Curriculum Vitae

Curriculum Vitae

(updated: 16/09/2026)

Antonio Pietrabissa received his M.Sc. degree in Electronic Engineering and his Ph.D. in Systems Engineering in 2000 and 2004, respectively, from the Sapienza University of Rome. Currently, he is an Associate Professor at the Department of Computer, Control and Management Engineering (DIAG) "Antonio Ruberti" of the same university, where he teaches the courses "Foundations of Automatic Control" for Electronic and Telecommunications Engineering, and "Process Automation" for the M.Sc. in Control Engineering. Since 2016, he has been leader of the research group “Networked System” and, since 2026, responsible of the Network Control Laboratory of the DIAG. From 2019 to 2025 he served as Secretary of the Master in Control Engineering (Ingegneria Automatica) of Sapienza. Since 2025, he serves as “Director of the MSc Program in Control Engineering" (Presidente del Corso di Studi in Ingegneria Automatica). He holds the National Scientific qualification (ASN) as Full Professor for the disciplinary field of 09/G1 - Systems and control engineering, obtained in Jan. 2022.

Since 2000, he participated in 32 research projects, out of which 4 as principal investigator of the full project and 15 as principal investigator of the research unit.

In 2023, he was among the founders of the Sapienza innovative startup “Automation Intelligence and Control s.r.l.”, for which he currently serves as Chief Executive Officer (CEO).

He is a Senior Editor for the IEEE Trans. Automation Science and Engineering and an Associate Editor for IEEE Trans. Cybernetics and Control Engineering Practice (Elsevier).

His main research activities encompass the fields of network control, non-cooperative control, multi-agent systems, model predictive control, and intelligent control.

His initial research focused on resource management in wireless, satellite, and heterogeneous networks. In this context, he applied time-delay control theory for congestion control and modeled admission control problems as Markov decision processes (MDPs), solved via approximate dynamic programming and reinforcement learning methodologies.

Subsequent research investigates non-cooperative routing and load balancing through the study of the dynamic Wardrop equilibrium (interpretable as a Nash equilibrium with infinite agents). The work on this topic includes setups such as, e.g., discrete-time multi-commodity routing algorithms with time-varying delays and latencies and subject to capacity constraints. Alongside this, he has contributed to works on coordination of multi-agent systems via consensus protocols, leader-following frameworks, and distributed network partitioning.

Other research interests also include the development of model predictive control (MPC) algorithms for energy distribution networks, as well as robust, fault-tolerant spacecraft attitude control utilizing extended-observer designs.

Recently, his focus has expanded towards intelligent control. Notable analytical results involve the integration of deep neural networks into MPC frameworks to obtain tractable and efficient data-driven algorithms. Furthermore, he has developed novel consensus-based algorithms for decentralized federated learning that eliminate the need for a central server, enabling secure, distributed AI training for critical applications such as intelligent healthcare platforms and smart energy communities.

On these subjects, he is author of more than 160 peer-reviewed papers in international journals and conference proceedings, with bibliometric indices (as of September 2026):

Google Scholar: citations = 2649, h-index = 30, i10-index = 80.

Scopus: citations = 1911, h-index = 25.}