org.hipparchus.filtering.kalman.unscented

Class UnscentedKalmanFilter<T extends Measurement>

java.lang.Object

org.hipparchus.filtering.kalman.unscented.UnscentedKalmanFilter<T>

Type Parameters:

T - the type of the measurements

All Implemented Interfaces:

KalmanFilter<T>

public class UnscentedKalmanFilter<T extends Measurement>
extends Object
implements KalmanFilter<T>

Unscented Kalman filter for unscented process.

Since:

2.2

See Also:

"Wan, E. A., & Van Der Merwe, R. (2000, October). The unscented Kalman filter for nonlinear estimation. In Proceedings of the IEEE 2000 Adaptive Systems for Signal Processing, Communications, and Control Symposium (Cat. No. 00EX373) (pp. 153-158)"

Constructor Summary

Constructors

Constructor and Description
UnscentedKalmanFilter(MatrixDecomposer decomposer, UnscentedProcess<T> process, ProcessEstimate initialState, UnscentedTransformProvider utProvider) Simple constructor.

Method Summary

Modifier and Type	Method and Description
ProcessEstimate	estimationStep(T measurement) Perform one estimation step.
ProcessEstimate	getCorrected() Get the corrected state.
ProcessEstimate	getPredicted() Get the predicted state.
UnscentedTransformProvider	getUnscentedTransformProvider() Get the unscented transform provider.
ProcessEstimate	predictionAndCorrectionSteps(T measurement, RealVector[] sigmaPoints) This method perform the prediction and correction steps of the Unscented Kalman Filter.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

UnscentedKalmanFilter

public UnscentedKalmanFilter(MatrixDecomposer decomposer,
                             UnscentedProcess<T> process,
                             ProcessEstimate initialState,
                             UnscentedTransformProvider utProvider)

Simple constructor.

Parameters:

decomposer - decomposer to use for the correction phase

process - unscented process to estimate

initialState - initial state

utProvider - unscented transform provider

Method Detail

estimationStep

public ProcessEstimate estimationStep(T measurement)
                               throws MathRuntimeException

Perform one estimation step.

Specified by:

estimationStep in interface KalmanFilter<T extends Measurement>

Parameters:

measurement - single measurement to handle

Returns:

estimated state after measurement has been considered

Throws:

MathRuntimeException - if estimation fails

predictionAndCorrectionSteps

public ProcessEstimate predictionAndCorrectionSteps(T measurement,
                                                    RealVector[] sigmaPoints)
                                             throws MathRuntimeException

This method perform the prediction and correction steps of the Unscented Kalman Filter.

Parameters:

measurement - single measurement to handle

sigmaPoints - computed sigma points

Returns:

estimated state after measurement has been considered

Throws:

MathRuntimeException - if matrix cannot be decomposed

getPredicted

public ProcessEstimate getPredicted()

Get the predicted state.

Specified by:

getPredicted in interface KalmanFilter<T extends Measurement>

Returns:

predicted state

getCorrected

public ProcessEstimate getCorrected()

Get the corrected state.

Specified by:

getCorrected in interface KalmanFilter<T extends Measurement>

Returns:

corrected state

getUnscentedTransformProvider

public UnscentedTransformProvider getUnscentedTransformProvider()

Get the unscented transform provider.

Returns:

unscented transform provider