Abstract: This paper presents a deep reinforcement learning approach for optimally controlling the execution of a set of integration tasks in an assembly line. The work is inspired by the problem of optimizing the assembly of a space vehicle at a launch base, to increase the launch rate. The main goal of the controller is to ensure that the tasks are executed in the minimal time, while satisfying all the existing constraints. A comparison with an advanced alternative control approach based on model predictive control is made. Proof of concept simulations are presented to show the effectiveness of the proposed solution.

Biography: Francesco Liberati is a research fellow in Automatic Control at the Sapienza University of Rome. He is currently working mainly on cyber-physical systems and smart grid control problems, using mainly optimal control and machine learning techniques.
He teaches the course of "System and Control Methods for Cyber-physical Security", at Sapienza University of Rome.
He obtained his PhD in Systems Engineering from Sapienza University, with a dissertation over recent control problems in the area of energy management in smart grids.
From May 2017 to December 2018, he was serving as energy research project manager at "The Innovation and Networks Executive Agency (INEA)", European Commission, Brussels, where he managed about 20 large energy and smart cities international research projects.
Previously, he carried out applied research in several european funded projects, taking up project management roles as team leader, work package leader, task leader. He is the author of about 60 publications.