# Assessing Safety-Critical Systems from Operational Testing: A Study on Autonomous Vehicles

arXiv: https://arxiv.org/abs/2008.09510 · HTML: https://mlsanity.com/paper/2008.09510/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 9 of 9)

- [Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance](https://mlsanity.com/paper/2112.00646/) (2021)
- [Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles](https://mlsanity.com/paper/2106.01258/) (2021)
- [Bayesian Learning for the Robust Verification of Autonomous Robots](https://mlsanity.com/paper/2303.08476/) (2023)
- [Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guide](https://mlsanity.com/paper/2502.14833/) (2025)
- [On the Need for a Statistical Foundation in Scenario-Based Testing of Autonomous Vehicles](https://mlsanity.com/paper/2505.02274/) (2025)
- [Symbiotic System of Systems Design for Safe and Resilient Autonomous Robotics in Offshore Wind Farms](https://mlsanity.com/paper/2101.09491/) (2021)
- [Bootstrapping confidence in future safety based on past safe operation](https://mlsanity.com/paper/2110.10718/) (2021)
- [A Hierarchical Imprecise Probability Approach to Reliability Assessment of Large Language Models](https://mlsanity.com/paper/2511.00527/) (2025)
- [Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification](https://mlsanity.com/paper/2608.03489/) (2026)

## Abstract (arXiv)

Context: Demonstrating high reliability and safety for safety-critical systems (SCSs) remains a hard problem. Diverse evidence needs to be combined in a rigorous way: in particular, results of operational testing with other evidence from design and verification. Growing use of machine learning in SCSs, by precluding most established methods for gaining assurance, makes operational testing even more important for supporting safety and reliability claims. Objective: We use Autonomous Vehicles (AVs) as a current example to revisit the problem of demonstrating high reliability. AVs are making their debut on public roads: methods for assessing whether an AV is safe enough are urgently needed. We demonstrate how to answer 5 questions that would arise in assessing an AV type, starting with those proposed by a highly-cited study. Method: We apply new theorems extending Conservative Bayesian Inference (CBI), which exploit the rigour of Bayesian methods while reducing the risk of involuntary misuse associated with now-common applications of Bayesian inference; we define additional conditions needed for applying these methods to AVs. Results: Prior knowledge can bring substantial advantages if the AV design allows strong expectations of safety before road testing. We also show how naive attempts at conservative assessment may lead to over-optimism instead; why extrapolating the trend of disengagements is not suitable for safety claims; use of knowledge that an AV has moved to a less stressful environment. Conclusion: While some reliability targets will remain too high to be practically verifiable, CBI removes a major source of doubt: it allows use of prior knowledge without inducing dangerously optimistic biases. For certain ranges of required reliability and prior beliefs, CBI thus supports feasible, sound arguments. Useful conservative claims can be derived from limited prior knowledge.