mlsanityData to 14 Oct 2026

Evaluating Uncertainty Quantification in End-to-End Autonomous Driving Control

arXiv 1811.06817 ↗First posted 16 Nov 2018cs.LG cs.CV stat.MLcited by 55

Not on the map. Why?

Abstract (arXiv)

A rise in popularity of Deep Neural Networks (DNNs), attributed to more powerful GPUs and widely available datasets, has seen them being increasingly used within safety-critical domains. One such domain, self-driving, has benefited from significant performance improvements, with millions of miles having been driven with no human intervention. Despite this, crashes and erroneous behaviours still occur, in part due to the complexity of verifying the correctness of DNNs and a lack of safety guarantees. In this paper, we demonstrate how quantitative measures of uncertainty can be extracted in real-time, and their quality evaluated in end-to-end controllers for self-driving cars. To this end we utilise a recent method for gathering approximate uncertainty information from DNNs without changing the network's architecture. We propose evaluation techniques for the uncertainty on two separate architectures which use the uncertainty to predict crashes up to five seconds in advance. We find that mutual information, a measure of uncertainty in classification networks, is a promising indicator of forthcoming crashes.

Key facts. Cited by 55 papers in the map (data through 14 Oct 2026). First posted on arXiv 16 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 18; 2022: 7; 2023: 13; 2024: 6; 2025: 6; 2026: 5.

55 papers.

Sort:

By area:

  1. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  2. 2022Quantifying Aleatoric and Epistemic Uncertainty in Machine Learning: Are Conditional Entropy and Mutual Information Appropriate Measures?cited by 125
  3. 2021Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learningcited by 113
  4. 2021Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Taskscited by 101
  5. 2021Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classificationcited by 39
  6. 2021How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Reviewcited by 39
  7. 2022BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networkscited by 23
  8. 2021Efficient and Robust LiDAR-Based End-to-End Navigationcited by 22
  9. 2024Label-wise Aleatoric and Epistemic Uncertainty Quantificationcited by 22
  10. 2021Dynamic Bottleneck for Robust Self-Supervised Explorationcited by 21
  11. 2023Second-Order Uncertainty Quantification: Variance-Based Measurescited by 19
  12. 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Drivingcited by 17
38 more
  1. 2025Challenger: Affordable Adversarial Driving Video Generationcited by 16
  2. 2022Modular Conformal Calibrationcited by 15
  3. 2021Fail-Safe Execution of Deep Learning based Systems through Uncertainty Monitoringcited by 11
  4. 2024Predicting Safety Misbehaviours in Autonomous Driving Systems using Uncertainty Quantificationcited by 11
  5. 2021Understanding the Under-Coverage Bias in Uncertainty Estimationcited by 10
  6. 2021Prediction Surface Uncertainty Quantification in Object Detection Models for Autonomous Drivingcited by 10
  7. 2021RoMA: a Method for Neural Network Robustness Measurement and Assessmentcited by 10
  8. 2021Quantifying Epistemic Uncertainty in Deep Learningcited by 10
  9. 2023Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networkscited by 10
  10. 2023SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agentscited by 10
  11. 2021A Quantitative Comparison of Epistemic Uncertainty Maps Applied to Multi-Class Segmentationcited by 9
  12. 2024Monocular 3D lane detection for Autonomous Driving: Recent Achievements, Challenges, and Outlookscited by 9
  13. 2025An Axiomatic Assessment of Entropy- and Variance-based Uncertainty Quantification in Regressioncited by 9
  14. 2021Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Drivingcited by 8
  15. 2021What classifiers know what they don't?cited by 6
  16. 2023Flexible Visual Recognition by Evidential Modeling of Confusion and Ignorancecited by 6
  17. 2024Probabilistic Calibration by Design for Neural Network Regressioncited by 6
  18. 2025Graph Evidential Learning for Anomaly Detectioncited by 5
  19. 2021Robust Vision-Based Cheat Detection in Competitive Gamingcited by 4
  20. 2023Deep Gaussian Mixture Ensemblescited by 4
  21. 2022Uncertainty Quantification for Deep Neural Networks: An Empirical Comparison and Usage Guidelinescited by 3
  22. 2023AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Imagescited by 3
  23. 2024The Misclassification Likelihood Matrix: Some Classes Are More Likely To Be Misclassified Than Otherscited by 3
  24. 2021Marginally calibrated response distributions for end-to-end learning in autonomous drivingcited by 2
  25. 2022Nonlinear MCMC for Bayesian Machine Learningcited by 2
  26. 2022A view on model misspecification in uncertainty quantificationcited by 2
  27. 2022Deep Variational Inverse Scatteringcited by 2
  28. 2023Confidence Calibration for Systems with Cascaded Predictive Modulescited by 2
  29. 2024When to Accept Automated Predictions and When to Defer to Human Judgment?cited by 2
  30. 2025Explorations of the Softmax Space: Knowing When the Neural Network Doesn't Knowcited by 2
  31. 2025Optimal and Provable Calibration in High-Dimensional Binary Classification: Angular Calibration and Platt Scalingcited by 2
  32. 2025Uncertainty Quantification for Regression: A Unified Framework based on kernel scorescited by 2
  33. 2026The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Modelscited by 2
  34. 2021A Complete Characterisation of ReLU-Invariant Distributionscited by 1
  35. 2023Towards Dependable Autonomous Systems Based on Bayesian Deep Learning Componentscited by 1
  36. 2023Towards Quantification of Assurance for Learning-enabled Componentscited by 1
  37. 2023Uncertainty-aware deep learning for digital twin-driven monitoring: Application to fault detection in power linescited by 1
  38. 2023Adopting Two Supervisors for Efficient Use of Large-Scale Remote Deep Neural Networkscited by 0

50 most cited of 55 All 55 (JSON)