Systolic implementation of Kalman filter

Sau-Gee Chen; Jiann Cherng Lee; Chieh Chih Li

Systolic implementation of Kalman filter

Sau-Gee Chen^*, Jiann Cherng Lee, Chieh Chih Li

^*Corresponding author for this work

National Chiao Tung University

Research output: Contribution to conference › Paper › peer-review

4 Scopus citations

Abstract

Several new real-time systolic implementations for three popular Kalman filtering algorithms are presented. These architectures are all composed of two units of systolic arrays, where the first one is based on three new systolic arrays for matrix multiplications and additions, while the second one is a conventional systolic array for matrix inversion. Mathematical formulations of the three Kalman filtering algorithms are scheduled for the best deployment of those systolic arrays. This results in nine new systolic Kalman filters. Among them, one has the best performances in both speed and hardware complexities among the existing architectures. Specifically, this architecture has a smaller number of O(2n²) PE's than O(2.5n²) PE's of the best known structures, and a highest throughput rate.

Original language	English
Pages	97-102
Number of pages	6
State	Published - 1 Dec 1994
Event	Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems - Taipei, Taiwan Duration: 5 Dec 1994 → 8 Dec 1994

Conference

Conference	Proceedings of the 1994 IEEE Asia-Pacific Conference on Circuits and Systems
City	Taipei, Taiwan
Period	5/12/94 → 8/12/94

Fingerprint Dive into the research topics of 'Systolic implementation of Kalman filter'. Together they form a unique fingerprint.

Cite this

@conference{984ef1d2661246faa411ac93893baf8b,

title = "Systolic implementation of Kalman filter",

abstract = "Several new real-time systolic implementations for three popular Kalman filtering algorithms are presented. These architectures are all composed of two units of systolic arrays, where the first one is based on three new systolic arrays for matrix multiplications and additions, while the second one is a conventional systolic array for matrix inversion. Mathematical formulations of the three Kalman filtering algorithms are scheduled for the best deployment of those systolic arrays. This results in nine new systolic Kalman filters. Among them, one has the best performances in both speed and hardware complexities among the existing architectures. Specifically, this architecture has a smaller number of O(2n2) PE's than O(2.5n2) PE's of the best known structures, and a highest throughput rate.",

author = "Sau-Gee Chen and Lee, {Jiann Cherng} and Li, {Chieh Chih}",

year = "1994",

month = dec,

day = "1",

language = "English",

pages = "97--102",

note = "null ; Conference date: 05-12-1994 Through 08-12-1994",

}

TY - CONF

T1 - Systolic implementation of Kalman filter

AU - Chen, Sau-Gee

AU - Lee, Jiann Cherng

AU - Li, Chieh Chih

PY - 1994/12/1

Y1 - 1994/12/1

N2 - Several new real-time systolic implementations for three popular Kalman filtering algorithms are presented. These architectures are all composed of two units of systolic arrays, where the first one is based on three new systolic arrays for matrix multiplications and additions, while the second one is a conventional systolic array for matrix inversion. Mathematical formulations of the three Kalman filtering algorithms are scheduled for the best deployment of those systolic arrays. This results in nine new systolic Kalman filters. Among them, one has the best performances in both speed and hardware complexities among the existing architectures. Specifically, this architecture has a smaller number of O(2n2) PE's than O(2.5n2) PE's of the best known structures, and a highest throughput rate.

AB - Several new real-time systolic implementations for three popular Kalman filtering algorithms are presented. These architectures are all composed of two units of systolic arrays, where the first one is based on three new systolic arrays for matrix multiplications and additions, while the second one is a conventional systolic array for matrix inversion. Mathematical formulations of the three Kalman filtering algorithms are scheduled for the best deployment of those systolic arrays. This results in nine new systolic Kalman filters. Among them, one has the best performances in both speed and hardware complexities among the existing architectures. Specifically, this architecture has a smaller number of O(2n2) PE's than O(2.5n2) PE's of the best known structures, and a highest throughput rate.

UR - http://www.scopus.com/inward/record.url?scp=0028728991&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0028728991

SP - 97

EP - 102

Y2 - 5 December 1994 through 8 December 1994

ER -