# KG-ASG: Collision-Knowledge-Guided Closed-Loop Adversarial Scenario Generation With Primary-Support Attribution

arXiv: https://arxiv.org/abs/2605.18895 · HTML: https://mlsanity.com/paper/2605.18895/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 19 of 19)

- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (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)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024)
- [On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles](https://mlsanity.com/paper/2201.05057/) (2022)
- ["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)
- [Asynchronous Large Language Model Enhanced Planner for Autonomous Driving](https://mlsanity.com/paper/2406.14556/) (2024)
- [AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion](https://mlsanity.com/paper/2410.08453/) (2024)
- [LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2501.15850/) (2025)
- [Safety-Critical Scenario Generation Via Reinforcement Learning Based Editing](https://mlsanity.com/paper/2306.14131/) (2023)
- [Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving](https://mlsanity.com/paper/2403.11057/) (2024)
- [CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models](https://mlsanity.com/paper/2502.15119/) (2025)
- [GOOSE: Goal-Conditioned Reinforcement Learning for Safety-Critical Scenario Generation](https://mlsanity.com/paper/2406.03870/) (2024)
- [SEAL: Towards Safe Autonomous Driving via Skill-Enabled Adversary Learning for Closed-Loop Scenario Generation](https://mlsanity.com/paper/2409.10320/) (2024)
- [Steerable Adversarial Scenario Generation through Test-Time Preference Alignment](https://mlsanity.com/paper/2509.20102/) (2025)
- [World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Driving](https://mlsanity.com/paper/2507.12762/) (2025)
- [Towards Full-Scenario Safety Evaluation of Automated Vehicles: A Volume-Based Method](https://mlsanity.com/paper/2506.09182/) (2025)

## Abstract (arXiv)

Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attributable multi-vehicle interactions. Existing safety-critical scenario generation methods often rely on low-level trajectory perturbations, collision-proxy optimization, or single-adversary search, which may produce adversarial samples with ambiguous collision causes or uncontrolled multi-vehicle collisions. This paper proposes KG-ASG, a collision-knowledge-guided closed-loop adversarial scenario generation framework with primary-support attribution. KG-ASG constructs a structured collision knowledge base and trains a lightweight Collision Expert to infer the target collision mode, the unique primary adversary, support vehicles, and their interaction roles. Guided by this semantic prior, multi-vehicle adversarial generation is formulated as a primary-support process, where the primary adversary induces the main conflict and support vehicles shape the surrounding risk structure without becoming additional colliders. Rule, physical, interaction-safety, and single-collider constraints are imposed as hard gates to filter non-executable samples. To handle reactive ego behaviors, planner-controller feedback is further used for failure diagnosis, candidate re-ranking, and terminal refinement. Experiments on WOMD scenarios reconstructed in MetaDrive show that KG-ASG achieves strong adversarial effectiveness while improving Valid Primary Attack, reducing multi-collision, and obtaining closed-loop recovery gains under IDM, Cruise, and Expert controllers. These results demonstrate that collision-knowledge guidance and primary-support single-collider reasoning improve adversarial effectiveness, interpretability, and executability for autonomous driving safety validation.