Abstract
We study modern implementations of the discrete Kalman filter, namely array square-root algorithms. An important feature of such algorithms is the use of orthogonal and J-orthogonal transformations on each filtering step. For the first time, we develop for this class of algorithms a simple universal approach that lets us generalize any numerically stable implementation of this type to the case of updates in sensitivity equations of the filter with respect to unknown system model parameters. An advantage of the resulting adaptive schemes is their numerical stability with respect to machine rounding errors. Estimation of the noisy state vector of the system and identification of unknown system parameters occur simultaneously. The proposed approach can be used for parameter identification problems, adaptive control problems, experiment planning, and others.
Similar content being viewed by others
References
Khazen, E.M., Metody optimal’nykh statisticheskikh reshenii i zadachi optimal’nogo upravleniya (Methods of Optimal Statistical Decisions, Optimal Control, and Stochastic Differential Equations), Moscow: Sovetskoe Radio, 1968.
Ogarkov, M.A., Metody statisticheskogo otsenivaniya parametrov sluchainykh protsessov (Statistic Estimation Methods for Parameters of Random Processes), Moscow: Energoatomizdat, 1990.
Ljung, L., System Identification: Theory for the User, Englewood Cliffs: Prentice Hall, 1987. Translated under the title Identifikatsiya sistem. Teoriya dlya pol’zovatelya, Moscow: Nauka, 1991.
Aström, K.J., Maximum Likelihood and Prediction Error Methods, Automatica, 1980, vol. 16, pp. 551–574.
Gupta, N.K. and Mehra, R.K., Computational Aspects of Maximum Likelihood Estimation and Reduction in Sensitivity Function Calculations, IEEE Trans. Automat. Control, 1974, vol. AC-19, no. 6, pp. 774–783.
Mehra, R.K., Optimal Input Signals for Parameter Estimation in Dynamic Systems—Survey and New Results, IEEE Trans. Automat. Control, 1974, vol. AC-19, no. 6, pp. 753–768.
Denisov, V.I., Chubich, V.M., and Chernikova, O.S., Active Parametric Identification of Stochastic Linear Discrete Systems in the Time Domain, Sib. J. Ind. Math., 2003, vol. 6, no. 3, pp. 70–87.
Verhaegen, M. and Van Dooren, P., Numerical Aspects of Different Kalman Filter Implementations, IEEE Trans. Automat. Control, 1986, vol. AC-31, no. 10, pp. 907–917.
Dyer, P. and McReynolds, S., Extension of Square-Root Filtering to Include Process Noise, J. Optim. Theory Appl., 1969, no. 3, pp. 444–459.
Kaminski, P.G., Bryson, A.E., and Schmidt, S.F., Discrete Square-Root Filtering: A Survey of Current Techniques, IEEE Trans. Automat. Control, 1971, vol. AC-16, no. 6, pp. 727–735.
Bierman, G.J., Factorization Methods for Discrete Sequential Estimation, New York: Academic, 1977.
Park, P. and Kailath, T., New Square-Root Algorithms for Kalman Filtering, IEEE Trans. Automat. Control, 1995, vol. 40, no. 5, pp. 895–899.
Kailath, T., Sayed, A.H., and Hassibi, B., Linear Estimation, New Jersey: Prentice Hall, 2000.
Kailath, T., Some New Algorithms for Recursive Estimation in Constant Linear Systems, IEEE Trans. Inform. Theory, 1973, vol. IT-19, no. 11, pp. 750–760.
Morf, M., Sidhu, G.S., and Kailath, T., Some New Algorithms for Recursive Estimation in Constant, Linear Discrete-Time Systems, IEEE Trans. Automat. Control, 1974, vol. AC-19, no. 4, pp. 315–323.
Morf, M. and Kailath, T., Square-Root Algorithms for Least-Squares Estimation, IEEE Trans. Automat. Control, 1975, vol. AC-20, no. 4, pp. 487–497.
Sayed, A.H. and Kailath, T., Extended Chandrasekhar Recursions, IEEE Trans. Automat. Control, 1994, vol. 39, no. 3, pp. 619–622.
Gibbs, R.G., Square Root Modified Bryson-Frazier Smoother, IEEE Trans. Automat. Control, 2011, vol. 56, no. 2, pp. 425–456.
Hassibi, B. and Sayed, A.H., Array Algorithms for H ∞ Estimation, IEEE Trans. Automat. Control, 2000, vol. 45, no. 4, pp. 702–706.
Bierman, G.J., Belzer, M.R., Vandergraft, J.S., and Porter, D.W., Maximum Likelihood Estimation Using Square Root Information Filters, IEEE Trans. Automat. Control, 1990, vol. 35, no. 12, pp. 1293–1299.
Kulikova, M.V., Likelihood Gradient Evaluation Using Square-Root Covariance Filters, IEEE Trans. Automat. Control, 2009, vol. 54, no. 3, pp. 646–651.
Kulikova, M.V., Maximum Likelihood Estimation of Linear Stochastic Systems in the Class of Sequential Square-Root Orthogonal Filtering Methods, Autom. Remote Control, 2011, vol. 72, no. 4, pp. 766–786.
Tsyganova, Yu.V., Computing the Gradient of the Auxiliary Quality Functional in the Parametric Identification Problem for Stochastic Systems, Autom. Remote Control, 2011, vol. 72, no. 9, pp. 1925–1940.
Tsyganova, Yu.V. and Kulikova, M.V., On Efficient Parametric Identification Methods for Linear Discrete Stochastic Systems, Autom. Remote Control, 2012, vol. 73, no. 6, pp. 962–975.
Grewal, M.S. and Andrews, A.P., Kalman Filtering: Theory and Practice, New Jersey: Prentice Hall, 2001.
Higham, N.J., Accuracy and Stability of Numerical Algorithms, Philadelphia: SIAM, 2002, 2nd ed.
Higham, N.J., J-Orthogonal Matrices: Properties and Generalization, SIAM Rev., 2003, vol. 45, no. 3, pp. 504–519.
Gantmaher, F.R., Teoriya matrits (Theory of Matrices), Moscow: Nauka, 1988, 4th ed.
Kulikova, M.V. and Pacheco, A., Kalman Filter Sensitivity Evaluation with Orthogonal and J-Orthogonal Transformations, IEEE Trans. Automat. Control, 2013, vol. 58, no. 7. pp. 1798–1804.
Särkkä, S. and Nummenmaa, A., Recursive Noise Adaptive Kalman Filtering by Variational Bayesian Approximation, IEEE Trans. Automat. Control, 2009, vol. 54, no. 3, pp. 596–600.
Tsyganova, J.V. and Kulikova, M.V., State Sensitivity Evaluation within UD Based Array Covariance Filter, IEEE Trans. Automat. Control, 2013, vol. 58, no. 11, pp. 2944–2950, DOI: 10.1109/TAC.2013.2259093.
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © M.V. Kulikova, Yu.V. Tsyganova, 2014, published in Avtomatika i Telemekhanika, 2014, No. 8, pp. 59–81.
Rights and permissions
About this article
Cite this article
Kulikova, M.V., Tsyganova, Y.V. A general approach to constructing parameter identification algorithms in the class of square root filters with orthogonal and J-orthogonal tranformations. Autom Remote Control 75, 1402–1419 (2014). https://doi.org/10.1134/S0005117914080050
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0005117914080050