Abstract
This paper elaborates how the time update of the continuous–discrete extended Kalman-filter (EKF) can be computed in the most efficient way. The specific structure of the EKF-moment differential equations leads to a hybrid integration algorithm, featuring a new Taylor–Heun-approximation of the nonlinear vector field and a modified Gauss–Legendre-scheme, generating positive semidefinite solutions for the state error covariance. Furthermore, the order of consistency and stability behavior of the outlined procedure is investigated. The results are incorporated into an algorithm with adaptive controlled step size, assuring a fixed numerical precision with minimal computational effort.
Similar content being viewed by others
References
Arnold VI (2001). Gewöhnliche Differentialgleichungen, 2nd edn. Springer, Heidelberg
Aït-Sahalia Y (2002). Maximum likelihood estimation of discretely sampled diffusions: a closed-form approximation approach. Econometrica 70(1): 223–262
Athans M, Wishner RP and Bertolini AB (1968). Suboptimal state estimation for continuous-time nonlinear systems from discrete noisy measurements. IEEE Trans Auto Control 13(5): 504–514
Curtiss CF and Hirschfelder JO (1952). Integration of stiff equations. Proc Nat Acad Sci USA 38(3): 235–243
Dormand JR and Prince PJ (1980). A family of embedded Runge–Kutta formulae. J Comput Appl Math 6: 19–26
Enright WH, Hull TE and Lindberg B (1975). Comparing numerical methods for stiff systems of ODEs. BIT Numer Math 15(1): 10–48
Gard TC (1988). Introduction to stochastic differential equations. Marcel Dekker, New York
Gottwald BA and Wanner G (1981). A reliable rosenbrock integrator for stiff differential equations. Computing 26(4): 355–360
Hairer E, Nørsett SP and Wanner G (1987). Solving ordinary differential equations I. Nonstiff problems. Springer, Heidelberg
Hairer E and Wanner G (1996). Solving ordinary differential equations II, 2nd edn. Springer, Heidelberg
Ito K and Xiong K (2000). Gaussian filters for nonlinear filtering problems. IEEE Trans Autom Control 45(5): 910–927
Jazwinski AH (1970). Stochastic processes and filtering theory. Academic, New York
Jensen B and Poulsen R (2002). Transition densities of diffusion processes: numerical comparison of approximation techniques. J Derivatives 9(4): 18–32
Johnston LA and Krishnamurthy V (2001). Derivation of a sawtooth iterated extended kalman smoother via the AECM algorithm. IEEE Trans Signal Process 49(9): 1899–1909
Julier S, Uhlmann J (1997) A new extension of the Kalman filter to nonlinear systems. Paper presented at the 11th international symposium on aerospace/defense sensing, simulation and control, Orlando
Julier S and Uhlmann J (2004). Unscented Kalman filtering and nonlinear estimation. Proc IEEE 92(3): 401–422
Julier S, Uhlmann J and Durrant-White HF (2000). A new method for the nonlinear transformation of means and covariances in filters and estimators. IEEE Trans Autom Control 45(3): 477–482
Kalman RE (1960). A new approach to linear filtering and prediction problems. Trans ASME–J Basic Eng 82(Series D): 35–45
Kloeden PE and Platen E (1992). Numerical solution of stochastic differential equations, 3rd edn. Springer, Heidelberg
La Viola JA (2003) Comparison of unscented and extended Kalman filtering for estimating quaternion motion. In: Proccedings of the 2003 American Control Conference. IEEE Press, New York, pp. 2435–2440
Lefebvre T, Bruyninckx H and de Schutter J (2004). Kalman filters for non-linear systems: a comparison of performance. Int J Control 77(7): 639–653
Magnus JR and Neudecker H (1988). Matrix differential calculus with applications in statistics and econometrics. Wiley, New York
Mamon RS (2004). Three ways to solve for bond prices in the Vasicek model. J Appl Math Decis Sci 8(1): 1–14
Mazzoni T (2007). Stetig/diskrete Zustandsraummodelle dynamischer Wirtschaftsprozesse. Shaker, Aachen
Nørgaard M, Poulsen NK and Ravn O (2000). New developments in state estimation for nonlinear systems. Automatica 36: 1627–1638
Rosenbrock HH (1963). Some general implicit processes for the numerical solution of differential equations. Comput J 5(4): 329–330
Schmidt SF (1966). Application of state-space methods to navigation problems. In: Leondes, CT (eds) Advances in Control Systems. Theory and Applications, vol 3, pp 293–340. Academic, New York
Schweppe F (1965). Evaluation of likelihood functions for Gaussian signals. IEEE Trans Inform Theory 11: 61–70
Singer H (2005) Continuous–discrete unscented kalman filtering. Technical Report 384, FernUniversität in Hagen
Singer H (2006) Stochastic differential equation models with sampled data. In: van Montfort K, Oud J, Satorra A (eds) Longitudinal models in the behavioral and related sciences, Chap. 4. Lawrence Erlbaum Associates, London, pp. 73–106
Sitz A, Schwarz U, Kurths J and Voss HU (2002). Estimation of parameters and unobserved components for nonlinear systems from noisy time series. Phys Rev E 66(016210): 1–9
Tanizaki H (1996). Nonlinear filters. Estimation and applications, 2nd edn. Springer, Heidelberg
Vasicek O (1977). An equilibrium characterization of the term structure. J Financ Econ 5: 177–188
Wanner G (1977) On the integration of stiff differential equations. In: Descloux, J (ed) Proceedings of the colloquium on numerical analysis, Lausanne 1976. International series of numerical mathematics, vol 37. BirkhSuser, Basel, pp. 209–226
Wanner G (2003). Dahlquist’s classical papers on stability theory. BIT Numer Math 43(1): 1–18
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mazzoni, T. Computational aspects of continuous–discrete extended Kalman-filtering. Comput Stat 23, 519–539 (2008). https://doi.org/10.1007/s00180-007-0094-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00180-007-0094-4