Learning MPC: a Data-efficient Model-based Reinforcement Learning Strategy for Iterative Tasks 

Ugo Rosolia
Senior Research Scientist and Science Manager, Amazon

Date/Time: 29 May 2025 / 10:30 – 11:30 am CET
Venue: UNINA Federico II - DIETI, Room CL-I-3, Via Claudio 21, 80125 Naples, Italy

This presentation will first provide an overview of the theory of Learning Model Predictive Control, showing in particular, how to leverage data in the decision-making process while ensuring safety, exploration, and performance improvement. The second part of the presentation will show that the proposed methodology can be used to teach a full-size real-world autonomous vehicle how to race, and culminate in a discussion on preliminary work to extend this strategy to multi-agent racing.

Optimisation-based Control of Flexible Resources in Sustainable Energy Networks 

Professor Alessandra Parisio
University of Manchester, Department of Electrical and Electronic Engineering (EEE)

Date/Time: 5 February 2025 / 12:00 – 13:00 am CET
Venue: Conference Room, Ist floor (ex Softel), Via Claudio 21, 80125 Naples, Italy

The growing deployment of distributed energy resources, while providing significant environmental and economic benefits, can induce reduced total system inertia and controllability, thus presenting new challenges in power grid operation. Within this context, flexibility (ability to adjust to time-varying grid conditions) is crucial for the transition towards power systems that can efficiently accommodate high shares of renewable energy sources. However, managing flexibility in urban districts and in distribution networks requires control and optimisation tools that are not yet available. This seminar will explore promising distributed control approaches for coordinating flexible resource, which leverage advanced methods, such as model predictive control and time-varying online optimisation, and data; moreover illustrative case studies will also be discussed.