Combined stochastic and set-membership information filtering in multisensor systems

In state estimation theory, stochastic and set-membership approaches are generally considered separately from each other. Both concepts have distinct advantages and disadvantages making each one inherently better suited to model different sources of estimation uncertainty. In order to better utilize the potentials of both concepts, the core element of this paper is a Kalman filtering scheme that allows for a simultaneous treatment of stochastic and set-membership uncertainties. An uncertain quantity is herein modeled by a set of Gaussian densities. Since many modern applications operate in networked systems that may consist of a multitude of local processing units and sensor nodes, estimates have to be computed in a distributed manner and measurements may arrive at high frequency. An algebraic reformulation of the Kalman filter, the information filter, significantly eases the implementation of such distributed fusion architectures. This paper explicates how stochastic and set-membership uncertainties can simultaneously be treated within this information form and compared to the Kalman filter, it becomes apparent that the quality of some required approximations is enhanced.

[1]  F. Chernousko.  State Estimation for Dynamic Systems , 1993 .

[2]  Wynn C. Stirling,et al.  Nonlinear Filtering of Convex Sets of Probability Distributions , 2002, ISIPTA.

[3]  Uwe D. Hanebeck,et al.  Nonlinear information filtering for distributed multisensor data fusion , 2011, Proceedings of the 2011 American Control Conference.

[4]  Uwe D. Hanebeck,et al.  Nonlinear Bayesian estimation with convex sets of probability densities , 2008, 2008 11th International Conference on Information Fusion.

[5]  Uwe D. Hanebeck,et al.  Bounding linearization errors with sets of densities in approximate Kalman filtering , 2010, 2010 13th International Conference on Information Fusion.

[6]  Marco Zaffalon,et al.  Robust Filtering Through Coherent Lower Previsions , 2011, IEEE Transactions on Automatic Control.

[7]  Ian Petersen,et al.  A discrete-time robust extended Kalman filter , 2009, 2009 American Control Conference.

[8]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[9]  Arthur G. O. Mutambara,et al.  Decentralized Estimation and Control for Multisensor Systems , 2019 .

[10]  S. Grime,et al.  Data fusion in decentralized sensor networks , 1994 .

[11]  Toivo Henningsson.  Recursive state estimation for linear systems with mixed stochastic and set-bounded disturbances , 2008, 2008 47th IEEE Conference on Decision and Control.

[12]  Hugh Durrant-Whyte,et al.  A Beginners Guide to Decentralised Data Fusion , 2006 .

[13]  Branko Ristic,et al.  A box particle filter for stochastic and set-theoretic measurements with association uncertainty , 2011, 14th International Conference on Information Fusion.

[14]  Ian R. Petersen,et al.  Minimax optimal control of stochastic uncertain systems with relative entropy constraints , 2000, IEEE Trans. Autom. Control..

[15]  Darryl Morrell,et al.  An Extended Set-valued Kalman Filter , 2003, ISIPTA.

[16]  Fred C. Schweppe,et al.  Uncertain dynamic systems , 1973 .

[17]  Uwe D. Hanebeck,et al.  State estimation with sets of densities considering stochastic and systematic errors , 2009, 2009 12th International Conference on Information Fusion.

[18]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[19]  W. Stirling,et al.  Set-valued Filtering And Smoothing , 1988, Twenty-Second Asilomar Conference on Signals, Systems and Computers.

[20]  Uwe D. Hanebeck,et al.  Fusing Information Simultaneously Corrupted by Uncertainties with Known Bounds and Random Noise with Known Distribution , 2000, Inf. Fusion.