Main MRPT website > C++ reference
MRPT logo
Classes | Public Member Functions | Public Attributes | Protected Attributes

mrpt::slam::CMetricMapBuilderRBPF Class Reference


Detailed Description

This class implements a Rao-Blackwelized Particle Filter (RBPF) approach to map building (SLAM).

Internally, the list of particles, each containing a hypothesis for the robot path plus its associated metric map, is stored in an object of class CMultiMetricMapPDF.

This class processes robot actions and observations sequentially (through the method CMetricMapBuilderRBPF::processActionObservation) and exploits the generic design of metric map classes in MRPT to deal with any number and combination of maps simultaneously: the likelihood of observations is the product of the likelihood in the different maps, etc.

A number of particle filter methods are implemented as well, by selecting the appropriate values in TConstructionOptions::PF_options. Not all the PF algorithms are implemented for all kinds of maps.

For an example of usage, check the application "rbpf-slam", in "apps/RBPF-SLAM". See also the wiki page.

Note:
Since MRPT 0.7.2, the new variables "localizeLinDistance,localizeAngDistance" are introduced to provide a way to update the robot pose at a different rate than the map is updated.
Since MRPT 0.7.1 the semantics of the parameters "insertionLinDistance" and "insertionAngDistance" changes: the entire RBFP is now NOT updated unless odometry increments surpass the threshold (previously, only the map was NOT updated). This is done to gain efficiency.
Since MRPT 0.6.2 this class implements full 6D SLAM. Previous versions worked in 2D + heading only.
See also:
CMetricMap

Definition at line 65 of file CMetricMapBuilderRBPF.h.

#include <mrpt/slam/CMetricMapBuilderRBPF.h>

Inheritance diagram for mrpt::slam::CMetricMapBuilderRBPF:
Inheritance graph
[legend]

List of all members.

Classes

struct  TConstructionOptions
 Options for building a CMetricMapBuilderRBPF object, passed to the constructor. More...
struct  TStats
 This structure will hold stats after each execution of processActionObservation. More...

Public Member Functions

 CMetricMapBuilderRBPF (const TConstructionOptions &initializationOptions)
 Constructor.
virtual ~CMetricMapBuilderRBPF ()
 Destructor.
void initialize (const CSimpleMap &initialMap=CSimpleMap(), CPosePDF *x0=NULL)
 Initialize the method, starting with a known location PDF "x0"(if supplied, set to NULL to left unmodified) and a given fixed, past map.
void clear ()
 Clear all elements of the maps.
CPose3DPDFPtr getCurrentPoseEstimation () const
 Returns a copy of the current best pose estimation as a pose PDF.
void getCurrentMostLikelyPath (std::deque< TPose3D > &outPath) const
 Returns the current most-likely path estimation (the path associated to the most likely particle).
void processActionObservation (CActionCollection &action, CSensoryFrame &observations)
 Appends a new action and observations to update this map: See the description of the class at the top of this page to see a more complete description.
void getCurrentlyBuiltMap (CSimpleMap &out_map) const
 Fills "out_map" with the set of "poses"-"sensory-frames", thus the so far built map.
CMultiMetricMapgetCurrentlyBuiltMetricMap ()
 Returns the map built so far.
unsigned int getCurrentlyBuiltMapSize ()
 Returns just how many sensory-frames are stored in the currently build map.
void saveCurrentEstimationToImage (const std::string &file, bool formatEMF_BMP=true)
 A useful method for debugging: the current map (and/or poses) estimation is dumped to an image file.
void drawCurrentEstimationToImage (utils::CCanvas *img)
 A usefull method for debugging: draws the current map and path hypotheses to a CCanvas.
void saveCurrentPathEstimationToTextFile (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).
double getCurrentJointEntropy ()

Public Attributes

CMultiMetricMapPDF mapPDF
 The map PDF: It includes a path and associated map for each particle.
TStats m_statsLastIteration
 This structure will hold stats after each execution of processActionObservation.

Protected Attributes

bayes::CParticleFilter::TParticleFilterOptions m_PF_options
 The configuration of the particle filter:
float insertionLinDistance
 Distances (linear and angular) for inserting a new observation into the map.
float insertionAngDistance
float localizeLinDistance
 Distances (linear and angular) for updating the robot pose estimate (and particles weighs, if applicable).
float localizeAngDistance
mrpt::poses::CPose3DPDFGaussian odoIncrementSinceLastLocalization
 Traveled distance since last localization update.
mrpt::poses::CPose3D odoIncrementSinceLastMapUpdate
 Traveled distance since last map update.
non_copiable_ptr< CMultiMetricMapcurrentMetricMapEstimation
 A buffer: memory is actually hold within "mapPDF".

Constructor & Destructor Documentation

mrpt::slam::CMetricMapBuilderRBPF::CMetricMapBuilderRBPF ( const TConstructionOptions initializationOptions )

Constructor.

virtual mrpt::slam::CMetricMapBuilderRBPF::~CMetricMapBuilderRBPF (  ) [virtual]

Destructor.


Member Function Documentation

void mrpt::slam::CMetricMapBuilderRBPF::clear (  )

Clear all elements of the maps.

Reimplemented from mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::drawCurrentEstimationToImage ( utils::CCanvas img )

A usefull method for debugging: draws the current map and path hypotheses to a CCanvas.

double mrpt::slam::CMetricMapBuilderRBPF::getCurrentJointEntropy (  )
void mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMap ( CSimpleMap out_map ) const [virtual]

Fills "out_map" with the set of "poses"-"sensory-frames", thus the so far built map.

Implements mrpt::slam::CMetricMapBuilder.

unsigned int mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMapSize (  ) [virtual]

Returns just how many sensory-frames are stored in the currently build map.

Implements mrpt::slam::CMetricMapBuilder.

CMultiMetricMap* mrpt::slam::CMetricMapBuilderRBPF::getCurrentlyBuiltMetricMap (  ) [virtual]

Returns the map built so far.

NOTE that for efficiency a pointer to the internal object is passed, DO NOT delete nor modify the object in any way, if desired, make a copy of ir with "duplicate()".

Implements mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::getCurrentMostLikelyPath ( std::deque< TPose3D > &  outPath ) const

Returns the current most-likely path estimation (the path associated to the most likely particle).

CPose3DPDFPtr mrpt::slam::CMetricMapBuilderRBPF::getCurrentPoseEstimation (  ) const [virtual]

Returns a copy of the current best pose estimation as a pose PDF.

Implements mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::initialize ( const CSimpleMap initialMap = CSimpleMap(),
CPosePDF x0 = NULL 
) [virtual]

Initialize the method, starting with a known location PDF "x0"(if supplied, set to NULL to left unmodified) and a given fixed, past map.

Implements mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::processActionObservation ( CActionCollection action,
CSensoryFrame observations 
) [virtual]

Appends a new action and observations to update this map: See the description of the class at the top of this page to see a more complete description.

Parameters:
actionThe incremental 2D pose change in the robot pose. This value is deterministic.
observationsThe set of observations that robot senses at the new pose. Statistics will be saved to statsLastIteration

Implements mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::saveCurrentEstimationToImage ( const std::string &  file,
bool  formatEMF_BMP = true 
) [virtual]

A useful method for debugging: the current map (and/or poses) estimation is dumped to an image file.

Parameters:
fileThe output file name
formatEMF_BMPOutput format = true:EMF, false:BMP

Implements mrpt::slam::CMetricMapBuilder.

void mrpt::slam::CMetricMapBuilderRBPF::saveCurrentPathEstimationToTextFile ( 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).


Member Data Documentation

A buffer: memory is actually hold within "mapPDF".

Definition at line 91 of file CMetricMapBuilderRBPF.h.

Definition at line 79 of file CMetricMapBuilderRBPF.h.

Distances (linear and angular) for inserting a new observation into the map.

Definition at line 79 of file CMetricMapBuilderRBPF.h.

Definition at line 83 of file CMetricMapBuilderRBPF.h.

Distances (linear and angular) for updating the robot pose estimate (and particles weighs, if applicable).

Definition at line 83 of file CMetricMapBuilderRBPF.h.

The configuration of the particle filter:

Definition at line 75 of file CMetricMapBuilderRBPF.h.

This structure will hold stats after each execution of processActionObservation.

Definition at line 206 of file CMetricMapBuilderRBPF.h.

The map PDF: It includes a path and associated map for each particle.

Definition at line 70 of file CMetricMapBuilderRBPF.h.

Traveled distance since last localization update.

Definition at line 86 of file CMetricMapBuilderRBPF.h.

Traveled distance since last map update.

Definition at line 87 of file CMetricMapBuilderRBPF.h.




Page generated by Doxygen 1.7.2 for MRPT 0.9.4 SVN: at Mon Jan 10 22:46:17 UTC 2011