Performance Prediction of the Interacting Multiple Model Algorithm

The Interacting Multiple Model (IMM) algorithm has been shown to be one of the most cost-effective hybrid state estimation schemes. Its performance, however, could only be evaluated via expensive Monte-Carlo simulations. An effective approach to the performance evaluation without recourse to simulations is presented in this paper. This approach is based on a performance measure of hybrid nature in the sense that it is a continuous-valued matrix function of a discrete-valued sequence - the system mode sequence. This system mode sequence is an essential description of the scenario of the problem on which the performance of the algorithm is dependent and being predicted. The performance measure is efficiently calculated in an off-line recursion. The capability of this approach in predicting quantitatively the average performance of the algorithm is illustrated via two important examples: a generic Air Traffic Control tracking problem and a nonstationary noise identification problem.

[1]  Ronald Sea.  An efficient suboptimal decision procedure for associating sensor data with stored tracks in real-time surveillance systems , 1971, CDC 1971.

[2]  J.B. Moore,et al.  Performance bounds for adaptive estimation , 1976, Proceedings of the IEEE.

[3]  Mitsuhiko Toda,et al.  Performance Bounds for Continuous-time Filters in the Presence of Modeling Errors , 1978, IEEE Transactions on Aerospace and Electronic Systems.

[4]  C. Chang.  Two lower bounds on the covariance for nonlinear estimation problems , 1981 .

[5]  H. Blom.  An efficient filter for abruptly changing systems , 1984 .

[6]  Chaw-Bing Chang,et al.  Application of state estimation to target tracking , 1984 .

[7]  Y. Bar-Shalom,et al.  Detection thresholds for tracking in clutter--A connection between estimation and signal processing , 1985 .

[8]  Y. Bar-Shalom,et al.  Multisensor tracking of a maneuvering target in clutter , 1989 .

[9]  Y. Bar-Shalom,et al.  The interacting multiple model algorithm for systems with Markovian switching coefficients , 1988 .

[10]  A. Haddad,et al.  Error bounds in the averaging of hybrid systems , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[11]  T. Kerr.  Status of CR-like lower bounds for nonlinear filtering , 1989 .

[12]  Y. Bar-Shalom,et al.  Tracking a maneuvering target using input estimation versus the interacting multiple model algorithm , 1989 .

[13]  Y. Bar-Shalom,et al.  Nonstationary noise identification with the interacting multiple model algorithm , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[14]  F. Daum.  Bounds on performance for multiple target tracking , 1990 .

[15]  Y. Bar-Shalom,et al.  State estimation for systems with sojourn-time-dependent Markov model switching , 1991 .

[16]  S. R. Rogers,et al.  Diffusion analysis of track loss in clutter , 1991 .

[17]  Che-Ho Wei,et al.  Maneuvering target tracking using IMM method at high measurement frequency , 1991 .

[18]  X. R. Li,et al.  Stability evaluation and track life of the PDAF for tracking in clutter , 1991 .

[19]  Amir Averbuch,et al.  Radar target tracking-Viterbi versus IMM , 1991 .

[20]  X.R. Li,et al.  A recursive hybrid system approach to noise identification , 1992, [Proceedings 1992] The First IEEE Conference on Control Applications.

[21]  Robert J. Dempster,et al.  Multiple hypothesis track confirmation for infrared surveillance systems , 1993 .

[22]  Yaakov Bar-Shalom,et al.  Interacting multiple model tracking with target amplitude feature , 1993 .

[23]  Yaakov Bar-Shalom,et al.  Design of an interacting multiple model algorithm for air traffic control tracking , 1993, IEEE Trans. Control. Syst. Technol..

[24]  Yaakov Bar-Shalom,et al.  Detection threshold selection for tracking performance optimization , 1994 .