mlsanityData to 7 Oct 2026

SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation

arXiv 2409.10320 ↗First posted 16 Sep 2024cs.RO cs.AI cs.LGcited by 10

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

Abstract (arXiv)

Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies through closed-loop training. However, existing approaches for scenario generation rely on simplistic objectives, resulting in overly-aggressive or non-reactive adversarial behaviors. To generate diverse adversarial yet realistic scenarios, we propose SEAL, a scenario perturbation approach which leverages learned objective functions and adversarial, human-like skills. SEAL-perturbed scenarios are more realistic than SOTA baselines, leading to improved ego task success across real-world, in-distribution, and out-of-distribution scenarios, of more than 20%. To facilitate future research, we release our code and tools: https://github.com/cmubig/SEAL

Key facts. Cited by 10 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 38 of its 56 references that are in the map. First posted on arXiv 16 Sep 2024.

Builds on

38 of 56 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation12 Apr
  2. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectories19 Mar
  3. 2023CAT: Closed-loop Adversarial Training for Safe End-to-End Driving19 Oct
  4. 2021Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior9 Dec

Other references · 34

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  2. 2023Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecastingcited by 701
  3. 2021Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Datasetcited by 532
  4. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  5. 2021NuPlan: A closed-loop ML-based planning benchmark for autonomous vehiclescited by 485
  6. 2021DenseTNT: End-to-end Trajectory Prediction from Dense Goal Setscited by 292
  7. 2021MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learningcited by 281
  8. 2021TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviorscited by 192
  9. 2022Guided Conditional Diffusion for Controllable Traffic Simulationcited by 189
  10. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  11. 2021AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehiclescited by 132
  12. 2022Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarioscited by 124
22 more
  1. 2023Language-Guided Traffic Simulation via Scene-Level Diffusioncited by 110
  2. 2022A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspectivecited by 100
  3. 2024DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Drivingcited by 98
  4. 2022KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradientscited by 95
  5. 2023The Waymo Open Sim Agents Challengecited by 86
  6. 2022BITS: Bi-level Imitation for Traffic Simulationcited by 80
  7. 2020Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Methodcited by 74
  8. 2019Adaptive Stress Testing for Autonomous Vehiclescited by 70
  9. 2020Diverse and Admissible Trajectory Forecasting through Multimodal Context Understandingcited by 68
  10. 2022"Curse of rarity" for autonomous vehiclescited by 62
  11. 2022AdvDO: Realistic Adversarial Attacks for Trajectory Predictioncited by 48
  12. 2023SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversariescited by 36
  13. 2022Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Roboticscited by 23
  14. 2022Interpretable Self-Aware Neural Networks for Robust Trajectory Predictioncited by 22
  15. 2021Testing of Autonomous Driving Systems: Where Are We and Where Should We Go?cited by 19
  16. 2021Safe Autonomous Racing via Approximate Reachability on Ego-visioncited by 13
  17. 2023Improving the Generalizability of Trajectory Prediction Models with Frenet-Based Domain Normalizationcited by 13
  18. 2022Quantifying Safety of Learning-based Self-Driving Control Using Almost-Barrier Functionscited by 10
  19. 2024GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generationcited by 10
  20. 2023SafeShift: Safety-Informed Distribution Shifts for Robust Trajectory Prediction in Autonomous Drivingcited by 9
  21. 2023Industry Practices for Challenging Autonomous Driving Systems with Critical Scenarioscited by 8
  22. 2022Distribution-aware Goal Prediction and Conformant Model-based Planning for Safe Autonomous Drivingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 7.

10 papers.

  1. 2025Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Modelscited by 7
  2. 2024Adversarial and Reactive Traffic Entities for Behavior-Realistic Driving Simulation: A Reviewcited by 3
  3. 2026ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Drivingcited by 3
  4. 2025Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledgecited by 1
  5. 2026World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planningcited by 1
  6. 2026KG-ASG: Collision-Knowledge-Guided Closed-Loop Adversarial Scenario Generation With Primary-Support Attributioncited by 0
  7. 2026ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Drivingcited by 0
  8. 2026EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agentscited by 0
  9. 2026CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generationcited by 0
  10. 2026Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026From Attacks to Curricula: Learnability-Guided Adversarial Training for Safe Autonomous Driving
  2. 2025AuthSim: Towards Authentic and Effective Safety-critical Scenario Generation for Autonomous Driving Tests
  3. 2026Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles
  4. 2024AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion
  5. 2026SaFeR: Safety-Critical Scenario Generation for Autonomous Driving Test via Feasibility-Constrained Token Resampling
  6. 2025LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models
  7. 2025From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios
  8. 2026VILTA: A VLM-in-the-Loop Adversary for Enhancing Driving Policy Robustness