The increasing adoption of Artificial Intelligence techniques in safety-critical systems, employed in real world scenarios, requires the design of reliable, robust, and verifiable methodologies. Artificial Intelligence systems employed in such applications need to provide formal guarantees about their safety, increasing the need for a close interaction between the Artificial Intelligence and Formal Methods scientific communities, and possibly leading to the proposal of novel neurosymbolic approaches.

To witness this increasing need, tools and methodologies integrating Formal Methods and Artificial Intelligence, and more broadly symbolic and sub-symbolic solutions, are getting more and more attention, especially considering the wide-range and pervasive applications of machine and deep learning models.

The workshop is the main official initiative supported by the OVERLAY group. The event aims at establishing a stable, long-term scientific forum on relevant topics connected to the relationships between Artificial Intelligence and Formal Methods, by providing a stimulating environment where researchers can discuss about opportunities and challenges at the border of the two areas.

Important goals of the workshop are (i) to encourage the ongoing interaction between the formal methods and artificial intelligence communities, (ii) to identify innovative tools and methodologies, and (iii) to elicit a discussion on open issues and new challenges.

This year edition will be held on November 28th and 29th, 2024, in Bolzano, Italy.

Invited speaker

Andrea Micheli

Fondazione Bruno Kessler, Trento, Italy

Title

Mixing automated temporal planning and ML: the role of opaque entities and RL-based guidance synthesis

Abstract

The integration of planning and Machine Learning (ML) is nowadays a very hot research topic, with significant efforts directed toward learning heuristics or even planning models from example data such as plans and execution traces. In this talk, I will report on my experience in two relatively underexplored approaches to integrating temporal planning and ML. First, I will present how the use of simulated entities within the planning model allows the representation of learned constraints and behaviors: this feature emerged from a need in our development of a new digital twin service in the space domain, and is being integrated in the Unified Planning framework. Second, I will discuss our experimental application of Reinforcement Learning (RL) for the automated synthesis of guidance, enhancing automated temporal planning beyond the traditional focus on heuristic learning.

Bio

Andrea Micheli is the head of the "Planning Scheduling and Optimization" research unit at Fondazione Bruno Kessler, Trento, Italy. His research focuses on the development and technology transfer of automated planning technologies. He obtained his PhD in Computer Science from the University of Trento in 2016. His PhD thesis titled "Planning and Scheduling in Temporally Uncertain Domains'' won several awards including the EurAI Best Dissertation Award and the honorable mention at the ICAPS Best Dissertation award. He currently works in the field of temporal planning and is the main developer of the TAMER planner (tamer.fbk.eu). He is also lead developer of the pysmt open-source project aiming at providing a standard Python API for satisfiability modulo theory solvers. Andrea coordinated the AIPlan4EU project aiming to remove the access barriers to automated planning technology and to bring such technology to the European AI On-Demand Platform. He authored more than 30 papers in the Formal Methods and Artificial Intelligence fields. Andrea recently won an ERC Starting Grant for researching novel solutions in the combination of temporal planning and reinforcement learning.

Call for contributions

We accept extended abstracts (5 pages + references) focusing on the interaction between Artificial Intelligence and Formal Methods and on the issue of symbolic/sub-symbolic integration. Invited talks will complement the presentations of contributed papers.

Topics of interest include (but are not limited to):

• automata theory
• automated reasoning
• automated planning and scheduling
• controller synthesis
• formal specification languages
• formal verification
• game theory
• hybrid and discrete systems
• logics in computer science
• neurosymbolic approaches
• logics for neural networks
• neural networks for logic
• reactive synthesis
• runtime verification and monitoring
• satisfiability modulo theories and theorem proving
• specification and verification of machine/deep learning systems
• tools and applications

Contributed papers can present recent results at the border of the two fields, new research directions, challenges and perspectives. Presentation of results recently published in other scientific journals or conferences is also welcome.

We plan to include all papers in the Proceedings of the event, published at CEUR Workshop Proceedings . CEUR WS proceedings are archival proceedings indexed by DBLP and Scopus.

Submissions

Submitted papers should not exceed five (5) pages plus references. Authors are asked to use the Overlay-specific CEURART LaTeX style, which is available here. Authors of accepted papers will have the possibility to extend their submissions for the final camera-ready version to eight (8) pages plus references.

Submissions must be in PDF format and will be handled via EasyChair at the following address: https://easychair.org/conferences/?conf=overlay2024 .

Venue

The workshop will take place at the Free University of Bozen-Bolzano, in the main building in Piazza Università 1, just in the middle of the wonderful historical city center.

Information about how to reach Bolzano and the venue will be published soon.

Program Committee

Chairs

• Daniele Porello • University of Genova, Italy
• Cosimo Vinci • University of Salento, Italy
• Matteo Zavatteri • University of Padova, Italy

PC Members

• Aniello Murano • University of Naples "Federico II", Italy
• Florian Bruse • Universität Kassel, Germany
• Nicolas Troquard • Gran Sasso Science Institute, Italy
• Andrea Orlandini • ISTC-CNR, Rome, Italy
• Carlo Taticchi • University of Perugia, Italy
• Laura Giordano • Università del Piemonte Orientale, Italy
• Bettina Könighofer • Graz University of Technology, Austria
• Enrico Tronci • Sapienza University of Rome, Italy
• Paolo Baldi • University of Salento, Italy
• Federico Mari • University of Rome Foro Italico, Italy
• Nicola Gigante • Free University of Bozen-Bolzano, Italy
• Michael Sioutis • University of Montpellier/CNRS, France
• Emilio Incerto • IMT School for Advanced Studies, Lucca, Italy
• Vadim Malvone • Télécom Paris, France
• Michel Reniers • Eindhoven University of Technology, Netherlands
• Ruben Becker • Ca' Foscari University of Venice, Italy
• Nicolò Navarin • University of Padova, Italy
• Stefano Tonetta • Fondazione Bruno Kessler, Trento, Italy
• Carla Piazza • University of Udine, Italy
• Sasha Rubin • The University of Sydney, Australia
• Laura Nenzi • University of Trieste, Italy
• Eleonora Giunchiglia • Imperial College London, U.K.

Local Organization

• Nicola Gigante (Chair) • Free University of Bozen-Bolzano, Italy
• Tiziano Dalmonte • Free University of Bozen-Bolzano, Italy
• Andrea Mazzullo • Free University of Bozen-Bolzano, Italy

Contacts

For more information email to any of the program chairs.

Support

Free University of Bozen-Bolzano

The workshop is hosted and organized by the Faculty of Engineering of the Free University of Bozen-Bolzano.

University of Salento

We acknowledge the support of the Department of Mathematics and Physics «Ennio De Giorgi» of the University of Salento.

AIPlan4EU project

We acknowledge the support of the PURPLE project, 1st Open Call for Innovators of the AIPlan4EU H2020 project, a project funded by EU Horizon 2020 research and innovation programme under GA n. 101016442 (since 2021).