Dependable Control and Decision Group

DECODE – Dependable Control and Decision Group

The DECODE (Dependable Control and Decision) group focuses on complex control systems, where coupling between subsystems, local sources of uncertainty, and structural changes can undermine reliability and generate dangerous behaviors. By leveraging tools from control theory, optimization, and machine learning, we contribute to the development of next-generation systems that are dependable, more autonomous and self adapt to changes in the internal dynamics and the surrounding environment.

The DECODE group is part of the EPFL Automatic Control Laboratory and the NCCR automation.

All software related to our publications is freely available on GitHub.

Do not forget to follow us on Linkedin!


Research topics


© 2023 EPFL

Distributionally robust state estimation can be computed in real time

— The manuscript entitled "Regularization for distributionally robust state estimation and prediction" has been accepted for publication in the Control Systems Letters journal. It describes how one can use regularization to minimize the mean absolute error of state estimates when the system is affected by noise distributed according to a distribution of which only samples are known. By design, the method is designed offline and provides out-of-sample guarantees when deployed in the field.

© 2023 EPFL

Hamiltonian Deep Neural Networks are Universal Approximators!

— Our paper "Universal Approximation Property of Hamiltonian Deep Neural Networks" is accepted in L-CSS. 

© 2023 EPFL

Baiwei Guo received the Best PhD paper award at ECC23

— Best PhD paper award at ECC23

© 2023 EPFL

Welcome to Daniele Martinelli

— The DECODE group welcomes a new Ph.D. student to their team: Daniele Martinelli.

© 2023 EPFL

New publication in IEEE Transactions on Smart Grid

— Our paper "Bayesian Error-in-Variables Models for the Identification of Distribution Grids" has been accepted and published in the March 2023 Volume of IEEE Transactions on smart grid (available here).

© 2023 EPFL

Top cited article in Optimal Control Applications and Methods

— The article "Supervised model predictive control of large-scale electricity networks via clustering methods" is among the top cited papers in OCAM from 1 Jan 2021 to 15 Dec 2022. A special thanks to Pascal Klaus, a student of our group who developed the core research during his master project at the Politecnico di Milano.

© 2023 EPFL

Leonardo Massai begins his PostDoc in DECODE

— Welcome to Leonardo Massai, who recently joined the DECODE group from Politecnico di Torino. Leonardo will strengthen our research on distributed control based on neural networks and machine learning.

© 2023 EPFL

Welcome to Massimiliano d'Angelo!

— Massimiliano, currently Postdoc researcher at Sapienza University of Rome, is visiting the DECODE group for two months bringing his expertise on dynamic systems and probability for studying the properties of neural ODES.

© 2023 EPFL

Danilo Saccani joins the DECODE group

— Danilo Saccani joined the group at the beginning of January 2023, bringing his expertise on distributed control, UAVs and MPC. Danilo is also a member of the NCCR automation. Welcome to DECODE!

All news


Funding acknowledgment


Head of the group: Giancarlo Ferrari Trecate
Office: ME C2 398
Mail: [email protected]

Administration : Nicole Bouendin
Office : ME C2 389
Phone : +41 21 693 38 45
Fax : +41 21 693 2574
Mail : [email protected]

How to reach the DECODE group and the Laboratoire d’Automatique from the M2 metro station

Dependable Control and Decision group (DECODE)
Ecole Polytechnique Fédérale de Lausanne
ME C2 398 (Bâtiment ME) , Station 9 
CH-1015 Lausanne

Access map