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

arXiv: https://arxiv.org/abs/2409.10320 · HTML: https://mlsanity.com/paper/2409.10320/

## Key facts

- Cited by 10 papers in the map (data through 14 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.

## Placed in

- End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/)

## Builds on (most cited first, 30 of 38)

- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting](https://mlsanity.com/paper/2301.00493/) (2023)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets](https://mlsanity.com/paper/2108.09640/) (2021)
- [MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning](https://mlsanity.com/paper/2109.12674/) (2021)
- [TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors](https://mlsanity.com/paper/2101.06557/) (2021)
- [Guided Conditional Diffusion for Controllable Traffic Simulation](https://mlsanity.com/paper/2210.17366/) (2022)
- [Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?](https://mlsanity.com/paper/2006.14911/) (2020)
- [Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior](https://mlsanity.com/paper/2112.05077/) (2021)
- [AdvSim: Generating Safety-Critical Scenarios for Self-Driving Vehicles](https://mlsanity.com/paper/2101.06549/) (2021)
- [Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios](https://mlsanity.com/paper/2212.11419/) (2022)
- [Language-Guided Traffic Simulation via Scene-Level Diffusion](https://mlsanity.com/paper/2306.06344/) (2023)
- [A Survey on Safety-Critical Driving Scenario Generation -- A Methodological Perspective](https://mlsanity.com/paper/2202.02215/) (2022)
- [DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving](https://mlsanity.com/paper/2408.00415/) (2024)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [The Waymo Open Sim Agents Challenge](https://mlsanity.com/paper/2305.12032/) (2023)
- [BITS: Bi-level Imitation for Traffic Simulation](https://mlsanity.com/paper/2208.12403/) (2022)
- [Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method](https://mlsanity.com/paper/2003.01197/) (2020)
- [Adaptive Stress Testing for Autonomous Vehicles](https://mlsanity.com/paper/1902.01909/) (2019)
- [Diverse and Admissible Trajectory Forecasting through Multimodal Context Understanding](https://mlsanity.com/paper/2003.03212/) (2020)
- ["Curse of rarity" for autonomous vehicles](https://mlsanity.com/paper/2207.02749/) (2022)
- [CAT: Closed-loop Adversarial Training for Safe End-to-End Driving](https://mlsanity.com/paper/2310.12432/) (2023)
- [AdvDO: Realistic Adversarial Attacks for Trajectory Prediction](https://mlsanity.com/paper/2209.08744/) (2022)
- [SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries](https://mlsanity.com/paper/2401.00391/) (2023)
- [Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics](https://mlsanity.com/paper/2211.02231/) (2022)
- [Interpretable Self-Aware Neural Networks for Robust Trajectory Prediction](https://mlsanity.com/paper/2211.08701/) (2022)
- [Testing of Autonomous Driving Systems: Where Are We and Where Should We Go?](https://mlsanity.com/paper/2106.12233/) (2021)
- [Enhancing Autonomous Vehicle Training with Language Model Integration and Critical Scenario Generation](https://mlsanity.com/paper/2404.08570/) (2024)

## Built on by (most cited first, 10 of 10)

- [Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Models](https://mlsanity.com/paper/2505.00972/) (2025)
- [Adversarial and Reactive Traffic Entities for Behavior-Realistic Driving Simulation: A Review](https://mlsanity.com/paper/2409.14196/) (2024)
- [ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving](https://mlsanity.com/paper/2603.15221/) (2026)
- [Learning from Risk: LLM-Guided Generation of Safety-Critical Scenarios with Prior Knowledge](https://mlsanity.com/paper/2511.20726/) (2025)
- [World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning](https://mlsanity.com/paper/2607.10630/) (2026)
- [KG-ASG: Collision-Knowledge-Guided Closed-Loop Adversarial Scenario Generation With Primary-Support Attribution](https://mlsanity.com/paper/2605.18895/) (2026)
- [ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving](https://mlsanity.com/paper/2605.21168/) (2026)
- [EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents](https://mlsanity.com/paper/2606.03678/) (2026)
- [CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation](https://mlsanity.com/paper/2609.02270/) (2026)
- [Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation](https://mlsanity.com/paper/2609.06433/) (2026)

## 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