mrpt::poses::CPosePDFSOG Class Reference

Declares a class that represents a Probability Density function (PDF) of a 2D pose $p(\mathbf{x}) = [x ~ y ~ \phi ]^t$ . More...

#include <mrpt/poses/CPosePDFSOG.h>

Inheritance diagram for mrpt::poses::CPosePDFSOG:

List of all members.

Classes

struct TGaussianMode

The struct for each mode:. More...

Public Member Functions

CPosePDFSOG (size_t nModes=1)

Default constructor.

size_t size () const

Return the number of Gaussians in the SOG.

void mergeModes (double max_KLd=0.5, bool verbose=false)

Merge very close modes so the overall number of modes is reduced while preserving the total distribution.

CPose2D getEstimatedPose () const

Returns an estimate of the pose, (the mean, or mathematical expectation of the PDF).

CMatrixD getEstimatedCovariance () const

Returns an estimate of the pose covariance matrix (3x3 cov.matrix for x,y,phi variables).

void normalizeWeights ()

Normalize the weights in m_modes such as the maximum log-weight is 0.

void copyFrom (const CPosePDF &o)

Copy operator, translating if necesary (for example, between particles and gaussian representations).

void saveToTextFile (const std::string &file) const

Save the density to a text file, with the following format: There is one row per Gaussian "mode", and each row contains 10 elements:

w (The weight)
x_mean (gaussian mean value)
y_mean (gaussian mean value)
phi_mean (gaussian mean value)
C11 (Covariance elements)
C22 (Covariance elements)
C33 (Covariance elements)
C12 (Covariance elements)
C13 (Covariance elements)
C23 (Covariance elements).

void changeCoordinatesReference (const CPose2D &newReferenceBase)

This can be used to convert a PDF from local coordinates to global, providing the point (newReferenceBase) from which "to project" the current pdf.

void rotateAllCovariances (const double &ang)

Rotate all the covariance matrixes by replacing them by $\mathbf{R}~\mathbf{COV}~\mathbf{R}^t$ , where $\mathbf{R} = \left[ \begin{array}{ccc} \cos\alpha & -\sin\alpha & 0 \\ \sin\alpha & \cos\alpha & 0 \\ 0 & 0 & 1 \end{array}\right]$ .

void drawSingleSample (CPose2D &outPart) const

Draws a single sample from the distribution.

void drawManySamples (size_t N, std::vector< vector_double > &outSamples) const

Draws a number of samples from the distribution, and saves as a list of 1x3 vectors, where each row contains a (x,y,phi) datum.

void inverse (CPosePDF &o) const

Returns a new PDF such as: NEW_PDF = (0,0,0) - THIS_PDF.

void operator+= (CPose2D Ap)

Makes: thisPDF = thisPDF + Ap, where "+" is pose composition (both the mean, and the covariance matrix are updated).

double evaluatePDF (const CPose2D &x, bool sumOverAllPhis=false) const

Evaluates the PDF at a given point.

double evaluateNormalizedPDF (const CPose2D &x) const

Evaluates the ratio PDF(x) / max_PDF(x*), that is, the normalized PDF in the range [0,1].

void evaluatePDFInArea (const double &x_min, const double &x_max, const double &y_min, const double &y_max, const double &resolutionXY, const double &phi, CMatrixD &outMatrix, bool sumOverAllPhis=false)

Evaluates the PDF within a rectangular grid (and a fixed orientation) and saves the result in a matrix (each row contains values for a fixed y-coordinate value).

void bayesianFusion (CPosePDF &p1, CPosePDF &p2, const double &minMahalanobisDistToDrop=0)

Bayesian fusion of two pose distributions, then save the result in this object (WARNING: Currently p1 must be a mrpt::poses::CPosePDFSOG object and p2 a mrpt::poses::CPosePDFGaussian object).

void getAs3DObject (mrpt::opengl::CSetOfObjectsPtr &outObj) const

Returns a 3D object representation of all the ellipses in the SoG.

Public Attributes

std::deque< TGaussianMode > m_modes

Access directly to this array for modify the modes as desired.

Protected Member Functions

void assureSymmetry ()

Assures the symmetry of the covariance matrix (eventually certain operations in the math-coprocessor lead to non-symmetric matrixes!).

Detailed Description

Declares a class that represents a Probability Density function (PDF) of a 2D pose $p(\mathbf{x}) = [x ~ y ~ \phi ]^t$ .

This class implements that PDF as the following multi-modal Gaussian distribution:

$p(\mathbf{x}) = \sum\limits_{i=1}^N \omega^i \mathcal{N}( \mathbf{x} ; \bar{\mathbf{x}}^i, \mathbf{\Sigma}^i )$

Where the number of modes N is the size of CPosePDFSOG::m_modes

See mrpt::poses::CPosePDF for more details.

See also:: CPose2D, CPosePDF, CPosePDFParticles

Definition at line 57 of file CPosePDFSOG.h.

Constructor & Destructor Documentation

mrpt::poses::CPosePDFSOG::CPosePDFSOG ( size_t nModes = 1 )

Default constructor.

Parameters:

nModes

The initial size of CPosePDFSOG::m_modes

Member Function Documentation

void mrpt::poses::CPosePDFSOG::assureSymmetry ( ) [protected]

Assures the symmetry of the covariance matrix (eventually certain operations in the math-coprocessor lead to non-symmetric matrixes!).

void mrpt::poses::CPosePDFSOG::bayesianFusion	(	CPosePDF &	p1,
		CPosePDF &	p2,
		const double &	minMahalanobisDistToDrop = `0`
	)			`[virtual]`

Bayesian fusion of two pose distributions, then save the result in this object (WARNING: Currently p1 must be a mrpt::poses::CPosePDFSOG object and p2 a mrpt::poses::CPosePDFGaussian object).

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::changeCoordinatesReference ( const CPose2D & newReferenceBase ) [virtual]

This can be used to convert a PDF from local coordinates to global, providing the point (newReferenceBase) from which "to project" the current pdf.

Result PDF substituted the currently stored one in the object.

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::copyFrom ( const CPosePDF & o ) [virtual]

Copy operator, translating if necesary (for example, between particles and gaussian representations).

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::drawManySamples	(	size_t	N,
		std::vector< vector_double > &	outSamples
	)			const `[virtual]`

Draws a number of samples from the distribution, and saves as a list of 1x3 vectors, where each row contains a (x,y,phi) datum.

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::drawSingleSample ( CPose2D & outPart ) const [virtual]

Draws a single sample from the distribution.

Implements mrpt::poses::CPosePDF.

double mrpt::poses::CPosePDFSOG::evaluateNormalizedPDF ( const CPose2D & x ) const

Evaluates the ratio PDF(x) / max_PDF(x*), that is, the normalized PDF in the range [0,1].

double mrpt::poses::CPosePDFSOG::evaluatePDF	(	const CPose2D &	x,
		bool	sumOverAllPhis = `false`
	)			const

Evaluates the PDF at a given point.

void mrpt::poses::CPosePDFSOG::evaluatePDFInArea	(	const double &	x_min,
		const double &	x_max,
		const double &	y_min,
		const double &	y_max,
		const double &	resolutionXY,
		const double &	phi,
		CMatrixD &	outMatrix,
		bool	sumOverAllPhis = `false`
	)

Evaluates the PDF within a rectangular grid (and a fixed orientation) and saves the result in a matrix (each row contains values for a fixed y-coordinate value).

void mrpt::poses::CPosePDFSOG::getAs3DObject ( mrpt::opengl::CSetOfObjectsPtr & outObj ) const

Returns a 3D object representation of all the ellipses in the SoG.

CMatrixD mrpt::poses::CPosePDFSOG::getEstimatedCovariance ( ) const [virtual]

Returns an estimate of the pose covariance matrix (3x3 cov.matrix for x,y,phi variables).

Implements mrpt::poses::CPosePDF.

CPose2D mrpt::poses::CPosePDFSOG::getEstimatedPose ( ) const [virtual]

Returns an estimate of the pose, (the mean, or mathematical expectation of the PDF).

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::inverse ( CPosePDF & o ) const [virtual]

Returns a new PDF such as: NEW_PDF = (0,0,0) - THIS_PDF.

Implements mrpt::poses::CPosePDF.

void mrpt::poses::CPosePDFSOG::mergeModes	(	double	max_KLd = `0.5`,
		bool	verbose = `false`
	)

Merge very close modes so the overall number of modes is reduced while preserving the total distribution.

This method uses the approach described in the paper:

"Kullback-Leibler Approach to Gaussian Mixture Reduction" AR Runnalls. IEEE Transactions on Aerospace and Electronic Systems, 2007.

Parameters:

max_KLd

The maximum KL-divergence to consider the merge of two nodes (and then stops the process).

void mrpt::poses::CPosePDFSOG::normalizeWeights ( )

Normalize the weights in m_modes such as the maximum log-weight is 0.

void mrpt::poses::CPosePDFSOG::operator+= ( CPose2D Ap )

Makes: thisPDF = thisPDF + Ap, where "+" is pose composition (both the mean, and the covariance matrix are updated).

void mrpt::poses::CPosePDFSOG::rotateAllCovariances ( const double & ang )

Rotate all the covariance matrixes by replacing them by $\mathbf{R}~\mathbf{COV}~\mathbf{R}^t$ , where $\mathbf{R} = \left[ \begin{array}{ccc} \cos\alpha & -\sin\alpha & 0 \\ \sin\alpha & \cos\alpha & 0 \\ 0 & 0 & 1 \end{array}\right]$ .

void mrpt::poses::CPosePDFSOG::saveToTextFile ( const std::string & file ) const [virtual]

Save the density to a text file, with the following format: There is one row per Gaussian "mode", and each row contains 10 elements:

w (The weight)
x_mean (gaussian mean value)
y_mean (gaussian mean value)
phi_mean (gaussian mean value)
C11 (Covariance elements)
C22 (Covariance elements)
C33 (Covariance elements)
C12 (Covariance elements)
C13 (Covariance elements)
C23 (Covariance elements).

Implements mrpt::poses::CPosePDF.

size_t mrpt::poses::CPosePDFSOG::size ( ) const [inline]

Return the number of Gaussians in the SOG.

Definition at line 97 of file CPosePDFSOG.h.

Member Data Documentation

std::deque<TGaussianMode> mrpt::poses::CPosePDFSOG::m_modes

Access directly to this array for modify the modes as desired.

Note that no weight can be zero!!

Definition at line 94 of file CPosePDFSOG.h.


Classes
struct	TGaussianMode
	The struct for each mode:. More...
Public Member Functions
	CPosePDFSOG (size_t nModes=1)
	Default constructor.
size_t	size () const
	Return the number of Gaussians in the SOG.
void	mergeModes (double max_KLd=0.5, bool verbose=false)
	Merge very close modes so the overall number of modes is reduced while preserving the total distribution.
CPose2D	getEstimatedPose () const
	Returns an estimate of the pose, (the mean, or mathematical expectation of the PDF).
CMatrixD	getEstimatedCovariance () const
	Returns an estimate of the pose covariance matrix (3x3 cov.matrix for x,y,phi variables).
void	normalizeWeights ()
	Normalize the weights in m_modes such as the maximum log-weight is 0.
void	copyFrom (const CPosePDF &o)
	Copy operator, translating if necesary (for example, between particles and gaussian representations).
void	saveToTextFile (const std::string &file) const
	Save the density to a text file, with the following format: There is one row per Gaussian "mode", and each row contains 10 elements: w (The weight) x_mean (gaussian mean value) y_mean (gaussian mean value) phi_mean (gaussian mean value) C11 (Covariance elements) C22 (Covariance elements) C33 (Covariance elements) C12 (Covariance elements) C13 (Covariance elements) C23 (Covariance elements).
void	changeCoordinatesReference (const CPose2D &newReferenceBase)
	This can be used to convert a PDF from local coordinates to global, providing the point (newReferenceBase) from which "to project" the current pdf.
void	rotateAllCovariances (const double &ang)
	Rotate all the covariance matrixes by replacing them by $\mathbf{R}~\mathbf{COV}~\mathbf{R}^t$ , where $\mathbf{R} = \left[ \begin{array}{ccc} \cos\alpha & -\sin\alpha & 0 \\ \sin\alpha & \cos\alpha & 0 \\ 0 & 0 & 1 \end{array}\right]$ .
void	drawSingleSample (CPose2D &outPart) const
	Draws a single sample from the distribution.
void	drawManySamples (size_t N, std::vector< vector_double > &outSamples) const
	Draws a number of samples from the distribution, and saves as a list of 1x3 vectors, where each row contains a (x,y,phi) datum.
void	inverse (CPosePDF &o) const
	Returns a new PDF such as: NEW_PDF = (0,0,0) - THIS_PDF.
void	operator+= (CPose2D Ap)
	Makes: thisPDF = thisPDF + Ap, where "+" is pose composition (both the mean, and the covariance matrix are updated).
double	evaluatePDF (const CPose2D &x, bool sumOverAllPhis=false) const
	Evaluates the PDF at a given point.
double	evaluateNormalizedPDF (const CPose2D &x) const
	Evaluates the ratio PDF(x) / max_PDF(x*), that is, the normalized PDF in the range [0,1].
void	evaluatePDFInArea (const double &x_min, const double &x_max, const double &y_min, const double &y_max, const double &resolutionXY, const double &phi, CMatrixD &outMatrix, bool sumOverAllPhis=false)
	Evaluates the PDF within a rectangular grid (and a fixed orientation) and saves the result in a matrix (each row contains values for a fixed y-coordinate value).
void	bayesianFusion (CPosePDF &p1, CPosePDF &p2, const double &minMahalanobisDistToDrop=0)
	Bayesian fusion of two pose distributions, then save the result in this object (WARNING: Currently p1 must be a mrpt::poses::CPosePDFSOG object and p2 a mrpt::poses::CPosePDFGaussian object).
void	getAs3DObject (mrpt::opengl::CSetOfObjectsPtr &outObj) const
	Returns a 3D object representation of all the ellipses in the SoG.
Public Attributes
std::deque< TGaussianMode >	m_modes
	Access directly to this array for modify the modes as desired.
Protected Member Functions
void	assureSymmetry ()
	Assures the symmetry of the covariance matrix (eventually certain operations in the math-coprocessor lead to non-symmetric matrixes!).