Learning-Enabled Robust Control with Noisy Measurements

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.

Cite

Text

Kjellqvist and Rantzer. "Learning-Enabled Robust Control with Noisy Measurements." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.

Markdown

[Kjellqvist and Rantzer. "Learning-Enabled Robust Control with Noisy Measurements." Proceedings of The 4th Annual Learning for Dynamics and Control Conference, 2022.](https://mlanthology.org/l4dc/2022/kjellqvist2022l4dc-learningenabled/)

BibTeX

@inproceedings{kjellqvist2022l4dc-learningenabled,
  title     = {{Learning-Enabled Robust Control with Noisy Measurements}},
  author    = {Kjellqvist, Olle and Rantzer, Anders},
  booktitle = {Proceedings of The 4th Annual Learning for Dynamics and Control Conference},
  year      = {2022},
  pages     = {86-96},
  volume    = {168},
  url       = {https://mlanthology.org/l4dc/2022/kjellqvist2022l4dc-learningenabled/}
}