jafar::filter::JacobianObserveModel Class Reference

Non linear observation model. More...

---

Detailed Description

Non linear observation model.

To define your own model you must derive this class.

Definition at line 95 of file observeModel.hpp.

#include <observeModel.hpp>

Inheritance diagram for jafar::filter::JacobianObserveModel:

List of all members.

Public Member Functions
	JacobianObserveModel (std::size_t sizeObs_, std::size_t sizeState_)
virtual jblas::vec const &	predictObservation (jblas::vec const &x_)=0
	Predict observation for state x_.
virtual jblas::vec const &	computeInnovation (jblas::vec const &z_, jblas::vec const &zPred_)
	By default, simply do the substraction.
virtual void	predictObservationJac (const jblas::vec &x_)=0
	call this method to compute the jacobian of the observation function
Public Attributes
jblas::mat	Jobs
	Jacobian of the observe function.

---

Member Function Documentation

virtual jblas::vec const& jafar::filter::JacobianObserveModel::predictObservation

(

jblas::vec const &

x_

)

[pure virtual]

Predict observation for state x_.

In order to minimize memory allocation, z vector is allocated once, predictObservation() implementation should look like:

   const vec& predictObservation(const vec& x_) {
     JFR_PRECOND(x_.size() == _sizeState, message);
     // compute z function of x_
     return z;
   }

Implemented in jafar::fusion::ObservationModelFusion.

---

Member Data Documentation

jblas::mat jafar::filter::JacobianObserveModel::Jobs

Jacobian of the observe function.

Warning:

do not forget to call predictObservationJac() before using Jobs

Definition at line 104 of file observeModel.hpp.

---

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

• modules/filter/include/filter/observeModel.hpp