Luca Furieri

Dr.

Luca Furieri

Alumni

EPF Lausanne

It is a unique opportunity to be working at the very intersection of control theory, optimization and machine learning.

Luca Furieri is a postdoctoral researcher at the Automatic Control Laboratory, EPFL - Lausanne, working in the DECODE group with Prof. Giancarlo Ferrari Trecate. In September 2020, he received a Ph.D. degree in Control and Optimization from ETH - Zurich in the Automatic Control Laboratory (IfA) under the supervision of Prof. Maryam Kamgarpour. Previously, he received the Bachelor and Master degrees in Automation Engineering from the University of Bologna, both with honours, in 2014 and 2016 respectively. Luca's research interests lie in the broad areas of learning and optimal control for distributed decision making and safety critical applications.

Scientific Publications

Published

Follow the Clairvoyant: An Imitation Learning Approach to Optimal Control

Proceedings of IFAC World congress 2023

Andrea Martin, Luca Furieri, Florian Dörfler, John Lygeros, Giancarlo Ferrari Trecate

2023

Doi.org Collection Arxiv.org

Published

Unconstrained Parametrization of Dissipative and Contracting Neural Ordinary Differential Equations

62nd IEEE Conference on Decision and Control

Daniele Martinelli, Clara Galimberti, Ian Manchester, Luca Furieri, Giancarlo Ferrari Trecate

2023

Doi.org Collection

Published

Hamiltonian Deep Neural Networks Guaranteeing Nonvanishing Gradients by Design

IEEE Transactions on Automatic Control

Vol 68 No 5 Pages 3155-3162

Clara Galimberti, Luca Furieri, Liang Xu, Giancarlo Ferrari Trecate

2023

Collection

Published

Distributed Neural Network Control with Dependability Guarantees: a Compositional Port-Hamiltonian Approach

Proceedings of The 4th Annual Learning for Dynamics and Control Conference

Vol 168 Pages 571-583

Luca Furieri, Clara Lucía Galimberti, Muhammad Zakwan, Giancarlo Ferrari Trecate

2022

Doi.org Collection

Published

Near-Optimal Design of Safe Output Feedback Controllers from Noisy Data

IEEE Transactions on Automatic Control

Pages 1-16

Luca Furieri, Baiwei Guo, Andrea Martin, Giancarlo Ferrari Trecate

2022

Doi.org Collection

to Appear

Neural System Level Synthesis: Learning Over All Stabilizing Policies for Nonlinear Systems

61st IEEE Conference on Decision and Control (CDC 2022)

Luca Furieri, Clara Galimberti, Giancarlo Ferrari Trecate

2022

Doi.org Collection

Published

Safe Control with Minimal Regret

Proceedings of The 4th Annual Learning for Dynamics and Control Conference

Vol 168 Pages 726-738

Andrea Martin, Luca Furieri, Florian Dörfler, John Lygeros, Giancarlo Ferrari Trecate

2022

Doi.org Collection

A Behavioral Input-Output Parametrization of Control Policies with Suboptimality Guarantees

60th IEEE Conference on Decision and Control (CDC21)

Luca Furieri, Baiwei Guo, Andrea Martin, Giancarlo Ferrari Trecate

2021

Collection

Research projects as Researcher

Title

Principal Investigators

Structured data-based distributed control

Giancarlo Ferrari Trecate

Summary

Cyberphysical systems are composed by subsystems linked through physical interconnections and communication channels enabling distributed control architectures. By leveraging recent results on optimal control, we will develop distributed algorithms for the data-driven generation of networked regulators adapted to the communication topology. Special attention will be devoted to the decentralization of the design process, so as to facilitate the addition and removal of subsystems in a plug-and-play fashion. As benchmark examples, we will consider energy systems and manufacturing processes, which are key applications in the NCCR.

People involved