Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing

Matthieu Barreau, John Liu, Karl Henrik Johansson
Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:34-46, 2021.

Abstract

The state reconstruction problem of a heterogeneous dynamic system under sporadic measurements is considered. This system consists of a conversation flow together with a multi-agent network modeling particles within the flow. We propose a partial-state reconstruction algorithm using physics-informed learning based on local measurements obtained from these agents. Traffic density reconstruction is used as an example to illustrate the results and it is shown that the approach provides an efficient noise rejection.

Cite this Paper

BibTeX
@InProceedings{pmlr-v144-barreau21a, title = {Learning-based State Reconstruction for a Scalar Hyperbolic {PDE} under noisy Lagrangian Sensing}, author = {Barreau, Matthieu and Liu, John and Johansson, Karl Henrik}, booktitle = {Proceedings of the 3rd Conference on Learning for Dynamics and Control}, pages = {34--46}, year = {2021}, editor = {Jadbabaie, Ali and Lygeros, John and Pappas, George J. and A. Parrilo, Pablo and Recht, Benjamin and Tomlin, Claire J. and Zeilinger, Melanie N.}, volume = {144}, series = {Proceedings of Machine Learning Research}, month = {07 -- 08 June}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v144/barreau21a/barreau21a.pdf}, url = {https://proceedings.mlr.press/v144/barreau21a.html}, abstract = {The state reconstruction problem of a heterogeneous dynamic system under sporadic measurements is considered. This system consists of a conversation flow together with a multi-agent network modeling particles within the flow. We propose a partial-state reconstruction algorithm using physics-informed learning based on local measurements obtained from these agents. Traffic density reconstruction is used as an example to illustrate the results and it is shown that the approach provides an efficient noise rejection.} }
Endnote
%0 Conference Paper %T Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing %A Matthieu Barreau %A John Liu %A Karl Henrik Johansson %B Proceedings of the 3rd Conference on Learning for Dynamics and Control %C Proceedings of Machine Learning Research %D 2021 %E Ali Jadbabaie %E John Lygeros %E George J. Pappas %E Pablo A. Parrilo %E Benjamin Recht %E Claire J. Tomlin %E Melanie N. Zeilinger %F pmlr-v144-barreau21a %I PMLR %P 34--46 %U https://proceedings.mlr.press/v144/barreau21a.html %V 144 %X The state reconstruction problem of a heterogeneous dynamic system under sporadic measurements is considered. This system consists of a conversation flow together with a multi-agent network modeling particles within the flow. We propose a partial-state reconstruction algorithm using physics-informed learning based on local measurements obtained from these agents. Traffic density reconstruction is used as an example to illustrate the results and it is shown that the approach provides an efficient noise rejection.
APA
Barreau, M., Liu, J. & Johansson, K.H.. (2021). Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing. Proceedings of the 3rd Conference on Learning for Dynamics and Control, in Proceedings of Machine Learning Research 144:34-46 Available from https://proceedings.mlr.press/v144/barreau21a.html.

Related Material