Journal Article

ROAD-R : the autonomous driving dataset for learning with requirements


Neural networks have proven to be very powerful at computer vision tasks. However, they often exhibit unexpected behaviors, acting against background knowledge about the problem at hand. This calls for models (i) able to learn from requirements expressing such background knowledge, and (ii) guaranteed to be compliant with the requirements themselves. Unfortunately, the development of such models is hampered by the lack of real-world datasets equipped with formally specified requirements. In this paper, we introduce the ROad event Awareness Dataset with logical Requirements (ROAD-R), the first publicly available dataset for autonomous driving with requirements expressed as logical constraints. Given ROAD-R, we show that current state-of-the-art models often violate its logical constraints, and that it is possible to exploit them to create models that (i) have a better performance, and (ii) are guaranteed to be compliant with the requirements themselves.

Attached files


Giunchiglia, Eleonora
Stoian, Mihaela
Khan, Salman
Cuzzolin, Fabio
Lukasiewicz, Thomas

Oxford Brookes departments

School of Engineering, Computing and Mathematics


Year of publication: 2023
Date of RADAR deposit: 2022-10-19

Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License

Related resources

This RADAR resource is Identical to ROAD-R: the autonomous driving dataset with logical requirements
This RADAR resource is the Version of Record of [arXiv preprint] ROAD-R: The Autonomous Driving Dataset with Logical Requirements


  • Owner: Joseph Ripp
  • Collection: Outputs
  • Version: 1 (show all)
  • Status: Live
  • Views (since Sept 2022): 544