Cognitoware.Robotics.dll
Class KalmanSensorModel<Z, X>
Z: The type of x being predicted.
X: The x from which the x is predicted.
System.Object
Cognitoware.Robotics.StateEstimation.KalmanSensorModel<Z, X>
Implemented Interfaces
Summary
A sensor model based on the linear system Z = C*X + error.
Constructor Summary
Method Summary
Creates a new GaussianMoment using GetMean and GetError.
Equals(Object)
Inherited from System.Object
Finalize()
Inherited from System.Object
Creates an covariance matrix that describes the Gaussian error around the sensor mean.
GetHashCode()
Inherited from System.Object
Creates the expected observation from a specific x.
GetType()
Inherited from System.Object
MemberwiseClone()
Inherited from System.Object
ToString()
Inherited from System.Object
Details
A linear sensor model is an implementation of GaussianSensorModel and RandomConditional.
The expected sensor reading is generated by multiplying the matrix C by the sensor x.
The error is the constant covariance matrix q.
P( Z | X ) = A * X + error.
KalmanSensorModel is used in the KalmanFilter algorithm.
Because of the requirement to interact with Matrix, Z and X must both be of type Vector or inherited from Vector.
Constructor Details
public KalmanSensorModel()
Method Details
public final virtual Double ConditionalProbabilityOf(Z observation, X state)
Creates a new GaussianMoment using GetMean and GetError.
Parameters:
observation - The observation for the error.
x - The current x.
Returns:
A new Gaussian distribution.
public final virtual Matrix GetError(Z z)
Creates an covariance matrix that describes the Gaussian error around the sensor mean.
Returns the constant value Q.
Parameters:
z - The observation for the error.
Returns:
A covariance matix that describes the error of the sensor reading.
public final virtual Z GetMean(X x)
Creates the expected observation from a specific x.
Z = C * X.
Parameters:
x - The x at which the observation is made.
Returns:
The expected observation at a x.