# Interpretable Safety Validation for Autonomous Vehicles

arXiv: https://arxiv.org/abs/2004.06805 · HTML: https://mlsanity.com/paper/2004.06805/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions](https://mlsanity.com/paper/2112.11561/) (2021)
- [Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review](https://mlsanity.com/paper/2402.10086/) (2024)
- [Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction](https://mlsanity.com/paper/2409.00265/) (2024)
- [The Reasonable Crowd: Towards evidence-based and interpretable models of driving behavior](https://mlsanity.com/paper/2107.13507/) (2021)
- [Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms](https://mlsanity.com/paper/2210.16575/) (2022)
- [Learning Temporal Logic Predicates from Data with Statistical Guarantees](https://mlsanity.com/paper/2406.10449/) (2024)
- [Diffusion Models for Safety Validation of Autonomous Driving Systems](https://mlsanity.com/paper/2506.08459/) (2025)

## Abstract (arXiv)

An open problem for autonomous driving is how to validate the safety of an autonomous vehicle in simulation. Automated testing procedures can find failures of an autonomous system but these failures may be difficult to interpret due to their high dimensionality and may be so unlikely as to not be important. This work describes an approach for finding interpretable failures of an autonomous system. The failures are described by signal temporal logic expressions that can be understood by a human, and are optimized to produce failures that have high likelihood. Our methodology is demonstrated for the safety validation of an autonomous vehicle in the context of an unprotected left turn and a crosswalk with a pedestrian. Compared to a baseline importance sampling approach, our methodology finds more failures with higher likelihood while retaining interpretability.