Using Automated Vehicles Operational Data to Confirm Safety and Anticipate Threats

Using Automated Vehicles Operational Data to Confirm Safety and Anticipate Threats

|Authors: Riccardo Donà, Espedito Rusciano, Germana Trentadue, Anastasios Tsakalidis, Maria Cristina Galassi

|Venue: arXiv preprint | Year: 2026

|arXiv: 2609.11549v1

Abstract

European Union (EU) policymakers adopted revolutionary data collection provisions for Automated Driving Systems (ADS) in the recently approved regulation that allows driverless vehicles to be operated on public roads. The framework is inspired by best practices developed at the United Nations Economic Commission for Europe(UNECE) level: the In-Service Monitoring and Reporting (ISMR); and by similar operational data collection regulatory approaches in nuclear energy production and transportation fields. The collection of real-world data will enable the competent safety authorities to gather the information needed to confirm the homologation safety target. Safety-relevant driving scenarios discovered during the real-world operation of a given ADS can also be stored in a scenario catalogue to investigate how other ADS types might have addressed such a traffic conflict. Moreover, lessons learnt deriving from the data collected can be shared among original equipment manufacturers (OEMs) and safety authorities. Ultimately, the ISMR is recognised as a necessary tool to properly tackle the challenges associated with ADS safety assessment given the number of unknowns that might remain undisclosed by leveraging the traditional homologation validation scheme only.

Key Contributions

• European Union (EU) policymakers adopted revolutionary data collection provisions for Automated D…
• The framework is inspired by best practices developed at the United Nations Economic Commission f…
• The collection of real-world data will enable the competent safety authorities to gather the info…
• Safety-relevant driving scenarios discovered during the real-world operation of a given ADS can a…
• Moreover, lessons learnt deriving from the data collected can be shared among original equipment …

Topics

• vision
• reinforcement-learning

Code & Data

No code repository linked in paper metadata.

BibTeX

@article{Donà2026_260911549v1,
  title     = {Using Automated Vehicles Operational Data to Confirm Safety and Anticipate Threats},
  author    = {Riccardo Donà and Espedito Rusciano and Germana Trentadue and Anastasios Tsakalidis and Maria Cristina Galassi},
  year      = {2026},
  eprint    = {2609.11549v1},
  archivePrefix = {arXiv},
  primaryClass  = {cs.RO},
  url       = {https://arxiv.org/abs/2609.11549v1}
}