gtsam 4.1.1 gtsam
gtsam::Marginals Class Reference

## Detailed Description

A class for computing Gaussian marginals of variables in a NonlinearFactorGraph.

## Public Member Functions

Marginals ()
Default constructor only for wrappers.

Marginals (const NonlinearFactorGraph &graph, const Values &solution, Factorization factorization=CHOLESKY)
Construct a marginals class from a nonlinear factor graph. More...

Marginals (const NonlinearFactorGraph &graph, const Values &solution, const Ordering &ordering, Factorization factorization=CHOLESKY)
Construct a marginals class from a nonlinear factor graph. More...

Marginals (const GaussianFactorGraph &graph, const Values &solution, Factorization factorization=CHOLESKY)
Construct a marginals class from a linear factor graph. More...

Marginals (const GaussianFactorGraph &graph, const Values &solution, const Ordering &ordering, Factorization factorization=CHOLESKY)
Construct a marginals class from a linear factor graph. More...

Marginals (const GaussianFactorGraph &graph, const VectorValues &solution, Factorization factorization=CHOLESKY)
Construct a marginals class from a linear factor graph. More...

Marginals (const GaussianFactorGraph &graph, const VectorValues &solution, const Ordering &ordering, Factorization factorization=CHOLESKY)
Construct a marginals class from a linear factor graph. More...

void print (const std::string &str="Marginals: ", const KeyFormatter &keyFormatter=DefaultKeyFormatter) const
print

GaussianFactor::shared_ptr marginalFactor (Key variable) const
Compute the marginal factor of a single variable.

Matrix marginalInformation (Key variable) const
Compute the marginal information matrix of a single variable. More...

Matrix marginalCovariance (Key variable) const
Compute the marginal covariance of a single variable.

JointMarginal jointMarginalCovariance (const KeyVector &variables) const
Compute the joint marginal covariance of several variables.

JointMarginal jointMarginalInformation (const KeyVector &variables) const
Compute the joint marginal information of several variables.

VectorValues optimize () const
Optimize the bayes tree.

## Public Types

enum  Factorization { CHOLESKY , QR }
The linear factorization mode - either CHOLESKY (faster and suitable for most problems) or QR (slower but more numerically stable for poorly-conditioned problems).

## Protected Member Functions

void computeBayesTree ()
Compute the Bayes Tree as a helper function to the constructor.

void computeBayesTree (const Ordering &ordering)
Compute the Bayes Tree as a helper function to the constructor.

## Protected Attributes

GaussianFactorGraph graph_

Values values_

Factorization factorization_

GaussianBayesTree bayesTree_

## ◆ Marginals() [1/6]

 gtsam::Marginals::Marginals ( const NonlinearFactorGraph & graph, const Values & solution, Factorization factorization = CHOLESKY )

Construct a marginals class from a nonlinear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The linearization point about which to compute Gaussian marginals (usually the MLE as obtained from a NonlinearOptimizer). factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems).

## ◆ Marginals() [2/6]

 gtsam::Marginals::Marginals ( const NonlinearFactorGraph & graph, const Values & solution, const Ordering & ordering, Factorization factorization = CHOLESKY )

Construct a marginals class from a nonlinear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The linearization point about which to compute Gaussian marginals (usually the MLE as obtained from a NonlinearOptimizer). factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems). ordering The ordering for elimination.

## ◆ Marginals() [3/6]

 gtsam::Marginals::Marginals ( const GaussianFactorGraph & graph, const Values & solution, Factorization factorization = CHOLESKY )

Construct a marginals class from a linear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The solution point to compute Gaussian marginals. factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems).

## ◆ Marginals() [4/6]

 gtsam::Marginals::Marginals ( const GaussianFactorGraph & graph, const Values & solution, const Ordering & ordering, Factorization factorization = CHOLESKY )

Construct a marginals class from a linear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The solution point to compute Gaussian marginals. factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems). ordering The ordering for elimination.

## ◆ Marginals() [5/6]

 gtsam::Marginals::Marginals ( const GaussianFactorGraph & graph, const VectorValues & solution, Factorization factorization = CHOLESKY )

Construct a marginals class from a linear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The solution point to compute Gaussian marginals. factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems). ordering An optional variable ordering for elimination.

## ◆ Marginals() [6/6]

 gtsam::Marginals::Marginals ( const GaussianFactorGraph & graph, const VectorValues & solution, const Ordering & ordering, Factorization factorization = CHOLESKY )

Construct a marginals class from a linear factor graph.

Parameters
 graph The factor graph defining the full joint density on all variables. solution The solution point to compute Gaussian marginals. factorization The linear decomposition mode - either Marginals::CHOLESKY (faster and suitable for most problems) or Marginals::QR (slower but more numerically stable for poorly-conditioned problems). ordering An optional variable ordering for elimination.

## ◆ marginalInformation()

 Matrix gtsam::Marginals::marginalInformation ( Key variable ) const

Compute the marginal information matrix of a single variable.

Use LLt(const Matrix&) or RtR(const Matrix&) to obtain the square-root information matrix.

The documentation for this class was generated from the following files: