Bias-compensated adaptive observer for a continuous-time model estimation
Kenji Ikeda, Yoshio Mogami, Takao Shimomura
In this paper, a bias-compensating method for a continuous-time model estimation by using adaptive observer is proposed. It is assumed that the observation noise is a white Gaussian signal while there are no process noises. The bias compensated least squares method is extended to the identification in the closed loop environment. It is shown that the proposed estimate is unbiased and consistent.