no code implementations • 18 Apr 2024 • Jiaqi Yan, Ankush Chakrabarty, Alisa Rupenyan, John Lygeros
The framework consists of two phases: the (offine) meta-training phase learns a aggregated NSSM using data from source systems, and the (online) meta-inference phase quickly adapts this aggregated model to the target system using only a few data points and few online training iterations, based on local loss function gradients.
no code implementations • 31 Oct 2023 • Sleiman Safaoui, Abraham P. Vinod, Ankush Chakrabarty, Rien Quirynen, Nobuyuki Yoshikawa, Stefano Di Cairano
For this problem, we present a tractable motion planner that builds upon the strengths of reinforcement learning and constrained-control-based trajectory planning.
no code implementations • 24 Jun 2023 • Truong X. Nghiem, Ján Drgoňa, Colin Jones, Zoltan Nagy, Roland Schwan, Biswadip Dey, Ankush Chakrabarty, Stefano Di Cairano, Joel A. Paulson, Andrea Carron, Melanie N. Zeilinger, Wenceslao Shaw Cortez, Draguna L. Vrabie
Specifically, the paper covers an overview of the theory, fundamental concepts and methods, tools, and applications on topics of: 1) physics-informed learning for system identification; 2) physics-informed learning for control; 3) analysis and verification of PIML models; and 4) physics-informed digital twins.
1 code implementation • 28 Jan 2023 • Wenjie Xu, Colin N Jones, Bratislav Svetozarevic, Christopher R. Laughman, Ankush Chakrabarty
We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics.
no code implementations • 14 Nov 2022 • Ankush Chakrabarty, Gordon Wichern, Christopher R. Laughman
Deep neural state-space models (SSMs) provide a powerful tool for modeling dynamical systems solely using operational data.
no code implementations • 31 Oct 2022 • Ankush Chakrabarty
In this paper, we propose the use of meta-learning to generate an initial surrogate model based on data collected from performance optimization tasks performed on a variety of systems that are different to the target system.
no code implementations • 13 Jul 2022 • Shen Wang, Ankush Chakrabarty, Ahmad F. Taha
Traditional control and monitoring of water quality in drinking water distribution networks (WDN) rely on mostly model- or toolbox-driven approaches, where the network topology and parameters are assumed to be known.
no code implementations • 14 Oct 2021 • Wenjie Xu, Colin N Jones, Bratislav Svetozarevic, Christopher R. Laughman, Ankush Chakrabarty
We study the problem of performance optimization of closed-loop control systems with unmodeled dynamics.
no code implementations • 29 Jun 2021 • Ankush Chakrabarty, Gordon Wichern, Christopher Laughman
Physics-informed dynamical system models form critical components of digital twins of the built environment.
no code implementations • 22 Feb 2021 • Shen Wang, Ahmad F. Taha, Ankush Chakrabarty, Lina Sela, Ahmed Abokifa
Such representation is a byproduct of space- and time-discretization of the PDE modeling transport dynamics.
no code implementations • 12 May 2020 • Ankush Chakrabarty, Mouhacine Benosman
Data generated from dynamical systems with unknown dynamics enable the learning of state observers that are: robust to modeling error, computationally tractable to design, and capable of operating with guaranteed performance.
no code implementations • 3 Jul 2019 • Ankush Chakrabarty, Devesh K. Jha, Gregery T. Buzzard, Yebin Wang, Kyriakos Vamvoudakis
We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics.
no code implementations • 26 Jun 2019 • Ankush Chakrabarty, Rien Quirynen, Claus Danielson, Weinan Gao
Enforcing state and input constraints during reinforcement learning (RL) in continuous state spaces is an open but crucial problem which remains a roadblock to using RL in safety-critical applications.