Advanced

State Estimation for Distributed and Hybrid Systems

Alriksson, Peter LU (2008) In PhD Theses TFRT-1084.
Abstract
This thesis deals with two aspects of recursive state estimation: distributed estimation and estimation for hybrid systems.

In the first part, an approximate distributed Kalman filter is developed. Nodes update their state estimates by linearly combining local measurements and estimates from their neighbors. This scheme allows nodes to save energy, thus prolonging their lifetime, compared to centralized information processing. The algorithm is evaluated experimentally as part of an ultrasound based positioning system.

The first part also contains an example of a sensor-actuator network, where a mobile robot navigates using both local sensors and information from a sensor network. This system was implemented using a... (More)
This thesis deals with two aspects of recursive state estimation: distributed estimation and estimation for hybrid systems.

In the first part, an approximate distributed Kalman filter is developed. Nodes update their state estimates by linearly combining local measurements and estimates from their neighbors. This scheme allows nodes to save energy, thus prolonging their lifetime, compared to centralized information processing. The algorithm is evaluated experimentally as part of an ultrasound based positioning system.

The first part also contains an example of a sensor-actuator network, where a mobile robot navigates using both local sensors and information from a sensor network. This system was implemented using a component-based framework.

The second part develops, a recursive joint maximum a posteriori state estimation scheme for Markov jump linear systems. The estimation problem is reformulated as dynamic programming and then approximated using so called relaxed dynamic programming. This allows the otherwise exponential complexity to be kept at manageable levels.

Approximate dynamic programming is also used to develop a sensor scheduling algorithm for linear systems. The algorithm produces an offline schedule that when used together with a Kalman filter minimizes the estimation error covariance. (Less)
Please use this url to cite or link to this publication:
author
supervisor
opponent
  • Professor D'Andrea, Raffaello, ETH, Zürich, Switzerland
organization
publishing date
type
Thesis
publication status
published
subject
keywords
Joint Maximum a Posteriori Estimation, Sensor Networks, Distributed State Estimation, Networked Embedded Systems, Markov Jump Linear Systems, Sensor Scheduling
in
PhD Theses
volume
TFRT-1084
pages
174 pages
publisher
Department of Automatic Control, Lund Institute of Technology, Lund University
defense location
Room M:B, M-building, Ole Römers väg 1, Faculty of Engineering, Lund University
defense date
2008-09-26 10:15
ISSN
0280-5316
language
English
LU publication?
yes
id
55817061-3253-44fd-a6cf-9c568df96185 (old id 1221325)
date added to LUP
2008-09-02 12:52:47
date last changed
2016-09-19 08:44:47
@phdthesis{55817061-3253-44fd-a6cf-9c568df96185,
  abstract     = {This thesis deals with two aspects of recursive state estimation: distributed estimation and estimation for hybrid systems.<br/><br>
In the first part, an approximate distributed Kalman filter is developed. Nodes update their state estimates by linearly combining local measurements and estimates from their neighbors. This scheme allows nodes to save energy, thus prolonging their lifetime, compared to centralized information processing. The algorithm is evaluated experimentally as part of an ultrasound based positioning system.<br/><br>
The first part also contains an example of a sensor-actuator network, where a mobile robot navigates using both local sensors and information from a sensor network. This system was implemented using a component-based framework.<br/><br>
The second part develops, a recursive joint maximum a posteriori state estimation scheme for Markov jump linear systems. The estimation problem is reformulated as dynamic programming and then approximated using so called relaxed dynamic programming. This allows the otherwise exponential complexity to be kept at manageable levels.<br/><br>
Approximate dynamic programming is also used to develop a sensor scheduling algorithm for linear systems. The algorithm produces an offline schedule that when used together with a Kalman filter minimizes the estimation error covariance.},
  author       = {Alriksson, Peter},
  issn         = {0280-5316},
  keyword      = {Joint Maximum a Posteriori Estimation,Sensor Networks,Distributed State Estimation,Networked Embedded Systems,Markov Jump Linear Systems,Sensor Scheduling},
  language     = {eng},
  pages        = {174},
  publisher    = {Department of Automatic Control, Lund Institute of Technology, Lund University},
  school       = {Lund University},
  series       = {PhD Theses},
  title        = {State Estimation for Distributed and Hybrid Systems},
  volume       = {TFRT-1084},
  year         = {2008},
}