Package org.hipparchus.filtering.kalman.unscented

Interface UnscentedProcess<T extends Measurement>

Type Parameters:

T - the type of the measurements

public interface UnscentedProcess<T extends Measurement>

Unscented process that can be estimated by a UnscentedKalmanFilter.

This interface must be implemented by users to represent the behavior of the process to be estimated

Since:

2.2

See Also:

• UnscentedKalmanFilter
• UnscentedProcess

Method Summary

Modifier and Type	Method	Description
UnscentedEvolution	getEvolution(double previousTime, RealVector[] sigmaPoints, T measurement)	Get the state evolution between two times.
RealVector	getInnovation(T measurement, RealVector predictedMeasurement, RealVector predictedState, RealMatrix innovationCovarianceMatrix)	Get the innovation brought by a measurement.
RealVector[]	getPredictedMeasurements(RealVector[] predictedSigmaPoints, T measurement)	Get the state evolution between two times.
RealMatrix	getProcessNoiseMatrix(double previousTime, RealVector predictedState, T measurement)	Get the process noise covariance corresponding to the state evolution between two times.

Method Details

getEvolution

UnscentedEvolution getEvolution(double previousTime,
 RealVector[] sigmaPoints,
 T measurement)

Get the state evolution between two times.

Parameters:

previousTime - time of the previous state

sigmaPoints - sigma points

measurement - measurement to process

Returns:

states evolution

getProcessNoiseMatrix

RealMatrix getProcessNoiseMatrix(double previousTime,
 RealVector predictedState,
 T measurement)

Get the process noise covariance corresponding to the state evolution between two times.

Parameters:

previousTime - time of the previous state

predictedState - predicted state

measurement - measurement to process

Returns:

states evolution

getPredictedMeasurements

RealVector[] getPredictedMeasurements(RealVector[] predictedSigmaPoints,
 T measurement)

Get the state evolution between two times.

Parameters:

predictedSigmaPoints - predicted state sigma points

measurement - measurement to process

Returns:

predicted measurement sigma points

getInnovation

RealVector getInnovation(T measurement,
 RealVector predictedMeasurement,
 RealVector predictedState,
 RealMatrix innovationCovarianceMatrix)

Get the innovation brought by a measurement.

Parameters:

measurement - measurement to process

predictedMeasurement - predicted measurement

predictedState - predicted state

innovationCovarianceMatrix - innovation covariance matrix

Returns:

innovation brought by a measurement, may be null if measurement should be rejected