mlsanityData to 7 Oct 2026

ECSAS: Exploring Critical Scenarios from Action Sequence in Autonomous Driving

arXiv 2209.10078 ↗First posted 21 Sep 2022cs.AI cs.LG cs.PLcited by 2

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

Abstract (arXiv)

Critical scenario generation requires the ability of sampling critical combinations from the infinite parameter space in the logic scenario. Existing solutions aim to explore the correlation of action parameters in the initial scenario rather than action sequences. How to model action sequences so that one can further consider the effects of different action parameters in the scenario is the bottleneck of the problem. In this paper, we attack the problem by proposing the ECSAS framework. Specifically, we first propose a description language, BTScenario, allowing us to model action sequences of the scenarios. We then use reinforcement learning to search for combinations of critical action parameters. To increase efficiency, we further propose several optimizations, including action masking and replay buffer. We have implemented ECSAS, and experimental results show that it is more efficient than native approaches such as random and combination testing in various nontrivial scenarios.

Key facts. Cited by 2 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 20 of its 41 references that are in the map. First posted on arXiv 21 Sep 2022.

Builds on

20 of 41 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior9 Dec

Other references · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  3. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  4. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 95
  5. 2018Scenic: A Language for Scenario Specification and Scene Generationcited by 79
  6. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  7. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 70
  8. 2020Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluationcited by 54
  9. 2020A Survey of Behavior Trees in Robotics and AIcited by 53
  10. 2018Scenarios for Development, Test and Validation of Automated Vehiclescited by 45
  11. 2020Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarioscited by 42
  12. 2020Scenic: A Language for Scenario Specification and Data Generationcited by 39
7 more
  1. 2019Failure-Scenario Maker for Rule-Based Agent using Multi-agent Adversarial Reinforcement Learning and its Application to Autonomous Drivingcited by 36
  2. 20206-Layer Model for a Structured Description and Categorization of Urban Traffic and Environmentcited by 26
  3. 2020Training Adversarial Agents to Exploit Weaknesses in Deep Control Policiescited by 24
  4. 2021CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generationcited by 20
  5. 2019Efficient Autonomy Validation in Simulation with Adaptive Stress Testingcited by 13
  6. 2021Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Reviewcited by 12
  7. 2021Optimized Execution of PDDL Plans using Behavior Treescited by 4

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safetycited by 1
  2. 2025CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Developmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Learning Critical Scenarios in Feedback Control Systems for Automated Driving
  2. 2026SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
  3. 2022Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving
  4. 2022A Real-time Critical-scenario-generation Framework for Testing Autonomous Driving System
  5. 2026SimWAM: A Simple World Action Model for End-to-End Autonomous Driving
  6. 2026Safety-Critical Scenarios Emerge from Initial Scenes ↗
  7. 2024Generating Critical Scenarios for Testing Automated Driving Systems
  8. 2026DriveMA: Driving Vision-Language-Action Models with verifiable Meta-Actions