Projects
The Hybrid Intelligence (HI) Center is a 10-year programme funded by the Dutch Ministry of Education, Culture and Science through the Netherlands Organisation for Scientific Research. The main goal of the HI project is develop methods, tools, and techniques to combine human and machine intelligence, expanding human intellect instead of replacing it. In the HI program, I am a member of the HI taskforce and my role is to investigate methodologies and metrics for designing and evaluating Hybrid Intelligence systems.
Research project --funded by NWO Open Competition Domain Science - XS 21-3 grant -- aimed at the development of original solutions for AI systems that can make decisions and interact with humans aligned with our norms and values. In healthcare applications, such capabilities imply higher chances for the patients to establish trust in an assistive robot, improving both the acceptance of the robot and the effectiveness of the therapeutic interventions.
Research project aimed at the development of a novel evolutionary artificial intelligence approach, combining fuzzy logic and genetic algorithm techniques, to design creative social robots that can be used in therapy for dementia patients.
Scientific collaboration aimed at developing a distributed agent-based simulation framework to allow scalable simulations of norm-governed behaviors in epidemics. The framework is used to develop an agent-based simulation of the COVID-19 epidemic. Agents behaviors and mobility are based on actual data, and the norms in force regard mask-wearing, physical distancing, and behavioral interventions such as school and business closures. My role concerns, among other things, the modeling of norm-aware agents and the analysing experimental data.
Scientific collaboration aimed at investigating explainable Machine Learning solutions in the context of Software Engineering (with a particular focus on Natural Language Processing for Requirements Engineering), and investigating adequate and sound empirical standards for conducting and reporting ML4SE research to foster replicability and verifiability.
Ph.D. research project focused on the design of an adaptive runtime supervision framework that continuously monitors the execution of software systems, evaluates their behavior against the current requirements, and intervenes by deciding which requirements should be added, ignored or weakened. Two main pillars of the envisioned approach: (i) accurate requirement models can be obtained only at runtime and through learning, (ii) requirement revision, including requirement approximation, is preferred over system adaptation.
This project--supported by Piedmont Region (Italy) and by Fondazione CRT under the grant "Big data supporting Emergency Care imprOveMEnt" (BECOME)--aimed at applying online optimization methods to the management of health services. My role concerned the modeling and evaluation of a discrete event simulation to assess the impact of dynamic policies for the allocation of patients to the emergency departments, based on the real-time workload of the regional network of departments.
The SMAT-F2 research project--funded by the European Regional Development Fund (ERDF) and Piedmont Region (Italy), and led by Alenia Aermacchi--aimed at the development of autonomous capabilities for an Advanced Environment Monitoring System, based on Unmanned Air Systems (UAS). I was awarded two research grants in the context of this project. My role concerned (1st grant) the design, development and testing of intelligent methods for supporting mission planning from user requirements to high level planning of multi-UAS missions, and (2nd grant) the integration of such intelligent methods in an end-to-end system for supporting mission planning.
Lab project for the Artificial Intelligence and Laboratory course, aimed at developing an intelligent agent combining both deliberative and reactive aspects in the context of service robotics for a Next Generation Cafe.