ukf_predict2.m

扩展卡尔曼和无迹卡尔曼的matlab仿真比较。

%UKF_PREDICT2  Augmented (state and process noise) UKF prediction step
%
% Syntax:
%   [M,P] = UKF_PREDICT2(M,P,a,Q,[param,alpha,beta,kappa])
%
% In:
%   M - Nx1 mean state estimate of previous step
%   P - NxN state covariance of previous step
%   a - Dynamic model function as inline function,
%       function handle or name of function in
%       form a([x;w],param)
%   Q - Non-singular covariance of process noise w
%   param - Parameters of a               (optional, default empty)
%   alpha - Transformation parameter      (optional)
%   beta  - Transformation parameter      (optional)
%   kappa - Transformation parameter      (optional)
%   mat   - If 1 uses matrix form         (optional, default 0)
%
% Out:
%   M - Updated state mean
%   P - Updated state covariance
%
% Description:
%   Perform augmented form Unscented Kalman Filter prediction step
%   for model
%
%    x[k+1] = a(x[k],w[k],param)
%
%   Function a should be such that it can be given
%   DxN matrix of N sigma Dx1 points and it returns 
%   the corresponding predictions for each sigma
%   point. 
%
% See also:
%   UKF_PREDICT1, UKF_UPDATE1, UKF_UPDATE2, UKF_PREDICT3, UKF_UPDATE3,
%   UT_TRANSFORM, UT_WEIGHTS, UT_MWEIGHTS, UT_SIGMAS

% Copyright (C) 2003-2006 Simo S鋜kk