INVITED SPEAKER SEMINAR - An Intelligent Multi-Layer Control Architecture for Logistics Operations of Autonomous Vehicles in Manufacturing Systems

Date: Thursday, June 13th, 2024, from 11 a.m.    
Location: EV 3.309

Abstract

This seminar explores the utilization of autonomous vehicles to enhance logistical operations within manufacturing systems. The primary concept involves organizing autonomous robots/vehicles into finite sets of platoons to execute specific tasks within the manufacturing system. Three key aspects are addressed: task scheduling, routing decisions, and command input computations. A novel distributed multi-layer architecture is introduced, exploiting three methodologies: timed colored Petri nets (TCPN), deep reinforcement learning, and model predictive control.

TCPNs are used to formally model the manufacturing system, enabling the derivation of an optimal scheduling task that aligns with the required jobs and available vehicles. Run-time routing decisions are made using a distributed reinforcement learning algorithm that leverages information from the vehicle sensor module. The distributed model predictive control algorithm is designed using a set-theoretic approach, with the majority of computations performed offline.

Biography

Dr. Domenico Famularo received a laurea degree in computer engineering from the University of Calabria, Italy, in 1991, and a Ph.D. in computational mechanics from the University of Rome, Italy, in 1996. From 1991 to 2000, he was a Research Associate at the University of Calabria. In 1997, he was a visiting Scholar Research at the University of New Mexico (USA), and in 1999, he held the same position at the University of Southern California (USA). He was a Researcher at ICAR-CNR, and since 2005, he has been an Associate Professor at the University of Calabria. His current research interests include control under constraints, control reconfiguration for fault-tolerant systems, and networked control systems.