Explainable and Neuro-Symbolic Artificial Intelligence

Robust and Bayesian Machine Learning

Simulation Intelligence and Reinforcement Learning

AI for Sustainability and Health

AI for Industry

The Artificial Intelligence lab is part of the Department of Mathematics and Geosciences of the University of Trieste. The lab, led by prof. Luca Bortolussi, is formed by phd students, post docs and researchers working in the areas of machine learning and explainable artificial intelligence. The lab also has several industry collaborations, solving practical problems and validating theoretical approaches on real world scenarios. Currently, The lab is involved in few national, EU-funded, and privately sponsored research projects.


News

iNEST Spoke 9 Kick-off
 
iNEST Spoke 9 Kick-off
The kick-off of Spoke 9 of the iNEST project will be hosted at SISSA on March 17, 2023 from 10.00 to 16.00.
iNEST Spoke 8 Kick-off
 
iNEST Spoke 8 Kick-off
The kick-off of Spoke 8 of the iNEST project will be hosted by the University of Trieste in the main building on the 1st of March 2023 from 10.00 to 17.00. Here you can find the detailed program: https://drive.google.com/file/d/1BEYqnmDM9Dms8BYOM_fgrB6tGnFKoTFc/view
SEDUCE Final Meeting
 
SEDUCE Final Meeting
The final meeting of the PRIN 2017 project SEDUCE will be held in Trieste on February 27 and 28, 2023. SEDUCE focuses on the use of Machine Learning for the verification and synthesis of cyber-physical systems. The project saw the collaboration of IMT Lucca, GSSI L’Aquila and the University of Camerino (UNICAM)/University of Firenze (UNIFI)...
Paper @Machines 2023
 
Paper @Machines 2023
Our paper Robot Navigation in Crowded Environments: A Reinforcement Learning Approach was accepted for publication in the scientific journal Machines 23. The paper is co-authored with Matteo Caruso, Enrico Regolin and Stefano Seriani. It presents controllers for driving mobile robots that must safely navigate a crowded environment while trying to reach a target location.
Paper @HSCC23
 
Paper @HSCC23
Our paper Conformal Quantitative Predictive Monitoring of STL Requirements for Stochastic Processes was accepted to HSCC23, co-authored with Nicola Paoletti for King’s College London. We propose a quantitative predictive monitor over the robustness of satisfaction of an STL property for stochastic processes.
AI dissemination project
 
AI dissemination project
The PCTO project organized in collaboration with Liceo Scientifico Galileo Galilei in Trieste has started. The project consists of a series of lectures targeted for high school students. They will familiarize with the handling and interpretation of data with the purpose of developing systems of recommendation