Emrys::HybridGaussianHistory< Space_, ModeSpace_, Scalar_, Allocator_ >::Step Class Reference

One recorded prediction and its smoothed hybrid state, built from the history's allocator. More...

#include <EmrysFilter/Smoothers/HybridGaussianHistory.h>

Public Types
using	allocator_type = Allocator_
	the allocator its joints and Gaussians come from
using	GainType = typename GaussianParams<Space_, Scalar_>::MatrixType
	One mode's Rauch-Tung-Striebel gain.
using	GainAllocator = internal::ReBound<Allocator_, GainType>
	The allocator of the gains.

Public Member Functions
	Step (JointType const &recorded, Allocator_ const &allocator={})
	A copy of recorded in storage from allocator, with the filtered state as its smoothed one until smooth() runs.
	Step (Step const &other, Allocator_ const &allocator)
	Copies other into storage from allocator.
	Step (Step &&other, Allocator_ const &allocator)
	Moves other into storage from allocator, taking its storage when the allocators are equal.
	Step (Step const &)=default
	copies the joint and the smoothed state
	Step (Step &&)=default
	moves the joint and the smoothed state
Step &	operator= (Step const &)=default
	Copies into this step's storage.
Step &	operator= (Step &&)=default
	Takes the other step's storage, as the members' do.
void	resetSmoothed ()
	Replaces the smoothed state with the filtered one: the joint's mode probabilities and each mode's filtered Gaussian.
void	computeGains ()
	Computes each mode's gain from its joint (internal::rtsGain()), once per recording.

Public Attributes
JointType	joint
	the prediction as predictJoint() recorded it
SmoothedType	smoothed
	\( p(x_t, r_t \mid z_{1:N}) \) as of the last smooth(); the filtered state until then
internal::Buffer< GainType, Allocator_ >	gains
	Each mode's Rauch-Tung-Striebel gain, made once when the joint is recorded.

Detailed Description

template<Space Space_, DiscreteSpace ModeSpace_, RealScalar Scalar_ = double, typename Allocator_ = DefaultAllocator>
class Emrys::HybridGaussianHistory< Space_, ModeSpace_, Scalar_, Allocator_ >::Step

One recorded prediction and its smoothed hybrid state, built from the history's allocator.

---

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

• EmrysFilter/Smoothers/HybridGaussianHistory.h