Sufficient Conditions for Parameter Convergence Over Embedded Manifolds Using Kernel Techniques

The persistence of excitation (PE) condition is sufficient to ensure parameter convergence in adaptive estimation problems. Recent results on adaptive estimation in reproducing kernel Hilbert spaces (RKHS) introduce PE conditions for RKHS. This paper presents sufficient conditions for PE for the particular class of uniformly embedded reproducing kernel Hilbert spaces (RKHS) defined over smooth Riemannian manifolds. This paper also studies the implications of the sufficient condition in the case when the RKHS is finite or infinite-dimensional. When the RKHS is finite-dimensional, the sufficient condition implies parameter convergence as in the conventional analysis. On the other hand, when the RKHS is infinite-dimensional, the same condition implies that the function estimate error is ultimately bounded by a constant that depends on the approximation error in the infinite-dimensional RKHS. We illustrate the effectiveness of the sufficient condition in a practical example.

[1]  Jia Guo,et al.  Persistence of Excitation in Uniformly Embedded Reproducing Kernel Hilbert (RKH) Spaces , 2020, 2020 American Control Conference (ACC).

[2]  Stephen P. Boyd,et al.  On parameter convergence in adaptive control , 1983 .

[3]  Michael A. Demetriou,et al.  On the persistence of excitation in the adaptive estimation of distributed parameter systems , 1994, IEEE Trans. Autom. Control..

[4]  A. Berlinet,et al.  Reproducing kernel Hilbert spaces in probability and statistics , 2004 .

[5]  John B. Ferris,et al.  Adaptive estimation for nonlinear systems using reproducing kernel Hilbert spaces , 2017, Advances in Computational Mathematics.

[6]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .

[7]  Girish Chowdhary,et al.  Exponential parameter and tracking error convergence guarantees for adaptive controllers without persistency of excitation , 2014, Int. J. Control.

[8]  Michael A. Demetriou,et al.  Adaptive identification of second-order distributed parameter systems , 1994 .

[9]  Michael A. Demetriou,et al.  Model reference adaptive control of structurally perturbed second‐order distributed parameter systems , 2006 .

[10]  Bassam Bamieh,et al.  Identification of linear parameter varying models , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).

[11]  E. Panteley,et al.  On global uniform asymptotic stability of nonlinear time-varying systems in cascade , 1998 .

[12]  齋藤 三郎,et al.  Theory of reproducing kernels and its applications , 1988 .

[13]  Robert M. Sanner,et al.  Stable Recursive Identification Using Radial Basis Function Networks , 1992, 1992 American Control Conference.

[14]  F. J. Narcowich,et al.  Persistency of excitation, identification, and radial basis functions , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[15]  Andrew R. Teel,et al.  Persistency of excitation for uniform convergence in nonlinear control systems , 2008 .

[16]  Kyriakos G. Vamvoudakis,et al.  Asymptotically Stable Adaptive–Optimal Control Algorithm With Saturating Actuators and Relaxed Persistence of Excitation , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[17]  Stephen P. Boyd,et al.  Necessary and sufficient conditions for parameter convergence in adaptive control , 1986, Autom..

[18]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[19]  T. Basar,et al.  Robust nonlinear system identification using neural network models , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[20]  Alexey A. Bobtsov,et al.  On Robust Parameter Estimation in Finite-Time Without Persistence of Excitation , 2020, IEEE Transactions on Automatic Control.

[21]  Jia Guo,et al.  Approximations of the Reproducing Kernel Hilbert Space (RKHS) Embedding Method over Manifolds , 2020, 2020 59th IEEE Conference on Decision and Control (CDC).

[22]  Cong Wang,et al.  Persistency of excitation and performance of deterministic learning , 2011, Proceedings of the 30th Chinese Control Conference.

[23]  K. Narendra,et al.  On the uniform asymptotic stability of certain linear nonautonomous differential equations , 1976 .

[24]  B. Anderson.  Exponential stability of linear equations arising in adaptive identification , 1977 .

[25]  Elena Panteley,et al.  Uniform exponential stability for families of linear time-varying systems , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[26]  Anuradha M. Annaswamy,et al.  Robust Adaptive Control , 1984, 1984 American Control Conference.

[27]  Michael A. Demetriou,et al.  Model Reference Adaptive Control of Distributed Parameter Systems , 1998 .

[28]  Michael A. Demetriou,et al.  On-Line Parameter Estimation for Infinite-Dimensional Dynamical Systems , 1997 .

[29]  Andrew J. Kurdila,et al.  Persistence of Excitation in Reproducing Kernel Hilbert Spaces, Positive Limit Sets, and Smooth Manifolds , 2019, ArXiv.

[30]  Cong Wang,et al.  Learning from neural control , 2006, IEEE Transactions on Neural Networks.

[31]  Saburou Saitoh,et al.  Theory of Reproducing Kernels and Its Applications , 1988 .

[32]  Carlo Novara,et al.  Parametric identification of structured nonlinear systems , 2011, Autom..

[33]  Martin Buss,et al.  Recursive estimation in piecewise affine systems using parameter identifiers and concurrent learning , 2019, Int. J. Control.

[34]  Jay A. Farrell.  Persistence of excitation conditions in passive learning control , 1997, Autom..

[35]  F. J. Narcowich,et al.  Persistency of Excitation in Identification Using Radial Basis Function Approximants , 1995 .

[36]  I. G. Rosen,et al.  On the Persistence of Excitation in the Adaptive Estimation of Distributed Parameter Systems , 1993, 1993 American Control Conference.

[37]  Andrew R. Teel,et al.  Uniform parametric convergence in the adaptive control of manipulators: a case restudied , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[38]  E. Bai,et al.  Persistency of excitation, sufficient richness and parameter convergence in discrete time adaptive control☆ , 1985 .

[39]  Yongduan Song,et al.  Adaptive Control With Exponential Regulation in the Absence of Persistent Excitation , 2017, IEEE Transactions on Automatic Control.

[40]  Cong Wang,et al.  Deterministic Learning of Nonlinear Dynamical Systems , 2009, Int. J. Bifurc. Chaos.

[41]  Martin Guay,et al.  Finite-time Parameter Estimation in Adaptive Control of Nonlinear Systems , 2008, 2007 American Control Conference.

[42]  K. Narendra,et al.  On the Stability of Nonautonomous Differential Equations $\dot x = [A + B(t)]x$, with Skew Symmetric Matrix $B(t)$ , 1977 .

[43]  Dimitry M. Gorinevsky,et al.  On the persistency of excitation in radial basis function network identification of nonlinear systems , 1995, IEEE Trans. Neural Networks.

[44]  Antonio Loría,et al.  Relaxed persistency of excitation for uniform asymptotic stability , 2001, IEEE Trans. Autom. Control..

[45]  Andrew Kurdila,et al.  Reproducing kernel Hilbert space embedding for adaptive estimation of nonlinearities in piezoelectric systems , 2020, Nonlinear Dynamics.

[46]  S. Sastry,et al.  Adaptive Control: Stability, Convergence and Robustness , 1989 .

[47]  Sergey Nikitin.  Generalized Persistency of Excitation , 2007, Int. J. Math. Math. Sci..