A Unified Approach to Optimally Solving Sensor Scheduling and Sensor Selection Problems in Kalman Filtering

Conference paper (2023)

Authors

Shamak Dutta University of Waterloo
N. Wilde Learning & Autonomous Control - Mechanical, Maritime and Materials Engineering
Stephen L. Smith University of Waterloo
Research Group
Learning & Autonomous Control (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2023 Shamak Dutta, N. Wilde, Stephen L. Smith
DOI: https://doi.org/10.1109/CDC49753.2023.10383721
More Info
expand_more

Published Date

2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Learning & Autonomous Control

Abstract

We consider a general form of the sensor scheduling problem for state estimation of linear dynamical systems, which involves selecting sensors that minimize the trace of the Kalman filter error covariance (weighted by a positive semidefinite matrix) subject to polyhedral constraints. This general form captures several well-studied problems including sensor placement, sensor scheduling with budget constraints, and Linear Quadratic Gaussian (LQG) control and sensing co-design. We present a mixed integer optimization approach that is derived by exploiting the optimality of the Kalman filter. While existing work has focused on approximate methods to specific problem variants, our work provides a unified approach to computing optimal solutions to the general version of sensor scheduling. In simulation, we show this approach finds optimal solutions for systems with 30 to 50 states in seconds.

Files

A_Unified_Approach_to_Optimall... (pdf)
(pdf | 0.807 Mb)
- Embargo expired in 19-07-2024
Unknown license