With Marco Roveri and Luigi Di Guglielmo
Artificial Intelligence-based methods are increasingly being deployed for a wide range of problems in the arena of Intelligent Autonomous Systems (IAS), which include autonomous cars, autonomous robots, unmanned aircraft systems, and beyond.
Even if Artificial Intelligence (AI) has made significant contributions to such applications, concerns remain about the lack of methods and tools to provide formal guarantees about the behaviors of the resulting systems.
In particular, it is essential that the behaviors generated by such AI-based systems are well-understood, are correct, safe, and can be predicted.
In this session we will discuss the possible synergies between Formal Methods (rigorous mathematical reasoning) and AI to guarantee and prove the safety of Intelligent Autonomous Systems controlled by AI-based methods.
Marco Roveri received a Ph.D. degree in Computer Science from the University of Milano. He is an Associate Professor in the Information Engineering and Computer Science Department of the University of Trento. He was Senior Researcher in the Embedded Systems Unit of Fondazione Bruno Kessler in Trento, and before a researcher in the Automated Reasoning Division of the Istituto Trentino di Cultura, Trento.
His research interests include automated formal verification of hardware and software systems, formal requirements validation of embedded systems, model-based predictive maintenance, and automated model-based AI planning and scheduling, and application of such techniques in industrial settings.
Luigi Di Guglielmo is the group leader for the Formal Methods team of Advanced Laboratory on Embedded Systems (ALES), a Raytheon Technology (RTX) company. He holds M.S. and Ph.D. in Computer Science from the University of Verona (Italy). He has 8+ years of experience in industrial innovation and applied research, developing methods and technologies based on formal methods for requirements formalization and analysis, model-based validation and verification.
He is the author of more than 20 technical papers.