Generalized damped least squares algorithm

We propose a new algorithm for adaptive control and self tuning control, referred to as the generalized damped least squares (GDLS) algorithm. This algorithm is constructed by adding a multi-step penalty for parameter variations to the objective function of the normal least squares algorithm to prevent the singularity problem that leads to estimation windup. We show that the proposed method has properties almost equivalent to those of the normal least squares method, which guarantees that the proposed algorithm is suitable for poorly excited situations. Simulation results show that the proposed method gives better estimation performance than previous methods in spite of its simplicity. The proposed method also shows good parameter tracking performance and no estimation windup.