easykf-2.04
 All Classes Namespaces Files Functions Variables Enumerations Enumerator Macros Pages
Namespaces | Enumerations
ukf Namespace Reference

In this section we implement the Unscented Kalman Filter for parameter estimation and Joint UKF involving the Scaled Unscented Transform detailed in Van der Merwe PhD Thesis. More...

Namespaces

 math
 
 parameter
 UKF for parameter estimation. The notations follow "Sigma-Point Kalman Filters for Probabilistic Inference in Dynamic State-Space Models",p93, PhD, van Der Merwe.
 
 samples
 
 srstate
 MUST NOT BE USED !!!!!!! Square root UKF for state estimation, additive noise case The notations follow "Sigma-Point Kalman Filters for Probabilistic Inference in Dynamic State-Space Models",p115, PhD, van Der Merwe.
 
 state
 UKF for state estimation, additive noise case The notations follow "Sigma-Point Kalman Filters for Probabilistic Inference in Dynamic State-Space Models",p108, PhD, van Der Merwe.
 

Enumerations

enum  ProcessNoise { UKF_PROCESS_FIXED, UKF_PROCESS_RLS }
 The different types of implemented process noise for UKF state estimation. More...
 

Detailed Description

In this section we implement the Unscented Kalman Filter for parameter estimation and Joint UKF involving the Scaled Unscented Transform detailed in Van der Merwe PhD Thesis.

Enumeration Type Documentation

The different types of implemented process noise for UKF state estimation.

Enumerator
UKF_PROCESS_FIXED 

The covariance of the evolution noise is fixed to $\textbf{P}_{\theta\theta_i} = \alpha . \textbf{I}$.

UKF_PROCESS_RLS 

The covariance of the evolution noise is defined as $\textbf{P}_{\theta\theta_i} = (\alpha^{-1} - 1)\textbf{P}_i$.