Program
November 26th, 2024
(12min Talk + 3 min Questions)
[10:30 - 10:40] Welcome
Chair: Enrico Scala
[10:40 - 12:30] Session 1
Chair: Riccardo De Benedictis and Elisa Tosello
[10:40-10:55] -- One to rule them all: natural language to bind communication, perception and action, Simone Colombani, Dimitri Ognibene and Giuseppe Boccignone.
[10:55-11:10] -- How Are Large Language Models Applied to Automated Planning? A Discussion, Mattia Chiari, Alfonso Emilio Gerevini, Luca Putelli, Nicholas Rossetti, Ivan Serina and Lorenzo Serina.
[11:10-11:25] -- Towards Automated Planning of Level Structures for Digital Interventions, Lorenzo J James, Emanuele De Pellegrin, Laura Genga, Barbara Montagne, Pieter Van Gorp and Ronald P. A. Petrick.
[11:25-11:40] -- A Bin-Packing Formulation for Radiotherapy Treatment Scheduling, Chiara Camilla Rambaldi Migliore, Giovanni Iacca and Marco Roveri.
[11:40-11:55] -- Automated PDDL Domain File Generation for Enhancing Production System Development based on SysML Models, Hamied Nabizada, Tom Jeleniewski, Lasse Beers, Felix Gehlhoff and Alexander Fay.
[11:55-12:10] -- PDDL+ Models for Deployable yet Effective Traffc Signal Optimisation, Anas El Kouaiti, Francesco Percassi, Alessandro Saetti,Thomas Leo McCluskey, Mauro Vallati.
[12:10-12:25] -- Synthesis of Domain-Specific Temporal Planning Guidance using Reinforcement Learning: What to Learn and How to Plan, Irene Brugnara, Alessandro Valentini and Andrea Micheli.
[12:25-12:30] -- Closing Remarks of the Morning Section
[12:30 - 13:30] Lunch
[13:30 - 14:30] Keynote Speaker
Chair: Enrico Scala
Chair: Enrico Scala
A Decade of Planning-based Urban Traffic Control: What did We Learn and Where Are We Going? -- Mauro Vallaty, University of Huddersfield, UK.
In this talk, we'll explore the current state of urban traffic control, understanding its significance. Then, we'll take a quick, painless journey through a decade of research performed by the Huddersfield AI for Urban Traffic Management and Control research team, picking up some valuable lessons along the way. Finally, we'll look ahead to the future and explore areas where AI planning can play a major role in traffic management. Buckle up, it's going to be a ride!
Bio:
Mauro Vallati is Professor of AI at the University of Huddersfield, where he leads the AI4UTMC (AI for Urban Traffic Management and Control https://www.ai4utmc.info/ ) research team. He has extensive experience in real-world applications of AI methods and techniques, spanning from healthcare to train dispatching. In 2014 he started working on AI applied to the field of urban traffic control, a line of research that led to numerous high-impact academic publications, and patents filed in United Kingdom, China, and United States. In 2021 he was awarded a prestigious UKRI Future Leaders Fellowship for investigating AI-based autonomic urban traffic monitoring and control, with the aim of designing intelligent systems that can autonomously recognise the insurgence of traffic congestion and implement traffic light strategies to mitigate its impact on the urban traffic network.
[14:30-15:15] Session 2
Chair: Alessandro Umbrico and Ivan Serina
[14:30-14:45] -- Automatic Selection of Macro-Events for Heuristic-Search Temporal Planning, Alessandro La Farciola, Alessandro Valentini and Andrea Micheli.
[14:45-15:00] -- Dealing with Numeric and Metric Time Constraints in PDDL3 via Compilation to Numeric Planning, Luigi Bonassi, Alfonso Emilio Gerevini, Enrico Scala.
[15:00-15:15] -- Learning Reliable PDDL Models for Classical Planning from Visual Data, Aymeric Barbin, Federico Cerutti, Alfonso Emilio Gerevini.
[15:15 - 15:30] Closing Remarks
Chair: Ivan Serina