Near-optimal MAP estimation for Markov jump linear systems using relaxed dynamic programming

A.R.P. Andrien; Duarte J. Guerreiro Tomé Antunes

doi:10.1109/LCSYS.2020.2993642

Near-optimal MAP estimation for Markov jump linear systems using relaxed dynamic programming

A.R.P. Andrien (Corresponding author), Duarte J. Guerreiro Tomé Antunes

Research output: Contribution to journal › Article › Academic › peer-review

4 Citations (Scopus)

Abstract

Computing the optimal joint maximum a posteriori probability (JMAP) estimate of the state and mode of a Markov jump linear system (MJLS) is known to be a computationally intractable problem. This letter provides a novel approximate method for such a problem that guarantees to be within a pre-specified bound of the optimal estimate. The proposed method builds upon relaxed dynamic programming. Through numerical examples, we show that this method can lead to better estimates with less computations than previous suboptimal methods proposed in the literature.

Original language	English
Article number	9090862
Pages (from-to)	815-820
Number of pages	6
Journal	IEEE Control Systems Letters
Volume	4
Issue number	4
DOIs	https://doi.org/10.1109/LCSYS.2020.2993642
Publication status	Published - 1 Oct 2020

Keywords

Estimation
Kalman filtering
Markov processes
Optimal control

Access to Document

10.1109/LCSYS.2020.2993642

Cite this

@article{1446e1617b62461a9f8533972193519c,

title = "Near-optimal MAP estimation for Markov jump linear systems using relaxed dynamic programming",

abstract = "Computing the optimal joint maximum a posteriori probability (JMAP) estimate of the state and mode of a Markov jump linear system (MJLS) is known to be a computationally intractable problem. This letter provides a novel approximate method for such a problem that guarantees to be within a pre-specified bound of the optimal estimate. The proposed method builds upon relaxed dynamic programming. Through numerical examples, we show that this method can lead to better estimates with less computations than previous suboptimal methods proposed in the literature.",

keywords = "Estimation, Kalman filtering, Markov processes, Optimal control",

author = "A.R.P. Andrien and {Guerreiro Tom{\'e} Antunes}, {Duarte J.}",

year = "2020",

month = oct,

day = "1",

doi = "10.1109/LCSYS.2020.2993642",

language = "English",

volume = "4",

pages = "815--820",

journal = "IEEE Control Systems Letters",

issn = "2475-1456",

publisher = "Institute of Electrical and Electronics Engineers",

number = "4",

}

TY - JOUR

T1 - Near-optimal MAP estimation for Markov jump linear systems using relaxed dynamic programming

AU - Andrien, A.R.P.

AU - Guerreiro Tomé Antunes, Duarte J.

PY - 2020/10/1

Y1 - 2020/10/1

N2 - Computing the optimal joint maximum a posteriori probability (JMAP) estimate of the state and mode of a Markov jump linear system (MJLS) is known to be a computationally intractable problem. This letter provides a novel approximate method for such a problem that guarantees to be within a pre-specified bound of the optimal estimate. The proposed method builds upon relaxed dynamic programming. Through numerical examples, we show that this method can lead to better estimates with less computations than previous suboptimal methods proposed in the literature.

AB - Computing the optimal joint maximum a posteriori probability (JMAP) estimate of the state and mode of a Markov jump linear system (MJLS) is known to be a computationally intractable problem. This letter provides a novel approximate method for such a problem that guarantees to be within a pre-specified bound of the optimal estimate. The proposed method builds upon relaxed dynamic programming. Through numerical examples, we show that this method can lead to better estimates with less computations than previous suboptimal methods proposed in the literature.

KW - Estimation

KW - Kalman filtering

KW - Markov processes

KW - Optimal control

UR - http://www.scopus.com/inward/record.url?scp=85084767776&partnerID=8YFLogxK

U2 - 10.1109/LCSYS.2020.2993642

DO - 10.1109/LCSYS.2020.2993642

M3 - Article

SN - 2475-1456

VL - 4

SP - 815

EP - 820

JO - IEEE Control Systems Letters

JF - IEEE Control Systems Letters

IS - 4

M1 - 9090862

ER -

Near-optimal MAP estimation for Markov jump linear systems using relaxed dynamic programming

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this