# Adversarial Safety-Critical Scenario Generation using Naturalistic Human Driving Priors arXiv: https://arxiv.org/abs/2408.03200 ยท HTML: https://mlsanity.com/paper/2408.03200/ ## Key facts - Cited by 15 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 37 of its 104 references that are in the map. - First posted on arXiv 6 Aug 2024. ## Placed in - End-to-end autonomous driving / [Adversarial scenarios and safety testing](https://mlsanity.com/driving/adversarial-scenarios-and-safety-testing/) - Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/) ## Builds on (most cited first, 30 of 37) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019) - [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017) - [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014) - [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022) - [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015) - [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017) - [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016) - [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016) - [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017) - [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018) - [Residual Reinforcement Learning for Robot Control](https://mlsanity.com/paper/1812.03201/) (2018) - [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020) - [INTERACTION Dataset: An INTERnational, Adversarial and Cooperative moTION Dataset in Interactive Driving Scenarios with Semantic Maps](https://mlsanity.com/paper/1910.03088/) (2019) - [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) - [Meta-Sim: Learning to Generate Synthetic Datasets](https://mlsanity.com/paper/1904.11621/) (2019) - [Reverse KL-Divergence Training of Prior Networks: Improved Uncertainty and Adversarial Robustness](https://mlsanity.com/paper/1905.13472/) (2019) - [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022) - [Imitating Driver Behavior with Generative Adversarial Networks](https://mlsanity.com/paper/1701.06699/) (2017) - [Universal Adversarial Perturbations Against Semantic Image Segmentation](https://mlsanity.com/paper/1704.05712/) (2017) - [On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles](https://mlsanity.com/paper/2201.05057/) (2022) - [Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method](https://mlsanity.com/paper/2003.01197/) (2020) - [Milestones in Autonomous Driving and Intelligent Vehicles: Survey of Surveys](https://mlsanity.com/paper/2303.17220/) (2023) - [Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1902.00089/) (2019) - [Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation](https://mlsanity.com/paper/2009.08311/) (2020) - [Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning](https://mlsanity.com/paper/2010.03118/) (2020) - [Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios](https://mlsanity.com/paper/2004.06531/) (2020) - [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021) ## Built on by (most cited first, 15 of 15) - [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025) - [Generating Out-Of-Distribution Scenarios Using Language Models](https://mlsanity.com/paper/2411.16554/) (2024) - [Seeking to Collide: Online Safety-Critical Scenario Generation for Autonomous Driving with Retrieval Augmented Large Language Models](https://mlsanity.com/paper/2505.00972/) (2025) - [Safety-Critical Traffic Simulation with Guided Latent Diffusion Model](https://mlsanity.com/paper/2505.00515/) (2025) - [CounterScene: Counterfactual Causal Reasoning in Generative World Models for Safety-Critical Closed-Loop Evaluation](https://mlsanity.com/paper/2603.21104/) (2026) - [Safety2Drive: Safety-Critical Scenario Benchmark for the Evaluation of Autonomous Driving](https://mlsanity.com/paper/2505.13872/) (2025) - [LinguaSim: Interactive Multi-Vehicle Testing Scenario Generation via Natural Language Instruction Based on Large Language Models](https://mlsanity.com/paper/2510.08046/) (2025) - [Quantitative Representation of Scenario Difficulty for Autonomous Driving Based on Adversarial Policy Search](https://mlsanity.com/paper/2408.14000/) (2024) - [VCAT: Vulnerability-aware and Curiosity-driven Adversarial Training for Enhancing Autonomous Vehicle Robustness](https://mlsanity.com/paper/2409.12997/) (2024) - [Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety](https://mlsanity.com/paper/2503.00077/) (2025) - [Towards Benchmarking and Assessing the Safety and Robustness of Autonomous Driving on Safety-critical Scenarios](https://mlsanity.com/paper/2503.23708/) (2025) - [CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Development](https://mlsanity.com/paper/2504.03989/) (2025) - [Artificial Intelligence for Modeling and Simulation of Mixed Automated and Human Traffic](https://mlsanity.com/paper/2604.12857/) (2026) - [ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving](https://mlsanity.com/paper/2605.21168/) (2026) - [End-to-end Conditional Diffusion for Realistic and Controllable Visual Traffic Scenario Generation](https://mlsanity.com/paper/2607.18637/) (2026) ## Abstract (arXiv) Evaluating the decision-making system is indispensable in developing autonomous vehicles, while realistic and challenging safety-critical test scenarios play a crucial role. Obtaining these scenarios is non-trivial, thanks to the long-tailed distribution, sparsity, and rarity in real-world data sets. To tackle this problem, in this paper, we introduce a natural adversarial scenario generation solution using naturalistic human driving priors and reinforcement learning techniques. By doing this, we can obtain large-scale test scenarios that are both diverse and realistic. Specifically, we build a simulation environment that mimics natural traffic interaction scenarios. Informed by this environment, we implement a two-stage procedure. The first stage incorporates conventional rule-based models, e.g., IDM~(Intelligent Driver Model) and MOBIL~(Minimizing Overall Braking Induced by Lane changes) model, to coarsely and discretely capture and calibrate key control parameters from the real-world dataset. Next, we leverage GAIL~(Generative Adversarial Imitation Learning) to represent driver behaviors continuously. The derived GAIL can be further used to design a PPO~(Proximal Policy Optimization)-based actor-critic network framework to fine-tune the reward function, and then optimizes our natural adversarial scenario generation solution. Extensive experiments have been conducted in the NGSIM dataset including the trajectory of 3,000 vehicles. Essential traffic parameters were measured in comparison with the baseline model, e.g., the collision rate, accelerations, steering, and the number of lane changes. Our findings demonstrate that the proposed model can generate realistic safety-critical test scenarios covering both naturalness and adversariality, which can be a cornerstone for the development of autonomous vehicles.