Dear Yi Cao,
According to the paper'performance evaluation of UKF-based nonlinear filtering',choose:f=@(x)[x(1)+tao*x(2);x(2)-tao*x(1)+tao*(x(1)^2+x(2)^2-1)*x(2)];
h=@(x)x(1),with covariance of the process noise w(k)given as:Q=0.003^2I,the covaiance of the noise v(k) is given by:R=0.001^2I,initial state:x0=[2.3;2.2],P0=I,the true value of the initial state:x=[0.8;0.2]. The paper proof that when given all these,UKF tends to be divergent.However,based on this code,it seems that the estimator is stable.Does it owe to the weights chosen when doing the prediction?
Thank you for your kind comment.
I have not the time to finish part 2 - the real-world implementation example.
However, please visit our site at www.aimagin.com to learn about our hardware and software code generation tools for microcontrollers.
Specifically, this is the tutorial for getting started: http://aimagin.com/blog/waijung-tutorials/.
Thank you very very much, you are the best one who explains and simplifies KALMAN filter in this clear way. Could you please send me the part 2 upon been ready. it will be very helpful also, thanks again.
01 Dec 2011
Generates a random orthogonal (real) square matrix of given size.