A novel real-time adaptive suboptimal recursive state estimation scheme for nonlinear discrete dynamic systems with non-Gaussian noise

https://doi.org/10.1016/j.dsp.2012.02.009Get rights and content

Abstract

A real-time state filtering and prediction scheme which is adaptive, recursive, and suboptimal is proposed for discrete time nonlinear dynamic systems with either Gaussian or non-Gaussian noise. The proposed scheme (PR) estimates states adaptively whenever both the observation is available and there exists a non-zero and finite number of real state roots of the observation model, otherwise the PR estimates states non-adaptively. The PR state transition and observation functions are as general as the state transition and observation functions for particle filters. The PR is based upon discrete noise approximation, state quantization, and a suboptimal implementation of multiple hypothesis testing. The PR first detects state estimate divergence points along the time axis, and then state estimate divergences are prevented by introducing new admissible state quantization levels; whereas the extended Kalman filter (EKF), sampling importance resampling (SIR) particle filter (bootstrap filter), and auxiliary sampling importance resampling (ASIR) particle filter produce diverging state estimates from actual state values for many dynamic models. The PR uses state transition functions in order to calculate transition probabilities from gates to gates. If these transition probabilities are somehow available, then state transition functions are not needed for state estimation with the PR; whereas state transition functions are necessary for state estimation with both particle filters and the EKF. The PR is very suitable for state estimation with either constraints imposed on state estimates or missing observations. The PR is more general than grid-based estimation approaches. Monte Carlo simulations have shown the effectiveness of the PR, that is, the PR performance is better than the performances of the EKF, SIR, and ASIR particle filters for many nonlinear models with white Gaussian noise, four examples of which are presented in the paper.

Section snippets

Kerim Demirbaş received the B.S. and M.S. degrees in electrical engineering from Istanbul Technical University (ITU), Turkey, in 1973; and the M.S., Engineer, and Ph.D. degrees, all in electrical engineering, from the University of California at Los Angeles (UCLA), USA, in 1977, 1979, and 1981 respectively. He was a senior research scientist at the Honeywell Systems and Research Center, Minneapolis, USA (1981–1984) and a faculty member of Electrical Engineering and Computer Science, the

References (28)

  • K. Demirbaş

    Information theoretic smoothing algorithms for dynamic systems with or without interference

  • H.W. Sorenson et al.

    Recursive Bayesian estimation using Gaussian sums

    Automatica

    (1971)
  • D.L. Alspach et al.

    Nonlinear Bayesian estimation using Gaussian sum approximations

    IEEE Trans. Automat. Control

    (1972)
  • M.S. Arulampalam et al.

    A tutorial on particle filters for online nonlinear/non-Gaussian bayesian tracking

    IEEE Trans. Signal Process.

    (2002)
  • V.E. Benes

    Exact finite-dimensional filters with certain diffusion nonlinear drift

    Stochastics

    (1981)
  • F.E. Daum

    Exact finite-dimensional nonlinear filters

    IEEE Trans. Automat. Control

    (1986)
  • F.E. Daum

    Beyond Kalman filters: Practical design of nonlinear filters

    Proc. SPIE

    (1995)
  • K. Demirbaş, New smoothing algorithms for dynamic systems with or without interference, in: The NATO AGARDograph...
  • K. Demirbaş

    Maneuvering target tracking with hypothesis testing

    IEEE Trans. Aerospace Electron. Syst.

    (1988)
  • K. Demirbaş

    Nonlinear state smoothing and filtering in blocks for dynamic systems with missing observation

    Internat. J. Systems Sci.

    (1990)
  • K. Demirbaş

    A state prediction scheme for discrete time nonlinear dynamic systems

    Int. J. Gen. Syst.

    (2007)
  • K. Demirbaş

    A new real-time suboptimum filtering and prediction scheme for general nonlinear discrete dynamic systems with Gaussian or non-Gaussian noise

    Internat. J. Systems Sci.

    (2011)
  • K. Demirbaş

    Real-time recursive state estimation for nonlinear discrete dynamic systems with Gaussian or non-Gaussian noise

  • K. Demirbaş et al.

    Optimum decoding based smoothing algorithm for dynamic systems

    Internat. J. Systems Sci.

    (1985)
  • Cited by (8)

    • Robust adaptive unscented Kalman filter for bearings-only tracking in three dimensional case

      2019, Applied Ocean Research
      Citation Excerpt :

      Furthermore, different recursive algorithms, such as Extended Kalman Filter (EKF), were applied to the 3DBOT problem [7]. High sensitivity to initial conditions and measurement errors, particularly in the problem with poor observability, are the main shortcomings of this technique [8]. To enhance the performance of EKF, Unscented KF (UKF) was developed.

    • Online state estimation for discrete nonlinear dynamic systems with nonlinear noise and interference

      2015, Journal of the Franklin Institute
      Citation Excerpt :

      In this paper, an online recursive nonlinear state filtering and prediction scheme is proposed for nonlinear dynamic systems with nonlinear noise and interference representing a random signal such jamming or clutter. The proposed estimation scheme (PR) is an online estimation scheme which also prevents some state estimate divergences caused by the estimation approaches presented in [5–7] for nonlinear dynamic systems with nonlinear noise and interference, whereas the estimation schemes in [9,10] were developed for nonlinear discrete dynamic models without interference. The PR is based upon first approximating the disturbance noise, initial state, and interference with a discrete random disturbance noise, discrete initial state, and discrete interference; then quantizing the state, that is, representing the state model with a time varying state machine; and then an online suboptimal implementation of multiple composite hypothesis testing.

    • Chebyshev polynomial Kalman filter

      2013, Digital Signal Processing: A Review Journal
      Citation Excerpt :

      This however comes with the expense of an applicability to low-dimensional problems only as the computational complexity growth exponentially with the dimension of the state space. To attenuate this computational burden, sophisticated techniques like adaptive discretization [12] or Rao–Blackwellization [13] have to be applied. In order to avoid the sample depletion problem of particle filters, the so-called Gaussian particle filter [14] has been proposed, which links sampling-based estimation with Gaussian filtering.

    • Oba Filter for Online-Adaptive Nonlinear State Estimation with Interference

      2019, IEEE Transactions on Aerospace and Electronic Systems
    View all citing articles on Scopus

    Kerim Demirbaş received the B.S. and M.S. degrees in electrical engineering from Istanbul Technical University (ITU), Turkey, in 1973; and the M.S., Engineer, and Ph.D. degrees, all in electrical engineering, from the University of California at Los Angeles (UCLA), USA, in 1977, 1979, and 1981 respectively. He was a senior research scientist at the Honeywell Systems and Research Center, Minneapolis, USA (1981–1984) and a faculty member of Electrical Engineering and Computer Science, the University of Illinois at Chicago, USA (1984–1992). Since 1992, he has been with Middle East Technical University (METU), Turkey, where he is currently a professor of Electrical and Electronics Engineering. His current research interests are in the areas of communication systems, signal and image processing.

    View full text