Self-convergence of weighted least-squares with applications to stochastic adaptive control

A recursive least-squares algorithm with slowly decreasing weights for linear stochastic systems is found to have self-convergence property, i.e., it converges to a certain random vector almost surely irrespective of the control law design. Such algorithms enjoy almost the same nice asymptotic properties as the standard least-squares. This universal convergence result combined with a method of random regularization then easily can be applied to construct a self-convergent and uniformly controllable estimated model and thus may enable us to form a general framework for adaptive control of possibly nonminimum phase autoregressive-moving average with exogenous input (ARMAX) systems. As an application, we give a simple solution to the well-known stochastic adaptive pole-placement and linear-quadratic-Gaussian (LQG) control problems in the paper.

[1]  Jan Sternby,et al.  On consistency for the method of least squares using martingale theory , 1977 .

[2]  B. Anderson,et al.  Detectability and Stabilizability of Time-Varying Discrete-Time Linear Systems , 1981 .

[3]  T. Lai,et al.  Least Squares Estimates in Stochastic Regression Models with Applications to Identification and Control of Dynamic Systems , 1982 .

[4]  John B. Moore,et al.  Convergence of adaptive minimum variance algorithms via weighting coefficient selection , 1982 .

[5]  G. Pólya,et al.  Problems and theorems in analysis , 1983 .

[6]  Graham C. Goodwin,et al.  Adaptive filtering prediction and control , 1984 .

[7]  Sean P. Meyn,et al.  The zero divisor problem of multivariable stochastic adaptive control , 1985 .

[8]  Han-Fu Chen,et al.  Convergence rate of least-squares identification and adaptive control for stochastic systems† , 1986 .

[9]  P. Caines.  Linear Stochastic Systems , 1988 .

[10]  D. Mayne,et al.  Design issues in adaptive control , 1988 .

[11]  Convergence of adaptive control schemes using least-squares estimates , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

[12]  P. Kumar,et al.  Convergence of adaptive control schemes using least-squares parameter estimates , 1990 .

[13]  Han-Fu Chen,et al.  The AAstrom-Wittenmark self-tuning regulator revisited and ELS-based adaptive trackers , 1991 .

[14]  Rogelio Lozano.  Singularity-free adaptive pole-placement without resorting to persistency of excitation : Detailed analysis for first order systems , 1992, Autom..

[15]  Sean P. Meyn,et al.  Model reference adaptive control of time varying and stochastic systems , 1993, IEEE Trans. Autom. Control..

[16]  P. Priouret,et al.  Performance analysis of the forgetting factor RLS algorithm , 1993 .

[17]  Lei Guo.  Further Results on Least Squares Based Adaptive Minimum Variance Control , 1994 .

[18]  Wei Ren,et al.  Stochastic adaptive prediction and model reference control , 1994, IEEE Trans. Autom. Control..

[19]  R. Lozano,et al.  Adaptive pole placement without excitation probing signals , 1994, IEEE Trans. Autom. Control..

[20]  Wei Ren,et al.  On the convergence of least squares estimates in white noise , 1994, IEEE Trans. Autom. Control..

[21]  Bernard Bercu.  Weighted Estimation and Tracking for ARMAX Models , 1995 .

[22]  Lei Guo,et al.  Convergence and logarithm laws of self-tuning regulators , 1995, Autom..