TwoFilterSmoother Class Template Reference

Inheritance diagram for TwoFilterSmoother:

[legend]

List of all members.

Detailed Description

template<class T = unsigned int, class P = indii::ml::aux::GaussianPdf>
class indii::ml::filter::TwoFilterSmoother< T, P >

Abstract smoother for estimating the state of a system by fusing forward and backward filtering passes.

Author:: Lawrence Murray <lawrence@indii.org>

Version:

Rev

Date:

Date

Parameters:

	T	The type of time.
	P	The type of probability distribution used to represent the system state.

See also:: indii::ml::filter for general usage guidelines.

Definition at line 27 of file TwoFilterSmoother.hpp.


Public Member Functions
	TwoFilterSmoother (const T tT, const P &p_xT)
	Constructor.
virtual	~TwoFilterSmoother ()
	Destructor.
P &	getBackwardFilteredState ()
	Get distribution over the state at the current time given present and future measurements.
void	setBackwardFilteredState (const P &p_xtn_ytn)
	Set distribution over the state at the current time given present and future measurements.
virtual void	smooth (const T tn, const aux::vector &ytn, const P &p_xtn_ytn)=0
	Rewind system to time of previous measurement and smooth.
virtual aux::GaussianPdf	backwardMeasure ()=0
	Apply the measurement function to the current filtered state to obtain an estimated measurement.
Protected Attributes
P	p_xtn_ytn_b
	$p(\mathbf{x}_n\,\|\,\mathbf{y}_{n:T})$ ; backward filter density.

Constructor & Destructor Documentation

TwoFilterSmoother	(	const T	tT,
		const P &	p_xT
	)			`[inline]`

Constructor.

Parameters:

	tT	; starting time.
	p_xT	$p(\mathbf{x}_T)$ ; prior over the state at time .

Definition at line 99 of file TwoFilterSmoother.hpp.

~TwoFilterSmoother ( ) [inline, virtual]

Destructor.

Definition at line 105 of file TwoFilterSmoother.hpp.

Member Function Documentation

P & getBackwardFilteredState ( ) [inline]

Get distribution over the state at the current time given present and future measurements.

Returns:: $P\big(\mathbf{x}(t_n)\, | \,\mathbf{y}(t_n),\ldots,\mathbf{y}(t_T)\big)$ ; distribution over the current state given present and future measurements.

Definition at line 110 of file TwoFilterSmoother.hpp.

void setBackwardFilteredState ( const P & p_xtn_ytn ) [inline]

Set distribution over the state at the current time given present and future measurements.

Parameters:

p_xtn_ytn

$P\big(\mathbf{x}(t_n)\, | \,\mathbf{y}(t_n),\ldots,\mathbf{y}(t_T)\big)$ ; distribution over the current state given present and future measurements.

Definition at line 115 of file TwoFilterSmoother.hpp.

virtual void smooth	(	const T	tn,
		const aux::vector &	ytn,
		const P &	p_xtn_ytn
	)			`[pure virtual]`

Rewind system to time of previous measurement and smooth.

Performs the backward filtering step and fuses this with the given prediction from the forward filtering step to produce the smoothed prediction.

Parameters:

	tn	; the time to which to rewind the system. This must be less than the current time $t_{n+1}$ .
	ytn	$\mathbf{y}_n$ ; measurement at time .
	p_xtn_ytn	$p(\mathbf{x}_n\,\|\,\mathbf{y}_{1:n})$ ; forward filter density.