mrpt::hmtslam::CLocalMetricHypothesis Class Reference

Detailed Description

This class is used in HMT-SLAM to represent each of the Local Metric Hypotheses (LMHs).

It has a set of particles representing the robot path in nearby poses.

See Also

CHMTSLAM, CLSLAM_RBPF_2DLASER

Definition at line 93 of file CLocalMetricHypothesis.h.

#include <mrpt/hmtslam/CLocalMetricHypothesis.h>

Inheritance diagram for mrpt::hmtslam::CLocalMetricHypothesis:

Classes
struct	TRobotPosesPartitioning
	Used by AA thread. More...

Public Types
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".
typedef CLSLAMParticleData	CParticleDataContent
	This is the type inside the corresponding CParticleData class.
typedef CProbabilityParticle < CLSLAMParticleData >	CParticleData
	Use this to refer to each element in the m_particles array.
typedef std::deque< CParticleData >	CParticleList
	Use this type to refer to the list of particles m_particles.

Public Member Functions
	CLocalMetricHypothesis (CHMTSLAM *parent=NULL)
	Constructor (Default param only used from STL classes)
	~CLocalMetricHypothesis ()
	Destructor.
void	getAs3DScene (mrpt::opengl::CSetOfObjectsPtr &objs) const
	Returns a 3D representation of the the current robot pose, all the poses in the auxiliary graph, and each of the areas they belong to.
void	getMeans (std::map< TPoseID, CPose3D > &outList) const
	Returns the mean of each robot pose in this LMH, as computed from the set of particles.
void	getPathParticles (std::map< TPoseID, CPose3DPDFParticles > &outList) const
	Returns the mean and covariance of each robot pose in this LMH, as computed from the set of particles.
void	getPoseParticles (const TPoseID &poseID, CPose3DPDFParticles &outPDF) const
	Returns the mean and covariance of each robot pose in this LMH, as computed from the set of particles.
void	getRelativePose (const TPoseID &reference, const TPoseID &pose, CPose3DPDFParticles &outPDF) const
	Returns the pose PDF of some pose relative to some other pose ID (both must be part of the the LMH).
void	dumpAsText (utils::CStringList &st) const
	Describes the LMH in text.
void	changeCoordinateOrigin (const TPoseID &newOrigin)
	Change all coordinates to set a given robot pose as the new coordinate origin, and rebuild metric maps and change coords in the partitioning subsystem as well.
void	rebuildMetricMaps ()
	Rebuild the metric maps of all particles from the observations and their estimated poses.
void	clearRobotPoses ()
	Rebuild the auxiliary metric maps in "m_robotPosesGraph" from the observations "m_SFs" and their estimated poses.
const CPose3D *	getCurrentPose (const size_t &particleIdx) const
	Returns the i'th particle hypothesis for the current robot pose.
CPose3D *	getCurrentPose (const size_t &particleIdx)
	Returns the i'th particle hypothesis for the current robot pose.
void	removeAreaFromLMH (const CHMHMapNode::TNodeID areaID)
	Removes a given area from the LMH:
void	updateAreaFromLMH (const CHMHMapNode::TNodeID areaID, bool eraseSFsFromLMH=false)
	The corresponding node in the HMT map is updated with the robot poses & SFs in the LMH: the poses are referenced to the area's reference poseID, such as that reference is at the origin.
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.
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).
virtual double	getW (size_t i) const =0
	Access to i'th particle (logarithm) weight, where first one is index 0.
virtual void	setW (size_t i, double w)=0
	Modifies i'th particle (logarithm) weight, where first one is index 0.
virtual size_t	particlesCount () const =0
	Get the m_particles count.
void	prediction_and_update (const mrpt::slam::CActionCollection *action, const mrpt::slam::CSensoryFrame *observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	Performs the prediction stage of the Particle Filter.
virtual void	performSubstitution (const std::vector< size_t > &indx)=0
	Performs the substitution for internal use of resample in particle filter algorithm, don't call it directly.
virtual double	normalizeWeights (double *out_max_log_w=NULL)=0
	Normalize the (logarithmic) weights, such as the maximum weight is zero.
virtual double	ESS ()=0
	Returns the normalized ESS (Estimated Sample Size), in the range [0,1].
void	performResampling (const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	Performs a resample of the m_particles, using the method selected in the constructor.
void	clearParticles ()
	Free the memory of all the particles and reset the array "m_particles" to length zero.
void	writeParticlesToStream (utils::CStream &out) const
	Dumps the sequence of particles and their weights to a stream (requires T implementing CSerializable).
void	readParticlesFromStream (utils::CStream &in)
	Reads the sequence of particles and their weights from a stream (requires T implementing CSerializable).
void	getWeights (vector_double &out_logWeights) const
	Returns a vector with the sequence of the logaritmic weights of all the samples.
const CParticleData *	getMostLikelyParticle () const
	Returns the particle with the highest weight.
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).
CObject *	clone () const
	Cloning interface for smart pointers.

Static Public Member Functions
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.
static void	computeResampling (CParticleFilter::TParticleResamplingAlgorithm method, const vector_double &in_logWeights, std::vector< size_t > &out_indexes)
	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.
static void	log2linearWeights (const vector_double &in_logWeights, vector_double &out_linWeights)
	A static method to compute the linear, normalized (the sum the unity) weights from log-weights.

Public Attributes
synch::CCriticalSection	m_lock
	Critical section for threads signaling they are working with the LMH.
THypothesisID	m_ID
	The unique ID of the hypothesis (Used for accessing mrpt::slam::CHierarchicalMHMap).
safe_ptr< CHMTSLAM >	m_parent
	For quick access to our parent object.
TPoseID	m_currentRobotPose
	The current robot pose (its global unique ID) for this hypothesis.
TNodeIDSet	m_neighbors
	The list of all areas sourronding the current one (this includes the current area itself).
std::map< TPoseID, CHMHMapNode::TNodeID >	m_nodeIDmemberships
	The hybrid map node membership for each robot pose.
std::map< TPoseID, CSensoryFrame >	m_SFs
	The SF gathered at each robot pose.
TPoseIDList	m_posesPendingAddPartitioner
	The list of poseIDs waiting to be added to the graph partitioner, what happens in the LSLAM thread main loop.
TNodeIDList	m_areasPendingTBI
	The list of area IDs waiting to be processed by the TBI (topological bayesian inference) engines to search for potential loop-closures. Set in CHMTSLAM::LSLAM_process_message_from_AA, read in.
double	m_log_w
	Log-weight of this hypothesis.
std::vector< std::map< TPoseID, double > >	m_log_w_metric_history
	The historic log-weights of the metric observations inserted in this LMH, for each particle.
CActionRobotMovement2D	m_accumRobotMovement
	Used in CLSLAM_RBPF_2DLASER.
bool	m_accumRobotMovementIsValid
	Used in CLSLAM_RBPF_2DLASER.
struct mrpt::hmtslam::CLocalMetricHypothesis::TRobotPosesPartitioning	m_robotPosesGraph
CParticleList	m_particles
	The array of particles.

Static Public Attributes
static const mrpt::utils::TRuntimeClassId	classCObject
RTTI stuff
static const mrpt::utils::TRuntimeClassId	classCSerializable

Protected Member Functions
virtual void	prediction_and_update_pfStandardProposal (const mrpt::slam::CActionCollection *action, const mrpt::slam::CSensoryFrame *observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	Performs the particle filter prediction/update stages for the algorithm "pfStandardProposal" (if not implemented in heritated class, it will raise a 'non-implemented' exception).
virtual void	prediction_and_update_pfAuxiliaryPFStandard (const mrpt::slam::CActionCollection *action, const mrpt::slam::CSensoryFrame *observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	Performs the particle filter prediction/update stages for the algorithm "pfAuxiliaryPFStandard" (if not implemented in heritated class, it will raise a 'non-implemented' exception).
CSerializable virtual methods
void	writeToStream (mrpt::utils::CStream &out, int *getVersion) const
	Introduces a pure virtual method responsible for writing to a CStream.
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.
Virtual methods for Particle Filter implementation (just a wrapper interface, actually implemented in CHMTSLAM::m_LSLAM_method)
void	prediction_and_update_pfAuxiliaryPFOptimal (const mrpt::slam::CActionCollection *action, const mrpt::slam::CSensoryFrame *observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	The PF algorithm implementation.
void	prediction_and_update_pfOptimalProposal (const mrpt::slam::CActionCollection *action, const mrpt::slam::CSensoryFrame *observation, const bayes::CParticleFilter::TParticleFilterOptions &PF_options)
	The PF algorithm implementation.

Protected Attributes
vector_double	m_pfAuxiliaryPFOptimal_estimatedProb
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.
std::vector< double >	m_maxLikelihood
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.
std::vector< CPose2D, Eigen::aligned_allocator < CPose2D > >	m_movementDraws
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.
unsigned int	m_movementDrawsIdx
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.
StdVector_CPose2D	m_movementDrawMaximumLikelihood
	Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.
TFastDrawAuxVars	m_fastDrawAuxiliary
	Auxiliary vectors, see CParticleFilterCapable::prepareFastDrawSample for more information.

Friends
class HMTSLAM_IMPEXP	CLSLAM_RBPF_2DLASER

RTTI stuff
typedef CLocalMetricHypothesisPtr	SmartPtr
static mrpt::utils::CLASSINIT	_init_CLocalMetricHypothesis
static mrpt::utils::TRuntimeClassId	classCLocalMetricHypothesis
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.
virtual mrpt::utils::CObject *	duplicate () const
	Returns a copy of the object, indepently of its class.
static mrpt::utils::CObject *	CreateObject ()
static CLocalMetricHypothesisPtr	Create ()

Member Typedef Documentation

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

inherited

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

Definition at line 61 of file CParticleFilterData.h.

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

inherited

This is the type inside the corresponding CParticleData class.

Definition at line 60 of file CParticleFilterData.h.

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

inherited

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

Definition at line 62 of file CParticleFilterData.h.

typedef CLocalMetricHypothesisPtr mrpt::hmtslam::CLocalMetricHypothesis::SmartPtr

A typedef for the associated smart pointer

Definition at line 100 of file CLocalMetricHypothesis.h.

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 73 of file CParticleFilterCapable.h.

Constructor & Destructor Documentation

mrpt::hmtslam::CLocalMetricHypothesis::CLocalMetricHypothesis

(

CHMTSLAM *

parent = NULL

)

Constructor (Default param only used from STL classes)

mrpt::hmtslam::CLocalMetricHypothesis::~CLocalMetricHypothesis

(

)

Destructor.

Member Function Documentation

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

staticprotected

void mrpt::hmtslam::CLocalMetricHypothesis::changeCoordinateOrigin

(

const TPoseID &

newOrigin

)

Change all coordinates to set a given robot pose as the new coordinate origin, and rebuild metric maps and change coords in the partitioning subsystem as well.

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

inlineinherited

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

Definition at line 72 of file CParticleFilterData.h.

void mrpt::hmtslam::CLocalMetricHypothesis::clearRobotPoses

(

)

Rebuild the auxiliary metric maps in "m_robotPosesGraph" from the observations "m_SFs" and their estimated poses.

Sets the number of particles to the initial number according to the PF options, and initialize them with no robot poses & empty metric maps.

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

inlineinherited

Cloning interface for smart pointers.

Definition at line 154 of file CObject.h.

static void mrpt::bayes::CParticleFilterCapable::computeResampling ( CParticleFilter::TParticleResamplingAlgorithm  method, const vector_double &  in_logWeights, std::vector< size_t > &  out_indexes  )

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

See Also

performResampling

static CLocalMetricHypothesisPtr mrpt::hmtslam::CLocalMetricHypothesis::Create ( )

static

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

static

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 84 of file CParticleFilterCapable.h.

References mrpt::bayes::CParticleFilterCapable::getW(), and MRPT_UNUSED_PARAM.

void mrpt::hmtslam::CLocalMetricHypothesis::dumpAsText

(

utils::CStringList &

st

)

const

Describes the LMH in text.

virtual mrpt::utils::CObject* mrpt::hmtslam::CLocalMetricHypothesis::duplicate ( ) const

virtual

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

Implements mrpt::utils::CObject.

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 151 of file CObject.h.

virtual double mrpt::bayes::CParticleFilterCapable::ESS ( )

pure virtualinherited

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.

size_t mrpt::bayes::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

void mrpt::hmtslam::CLocalMetricHypothesis::getAs3DScene

(

mrpt::opengl::CSetOfObjectsPtr &

objs

)

const

Returns a 3D representation of the the current robot pose, all the poses in the auxiliary graph, and each of the areas they belong to.

The metric maps are not included here for convenience, call m_metricMaps.getAs3DScene(). The previous contents of "objs" will be discarded

const CPose3D* mrpt::hmtslam::CLocalMetricHypothesis::getCurrentPose

(

const size_t &

particleIdx

)

const

Returns the i'th particle hypothesis for the current robot pose.

CPose3D* mrpt::hmtslam::CLocalMetricHypothesis::getCurrentPose

(

const size_t &

particleIdx

)

Returns the i'th particle hypothesis for the current robot pose.

void mrpt::hmtslam::CLocalMetricHypothesis::getMeans

(

std::map< TPoseID, CPose3D > &

outList

)

const

Returns the mean of each robot pose in this LMH, as computed from the set of particles.

See Also

getPathParticles, getRelativePose

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

inlineinherited

Returns the particle with the highest weight.

Definition at line 140 of file CParticleFilterData.h.

void mrpt::hmtslam::CLocalMetricHypothesis::getPathParticles

(

std::map< TPoseID, CPose3DPDFParticles > &

outList

)

const

Returns the mean and covariance of each robot pose in this LMH, as computed from the set of particles.

See Also

getMeans, getPoseParticles

void mrpt::hmtslam::CLocalMetricHypothesis::getPoseParticles	(	const TPoseID &	poseID,
		CPose3DPDFParticles &	outPDF
	)		const

Returns the mean and covariance of each robot pose in this LMH, as computed from the set of particles.

See Also

getMeans, getPathParticles

void mrpt::hmtslam::CLocalMetricHypothesis::getRelativePose	(	const TPoseID &	reference,
		const TPoseID &	pose,
		CPose3DPDFParticles &	outPDF
	)		const

Returns the pose PDF of some pose relative to some other pose ID (both must be part of the the LMH).

See Also

getMeans, getPoseParticles

virtual const mrpt::utils::TRuntimeClassId* mrpt::hmtslam::CLocalMetricHypothesis::GetRuntimeClass ( ) const

virtual

Returns information about the class of an object in runtime.

Reimplemented from mrpt::utils::CSerializable.

virtual double mrpt::bayes::CParticleFilterCapable::getW ( size_t  i ) const

pure virtualinherited

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

Referenced by mrpt::bayes::CParticleFilterCapable::defaultEvaluator().

void mrpt::bayes::CParticleFilterData< CLSLAMParticleData >::getWeights ( vector_double &  out_logWeights ) const

inlineinherited

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

Definition at line 127 of file CParticleFilterData.h.

static void mrpt::bayes::CParticleFilterCapable::log2linearWeights ( const vector_double &  in_logWeights, vector_double &  out_linWeights  )

staticinherited

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

See Also

performResampling

virtual double mrpt::bayes::CParticleFilterCapable::normalizeWeights ( double *  out_max_log_w = NULL )

pure virtualinherited

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")

virtual size_t mrpt::bayes::CParticleFilterCapable::particlesCount ( ) const

pure virtualinherited

Get the m_particles count.

void mrpt::bayes::CParticleFilterCapable::performResampling ( const bayes::CParticleFilter::TParticleFilterOptions &  PF_options )

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"

See Also

resample

virtual void mrpt::bayes::CParticleFilterCapable::performSubstitution ( const std::vector< size_t > &  indx )

pure virtualinherited

Performs the substitution for internal use of resample in particle filter algorithm, don't call it directly.

Parameters

indx	The indices of current m_particles to be saved as the new m_particles set.

void mrpt::bayes::CParticleFilterCapable::prediction_and_update ( const mrpt::slam::CActionCollection *  action, const mrpt::slam::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

void mrpt::hmtslam::CLocalMetricHypothesis::prediction_and_update_pfAuxiliaryPFOptimal ( const mrpt::slam::CActionCollection *  action, const mrpt::slam::CSensoryFrame *  observation, const bayes::CParticleFilter::TParticleFilterOptions &  PF_options  )

protectedvirtual

The PF algorithm implementation.

Reimplemented from mrpt::bayes::CParticleFilterCapable.

virtual void mrpt::bayes::CParticleFilterCapable::prediction_and_update_pfAuxiliaryPFStandard ( const mrpt::slam::CActionCollection *  action, const mrpt::slam::CSensoryFrame *  observation, const bayes::CParticleFilter::TParticleFilterOptions &  PF_options  )

protectedvirtualinherited

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 in mrpt::slam::CMonteCarloLocalization2D, and mrpt::slam::CMonteCarloLocalization3D.

void mrpt::hmtslam::CLocalMetricHypothesis::prediction_and_update_pfOptimalProposal ( const mrpt::slam::CActionCollection *  action, const mrpt::slam::CSensoryFrame *  observation, const bayes::CParticleFilter::TParticleFilterOptions &  PF_options  )

protectedvirtual

The PF algorithm implementation.

Reimplemented from mrpt::bayes::CParticleFilterCapable.

virtual void mrpt::bayes::CParticleFilterCapable::prediction_and_update_pfStandardProposal ( const mrpt::slam::CActionCollection *  action, const mrpt::slam::CSensoryFrame *  observation, const bayes::CParticleFilter::TParticleFilterOptions &  PF_options  )

protectedvirtualinherited

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 in mrpt::slam::CMonteCarloLocalization2D, mrpt::slam::CMultiMetricMapPDF, and mrpt::slam::CMonteCarloLocalization3D.

void mrpt::bayes::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

void mrpt::hmtslam::CLocalMetricHypothesis::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.

void mrpt::bayes::CParticleFilterData< CLSLAMParticleData >::readParticlesFromStream ( utils::CStream &  in )

inlineinherited

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

See Also

writeParticlesToStream

Definition at line 107 of file CParticleFilterData.h.

void mrpt::hmtslam::CLocalMetricHypothesis::rebuildMetricMaps

(

)

Rebuild the metric maps of all particles from the observations and their estimated poses.

void mrpt::hmtslam::CLocalMetricHypothesis::removeAreaFromLMH

(

const CHMHMapNode::TNodeID

areaID

)

Removes a given area from the LMH:

- The corresponding node in the HMT map is updated with the robot poses & SFs in the LMH.
- Robot poses belonging to that area are removed from:
    - the particles.
    - the graph partitioner.
    - the list of SFs.
    - the list m_nodeIDmemberships.
- m_neighbors is updated.

• The weights of all particles are changed to remove the effects of the removed metric observations.
  • After calling this the metric maps should be updated.
• This method internally calls updateAreaFromLMH

virtual void mrpt::bayes::CParticleFilterCapable::setW ( size_t  i, double  w  )

pure virtualinherited

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

void mrpt::hmtslam::CLocalMetricHypothesis::updateAreaFromLMH	(	const CHMHMapNode::TNodeID	areaID,
		bool	eraseSFsFromLMH = false
	)

The corresponding node in the HMT map is updated with the robot poses & SFs in the LMH: the poses are referenced to the area's reference poseID, such as that reference is at the origin.

If eraseSFsFromLMH=true, the sensoryframes are moved rather than copied to the area, and removed from the LMH.

Note

The critical section m_map_cs is locked internally, unlock it before calling this.

void mrpt::bayes::CParticleFilterData< CLSLAMParticleData >::writeParticlesToStream ( utils::CStream &  out ) const

inlineinherited

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

See Also

readParticlesFromStream

Definition at line 93 of file CParticleFilterData.h.

void mrpt::hmtslam::CLocalMetricHypothesis::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.

Friends And Related Function Documentation

friend class HMTSLAM_IMPEXP CLSLAM_RBPF_2DLASER

friend

Definition at line 97 of file CLocalMetricHypothesis.h.

Member Data Documentation

mrpt::utils::CLASSINIT mrpt::hmtslam::CLocalMetricHypothesis::_init_CLocalMetricHypothesis

staticprotected

Definition at line 100 of file CLocalMetricHypothesis.h.

mrpt::utils::TRuntimeClassId mrpt::hmtslam::CLocalMetricHypothesis::classCLocalMetricHypothesis

static

Definition at line 100 of file CLocalMetricHypothesis.h.

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

staticinherited

Definition at line 139 of file CObject.h.

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

staticinherited

Definition at line 56 of file CSerializable.h.

const mrpt::utils::TRuntimeClassId* mrpt::hmtslam::CLocalMetricHypothesis::classinfo

static

Definition at line 100 of file CLocalMetricHypothesis.h.

CActionRobotMovement2D mrpt::hmtslam::CLocalMetricHypothesis::m_accumRobotMovement

Used in CLSLAM_RBPF_2DLASER.

Definition at line 126 of file CLocalMetricHypothesis.h.

bool mrpt::hmtslam::CLocalMetricHypothesis::m_accumRobotMovementIsValid

Used in CLSLAM_RBPF_2DLASER.

Definition at line 127 of file CLocalMetricHypothesis.h.

TNodeIDList mrpt::hmtslam::CLocalMetricHypothesis::m_areasPendingTBI

The list of area IDs waiting to be processed by the TBI (topological bayesian inference) engines to search for potential loop-closures. Set in CHMTSLAM::LSLAM_process_message_from_AA, read in.

Definition at line 120 of file CLocalMetricHypothesis.h.

TPoseID mrpt::hmtslam::CLocalMetricHypothesis::m_currentRobotPose

The current robot pose (its global unique ID) for this hypothesis.

Definition at line 114 of file CLocalMetricHypothesis.h.

TFastDrawAuxVars mrpt::bayes::CParticleFilterCapable::m_fastDrawAuxiliary

mutableprotectedinherited

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

Definition at line 249 of file CParticleFilterCapable.h.

THypothesisID mrpt::hmtslam::CLocalMetricHypothesis::m_ID

The unique ID of the hypothesis (Used for accessing mrpt::slam::CHierarchicalMHMap).

Definition at line 112 of file CLocalMetricHypothesis.h.

synch::CCriticalSection mrpt::hmtslam::CLocalMetricHypothesis::m_lock

Critical section for threads signaling they are working with the LMH.

Definition at line 111 of file CLocalMetricHypothesis.h.

double mrpt::hmtslam::CLocalMetricHypothesis::m_log_w

Log-weight of this hypothesis.

Definition at line 122 of file CLocalMetricHypothesis.h.

std::vector<std::map<TPoseID,double> > mrpt::hmtslam::CLocalMetricHypothesis::m_log_w_metric_history

The historic log-weights of the metric observations inserted in this LMH, for each particle.

Definition at line 123 of file CLocalMetricHypothesis.h.

std::vector<double> mrpt::hmtslam::CLocalMetricHypothesis::m_maxLikelihood

mutableprotected

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 243 of file CLocalMetricHypothesis.h.

StdVector_CPose2D mrpt::hmtslam::CLocalMetricHypothesis::m_movementDrawMaximumLikelihood

mutableprotected

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 255 of file CLocalMetricHypothesis.h.

std::vector<CPose2D,Eigen::aligned_allocator<CPose2D> > mrpt::hmtslam::CLocalMetricHypothesis::m_movementDraws

mutableprotected

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 247 of file CLocalMetricHypothesis.h.

unsigned int mrpt::hmtslam::CLocalMetricHypothesis::m_movementDrawsIdx

mutableprotected

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 251 of file CLocalMetricHypothesis.h.

TNodeIDSet mrpt::hmtslam::CLocalMetricHypothesis::m_neighbors

The list of all areas sourronding the current one (this includes the current area itself).

Definition at line 116 of file CLocalMetricHypothesis.h.

std::map<TPoseID,CHMHMapNode::TNodeID> mrpt::hmtslam::CLocalMetricHypothesis::m_nodeIDmemberships

The hybrid map node membership for each robot pose.

Definition at line 117 of file CLocalMetricHypothesis.h.

safe_ptr<CHMTSLAM> mrpt::hmtslam::CLocalMetricHypothesis::m_parent

For quick access to our parent object.

Definition at line 113 of file CLocalMetricHypothesis.h.

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

inherited

The array of particles.

Definition at line 64 of file CParticleFilterData.h.

vector_double mrpt::hmtslam::CLocalMetricHypothesis::m_pfAuxiliaryPFOptimal_estimatedProb

mutableprotected

Auxiliary variable used in the "pfAuxiliaryPFOptimal" algorithm.

Definition at line 239 of file CLocalMetricHypothesis.h.

TPoseIDList mrpt::hmtslam::CLocalMetricHypothesis::m_posesPendingAddPartitioner

The list of poseIDs waiting to be added to the graph partitioner, what happens in the LSLAM thread main loop.

Definition at line 119 of file CLocalMetricHypothesis.h.

struct mrpt::hmtslam::CLocalMetricHypothesis::TRobotPosesPartitioning mrpt::hmtslam::CLocalMetricHypothesis::m_robotPosesGraph

std::map<TPoseID,CSensoryFrame> mrpt::hmtslam::CLocalMetricHypothesis::m_SFs

The SF gathered at each robot pose.

Definition at line 118 of file CLocalMetricHypothesis.h.