A historical perspective of adaptive control and learning

AM Annaswamy, AL Fradkov - Annual Reviews in Control, 2021 - Elsevier
This article provides a historical perspective of the field of adaptive control over the past
seven decades and its intersection with learning. A chronology of key events over this large …

State estimation of the Stefan PDE: A tutorial on design and applications to polar ice and batteries

S Koga, M Krstic - Annual Reviews in Control, 2022 - Elsevier
The Stefan PDE system is a representative model for thermal phase change phenomena,
such as melting and solidification, arising in numerous science and engineering processes …

[KNYGA][B] Traffic congestion control by PDE backstep**

H Yu, M Krstic - 2022 - Springer
This book explores the development of PDE (partial differential equation) backstep**
controllers for the suppression of stop-and-go instabilities and oscillations in congested …

A stochastic model for stop-and-go phenomenon in traffic oscillation: On the prospective of macro and micro traffic flow

J Wen, L Hong, M Dai, X **
V Alleaume, M Krstic - IEEE Transactions on Automatic Control, 2024 - ieeexplore.ieee.org
For the quite extensively developed PDE backstep** methodology for coupled linear
hyperbolic PDEs, we provide a generalization from finite collections of such PDEs, whose …

Mitigating stop-and-go traffic congestion with operator learning

Y Zhang, R Zhong, H Yu - Transportation Research Part C: Emerging …, 2025 - Elsevier
This paper presents a novel neural operator learning framework for designing boundary
control to mitigate stop-and-go congestion on freeways. The freeway traffic dynamics are …

Neural operator approximations of backstep** kernels for 2× 2 hyperbolic PDEs

S Wang, M Diagne, M Krstić - 2024 American Control …, 2024 - ieeexplore.ieee.org
Deep neural network approximation of nonlinear operators, commonly referred to as
DeepONet, has so far proven capable of approximating PDE backstep** designs in which …