The impact of Artificial Intelligence (AI) on the industry has been so disruptive that it has given rise to a new wave of research and applications. Several sectors have benefited significantly from AI adoption and this positive trend is planned to continue. Modern and future railways represent one of the fields in which AI is expected to have a significant impact in a medium to long-term perspective, to get higher levels of automation. Despite this opening for unprecedented scenarios in railway systems, it also raises concerns regarding system dependability and new threats associated with a high level of autonomy. 

Therefore, the first step towards adopting AI in the railway sector is understanding to what extent AI can be considered reliable, safe, and secure. In such a context, the AI4RAILS workshop series started in 2020, stemming from the Shift2Rail project RAILS (Roadmaps for the AI integration in the raiL Sector), to provide annually a forum for researchers, practitioners, and business leaders to discuss and share new perspectives, ideas, technologies, and solutions for effective and dependable integration of AI techniques in rail-based transportation systems. The current edition is supported by  the Europe's Rail project Academics4Rail.

Submission Guidelines

All papers must be original and not simultaneously submitted to another journal or conference.

Please refer to https://sites.google.com/view/ai4rails2025/ for further information.

List of Topics

The 2025 edition of AI4RAILS highlights trustworthy, dependable, and safe AI applications for rail freight and passenger systems. It welcomes AI techniques such as machine learning, neural networks, evolutionary algorithms, computer vision, and knowledge-based systems to enhance the reliability and efficiency of modern railways.

Topics of interest include, but are not limited to:

• AI for railway safety, availability, reliability, and security

• Transferability to railways of AI approaches from other sectors (e.g., avionics, automotive, etc.)

• Autonomous and cooperative train driving, including virtual coupling

• Automatic detection of signals, pedestrians, and obstacles

• Predictive maintenance and defect detection in railways

• AI for traffic planning and management

• Adversarial challenges in AI with a focus on railway case-studies

• Cognitive Digital Twins and Resource Allocation for railways

• Run-time model checking and AI with a focus on railway case studies

• Explainable and trustworthy AI in railway applications

• Certification and compliance standards for autonomous trains

Committees

Program Committee

• Nikola Bešinović, Delft University of Technology, Netherlands

• Lorenzo De Donato, Unversity of Naples Federico II, Italy

• Francesco Flammini, IDSIA USI-SUPSI, Switzerland, and University of Florence, Italy

• Hangli Ge, University of Tokyo, Japan

• Rob Goverde, TU Delft Transport Institute, Netherlands

• Ronghui Liu, University of Leeds, United Kingdom 

• Fredrik Heintz, Linköping University, Sweden

• Zhiyuan Lin, University of Leeds, UK

• Stefano Marrone, University of Naples Federico II, Italy

• Claudio Mazzariello, Hitachi Rail STS, Italy

• Roberto Nardone, University of Naples "Parthenope", Italy

• Alberto Petrillo,  University of Naples Federico II, Italy

• Danijela Ristic-Durrant, University of Bremen, Germany

• Matteo Salani, IDSIA USI-SUPSI, Switzerland

• Carlo Sansone, University of Naples Federico II, Italy

• Stefania Santini, University of Naples Federico II, Italy

• Ruifan Tang, University of Leeds, UK

• Valeria Vittorini, University of Naples Federico II, Italy

Workshop chairs

• Francesco Flammini, IDSIA USI-SUPSI, Switzerland, and University of Florence, Italy
• Valeria Vittorini, University of Naples Federico II, Italy

Venue

The conference will be held on April 8th 2025 in Lisbon, Portugal, colocated with EDCC 2025.

Contact

All questions about submissions should be emailed to francesco.flammini@ieee.org and valeria.vittorini@unina.it.