mlsanityData to 14 Oct 2026

Scenario Generation for Testing of Autonomous Driving Systems Using Real-World Failure Records

arXiv 2606.31131 ↗First posted 30 Jun 2026cs.AI cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

To ensure safe on-road behavior, pre-deployment testing and failure discovery of Autonomous Driving Systems (ADS) is crucial. Present day simulation based testing methods focus largely on mathematical models for efficient search of optimal scenarios, assuming a fixed scenario representation. On the other hand, real-world testing involves substantial manual effort to design scenario templates for testing. These templates represent distinct failure scenarios consisting of pre-deployment vehicle movements, map types, etc. Historical failure records for ADS are a reliable source of real-world failure conditions, which can be used for scenario generation. In this work, we propose a scenario generation pipeline using categorical and contextual information available from historical records in natural language format. Our approach consists of modular LLM based synthetic scenario generation, compatible with the testing constraints of a given system. We successfully apply our method to generate a diverse set of scenarios for testing autonomous navigation on Metadrive simulator using the NHTSA ADS crash records. Our approach results in accurate and diverse scenario generation with a combination of 4 road types, 3 non ego vehicle movement types, including on road anomalies in the form of working zones. Generated scenarios align with the provided testing conditions, and reveals interesting failures of the system within a limited testing budget of 20 scenarios. Code is available at https://github.com/anjaliParashar/crash2scenario.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 34 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

15 of 34 references.

References · 15

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  3. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  4. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 290
  5. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 96
  6. 2018Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulationcited by 77
  7. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 71
  8. 2017Ontology based Scene Creation for the Development of Automated Vehiclescited by 40
  9. 2020Scenic: A Language for Scenario Specification and Data Generationcited by 40
  10. 2020Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systemscited by 35
  11. 2022How Do We Fail? Stress Testing Perception in Autonomous Vehiclescited by 18
  12. 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyondcited by 15
3 more
  1. 2021Finding Failures in High-Fidelity Simulation using Adaptive Stress Testing and the Backward Algorithmcited by 7
  2. 2020Generating Adversarial Disturbances for Controller Verificationcited by 4
  3. 2024Rate-Informed Discovery via Bayesian Adaptive Multifidelity Samplingcited by 3

Built on by

Not cited yet.