mlsanityData to 7 Oct 2026

ROAD-R: The Autonomous Driving Dataset with Logical Requirements

arXiv 2210.01597 ↗First posted 4 Oct 2022cs.LG cs.AI cs.CVcited by 34

Not on the map. Why?

Abstract (arXiv)

Neural networks have proven to be very powerful at computer vision tasks. However, they often exhibit unexpected behaviours, violating known requirements expressing background knowledge. This calls for models (i) able to learn from the requirements, and (ii) guaranteed to be compliant with the requirements themselves. Unfortunately, the development of such models is hampered by the lack of 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.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 20 of its 61 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

20 of 61 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  3. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  4. 2017Non-local Neural Networkscited by 2,290
  5. 2018SlowFast Networks for Video Recognitioncited by 1,862
  6. 2016Concrete Problems in AI Safetycited by 1,582
  7. 2017A Semantic Loss Function for Deep Learning with Symbolic Knowledgecited by 267
  8. 2016Harnessing Deep Neural Networks with Logic Rulescited by 135
  9. 2017Logic Tensor Networks for Semantic Image Interpretationcited by 92
  10. 2017Action Tubelet Detector for Spatio-Temporal Action Localizationcited by 77
  11. 2020Coherent Hierarchical Multi-Label Classification Networkscited by 65
  12. 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54
8 more
  1. 2019Augmenting Neural Networks with First-order Logiccited by 51
  2. 2021MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networkscited by 44
  3. 2022Deep Learning with Logical Constraintscited by 44
  4. 2021Multi-Label Classification Neural Networks with Hard Logical Constraintscited by 36
  5. 2021Neuro-Symbolic Constraint Programming for Structured Predictioncited by 11
  6. 2020Knowledge Graph Extraction from Videoscited by 10
  7. 2020HLVU : A New Challenge to Test Deep Understanding of Movies the Way Humans docited by 6
  8. 2017Traffic Prediction Based on Random Connectivity in Deep Learning with Long Short-Term Memorycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 11; 2025: 11; 2026: 5.

34 papers.

Sort:

By area:

  1. 2022Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computingcited by 34
  2. 2024Logically Consistent Language Models via Neuro-Symbolic Integrationcited by 30
  3. 2023Random-Set Neural Networks (RS-NN)cited by 19
  4. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  5. 2024On the Independence Assumption in Neurosymbolic Learningcited by 18
  6. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  7. 2025Neurosymbolic Diffusion Modelscited by 12
  8. 2025A Probabilistic Neuro-symbolic Layer for Algebraic Constraint Satisfactioncited by 11
  9. 2025Integral Imprecise Probability Metricscited by 11
  10. 2024On the Hardness of Probabilistic Neurosymbolic Learningcited by 9
  11. 2025Random-Set Large Language Modelscited by 7
  12. 2025Neuro-Symbolic Predictive Process Monitoringcited by 7
22 more
  1. 2024Atom-Level Optical Chemical Structure Recognition with Limited Supervisioncited by 5
  2. 2023Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spacescited by 4
  3. 2023LogicNet: A Logical Consistency Embedded Face Attribute Learning Networkcited by 4
  4. 2024Exploiting T-norms for Deep Learning in Autonomous Drivingcited by 4
  5. 2026Quantifying Epistemic Predictive Uncertainty in Conformal Predictioncited by 4
  6. 2023Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detectioncited by 3
  7. 2023IntelliGraphs: Datasets for Benchmarking Knowledge Graph Generationcited by 3
  8. 2024Improving Neural-based Classification with Logical Background Knowledgecited by 2
  9. 2024Simple and Effective Transfer Learning for Neuro-Symbolic Integrationcited by 2
  10. 2024Good Data Is All Imitation Learning Needscited by 2
  11. 2024MOD-CL: Multi-label Object Detection with Constrained Losscited by 1
  12. 2025A Scalable Approach to Probabilistic Neuro-Symbolic Robustness Verificationcited by 1
  13. 2025On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNscited by 1
  14. 2025Assured Autonomy with Neuro-Symbolic Perceptioncited by 1
  15. 2025When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updatescited by 1
  16. 2026The Theory and Practice of MAP Inference over Non-Convex Constraintscited by 1
  17. 2026A neurosymbolic Approach with Epistemic Deep Learning for Hierarchical Image Classificationcited by 1
  18. 2023Spatiotemporal Event Graphs for Dynamic Scene Understandingcited by 0
  19. 2025Attack logics, not outputs: Towards efficient robustification of deep neural networks by falsifying concept-based propertiescited by 0
  20. 2025Integrating Legal and Logical Specifications in Perception, Prediction, and Planning for Automated Driving: A Survey of Methodscited by 0
  21. 2026DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applicationscited by 0
  22. 2026Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Modelscited by 0