Zonotopic Constrained Kalman Filter Based on a Dual Formulation

This paper presents a new zonotopic constrained approach for the Kalman filter that takes advantage of the particular structure of the original optimization problem. This technique consists in projecting the state estimation by solving an optimization problem, to ensure that the estimated state belo...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings of the IEEE Conference on Decision & Control s. 6396 - 6401
Hlavní autoři: Merhy, Dory, Alamo, Teodoro, Stoica Maniu, Cristina, Camacho, Eduardo F.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2018
Témata:
Complexity theory
constrained Kalman filter
Generators
Kalman filters
Noise measurement
Optimization
primal-dual form
State estimation
ISSN:2576-2370
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper presents a new zonotopic constrained approach for the Kalman filter that takes advantage of the particular structure of the original optimization problem. This technique consists in projecting the state estimation by solving an optimization problem, to ensure that the estimated state belongs to a zonotope. Based on a classical gradient algorithm method, i.e. the iterative shrinkage-thresholding algorithm (ISTA), this paper proposes a reduced complexity approach suitable for the state estimation of systems subject to a large number of state constraints. The algorithm's speed is improved via a faster ISTA approach, called FISTA.
ISSN:2576-2370
DOI:10.1109/CDC.2018.8619177