Abstract
An algorithm specific architecture for Kalman filter is presented. It is based on systolic arrays. Parallelism has been exploited on both algorithm and architecture levels. Faddeev's algorithm has been employed. The involved computation tasks, triangularization and nullification are performed in parallel which leads to a speedup of about 40%. Throughput has been increased by using bi-trapezoidal arrays. Techniques have been employed for data storage and skewing which enables fast data transfer rates. A VLSI implementation of a prototype of matrix of size 4×4 has been discussed.
Similar content being viewed by others
References
M.A. Bayoumi, “Guest Editorial,” Special Issue on VLSI Design Methodologies for Special Processing Architectures,International Journal of Computer Aided Design,
F.M.F. Gaston and G.W. Irwin, “A Systolic square rooting information kalman filter,” inProc. of International Conf. on Systolic Arrays, 1988, pp. 643–652.
R.A. Lincoln and K. Yao, “Efficient systolic kalman filter design by dependence graph mapping,” IVLSI and Signal Processing, vol. 3, IEEE press.
J.M. Jover and T. Kailath, “A parallel architecture for kalman filter measurement update and parameter estimation,”Automatica, vol. 22, 1986, pp. 43–47.
M.J. Chen and K. Yao, “On realization and implementation of kalman filtering by systolic array,” inProc. of the 1987 Conf. on Information Sciences and Systems, John Hopkins Univ. 1987, pp. 375–380.
S.Y. Kung and J.N. Hwang, “Systolic designs for State Space Models: kalman filtering and neural network,” inProc. of 26th Conf. on Decision and Control, 1987, pp. 1461–1476.
R.E. Kalman, “A new approach to linear filtering and prediction problems,”Journal of Basic Engineering, vol. 82, 1960, pp. 35–45.
Paul G. Kaminski, “Discrete square root filtering: a Survey of current techniques,”IEEE Trans. Automatic Control, vol. AC-16, 1971, pp. 727–735.
Angus Andrews, “Parallel Processing Of the Kalman Filter,”Proc. of the 1981 International Conference of Parallel Processing, pp. 216–220.
J.G. Nash and S. Hassen, “Modified Faddeev algorithm for Matrix manipulation,” SPIE vol. 495,Real Time Signal Processing IV, 1984, pp. 39–45.
Jaime H. Moreno and Tomas Lang, “Designing arrays for Faddeev's Algorithm,” Technical Report, UCLA, March 1988.
W.M. Gentleman and H.T. Kung, “Matrix triangularization by systolic arrays,” SPIE vol. 298, Real-Time Signal Processing IV, 1981.
Nam Ling, Magdy A. Bayoumi and K.S. Reddy, “VLSI array implementation of modified booth algorithm,”Symposium of ACM, pp. 205–221.
M.A. Bayoumi, et.al, “An area-time efficient NMOS adder,”INTEGRATION, the VLSI journal, vol. 1, 1983, pp. 317–334.
Padma Rao, “An algorithm specific VLSI architecture for kalman filter,” M.Sc. Thesis, U. of SW Louisiana, 1990.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Bayoumi, M.A., Rao, P. & Alhalabi, B. VLSI parallel architecture for Kalman filterAn algorithm specific approach . J VLSI Sign Process Syst Sign Image Video Technol 4, 147–163 (1992). https://doi.org/10.1007/BF00925119
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00925119