mlsanityData to 7 Oct 2026

Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehicles

arXiv 2102.03483 ↗First posted 6 Feb 2021cs.AI cs.LG cs.ROcited by 27

On the map: End-to-end autonomous driving → Adversarial scenarios and safety testing

Abstract (arXiv)

Testing and evaluation is a crucial step in the development and deployment of Connected and Automated Vehicles (CAVs). To comprehensively evaluate the performance of CAVs, it is of necessity to test the CAVs in safety-critical scenarios, which rarely happen in naturalistic driving environment. Therefore, how to purposely and systematically generate these corner cases becomes an important problem. Most existing studies focus on generating adversarial examples for perception systems of CAVs, whereas limited efforts have been put on the decision-making systems, which is the highlight of this paper. As the CAVs need to interact with numerous background vehicles (BVs) for a long duration, variables that define the corner cases are usually high dimensional, which makes the generation a challenging problem. In this paper, a unified framework is proposed to generate corner cases for the decision-making systems. To address the challenge brought by high dimensionality, the driving environment is formulated based on Markov Decision Process, and the deep reinforcement learning techniques are applied to learn the behavior policy of BVs. With the learned policy, BVs will behave and interact with the CAVs more aggressively, resulting in more corner cases. To further analyze the generated corner cases, the techniques of feature extraction and clustering are utilized. By selecting representative cases of each cluster and outliers, the valuable corner cases can be identified from all generated corner cases. Simulation results of a highway driving environment show that the proposed methods can effectively generate and identify the valuable corner cases.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Placed in Adversarial scenarios and safety testing, one of 9 directions in End-to-end autonomous driving. Builds on 24 of its 59 references that are in the map. First posted on arXiv 6 Feb 2021.

Builds on

24 of 59 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2015Continuous control with deep reinforcement learningcited by 3,279
  4. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  5. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  8. 2017Rainbow: Combining Improvements in Deep Reinforcement Learningcited by 774
  9. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
  10. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  11. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  12. 2017On a Formal Model of Safe and Scalable Self-driving Carscited by 129
12 more
  1. 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 90
  2. 2018Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulationcited by 76
  3. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  4. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 70
  5. 2017NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehiclescited by 48
  6. 2016Accelerated Evaluation of Automated Vehicles Safety in Lane Change Scenarios Based on Importance Sampling Techniquescited by 44
  7. 2019Testing Scenario Library Generation for Connected and Automated Vehicles, Part I: Methodologycited by 24
  8. 2019Testing Scenario Library Generation for Connected and Automated Vehicles, Part II: Case Studiescited by 10
  9. 2020Efficient statistical validation with edge cases to evaluate Highly Automated Vehiclescited by 8
  10. 2017Standard detectors aren't (currently) fooled by physical adversarial stop signscited by 7
  11. 2020Model Predictive Instantaneous Safety Metric for Evaluation of Automated Driving Systemscited by 4
  12. 2021Distributionally Consistent Simulation of Naturalistic Driving Environment for Autonomous Vehicle Testingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 6; 2024: 7; 2025: 8; 2026: 2.

27 papers.

Sort:

By area:

  1. 2022A Survey on Model-based Reinforcement Learningcited by 65
  2. 2025Reinforced Refinement with Self-Aware Expansion for End-to-End Autonomous Drivingcited by 19
  3. 2024Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priorscited by 15
  4. 2023Testing of Deep Reinforcement Learning Agents with Surrogate Modelscited by 12
  5. 2025From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarioscited by 8
  6. 2023(Re)2H2O: Autonomous Driving Scenario Generation via Reversely Regularized Hybrid Offline-and-Online Reinforcement Learningcited by 6
  7. 2024Generating Traffic Scenarios via In-Context Learning to Learn Better Motion Plannercited by 6
  8. 2022A-Eye: Driving with the Eyes of AI for Corner Case Generationcited by 5
  9. 2025Sim2Real Diffusion: Leveraging Foundation Vision Language Models for Adaptive Automated Drivingcited by 5
  10. 2021Building Safer Autonomous Agents by Leveraging Risky Driving Behavior Knowledgecited by 4
  11. 2023CC-SGG: Corner Case Scenario Generation using Learned Scene Graphscited by 4
  12. 2023Continual Driving Policy Optimization with Closed-Loop Individualized Curriculacited by 4
15 more
  1. 2025VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Drivingcited by 4
  2. 2023Stackelberg Driver Model for Continual Policy Improvement in Scenario-Based Closed-Loop Autonomous Drivingcited by 3
  3. 2024Adaptive Testing Environment Generation for Connected and Automated Vehicles with Dense Reinforcement Learningcited by 2
  4. 2024Edge Case Detection in Automated Driving: Methods, Challenges, and Future Directionscited by 2
  5. 2024CRASH: Challenging Reinforcement-Learning Based Adversarial Scenarios For Safety Hardeningcited by 2
  6. 2025AED: Automatic Discovery of Effective and Diverse Vulnerabilities for Autonomous Driving Policy with Large Language Modelscited by 2
  7. 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safetycited by 1
  8. 2025Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarioscited by 1
  9. 2021An NCAP-like Safety Indicator for Self-Driving Carscited by 0
  10. 2023Generating and Explaining Corner Cases Using Learnt Probabilistic Lane Graphscited by 0
  11. 2024Dynamically Expanding Capacity of Autonomous Driving with Near-Miss Focused Training Frameworkcited by 0
  12. 2024GraphSCENE: On-Demand Critical Scenario Generation for Autonomous Vehicles in Simulationcited by 0
  13. 2025CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Developmentcited by 0
  14. 2026ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testingcited by 0
  15. 2026OVPD: A Virtual-Physical Fusion Testing Dataset of OnSite Auton-omous Driving Challengecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026How corner is a corner case? Percentile control for highway scenario generation
  2. 2025Driving in Corner Case: A Real-World Adversarial Closed-Loop Evaluation Platform for End-to-End Autonomous Driving
  3. 2024Training Adversarial yet Safe Agent to Characterize Safety Performance of Highly Automated Vehicles
  4. 2023Evolving Testing Scenario Generation Method and Intelligence Evaluation Framework for Automated Vehicles
  5. 2024Realistic Corner Case Generation for Autonomous Vehicles with Multimodal Large Language Model
  6. 2022SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles
  7. 2023Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation
  8. 2021DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning