Learning-Enabled Robust Control with Noisy Measurements
Kjellqvist, Olle LU
and Rantzer, Anders
LU
(2022)
168.
p.86-96
- Abstract
- We present a constructive approach to bounded l2-gain adaptive control with noisy measurements for linear time-invariant scalar systems with uncertain parameters belonging to a finite set. The gain bound refers to the closed-loop system, including the learning procedure. The approach is based on forward dynamic programming to construct a finite-dimensional information state consisting of H-infinity-observers paired with a recursively computed performance metric. We do not assume prior knowledge of a stabilizing controller.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/c6e62692-4f27-4a7a-aefa-bf593fa848df
- author
- Kjellqvist, Olle
LU
and Rantzer, Anders
LU
- organization
- publishing date
- 2022-06-23
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Proceedings of The 4th Annual Learning for Dynamics and Control
- volume
- 168
- pages
- 10 pages
- publisher
- PMLR
- external identifiers
-
- scopus:85163706160
- project
- Scalable Control of Interconnected Systems
- language
- English
- LU publication?
- yes
- id
- c6e62692-4f27-4a7a-aefa-bf593fa848df
- alternative location
- https://proceedings.mlr.press/v168/kjellqvist22a.html
- date added to LUP
- 2022-07-15 09:53:14
- date last changed
- 2025-10-14 13:16:33
@inproceedings{c6e62692-4f27-4a7a-aefa-bf593fa848df,
abstract = {{We present a constructive approach to bounded l2-gain adaptive control with noisy measurements for linear time-invariant scalar systems with uncertain parameters belonging to a finite set. The gain bound refers to the closed-loop system, including the learning procedure. The approach is based on forward dynamic programming to construct a finite-dimensional information state consisting of H-infinity-observers paired with a recursively computed performance metric. We do not assume prior knowledge of a stabilizing controller.}},
author = {{Kjellqvist, Olle and Rantzer, Anders}},
booktitle = {{Proceedings of The 4th Annual Learning for Dynamics and Control}},
language = {{eng}},
month = {{06}},
pages = {{86--96}},
publisher = {{PMLR}},
title = {{Learning-Enabled Robust Control with Noisy Measurements}},
url = {{https://proceedings.mlr.press/v168/kjellqvist22a.html}},
volume = {{168}},
year = {{2022}},
}