MENU

Andrea Martin

Andrea Martin
Andrea Martin
PhD Student
EPF Lausanne and ETH Zurich
andrea.martin@epfl.ch
Curriculum Vitae
Developing cooperation between researchers in the more and more ubiquitous areas of automation and control is crucial to shaping a sustainable future.

Andrea Martin joined the National Centre of Competence in Research (NCCR) Automation through a joint PhD program between EPF Lausanne and ETH Zurich. His research focuses on stochastic system modeling for data-based control. Andrea received his Bachelor’s Degree (cum laude) in Information Engineering from the University of Padua, Italy, and his Double Master’s Degree in Automation Engineering (cum laude) and in Automatic Control and Robotics from the same University and from the Polytechnic University of Catalonia, Spain. During his studies, he worked at the Institute for Robotics and Industrial Informatics in Barcelona. Outside office hours, he enjoys woodworking, hiking and photography.

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
Doi.org Collection Arxiv.org
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
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
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
Collection

Research projects as Researcher

Title
Principal Investigators

Stochastic behavioural models for data-driven control

Giancarlo Ferrari-Trecate, John Lygeros, Florian Dörfler

Summary

Recent results on data-based control exploit alternative parametrizations of linear and nonlinear systems, such as those provided by behavioral theory and deep neural networks. In this project we focus on Input/Output Behavioral (IOB) models that have been used for control by assuming noiseless measurement or deterministic bounded disturbances. The goal of the project is to study the relation between IOB-based control methods and the existing approaches for stochastic systems, including system identification and stochastic model predictive control. New controllers will be tested on the energy systems relevant for the NCCR.

People involved

Florian Dörfler
Andrea Martin
Giancarlo Ferrari-Trecate, John Lygeros, Florian Dörfler, Andrea Martin
Stochastic behavioural models for data-driven control
Giancarlo Ferrari-Trecate, John Lygeros, Florian Dörfler

Recent results on data-based control exploit alternative parametrizations of linear and nonlinear systems, such as those provided by behavioral theory and deep neural networks. In this project we focus on Input/Output Behavioral (IOB) models that have been used for control by assuming noiseless measurement or deterministic bounded disturbances. The goal of the project is to study the relation between IOB-based control methods and the existing approaches for stochastic systems, including system identification and stochastic model predictive control. New controllers will be tested on the energy systems relevant for the NCCR.

Florian Dörfler
Andrea Martin
Giancarlo Ferrari-Trecate, John Lygeros, Florian Dörfler, Andrea Martin
111
76577dd2-3aa6-4cf9-a61a-0755301b30cb