Established by the Gerla family in 2019, this award is in memory of Dr. Mario Gerla, pioneer in computer networking, professor of Computer Science at UCLA and ISSNAF founding member.
We are thrilled to announce and congratulate the exceptional finalists of the 2024 edition:
Leonardo Bonati
Mario de Florio
Federico Rossi
You can catch their outstanding research presentation at the Symposium on October 21, 2024, where they will present to a jury chaired by Prof. Leila De Floriani. Register here for the ISSNAF YI Mario Gerla Award Symposium.
The winner will be announced at ISSNAF 2024 Annual Event in Washington D.C. on November 14.
LEONARDO BONATI
Leonardo Bonati is an Associate Research Scientist at Northeastern University's Institute for the Wireless Internet of Things. He earned his Ph.D. in Computer Engineering from Northeastern University in 2022. His research focuses on software-based solutions for the Open RAN in next-generation cellular networks, with a particular emphasis on O-RAN-managed networks, network automation, and orchestration. He has served on the Technical Program Committees of several IEEE and ACM conferences and was a guest editor for a special issue of Elsevier Computer Networks on Advances in Experimental Wireless Platforms and Systems.
Research Focus
The digital society relies on high-performance, reliable wireless connectivity. Next-generation mobile networks, such as 5G and 6G, introduce promising technologies that enable faster data rates and ultra-low latency communication. However, their deployment faces several challenges, including the need to support new frequency bands, coexist with other spectrum users, and intelligently manage and optimize network operations at scale.
My research focuses on developing system-level, end-to-end solutions to make 5G and beyond networks functional and capable of meeting future digital society demands. I aim to design architectures, protocols, and algorithms that enhance network performance and adaptability, experimentally testing these solutions in large-scale testbeds to optimize the user experience.
Ultimately, my work contributes to advancing wireless network technologies by addressing critical challenges in deploying and operating next-generation mobile networks. By focusing on comprehensive solutions and utilizing cutting-edge techniques such as machine learning, network orchestration, and automation, my research strives to create more efficient, adaptable, and reliable wireless networks that can support the ever-growing connectivity needs of our world.
About me
For the past few years, my research has focused on next-generation 5G-and-beyond mobile networks, with a particular emphasis on prototyping and experimentation. I design and evaluate solutions aimed at optimizing network performance and sustainability, testing them on real systems ranging from lab environments to large-scale testbeds. Additionally, I actively contribute to the research community by developing and maintaining publicly accessible testbeds and experimental frameworks for wireless research. I also contribute to open-source projects within the Open RAN ecosystem, helping to advance innovation in this critical area.
MARIO DE FLORIO
Mario De Florio received his BSc and MSc in Energy and Nuclear Engineering from the University of Bologna in 2016 and 2019, respectively. He earned his PhD in Systems and Industrial Engineering from the University of Arizona in 2022, where he focused on optimization algorithms for parameter estimation of meteorites and asteroids. His research also involved developing physics-informed machine learning frameworks for applications in photon transport, rarefied gas dynamics, and stiff chemical kinetics.
In 2023, Mario began his role as a Postdoctoral Research Associate at Brown University in the Division of Applied Mathematics. There, he advanced physics-informed machine learning algorithms for dynamical system identification from time-series data, with applications in systems biology, cardiovascular modeling, chaotic systems, and energy systems. Most recently, in September 2024, Mario joined the National Renewable Energy Laboratory (NREL) to further his research in cutting-edge machine learning techniques for innovative advancements in renewable energy.
Research Focus
My research focuses on advancing Physics-Informed Machine Learning (PIML) methods to empower scientists to swiftly and effectively address unresolved and complex physics problems across various applied sciences, including engineering, physics, chemistry, biology, and neuroscience, among others. My Scientific Machine Learning algorithms are distinguished by their exceptional computational speed, reliability, robustness, and adaptability, enhancing their efficiency and versatility in a wide range of applications.
I categorize the problems based on the level of physical knowledge and available data into three scenarios:
No available data, but well-established physics: In this case, a numerical method is required to solve the forward problem, which is driven by physics and typically modeled by a differential equation.
Limited data with partial physics knowledge: This is the most common scenario in engineering applications, where PIML methods can effectively integrate the available data with partially known physics models for parameter discovery.
Available observed data with unknown physics: In this data-driven scenario, the physics governing the phenomena is entirely unknown, necessitating the learning of the underlying physical principles from the data.
The PIML algorithms I have developed are designed to address all three scenarios, merging machine learning techniques to tackle complex nonlinear dynamical systems effectively
About me
Mario was born in Foggia in 1993 and raised in Torremaggiore, where he studied at the Scientific High School "Nicola Fiani". He left the South to pursue his engineering degrees in Bologna and two abroad experiences at the Complutense University of Madrid and the University of Arizona for his master's thesis. In addition to his passion for science, Mario enjoys playing drums and piano.
FEDERICO ROSSI
Dr. Federico Rossi is a Robotics Technologist in the Maritime and Multi-Agent Autonomy Group within the Robotics section at NASA’s Jet Propulsion Laboratory. He earned his Ph.D. in Aeronautics and Astronautics from Stanford University in 2018, under the mentorship of Prof. Marco Pavone. His doctoral thesis, titled "On the Interaction between Autonomous Mobility-on-Demand Systems and the Built Environment: Models and Large Scale Coordination Algorithms," focused on the large-scale coordination of autonomous systems. Prior to his Ph.D., Federico completed a dual M.Sc. in Space Engineering from Politecnico di Milano and Politecnico di Torino in 2013, and he is an alumnus of the prestigious Alta Scuola Politecnica.
Federico's research centers on optimal control and sequential decision-making under uncertainty in multi-agent robotic systems. His work has broad applications, including autonomous multi-robot lunar exploration, coordinating aerobots for atmospheric exploration on Venus, and guiding autonomous under-ice buoyant vehicles to study the melting of Antarctic glaciers. He has also collaborated with Universidad San Francisco de Quito and the Galapagos Marine Reserve on using multi-UAV systems to patrol and protect Galapagos sharks from illegal poaching.
Research Focus
Teams of autonomous robots have the potential to transform the field of planetary science. Sensor networks are particularly well-equipped to identify the sources of methane emissions on Mars, which could indicate the presence of bacterial life. Coordinated seismometers and magnetometers can provide valuable insights into the internal composition of celestial bodies such as Europa, Enceladus, and our Moon. Meanwhile, on Venus, teams of aerobots harnessing high-altitude winds can monitor the planet's geology, enabling them to detect and closely study volcanic eruptions.
To realize this vision, innovative autonomy tools are essential for coordinating these robotic teams. These tools must be capable of adapting to infrequent communication, stringent power constraints, and the possibility of hardware failures. Additionally, they need to be reliable and verifiable to safeguard NASA's high-value equipment, while also ensuring that their decision-making processes are transparent and understandable to scientists and operators.
My research focuses on developing these critical tools to address these challenges. I serve as the multi-agent autonomy lead for CADRE, a NASA-funded technology demonstration mission set to launch in 2025, which will involve three autonomous rovers exploring the Moon's Reiner Gamma region. Additionally, I design algorithms for autonomous aerobots on Venus and under-ice probes in Antarctica, contribute to the development of formal verification tools for autonomy, and create user interfaces to facilitate interaction between scientists, operators, and future autonomous explorers.
About me
I grew up in Gallarate, nestled on the train line between Milan and Switzerland. After studying at Politecnico di Milano and in Toulouse, I had the incredible opportunity to visit Stanford for my M.Sc. thesis, guided by the esteemed Prof. Marco Pavone, a past recipient of the Franco Strazzabosco Award. My fascination with the sky has always been a part of me, and I still find it hard to believe that my research contributes to NASA’s exploration of the Solar System!
One of the highlights of my job is collaborating with Italian students and researchers who come to JPL. It’s truly rewarding to share the excitement of discovery while celebrating our shared heritage. The ISSNAF community has played a vital role in this journey, helping me and others forge new connections with universities in Italy. This initiative has brought talented students to JPL, allowing them to either pursue academic careers in the U.S. or return to Italy with invaluable insights and enthusiasm from their experiences here. I sincerely appreciate your efforts in fostering this vibrant community!
Comentarios