A generic implementation of the PF method "prediction_and_update_pfAuxiliaryPFStandard" (Auxiliary particle filter with the standard proposal), common to both localization and mapping. More...

void	PF_SLAM_implementation_pfStandardProposal (const mrpt::obs::CActionCollection actions, const mrpt::obs::CSensoryFrame sf, const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const TKLDParams &KLD_options)
	A generic implementation of the PF method "pfStandardProposal" (standard proposal distribution, that is, a simple SIS particle filter), common to both localization and mapping. More...

Protected Attributes
TFastDrawAuxVars	m_fastDrawAuxiliary
	Auxiliary vectors, see CParticleFilterCapable::prepareFastDrawSample for more information. More...

Private Member Functions
void	rebuildAverageMap ()
	Rebuild the "expected" grid map. More...

Private Attributes
mrpt::maps::CMultiMetricMap	averageMap
	Internal buffer for the averaged map. More...

bool	averageMapIsUpdated

mrpt::maps::CSimpleMap	SFs
	The SFs and their corresponding pose estimations. More...

std::vector< uint32_t >	SF2robotPath
	A mapping between indexes in the SFs to indexes in the robot paths from particles. More...

float	newInfoIndex
	An index [0,1] measuring how much information an observation aports to the map (Typ. threshold=0.07) More...

Friends
class	mrpt::slam::CMetricMapBuilderRBPF

RTTI stuff
typedef CMultiMetricMapPDFPtr	Ptr

typedef CMultiMetricMapPDFPtr	ConstPtr

static mrpt::utils::CLASSINIT	_init_CMultiMetricMapPDF

static mrpt::utils::TRuntimeClassId	classCMultiMetricMapPDF

static const mrpt::utils::TRuntimeClassId *	classinfo

static const mrpt::utils::TRuntimeClassId *	_GetBaseClass ()

virtual const mrpt::utils::TRuntimeClassId *	GetRuntimeClass () const
	Returns information about the class of an object in runtime. More...

virtual mrpt::utils::CObject *	duplicate () const
	Returns a copy of the object, indepently of its class. More...

static mrpt::utils::CObject *	CreateObject ()

static CMultiMetricMapPDFPtr	Create ()

Data members and methods used by generic PF implementations
static double	PF_SLAM_particlesEvaluator_AuxPFStandard (const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const mrpt::bayes::CParticleFilterCapable obj, size_t index, const void action, const void *observation)
	Compute w[i]*p(z_t \| mu_t^i), with mu_t^i being the mean of the new robot pose. More...

static double	PF_SLAM_particlesEvaluator_AuxPFOptimal (const mrpt::bayes::CParticleFilter::TParticleFilterOptions &PF_options, const mrpt::bayes::CParticleFilterCapable obj, size_t index, const void action, const void *observation)

mrpt::obs::CActionRobotMovement2D	m_accumRobotMovement2D

bool	m_accumRobotMovement2DIsValid

mrpt::poses::CPose3DPDFGaussian	m_accumRobotMovement3D

bool	m_accumRobotMovement3DIsValid

mrpt::poses::CPoseRandomSampler	m_movementDrawer
	Used in al PF implementations. More...

mrpt::math::CVectorDouble	m_pfAuxiliaryPFOptimal_estimatedProb
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm. More...

mrpt::math::CVectorDouble	m_pfAuxiliaryPFStandard_estimatedProb
	Auxiliary variable used in the "pfAuxiliaryPFStandard" algorithm. More...

mrpt::math::CVectorDouble	m_pfAuxiliaryPFOptimal_maxLikelihood
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm. More...

std::vector< mrpt::math::TPose3D >	m_pfAuxiliaryPFOptimal_maxLikDrawnMovement
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm. More...

std::vector< bool >	m_pfAuxiliaryPFOptimal_maxLikMovementDrawHasBeenUsed

Member Typedef Documentation

◆ ConstPtr

typedef CMultiMetricMapPDFPtr mrpt::maps::CMultiMetricMapPDF::ConstPtr

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ CParticleData

typedef CProbabilityParticle<CRBPFParticleData > mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleData

inherited

Use this to refer to each element in the m_particles array.

Definition at line 174 of file CParticleFilterData.h.

◆ CParticleDataContent

typedef CRBPFParticleData mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleDataContent

inherited

This is the type inside the corresponding CParticleData class.

Definition at line 173 of file CParticleFilterData.h.

◆ CParticleList

typedef std::deque<CParticleData> mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList

inherited

Use this type to refer to the list of particles m_particles.

Definition at line 175 of file CParticleFilterData.h.

◆ Ptr

typedef CMultiMetricMapPDFPtr mrpt::maps::CMultiMetricMapPDF::Ptr

A typedef for the associated smart pointer

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ TParticleProbabilityEvaluator

typedef double( * mrpt::bayes::CParticleFilterCapable::TParticleProbabilityEvaluator) (const bayes::CParticleFilter::TParticleFilterOptions &PF_options, const CParticleFilterCapable *obj, size_t index, const void *action, const void *observation)

inherited

A callback function type for evaluating the probability of m_particles of being selected, used in "fastDrawSample".

The default evaluator function "defaultEvaluator" simply returns the particle weight.

Parameters

index	This is the index of the particle its probability is being computed.
action	The value of this is the parameter passed to "prepareFastDrawSample"
observation	The value of this is the parameter passed to "prepareFastDrawSample" The action and the observation are declared as "void*" for a greater flexibility.

See also: prepareFastDrawSample

Definition at line 54 of file CParticleFilterCapable.h.

Constructor & Destructor Documentation

◆ CMultiMetricMapPDF()

CMultiMetricMapPDF::CMultiMetricMapPDF	(	const bayes::CParticleFilter::TParticleFilterOptions &	opts = `bayes::CParticleFilter::TParticleFilterOptions()`,
		const mrpt::maps::TSetOfMetricMapInitializers *	mapsInitializers = `NULL`,
		const TPredictionParams *	predictionOptions = `NULL`
	)

Constructor.

Definition at line 47 of file CMultiMetricMapPDF.cpp.

References mrpt::utils::clear().

Member Function Documentation

◆ _GetBaseClass()

static const mrpt::utils::TRuntimeClassId* mrpt::maps::CMultiMetricMapPDF::_GetBaseClass ( )

staticprotected

◆ clear() [1/3]

void CMultiMetricMapPDF::clear ( const mrpt::poses::CPose2D & initialPose )

Clear all elements of the maps, and restore all paths to a single starting pose.

Definition at line 77 of file CMultiMetricMapPDF.cpp.

References mrpt::utils::clear().

Referenced by mrpt::slam::CMetricMapBuilderRBPF::clear(), and mrpt::slam::CMetricMapBuilderRBPF::initialize().

◆ clear() [2/3]

void CMultiMetricMapPDF::clear ( const mrpt::poses::CPose3D & initialPose )

This is an overloaded member function, provided for convenience. It differs from the above function only in what argument(s) it accepts.

Definition at line 86 of file CMultiMetricMapPDF.cpp.

◆ clear() [3/3]

void CMultiMetricMapPDF::clear	(	const mrpt::maps::CSimpleMap &	prevMap,
		const mrpt::poses::CPose3D &	currentPose
	)

Resets the map by loading an already-mapped map for past poses.

Current robot pose should be normally set to the last keyframe in the simplemap.

Definition at line 105 of file CMultiMetricMapPDF.cpp.

References ASSERT_, mrpt::utils::clear(), mrpt::maps::CSimpleMap::clear(), mrpt::maps::CSimpleMap::get(), IS_CLASS, and mrpt::maps::CSimpleMap::size().

◆ clearParticles()

void mrpt::bayes::CParticleFilterData< CRBPFParticleData >::clearParticles ( )

inlineinherited

Free the memory of all the particles and reset the array "m_particles" to length zero.

Definition at line 183 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterData< T >::m_particles.

◆ clone()

CObject* mrpt::utils::CObject::clone ( ) const

inlineinherited

Cloning interface for smart pointers.

Definition at line 143 of file CObject.h.

◆ computeResampling()

void CParticleFilterCapable::computeResampling	(	CParticleFilter::TParticleResamplingAlgorithm	method,
		const std::vector< double > &	in_logWeights,
		std::vector< size_t > &	out_indexes,
		size_t	out_particle_count = `0`
	)

staticinherited

A static method to perform the computation of the samples resulting from resampling a given set of particles, given their logarithmic weights, and a resampling method.

It returns the sequence of indexes from the resampling. The number of output samples is the same than the input population. This generic method just computes these indexes, to actually perform a resampling in a particle filter object, call performResampling

Parameters

[in] out_particle_count The desired number of output particles after resampling; 0 means don't modify the current number.

See also: performResampling

Definition at line 64 of file CParticleFilterCapable.cpp.

References ASSERT_, mrpt::random::CRandomGenerator::drawUniform(), mrpt::random::CRandomGenerator::drawUniformVector(), mrpt::format(), mrpt::math::maximum(), MRPT_END, MRPT_START, R, mrpt::random::randomGenerator, and THROW_EXCEPTION.

◆ Create()

static CMultiMetricMapPDFPtr mrpt::maps::CMultiMetricMapPDF::Create ( )

static

◆ CreateObject()

static mrpt::utils::CObject* mrpt::maps::CMultiMetricMapPDF::CreateObject ( )

static

◆ defaultEvaluator()

static double mrpt::bayes::CParticleFilterCapable::defaultEvaluator	(	const bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const CParticleFilterCapable *	obj,
		size_t	index,
		const void *	action,
		const void *	observation
	)

inlinestaticinherited

The default evaluator function, which simply returns the particle weight.

The action and the observation are declared as "void*" for a greater flexibility.

See also: prepareFastDrawSample

Definition at line 65 of file CParticleFilterCapable.h.

References MRPT_UNUSED_PARAM.

◆ derived() [1/2]

const CMultiMetricMapPDF & mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::derived ( ) const

inlineinherited

CRTP helper method.

Definition at line 34 of file CParticleFilterData.h.

◆ derived() [2/2]

CMultiMetricMapPDF & mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::derived ( )

inlineinherited

CRTP helper method.

Definition at line 36 of file CParticleFilterData.h.

◆ duplicate()

virtual mrpt::utils::CObject* mrpt::maps::CMultiMetricMapPDF::duplicate ( ) const

virtual

Returns a copy of the object, indepently of its class.

Implements mrpt::utils::CObject.

◆ duplicateGetSmartPtr()

mrpt::utils::CObjectPtr mrpt::utils::CObject::duplicateGetSmartPtr ( ) const

inlineinherited

Returns a copy of the object, indepently of its class, as a smart pointer (the newly created object will exist as long as any copy of this smart pointer).

Definition at line 140 of file CObject.h.

Referenced by mrpt::obs::CRawlog::addActions(), mrpt::slam::CIncrementalMapPartitioner::addMapFrame(), and mrpt::obs::CRawlog::addObservations().

◆ ESS()

double mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::ESS ( ) const

inlinevirtualinherited

Returns the normalized ESS (Estimated Sample Size), in the range [0,1].

Note that you do NOT need to normalize the weights before calling this.

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 78 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived(), MRPT_END, MRPT_START, and mrpt::math::square().

◆ fastDrawSample()

size_t CParticleFilterCapable::fastDrawSample ( const bayes::CParticleFilter::TParticleFilterOptions & PF_options ) const

inherited

Draws a random sample from the particle filter, in such a way that each particle has a probability proportional to its weight (in the standard PF algorithm).

This method can be used to generate a variable number of m_particles when resampling: to vary the number of m_particles in the filter. See prepareFastDrawSample for more information, or the Particle Filter tutorial.

NOTES:

You MUST call "prepareFastDrawSample" ONCE before calling this method. That method must be called after modifying the particle filter (executing one step, resampling, etc...)
This method returns ONE index for the selected ("drawn") particle, in the range [0,M-1]
You do not need to call "normalizeWeights" before calling this.
See also
prepareFastDrawSample

Definition at line 454 of file CParticleFilterCapable.cpp.

References mrpt::bayes::CParticleFilter::TParticleFilterOptions::adaptiveSampleSize, mrpt::random::CRandomGenerator::drawUniform(), MRPT_END, MRPT_END_WITH_CLEAN_UP, MRPT_START, mrpt::random::randomGenerator, mrpt::bayes::CParticleFilter::TParticleFilterOptions::resamplingMethod, and THROW_EXCEPTION.

Referenced by mrpt::hmtslam::CLSLAM_RBPF_2DLASER::prediction_and_update_pfAuxiliaryPFOptimal().

◆ getAveragedMetricMapEstimation()

const CMultiMetricMap * CMultiMetricMapPDF::getAveragedMetricMapEstimation ( )

Returns the weighted averaged map based on the current best estimation.

If you need a persistent copy of this object, please use "CSerializable::duplicate" and use the copy.

See also: Almost 100% sure you would prefer the best current map, given by getCurrentMostLikelyMetricMap()

Definition at line 307 of file CMultiMetricMapPDF.cpp.

◆ getCurrentEntropyOfPaths()

double CMultiMetricMapPDF::getCurrentEntropyOfPaths ( )

Returns the current entropy of paths, computed as the average entropy of poses along the path, where entropy of each pose estimation is computed as the entropy of the gaussian approximation covariance.

Definition at line 471 of file CMultiMetricMapPDF.cpp.

References mrpt::utils::CProbabilityDensityFunction< TDATA, STATE_LEN >::getCovarianceEntropy().

◆ getCurrentJointEntropy()

double CMultiMetricMapPDF::getCurrentJointEntropy ( )

Returns the joint entropy estimation over paths and maps, acording to "Information Gain-based Exploration Using" by C.

Stachniss, G. Grissetti and W.Burgard.

Definition at line 501 of file CMultiMetricMapPDF.cpp.

References ASSERT_, mrpt::maps::COccupancyGridMap2D::TEntropyInfo::H, and min.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::getCurrentJointEntropy().

◆ getCurrentMostLikelyMetricMap()

const CMultiMetricMap * CMultiMetricMapPDF::getCurrentMostLikelyMetricMap ( ) const

Returns a pointer to the current most likely map (associated to the most likely particle)

Definition at line 555 of file CMultiMetricMapPDF.cpp.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::drawCurrentEstimationToImage(), and mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMetricMap().

◆ getEstimatedPosePDF()

void CMultiMetricMapPDF::getEstimatedPosePDF ( mrpt::poses::CPose3DPDFParticles & out_estimation ) const

Returns the current estimate of the robot pose, as a particles PDF.

See also: getEstimatedPosePDFAtTime

Definition at line 169 of file CMultiMetricMapPDF.cpp.

References ASSERT_.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::getCurrentPoseEstimation(), and mrpt::slam::CMetricMapBuilderRBPF::processActionObservation().

◆ getEstimatedPosePDFAtTime()

void CMultiMetricMapPDF::getEstimatedPosePDFAtTime	(	size_t	timeStep,
		mrpt::poses::CPose3DPDFParticles &	out_estimation
	)		const

Returns the estimate of the robot pose as a particles PDF for the instant of time "timeStep", from 0 to N-1.

See also: getEstimatedPosePDF

Definition at line 178 of file CMultiMetricMapPDF.cpp.

References mrpt::bayes::CParticleFilterData< T >::clearParticles(), and mrpt::bayes::CParticleFilterData< T >::m_particles.

◆ getLastPose()

TPose3D CMultiMetricMapPDF::getLastPose	(	const size_t	i,
		bool &	pose_is_valid
	)		const

virtual

Return the last robot pose in the i'th particle; pose_is_valid will be false if particle is a path and it's empty.

Implements mrpt::slam::PF_implementation< CRBPFParticleData, CMultiMetricMapPDF >.

Definition at line 292 of file CMultiMetricMapPDF.cpp.

References THROW_EXCEPTION.

◆ getMostLikelyParticle()

const CParticleData* mrpt::bayes::CParticleFilterData< CRBPFParticleData >::getMostLikelyParticle ( ) const

inlineinherited

Returns the particle with the highest weight.

Definition at line 240 of file CParticleFilterData.h.

References ASSERT_, mrpt::bayes::CParticleFilterData< T >::m_particles, MRPT_END, and MRPT_START.

◆ getNumberOfObservationsInSimplemap()

size_t mrpt::maps::CMultiMetricMapPDF::getNumberOfObservationsInSimplemap ( ) const

inline

Get the number of CSensoryFrame inserted into the internal member SFs.

Definition at line 176 of file maps/CMultiMetricMapPDF.h.

References mrpt::maps::CSimpleMap::size().

◆ getPath()

void CMultiMetricMapPDF::getPath	(	size_t	i,
		std::deque< math::TPose3D > &	out_path
	)		const

Return the path (in absolute coordinate poses) for the i'th particle.

Exceptions

On	index out of bounds

Definition at line 461 of file CMultiMetricMapPDF.cpp.

References THROW_EXCEPTION.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::drawCurrentEstimationToImage(), and mrpt::slam::CMetricMapBuilderRBPF::getCurrentMostLikelyPath().

◆ GetRuntimeClass()

virtual const mrpt::utils::TRuntimeClassId* mrpt::maps::CMultiMetricMapPDF::GetRuntimeClass ( ) const

virtual

Returns information about the class of an object in runtime.

Reimplemented from mrpt::utils::CSerializable.

◆ getW()

double mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::getW ( size_t i ) const

inlinevirtualinherited

Access to i'th particle (logarithm) weight, where first one is index 0.

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 38 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived(), and THROW_EXCEPTION_FMT.

◆ getWeights()

void mrpt::bayes::CParticleFilterData< CRBPFParticleData >::getWeights ( std::vector< double > & out_logWeights ) const

inlineinherited

Returns a vector with the sequence of the logaritmic weights of all the samples.

Definition at line 227 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterData< T >::m_particles, MRPT_END, and MRPT_START.

◆ insertObservation()

bool CMultiMetricMapPDF::insertObservation ( mrpt::obs::CSensoryFrame & sf )

Insert an observation to the map, at each particle's pose and to each particle's metric map.

Parameters

sf	The SF to be inserted

Returns: true if any may was updated, false otherwise

Definition at line 428 of file CMultiMetricMapPDF.cpp.

References mrpt::poses::CPose3DPDFParticles::Create(), and mrpt::obs::CSensoryFrame::insertObservationsInto().

Referenced by mrpt::slam::CMetricMapBuilderRBPF::processActionObservation().

◆ log2linearWeights()

void CParticleFilterCapable::log2linearWeights	(	const std::vector< double > &	in_logWeights,
		std::vector< double > &	out_linWeights
	)

staticinherited

A static method to compute the linear, normalized (the sum the unity) weights from log-weights.

See also: performResampling

Definition at line 509 of file CParticleFilterCapable.cpp.

References ASSERT_, MRPT_END, and MRPT_START.

◆ normalizeWeights()

double mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::normalizeWeights ( double * out_max_log_w = NULL )

inlinevirtualinherited

Normalize the (logarithmic) weights, such as the maximum weight is zero.

Parameters

out_max_log_w If provided, will return with the maximum log_w before normalizing, such as new_weights = old_weights - max_log_w.

Returns: The max/min ratio of weights ("dynamic range")

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 55 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived(), MRPT_END, and MRPT_START.

◆ operator delete() [1/3]

void mrpt::maps::CMultiMetricMapPDF::operator delete	(	void *	ptr	)
throw	(
	)

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator delete() [2/3]

void mrpt::maps::CMultiMetricMapPDF::operator delete	(	void *	memory,
		void *	ptr
	)
throw	(
	)

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator delete() [3/3]

void mrpt::maps::CMultiMetricMapPDF::operator delete	(	void *	ptr,
		const std::nothrow_t &
	)
throw	(
	)

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator delete[]()

void mrpt::maps::CMultiMetricMapPDF::operator delete[]	(	void *	ptr	)
throw	(
	)

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator new() [1/3]

static void* mrpt::maps::CMultiMetricMapPDF::operator new	(	size_t	size,
		void *	ptr
	)

inlinestatic

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator new() [2/3]

void* mrpt::maps::CMultiMetricMapPDF::operator new	(	size_t	size,
		const std::nothrow_t &
	)
throw	(
	)

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator new() [3/3]

void* mrpt::maps::CMultiMetricMapPDF::operator new ( size_t size )

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ operator new[]()

void* mrpt::maps::CMultiMetricMapPDF::operator new[] ( size_t size )

inline

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ particlesCount()

size_t mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::particlesCount ( ) const

inlinevirtualinherited

Get the m_particles count.

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 50 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived().

◆ performResampling()

void CParticleFilterCapable::performResampling	(	const bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		size_t	out_particle_count = `0`
	)

inherited

Performs a resample of the m_particles, using the method selected in the constructor.

After computing the surviving samples, this method internally calls "performSubstitution" to actually perform the particle replacement. This method is called automatically by CParticleFilter::execute, andshould not be invoked manually normally. To just obtaining the sequence of resampled indexes from a sequence of weights, use "resample"

Parameters

[in] out_particle_count The desired number of output particles after resampling; 0 means don't modify the current number.

See also: resample

Definition at line 29 of file CParticleFilterCapable.cpp.

References ASSERT_, MRPT_END, MRPT_START, and mrpt::bayes::CParticleFilter::TParticleFilterOptions::resamplingMethod.

◆ performSubstitution()

void mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::performSubstitution ( const std::vector< size_t > & indx )

inlinevirtualinherited

Replaces the old particles by copies determined by the indexes in "indx", performing an efficient copy of the necesary particles only and allowing the number of particles to change.

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 98 of file CParticleFilterData.h.

References ASSERT_, mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived(), MRPT_END, and MRPT_START.

◆ PF_SLAM_computeObservationLikelihoodForParticle()

double CMultiMetricMapPDF::PF_SLAM_computeObservationLikelihoodForParticle	(	const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const size_t	particleIndexForMap,
		const mrpt::obs::CSensoryFrame &	observation,
		const mrpt::poses::CPose3D &	x
	)		const

virtual

Evaluate the observation likelihood for one particle at a given location.

Implements mrpt::slam::PF_implementation< CRBPFParticleData, CMultiMetricMapPDF >.

Definition at line 915 of file CMultiMetricMapPDF_RBPF.cpp.

References mrpt::obs::CSensoryFrame::begin(), mrpt::maps::CMetricMap::computeObservationLikelihood(), mrpt::obs::CSensoryFrame::end(), and MRPT_UNUSED_PARAM.

◆ PF_SLAM_implementation_custom_update_particle_with_new_pose() [1/2]

virtual void mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_custom_update_particle_with_new_pose	(	CRBPFParticleData *	particleData,
		const mrpt::math::TPose3D &	newPose
	)		const

pure virtualinherited

◆ PF_SLAM_implementation_custom_update_particle_with_new_pose() [2/2]

void CMultiMetricMapPDF::PF_SLAM_implementation_custom_update_particle_with_new_pose	(	CParticleDataContent *	particleData,
		const mrpt::math::TPose3D &	newPose
	)		const

Definition at line 886 of file CMultiMetricMapPDF_RBPF.cpp.

References mrpt::maps::CRBPFParticleData::robotPath.

◆ PF_SLAM_implementation_doWeHaveValidObservations() [1/2]

bool CMultiMetricMapPDF::PF_SLAM_implementation_doWeHaveValidObservations	(	const CParticleList &	particles,
		const mrpt::obs::CSensoryFrame *	sf
	)		const

Definition at line 894 of file CMultiMetricMapPDF_RBPF.cpp.

References ASSERT_.

◆ PF_SLAM_implementation_doWeHaveValidObservations() [2/2]

virtual bool mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_doWeHaveValidObservations	(	const typename mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList &	particles,
		const mrpt::obs::CSensoryFrame *	sf
	)		const

inlinevirtualinherited

Definition at line 230 of file PF_implementations_data.h.

◆ PF_SLAM_implementation_gatherActionsCheckBothActObs()

bool mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_gatherActionsCheckBothActObs	(	const mrpt::obs::CActionCollection *	actions,
		const mrpt::obs::CSensoryFrame *	sf
	)

inherited

Auxiliary method called by PF implementations: return true if we have both action & observation, otherwise, return false AND accumulate the odometry so when we have an observation we didn't lose a thing.

On return=true, the "m_movementDrawer" member is loaded and ready to draw samples of the increment of pose since last step. This method is smart enough to accumulate CActionRobotMovement2D or CActionRobotMovement3D, whatever comes in.

Definition at line 44 of file PF_implementations.h.

◆ PF_SLAM_implementation_pfAuxiliaryPFOptimal()

void mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_pfAuxiliaryPFOptimal	(	const mrpt::obs::CActionCollection *	actions,
		const mrpt::obs::CSensoryFrame *	sf,
		const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const TKLDParams &	KLD_options
	)

protectedinherited

A generic implementation of the PF method "prediction_and_update_pfAuxiliaryPFOptimal" (optimal sampling with rejection sampling approximation), common to both localization and mapping.

BINTYPE: TPoseBin or whatever to discretize the sample space for KLD-sampling.

This method implements optimal sampling with a rejection sampling-based approximation of the true posterior. For details, see the papers:

J.L. Blanco, J. Gonzalez, and J.-A. Fernandez-Madrigal, "An Optimal Filtering Algorithm for Non-Parametric Observation Models in Robot Localization," in Proc. IEEE International Conference on Robotics and Automation (ICRA'08), 2008, pp. 461-466.
BINTYPE: TPoseBin or whatever to discretize the sample space for KLD-sampling.

This method implements optimal sampling with a rejection sampling-based approximation of the true posterior. For details, see the papers:

J.-L. Blanco, J. Gonzalez, and J.-A. Fernandez-Madrigal, "An Optimal Filtering Algorithm for Non-Parametric Observation Models in Robot Localization," in Proc. IEEE International Conference on Robotics and Automation (ICRA'08), 2008, pp. 461466.

Definition at line 130 of file PF_implementations.h.

◆ PF_SLAM_implementation_pfAuxiliaryPFStandard()

void mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_pfAuxiliaryPFStandard	(	const mrpt::obs::CActionCollection *	actions,
		const mrpt::obs::CSensoryFrame *	sf,
		const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const TKLDParams &	KLD_options
	)

protectedinherited

A generic implementation of the PF method "prediction_and_update_pfAuxiliaryPFStandard" (Auxiliary particle filter with the standard proposal), common to both localization and mapping.

BINTYPE: TPoseBin or whatever to discretize the sample space for KLD-sampling.

This method is described in the paper: Pitt, M.K.; Shephard, N. (1999). "Filtering Via Simulation: Auxiliary Particle Filters". Journal of the American Statistical Association 94 (446): 590-591. doi:10.2307/2670179.

Definition at line 321 of file PF_implementations.h.

◆ PF_SLAM_implementation_pfStandardProposal()

void mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_pfStandardProposal	(	const mrpt::obs::CActionCollection *	actions,
		const mrpt::obs::CSensoryFrame *	sf,
		const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const TKLDParams &	KLD_options
	)

protectedinherited

A generic implementation of the PF method "pfStandardProposal" (standard proposal distribution, that is, a simple SIS particle filter), common to both localization and mapping.

BINTYPE: TPoseBin or whatever to discretize the sample space for KLD-sampling.

Definition at line 148 of file PF_implementations.h.

◆ PF_SLAM_implementation_replaceByNewParticleSet()

virtual void mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_implementation_replaceByNewParticleSet	(	typename mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList &	old_particles,
		const std::vector< mrpt::math::TPose3D > &	newParticles,
		const std::vector< double > &	newParticlesWeight,
		const std::vector< size_t > &	newParticlesDerivedFromIdx
	)		const

inlinevirtualinherited

This is the default algorithm to efficiently replace one old set of samples by another new set.

The method uses pointers to make fast copies the first time each particle is duplicated, then makes real copies for the next ones.

Note that more efficient specializations might exist for specific particle data structs.

Definition at line 164 of file PF_implementations_data.h.

◆ PF_SLAM_implementation_skipRobotMovement()

bool CMultiMetricMapPDF::PF_SLAM_implementation_skipRobotMovement ( ) const

virtual

Do not move the particles until the map is populated.

Reimplemented from mrpt::slam::PF_implementation< CRBPFParticleData, CMultiMetricMapPDF >.

Definition at line 904 of file CMultiMetricMapPDF_RBPF.cpp.

◆ PF_SLAM_particlesEvaluator_AuxPFOptimal()

double mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_particlesEvaluator_AuxPFOptimal	(	const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const mrpt::bayes::CParticleFilterCapable *	obj,
		size_t	index,
		const void *	action,
		const void *	observation
	)

staticprotectedinherited

Definition at line 336 of file PF_implementations.h.

◆ PF_SLAM_particlesEvaluator_AuxPFStandard()

double mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::PF_SLAM_particlesEvaluator_AuxPFStandard	(	const mrpt::bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		const mrpt::bayes::CParticleFilterCapable *	obj,
		size_t	index,
		const void *	action,
		const void *	observation
	)

staticprotectedinherited

Compute w[i]*p(z_t | mu_t^i), with mu_t^i being the mean of the new robot pose.

Parameters

action	MUST be a "const CPose3D*"
observation	MUST be a "const CSensoryFrame*"
action	MUST be a "const mrpt::poses::CPose3D*"
observation	MUST be a "const CSensoryFrame*"

Definition at line 412 of file PF_implementations.h.

◆ prediction_and_update()

void CParticleFilterCapable::prediction_and_update	(	const mrpt::obs::CActionCollection *	action,
		const mrpt::obs::CSensoryFrame *	observation,
		const bayes::CParticleFilter::TParticleFilterOptions &	PF_options
	)

inherited

Performs the prediction stage of the Particle Filter.

This method simply selects the appropiate protected method according to the particle filter algorithm to run.

See also: prediction_and_update_pfStandardProposal,prediction_and_update_pfAuxiliaryPFStandard,prediction_and_update_pfOptimalProposal,prediction_and_update_pfAuxiliaryPFOptimal

Definition at line 272 of file CParticleFilterCapable.cpp.

References mrpt::bayes::CParticleFilter::TParticleFilterOptions::PF_algorithm, and THROW_EXCEPTION.

◆ prediction_and_update_pfAuxiliaryPFOptimal()

void CMultiMetricMapPDF::prediction_and_update_pfAuxiliaryPFOptimal	(	const mrpt::obs::CActionCollection *	action,
		const mrpt::obs::CSensoryFrame *	observation,
		const bayes::CParticleFilter::TParticleFilterOptions &	PF_options
	)

protectedvirtual

Performs the particle filter prediction/update stages for the algorithm "pfAuxiliaryPFOptimal" (if not implemented in heritated class, it will raise a 'non-implemented' exception).

See also: prediction_and_update

Reimplemented from mrpt::bayes::CParticleFilterCapable.

Definition at line 139 of file CMultiMetricMapPDF_RBPF.cpp.

References MRPT_END, and MRPT_START.

◆ prediction_and_update_pfAuxiliaryPFStandard()

void CMultiMetricMapPDF::prediction_and_update_pfAuxiliaryPFStandard	(	const mrpt::obs::CActionCollection *	action,
		const mrpt::obs::CSensoryFrame *	observation,
		const bayes::CParticleFilter::TParticleFilterOptions &	PF_options
	)

protectedvirtual

Performs the particle filter prediction/update stages for the algorithm "pfAuxiliaryPFStandard" (if not implemented in heritated class, it will raise a 'non-implemented' exception).

See also: prediction_and_update

Reimplemented from mrpt::bayes::CParticleFilterCapable.

Definition at line 154 of file CMultiMetricMapPDF_RBPF.cpp.

References MRPT_END, and MRPT_START.

◆ prediction_and_update_pfOptimalProposal()

void CMultiMetricMapPDF::prediction_and_update_pfOptimalProposal	(	const mrpt::obs::CActionCollection *	action,
		const mrpt::obs::CSensoryFrame *	observation,
		const bayes::CParticleFilter::TParticleFilterOptions &	PF_options
	)

protectedvirtual

Performs the particle filter prediction/update stages for the algorithm "pfOptimalProposal" (if not implemented in heritated class, it will raise a 'non-implemented' exception).

See also: prediction_and_update

Todo:: Add paper ref!

COpenGLScene scene; opengl::CSetOfObjects *obj = new opengl::CSetOfObjects(); fusedObsModels.getAs3DObject( *obj ); scene.insert( obj ); CFileStream("debug.3Dscene",fomWrite) << scene; cout << "fusedObsModels # of modes: " << fusedObsModels.m_modes.size() << endl; printf("ESS: %f\n",fusedObsModels.ESS() ); cout << fusedObsModels.getEstimatedCovariance() << endl; mrpt::system::pause(); /

/
                                                            CPointPDFSOG    newObsModel;
                                                            (itBeacs)->generateObservationModelDistribution(
                                                                    sensedRange,
                                                                    newObsModel,
                                                                    beacMap,                                 // The beacon map, for options
                                                                    itObs->sensorLocationOnRobot,// Sensor location on robot
                                                                    centerPositionPrior,
                                                                    centerPositionPriorRadius );

/

Todo:: If there are 2+ sensors on the robot, compute phi?

Reimplemented from mrpt::bayes::CParticleFilterCapable.

Definition at line 182 of file CMultiMetricMapPDF_RBPF.cpp.

◆ prediction_and_update_pfStandardProposal()

void CMultiMetricMapPDF::prediction_and_update_pfStandardProposal	(	const mrpt::obs::CActionCollection *	action,
		const mrpt::obs::CSensoryFrame *	observation,
		const bayes::CParticleFilter::TParticleFilterOptions &	PF_options
	)

protectedvirtual

Performs the particle filter prediction/update stages for the algorithm "pfStandardProposal" (if not implemented in heritated class, it will raise a 'non-implemented' exception).

See also: prediction_and_update

Reimplemented from mrpt::bayes::CParticleFilterCapable.

Definition at line 869 of file CMultiMetricMapPDF_RBPF.cpp.

References MRPT_END, and MRPT_START.

◆ prepareFastDrawSample()

void CParticleFilterCapable::prepareFastDrawSample	(	const bayes::CParticleFilter::TParticleFilterOptions &	PF_options,
		TParticleProbabilityEvaluator	partEvaluator = `defaultEvaluator`,
		const void *	action = `NULL`,
		const void *	observation = `NULL`
	)		const

inherited

Prepares data structures for calling fastDrawSample method next.

This method must be called once before using "fastDrawSample" (calling this more than once has no effect, but it takes time for nothing!) The behavior depends on the configuration of the PF (see CParticleFilter::TParticleFilterOptions):

DYNAMIC SAMPLE SIZE=NO: In this case this method fills out an internal array (m_fastDrawAuxiliary.alreadyDrawnIndexes) with the random indexes generated according to the selected resample scheme in TParticleFilterOptions. Those indexes are read sequentially by subsequent calls to fastDrawSample.
DYNAMIC SAMPLE SIZE=YES: Then:
- If TParticleFilterOptions.resamplingMethod = prMultinomial, the internal buffers will be filled out (m_fastDrawAuxiliary.CDF, CDF_indexes & PDF) and then fastDrawSample can be called an arbitrary number of times to generate random indexes.
- For the rest of resampling algorithms, an exception will be raised since they are not appropriate for a dynamic (unknown in advance) number of particles.

The function pointed by "partEvaluator" should take into account the particle filter algorithm selected in "m_PFAlgorithm". If called without arguments (defaultEvaluator), the default behavior is to draw samples with a probability proportional to their current weights. The action and the observation are declared as "void*" for a greater flexibility. For a more detailed information see the Particle Filter tutorial. Custom supplied "partEvaluator" functions must take into account the previous particle weight, i.e. multiplying the current observation likelihood by the weights.

See also: fastDrawSample

Definition at line 348 of file CParticleFilterCapable.cpp.

References mrpt::bayes::CParticleFilter::TParticleFilterOptions::adaptiveSampleSize, ASSERT_, mrpt::math::maximum(), MRPT_CHECK_NORMAL_NUMBER, MRPT_END, MRPT_END_WITH_CLEAN_UP, MRPT_START, mrpt::bayes::CParticleFilter::TParticleFilterOptions::resamplingMethod, and THROW_EXCEPTION.

Referenced by mrpt::hmtslam::CLSLAM_RBPF_2DLASER::prediction_and_update_pfAuxiliaryPFOptimal().

◆ readFromStream()

void CMultiMetricMapPDF::readFromStream	(	mrpt::utils::CStream &	in,
		int	version
	)

protectedvirtual

Introduces a pure virtual method responsible for loading from a CStream This can not be used directly be users, instead use "stream >> object;" for reading it from a stream or "stream >> object_ptr;" if the class is unknown apriori.

Parameters

in	The input binary stream where the object data must read from.
version	The version of the object stored in the stream: use this version number in your code to know how to read the incoming data.

Exceptions

std::exception On any error, see CStream::ReadBuffer

See also: CStream

Implements mrpt::utils::CSerializable.

Definition at line 246 of file CMultiMetricMapPDF.cpp.

References MRPT_THROW_UNKNOWN_SERIALIZATION_VERSION, and version.

◆ readParticlesFromStream()

void mrpt::bayes::CParticleFilterData< CRBPFParticleData >::readParticlesFromStream ( STREAM & in )

inlineinherited

Reads the sequence of particles and their weights from a stream (requires T implementing CSerializable).

See also: writeParticlesToStream

Definition at line 207 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterData< T >::clearParticles(), mrpt::bayes::CParticleFilterData< T >::m_particles, MRPT_END, and MRPT_START.

◆ rebuildAverageMap()

void CMultiMetricMapPDF::rebuildAverageMap ( )

private

Rebuild the "expected" grid map.

Used internally, do not call

Definition at line 317 of file CMultiMetricMapPDF.cpp.

References ASSERT_, min, MRPT_END, and MRPT_START.

◆ saveCurrentPathEstimationToTextFile()

void CMultiMetricMapPDF::saveCurrentPathEstimationToTextFile ( const std::string & fil )

A logging utility: saves the current path estimation for each particle in a text file (a row per particle, each 3-column-entry is a set [x,y,phi], respectively).

Definition at line 601 of file CMultiMetricMapPDF.cpp.

References mrpt::system::os::fclose(), mrpt::system::os::fopen(), and mrpt::system::os::fprintf().

Referenced by mrpt::slam::CMetricMapBuilderRBPF::saveCurrentPathEstimationToTextFile().

◆ setW()

void mrpt::bayes::CParticleFilterDataImpl< CMultiMetricMapPDF , mrpt::bayes::CParticleFilterData< CRBPFParticleData >::CParticleList >::setW	(	size_t	i,
		double	w
	)

inlinevirtualinherited

Modifies i'th particle (logarithm) weight, where first one is index 0.

Implements mrpt::bayes::CParticleFilterCapable.

Definition at line 44 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterDataImpl< Derived, particle_list_t >::derived(), and THROW_EXCEPTION_FMT.

◆ updateSensoryFrameSequence()

void CMultiMetricMapPDF::updateSensoryFrameSequence ( )

Update the poses estimation of the member "SFs" according to the current path belief.

Definition at line 576 of file CMultiMetricMapPDF.cpp.

References MRPT_END, and MRPT_START.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMap().

◆ writeParticlesToStream()

void mrpt::bayes::CParticleFilterData< CRBPFParticleData >::writeParticlesToStream ( STREAM & out ) const

inlineinherited

Dumps the sequence of particles and their weights to a stream (requires T implementing CSerializable).

See also: readParticlesFromStream

Definition at line 192 of file CParticleFilterData.h.

References mrpt::bayes::CParticleFilterData< T >::m_particles, MRPT_END, and MRPT_START.

◆ writeToMatlab()

virtual mxArray* mrpt::utils::CSerializable::writeToMatlab ( ) const

inlinevirtualinherited

Introduces a pure virtual method responsible for writing to a mxArray Matlab object, typically a MATLAB struct whose contents are documented in each derived class.

Returns: A new mxArray (caller is responsible of memory freeing) or NULL is class does not support conversion to MATLAB.

Definition at line 79 of file CSerializable.h.

◆ writeToStream()

void CMultiMetricMapPDF::writeToStream	(	mrpt::utils::CStream &	out,
		int *	getVersion
	)		const

protectedvirtual

Introduces a pure virtual method responsible for writing to a CStream.

This can not be used directly be users, instead use "stream << object;" for writing it to a stream.

Parameters

out	The output binary stream where object must be dumped.
getVersion	If NULL, the object must be dumped. If not, only the version of the object dump must be returned in this pointer. This enables the versioning of objects dumping and backward compatibility with previously stored data.

Exceptions

std::exception On any error, see CStream::WriteBuffer

See also: CStream

Implements mrpt::utils::CSerializable.

Definition at line 220 of file CMultiMetricMapPDF.cpp.

References version.

Friends And Related Function Documentation

◆ mrpt::slam::CMetricMapBuilderRBPF

friend class mrpt::slam::CMetricMapBuilderRBPF

friend

Definition at line 68 of file maps/CMultiMetricMapPDF.h.

Member Data Documentation

◆ _init_CMultiMetricMapPDF

mrpt::utils::CLASSINIT mrpt::maps::CMultiMetricMapPDF::_init_CMultiMetricMapPDF

staticprotected

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ averageMap

mrpt::maps::CMultiMetricMap mrpt::maps::CMultiMetricMapPDF::averageMap

private

Internal buffer for the averaged map.

Definition at line 95 of file maps/CMultiMetricMapPDF.h.

◆ averageMapIsUpdated

bool mrpt::maps::CMultiMetricMapPDF::averageMapIsUpdated

private

Definition at line 96 of file maps/CMultiMetricMapPDF.h.

◆ classCMultiMetricMapPDF

mrpt::utils::TRuntimeClassId mrpt::maps::CMultiMetricMapPDF::classCMultiMetricMapPDF

static

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ classCObject

const mrpt::utils::TRuntimeClassId mrpt::utils::CObject::classCObject

staticinherited

Definition at line 128 of file CObject.h.

◆ classCSerializable

const mrpt::utils::TRuntimeClassId mrpt::utils::CSerializable::classCSerializable

staticinherited

Definition at line 42 of file CSerializable.h.

◆ classinfo

const mrpt::utils::TRuntimeClassId* mrpt::maps::CMultiMetricMapPDF::classinfo

static

Definition at line 71 of file maps/CMultiMetricMapPDF.h.

◆ m_accumRobotMovement2D

mrpt::obs::CActionRobotMovement2D mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_accumRobotMovement2D

protectedinherited

Definition at line 55 of file PF_implementations_data.h.

◆ m_accumRobotMovement2DIsValid

bool mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_accumRobotMovement2DIsValid

protectedinherited

Definition at line 56 of file PF_implementations_data.h.

◆ m_accumRobotMovement3D

mrpt::poses::CPose3DPDFGaussian mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_accumRobotMovement3D

protectedinherited

Definition at line 57 of file PF_implementations_data.h.

◆ m_accumRobotMovement3DIsValid

bool mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_accumRobotMovement3DIsValid

protectedinherited

Definition at line 58 of file PF_implementations_data.h.

◆ m_fastDrawAuxiliary

TFastDrawAuxVars mrpt::bayes::CParticleFilterCapable::m_fastDrawAuxiliary

mutableprotectedinherited

Auxiliary vectors, see CParticleFilterCapable::prepareFastDrawSample for more information.

Definition at line 233 of file CParticleFilterCapable.h.

◆ m_movementDrawer

mrpt::poses::CPoseRandomSampler mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_movementDrawer

protectedinherited

Used in al PF implementations.

See also: PF_SLAM_implementation_gatherActionsCheckBothActObs

Definition at line 60 of file PF_implementations_data.h.

◆ m_particles

CParticleList mrpt::bayes::CParticleFilterData< CRBPFParticleData >::m_particles

inherited

The array of particles.

Definition at line 177 of file CParticleFilterData.h.

◆ m_pfAuxiliaryPFOptimal_estimatedProb

mrpt::math::CVectorDouble mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_pfAuxiliaryPFOptimal_estimatedProb

mutableprotectedinherited

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 61 of file PF_implementations_data.h.

◆ m_pfAuxiliaryPFOptimal_maxLikDrawnMovement

std::vector<mrpt::math::TPose3D> mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_pfAuxiliaryPFOptimal_maxLikDrawnMovement

mutableprotectedinherited

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 64 of file PF_implementations_data.h.

◆ m_pfAuxiliaryPFOptimal_maxLikelihood

mrpt::math::CVectorDouble mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_pfAuxiliaryPFOptimal_maxLikelihood

mutableprotectedinherited

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 63 of file PF_implementations_data.h.

◆ m_pfAuxiliaryPFOptimal_maxLikMovementDrawHasBeenUsed

std::vector<bool> mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_pfAuxiliaryPFOptimal_maxLikMovementDrawHasBeenUsed

protectedinherited

Definition at line 65 of file PF_implementations_data.h.

◆ m_pfAuxiliaryPFStandard_estimatedProb

mrpt::math::CVectorDouble mrpt::slam::PF_implementation< CRBPFParticleData , CMultiMetricMapPDF >::m_pfAuxiliaryPFStandard_estimatedProb

mutableprotectedinherited

Auxiliary variable used in the "pfAuxiliaryPFStandard" algorithm.

Definition at line 62 of file PF_implementations_data.h.

◆ newInfoIndex

float mrpt::maps::CMultiMetricMapPDF::newInfoIndex

private

An index [0,1] measuring how much information an observation aports to the map (Typ. threshold=0.07)

Definition at line 209 of file maps/CMultiMetricMapPDF.h.

◆ options

mrpt::maps::CMultiMetricMapPDF::TPredictionParams mrpt::maps::CMultiMetricMapPDF::options

◆ SF2robotPath

std::vector<uint32_t> mrpt::maps::CMultiMetricMapPDF::SF2robotPath

private

A mapping between indexes in the SFs to indexes in the robot paths from particles.

Definition at line 99 of file maps/CMultiMetricMapPDF.h.

◆ SFs

mrpt::maps::CSimpleMap mrpt::maps::CMultiMetricMapPDF::SFs

private

The SFs and their corresponding pose estimations.

Definition at line 98 of file maps/CMultiMetricMapPDF.h.

Referenced by mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMap(), mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMapSize(), and mrpt::slam::CMetricMapBuilderRBPF::processActionObservation().

Detailed Description

Classes

Public Types

Public Member Functions

Static Public Member Functions

Public Attributes

Static Public Attributes

Protected Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Friends

RTTI stuff

Data members and methods used by generic PF implementations

Member Typedef Documentation

◆ ConstPtr

◆ CParticleData

◆ CParticleDataContent

◆ CParticleList

◆ Ptr

◆ TParticleProbabilityEvaluator

Constructor & Destructor Documentation

◆ CMultiMetricMapPDF()

Member Function Documentation

◆ _GetBaseClass()

◆ clear() [1/3]

◆ clear() [2/3]

◆ clear() [3/3]

◆ clearParticles()

◆ clone()

◆ computeResampling()

◆ Create()

◆ CreateObject()

◆ defaultEvaluator()

◆ derived() [1/2]

◆ derived() [2/2]

◆ duplicate()

◆ duplicateGetSmartPtr()

◆ ESS()

◆ fastDrawSample()

◆ getAveragedMetricMapEstimation()

◆ getCurrentEntropyOfPaths()

◆ getCurrentJointEntropy()

◆ getCurrentMostLikelyMetricMap()

◆ getEstimatedPosePDF()

◆ getEstimatedPosePDFAtTime()

◆ getLastPose()

◆ getMostLikelyParticle()

◆ getNumberOfObservationsInSimplemap()

◆ getPath()

◆ GetRuntimeClass()

◆ getW()

◆ getWeights()

◆ insertObservation()

◆ log2linearWeights()

◆ normalizeWeights()

◆ operator delete() [1/3]

◆ operator delete() [2/3]

◆ operator delete() [3/3]

◆ operator delete[]()

◆ operator new() [1/3]

◆ operator new() [2/3]

◆ operator new() [3/3]

◆ operator new[]()

◆ particlesCount()

◆ performResampling()

◆ performSubstitution()

◆ PF_SLAM_computeObservationLikelihoodForParticle()

◆ PF_SLAM_implementation_custom_update_particle_with_new_pose() [1/2]

◆ PF_SLAM_implementation_custom_update_particle_with_new_pose() [2/2]

◆ PF_SLAM_implementation_doWeHaveValidObservations() [1/2]

◆ PF_SLAM_implementation_doWeHaveValidObservations() [2/2]

◆ PF_SLAM_implementation_gatherActionsCheckBothActObs()

◆ PF_SLAM_implementation_pfAuxiliaryPFOptimal()

◆ PF_SLAM_implementation_pfAuxiliaryPFStandard()

◆ PF_SLAM_implementation_pfStandardProposal()

◆ PF_SLAM_implementation_replaceByNewParticleSet()

◆ PF_SLAM_implementation_skipRobotMovement()

◆ PF_SLAM_particlesEvaluator_AuxPFOptimal()

◆ PF_SLAM_particlesEvaluator_AuxPFStandard()