ISLa - Intelligent Systems Lab

Group Members

Multiple Master’s and Bachelor’s thesis are currently available in our research group. If interested, please email to alessandro.farinelli@univr.it. Please specify your area of interest:

  • Artificial Intelligence algorithms for Autonomous Surface Vehicles.
  • Deep Reinforcement Learning for Robotic Systems in Complex Environments with Unity3D.
  • Situation Awareness and Safe Navigation for Drones.
  • Formal Verification methods for Deep Neural Networks.
  • Neurosymbolic AI.
  • Monte Carlo Methods for solving POMDP.

Director

Professor Alessandro Farinelli, Ph.D.

Personal Website
Prof. Alessandro Farinelli, is full professor and head of the Computer Science Department at University of Verona. His research interests focus on developing novel methodologies for Artificial Intelligence systems applied to robotics and cyber physical systems. In particular, he focuses on multi-agent coordination, decentralized optimization, reinforcement learning and data analysis for cyber-phisical systems. Alessandro Farinelli was principal investigator for several national and international research projects in the broad area of Artificial Intelligence. His research contributions target mainly international journals in the area of Artificial Intelligence (e.g., Artificial Intelligence journal and Journal of Artificial Intelligence Research) and Autonomous Robotic Systems (Autonomous Robots and Robotics and Autonomous Systems). The main scientific conferences he contributes to (both as organizer and speaker) include the International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), the International Joint Conference on Artificial Intelligence (IJCAI) and the International Conference on Intelligent Robots and Systems (IROS).

Faculty

Alberto Castellini, Ph.D.

Personal Website
Alberto Castellini is a fixed-term researcher (Rtd-b) at the Computer Science department of the University of Verona. His research interests focus on the development of Artificial Intelligence, Machine Learning and Data Analysis techniques, with applications on intelligent systems of various kinds, such as, cyber-physical systems, robotic systems, smart grids and smart buildings. The main methodologies he works on are predictive models for multivariate time series, methods for planning under uncertainty, reinforcement learning, regression and clustering techniques, interpretability of predictive models, situation assessment and anomaly detection.

Daniele Meli, Ph.D.

Personal Website
Daniele Meli received his Master’s degree in Automation Engineering from Politecnico di Bari, IT, in 2017, and his PhD in Computer Science at University of Verona in 2021. He is currently a research fellow and assistant professor in Artificial intelligence at University of Verona. His research is mainly focused on robotics and artificial intelligence, specifically on explainable and trustworthy AI, inductive logic programming and merging symbolic and probabilistic AI.

Research Fellow

Federico Bianchi

Personal Website
Federico Bianchi is a Ph.D. student in Computer Science at the University of Verona, advised by Prof. Alberto Castellini and Prof. Alessandro Farinelli. His research focuses on the development of scalable Safe Policy Improvement methods in real-world environments, that guarantee an increase in performance while respecting safety constraints. He is also focusing on the development of Safe Policy Improvement methods for multi-agent systems and strategic planning methods based on Monte Carlo Tree Search in continuous domains.

Francesco Trotti

Personal Website
Francesco Trotti is a Ph.D. candidate in Computer Science at the University of Verona in collaboration with Leonardo S.p.A. His research focuses on developing control techniques that integrate nonlinear control strategies with online reinforcement learning model-based algorithms while considering model and/or environment uncertainties. He also focuses on designing control strategies for multi-agent systems, particularly emphasizing the collaboration and coordination aspects of multi-agents. The possible application ranges from designing controllers for manned or unmanned fixed-wing sub supersonic vehicles to controlling robotic manipulators or mobile robots.

Ph.D. Students

Luca Marzari

Personal Website
is a PhD candidate at the University of Verona, advised by Prof. Alessandro Farinelli and Prof. Ferdinando Cicalese. He has recently been a visiting researcher in the Robotics Institute at Carnegie Mellon University (CMU), advised by Prof. Changliu Liu. His main research interests focus on developing efficient and reliable methods for verifying and enhancing the explainability of deep neural networks (DNNs). He also developed probabilistic verification algorithms with strong theoretical guarantees to bridge the gap between Formal Verification of DNNs and safe deep reinforcement learning. The results of his research resulted in several publications at top-level international conferences and prestigious collaborations with world-leading universities.

Celeste Veronese

Personal Website
is a second-year PhD student at the University of Verona, supervised by Prof. Alessandro Farinelli and Daniele Meli, PhD. Her current research focuses on the integration of symbolic, logic-based reasoning and Reinforcement Learning to improve the efficiency, interpretability, and generalization of AI systems, particularly in complex decision-making environments.

Davide Villaboni

Personal Website
is a second-year PhD student at the University of Verona, supervised by Prof. Alessandro Farinelli and Alberto Castellini, PhD. His current research focuses on enhancing forecast prediction through offline reinforcement learning and transformers.

Alumni

- Maddelena Zuccotto. Thesis title: "Learning in Monte Carlo Tree Search Planning". (PhD cycle XXXV).
- Davide Corsi. Thesis title: "Safe Deep Reinforcement Learning: Enhancing the Reliability of Intelligent Systems". (PhD cycle XXXV). Davide Corsi is a Postdoctoral Associate at University of California Irvine (updated on 2024).
- Adrià Fenoy. Thesis title: "Combining Optimization and Machine Learning for the Formation of Collectives". (PhD cycle XXXV). Adrià Fenoy is an AI engineer at MeteoSim (updated on 2024)
- Giulio Mazzi. Thesis title: "Rule-Based Policy Interpretation and Shielding for Partially Observable Monte Carlo Planning" (PhD cycle XXXIV).
- Enrico Marchesini. Thesis title: "Enhancing Exploration and Safety in Deep Reinforcement Learning". (PhD cycle XXXIV). Enrico Marchesini is a Postdoctoral Associate at Massachusetts Institute of Technology (MIT) (updated on 2024).
- Riccardo Sartea. Thesis title: "Active Malware Analysis based on reinforcement learning techniques". (PhD cycle XXXII). Riccardo Sartea is Data Scientist at Amazon Web Services (AWS) (updated on 2024).
- Lorenzo Bottarelli. Thesis Title: "Optimizing Information Gathering for Environmental Monitoring Applications". (PhD Cycle XXXI). Lorenzo Bottarelli is head of Machine Learning at Ignitia AB (updated on 2024).
- Masoume M. Raeissi. Thesis Title: "Modeling Supervisory Control in Multi-Robot Applications". (PhD cycle XXX). Masoume Raeissi is Research Associate (AI) at Wageningen University & Research (updated on 2024)
- Filippo Bistaffa. Thesis Title: "Constraint Optimisation Techniques for Real-World Applications". (PhD Cycle XXVIII). Filippo Bistaffa is tenured researcher at IIIA-CSIC (updated on 2024)