Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World
Not on the map. Why?
Abstract (arXiv)
We present a new approach to automated scenario-based testing of the safety of autonomous vehicles, especially those using advanced artificial intelligence-based components, spanning both simulation-based evaluation as well as testing in the real world. Our approach is based on formal methods, combining formal specification of scenarios and safety properties, algorithmic test case generation using formal simulation, test case selection for track testing, executing test cases on the track, and analyzing the resulting data. Experiments with a real autonomous vehicle at an industrial testing facility support our hypotheses that (i) formal simulation can be effective at identifying test cases to run on the track, and (ii) the gap between simulated and real worlds can be systematically evaluated and bridged.
Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). First posted on arXiv 17 Mar 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 8; 2022: 3; 2023: 7; 2024: 5; 2025: 6; 2026: 9.
38 papers.
Sort:
By area:
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 94
- 2021Software Engineering for AI-Based Systems: A Surveycited by 68
- 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 55
- 2023Testing Language Model Agents Safely in the Wildcited by 45
- 2022RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systemscited by 23
- 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
- 2021Statistical Perspectives on Reliability of Artificial Intelligence Systemscited by 10
- 2023Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulationcited by 10
- 2024LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trendscited by 10
- 2021Parallel and Multi-Objective Falsification with Scenic and VerifAIcited by 8
- 2021A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulationcited by 6
- 2022Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logiccited by 5
26 more
- 2022Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysiscited by 5
- 2021Coverage-based Scene Fuzzing for Virtual Autonomous Driving Testingcited by 4
- 2023Continual Driving Policy Optimization with Closed-Loop Individualized Curriculacited by 4
- 2021Querying Labelled Data with Scenario Programs for Sim-to-Real Validationcited by 3
- 2023SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stackscited by 3
- 2023Pedestrian and Passenger Interaction with Autonomous Vehicles: Field Study in a Crosswalk Scenariocited by 2
- 2025Scenario-based Compositional Verification of Autonomous Systems with Neural Perceptioncited by 2
- 2021SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testingcited by 1
- 2024A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)cited by 1
- 2024Representation Alignment Contrastive Regularization for Multi-Object Trackingcited by 1
- 2024Flow to Rare Events: An Application of Normalizing Flow in Temporal Importance Sampling for Automated Vehicle Validationcited by 1
- 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Testscited by 1
- 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safetycited by 1
- 2025From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Drivingcited by 1
- 2025A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Drivingcited by 1
- 2026Warm Starting State-Space Models with Automata Learningcited by 1
- 2026Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational modelcited by 1
- 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspectivecited by 1
- 2023Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulationscited by 0
- 2025Path Diffuser: Diffusion Model for Data-Driven Traffic Simulatorcited by 0
- 2026Emergency Lane-Change Simulation: A Behavioral Guidance Approach for Risky Scenario Generationcited by 0
- 2026SPHINX: First Explain, Then Explorecited by 0
- 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levelscited by 0
- 2026Emotion in an active inference model of human drivingcited by 0
- 2026SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networkscited by 0
- 2026SimVerity: When Does Simulated Agent Success Survive Physical Deployment?cited by 0
- 2026SimVerity: When Does Simulated Agent Success Survive Physical Deployment?25 Aug 2026
- 2026SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks10 Aug 2026
- 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels28 Jul 2026
- 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective7 Jul 2026
- 2026SPHINX: First Explain, Then Explore16 Jun 2026
- 2026Emotion in an active inference model of human driving9 Jun 2026
- 2026Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model21 Apr 2026
- 2026Emergency Lane-Change Simulation: A Behavioral Guidance Approach for Risky Scenario Generation8 Mar 2026
- 2026Warm Starting State-Space Models with Automata Learning5 Mar 2026
- 2025Path Diffuser: Diffusion Model for Data-Driven Traffic Simulator29 Sep 2025
- 2025A Hierarchical Test Platform for Vision Language Model (VLM)-Integrated Real-World Autonomous Driving17 Jun 2025
- 2025From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving28 May 2025
26 more
- 2025Scenario-based Compositional Verification of Autonomous Systems with Neural Perception29 Apr 2025
- 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests28 Feb 2025
- 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety27 Feb 2025
- 2024LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends20 Oct 2024
- 2024Flow to Rare Events: An Application of Normalizing Flow in Temporal Importance Sampling for Automated Vehicle Validation10 Jul 2024
- 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems10 May 2024
- 2024Representation Alignment Contrastive Regularization for Multi-Object Tracking3 Apr 2024
- 2024A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)24 Jan 2024
- 2023Pedestrian and Passenger Interaction with Autonomous Vehicles: Field Study in a Crosswalk Scenario11 Dec 2023
- 2023Testing Language Model Agents Safely in the Wild17 Nov 2023
- 2023Continual Driving Policy Optimization with Closed-Loop Individualized Curricula25 Sep 2023
- 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligence2 May 2023
- 2023Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulation24 Mar 2023
- 2023SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stacks27 Feb 2023
- 2023Finding Needles in Haystack: Formal Generative Models for Efficient Massive Parallel Simulations3 Jan 2023
- 2022RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systems11 Nov 2022
- 2022Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysis4 Nov 2022
- 2022Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic29 Jun 2022
- 2021Querying Labelled Data with Scenario Programs for Sim-to-Real Validation1 Dec 2021
- 2021Statistical Perspectives on Reliability of Artificial Intelligence Systems9 Nov 2021
- 2021A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulation28 Oct 2021
- 2021Parallel and Multi-Objective Falsification with Scenic and VerifAI9 Jul 2021
- 2021SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testing5 Jul 2021
- 2021Taxonomy of Machine Learning Safety: A Survey and Primer9 Jun 2021
- 2021Coverage-based Scene Fuzzing for Virtual Autonomous Driving Testing2 Jun 2021
- 2021Software Engineering for AI-Based Systems: A Survey5 May 2021
- 2024LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trendscited by 10
- 2023Continual Driving Policy Optimization with Closed-Loop Individualized Curriculacited by 4
- 2023SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stackscited by 3
- 2021SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testingcited by 1
- 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Testscited by 1
- 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspectivecited by 1
- 2026Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective7 Jul 2026
- 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests28 Feb 2025
- 2024LLM4AD: Large Language Models for Autonomous Driving -- Concept, Review, Benchmark, Experiments, and Future Trends20 Oct 2024
- 2023Continual Driving Policy Optimization with Closed-Loop Individualized Curricula25 Sep 2023
- 2023SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stacks27 Feb 2023
- 2021SilGAN: Generating driving maneuvers for scenario-based software-in-the-loop testing5 Jul 2021
- 2023Testing Language Model Agents Safely in the Wildcited by 45
- 2023Testing Language Model Agents Safely in the Wild17 Nov 2023
- 2026SPHINX: First Explain, Then Explorecited by 0
- 2026SPHINX: First Explain, Then Explore16 Jun 2026
- 2021Software Engineering for AI-Based Systems: A Surveycited by 68
- 2023How Simulation Helps Autonomous Driving:A Survey of Sim2real, Digital Twins, and Parallel Intelligencecited by 55
- 2022RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systemscited by 23
- 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
- 2021Statistical Perspectives on Reliability of Artificial Intelligence Systemscited by 10
- 2023Editing Driver Character: Socially-Controllable Behavior Generation for Interactive Traffic Simulationcited by 10
- 2021Parallel and Multi-Objective Falsification with Scenic and VerifAIcited by 8
- 2021A Scenario-Based Platform for Testing Autonomous Vehicle Behavior Prediction Models in Simulationcited by 6
- 2022Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logiccited by 5
- 2022Discovering Closed-Loop Failures of Vision-Based Controllers via Reachability Analysiscited by 5
- 2021Coverage-based Scene Fuzzing for Virtual Autonomous Driving Testingcited by 4
- 2021Querying Labelled Data with Scenario Programs for Sim-to-Real Validationcited by 3
12 most cited of 26 All 26 (JSON)
- 2026SimVerity: When Does Simulated Agent Success Survive Physical Deployment?25 Aug 2026
- 2026SeFaR: Semantic Feature-aware Robustness Testing of Deep Neural Networks10 Aug 2026
- 2026Towards Trustworthy Embodied Intelligence: A Systems Framework and Graded Trustworthiness Levels28 Jul 2026
- 2026Emotion in an active inference model of human driving9 Jun 2026
- 2026Resolving space-sharing conflicts in road user interactions through uncertainty reduction: An active inference-based computational model21 Apr 2026
- 2026Emergency Lane-Change Simulation: A Behavioral Guidance Approach for Risky Scenario Generation8 Mar 2026
- 2026Warm Starting State-Space Models with Automata Learning5 Mar 2026
- 2025Scenario-based Compositional Verification of Autonomous Systems with Neural Perception29 Apr 2025
- 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety27 Feb 2025
- 2024Flow to Rare Events: An Application of Normalizing Flow in Temporal Importance Sampling for Automated Vehicle Validation10 Jul 2024
- 2024Representation Alignment Contrastive Regularization for Multi-Object Tracking3 Apr 2024
- 2024A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)24 Jan 2024
12 newest of 26 All 26 (JSON)