Research Analyzer
← Back ICRA 2026

CRASH: Context-Aware Recognition of Agents for Simulation of High‑risk Driving

Minhee Cho, Hayeon Jo, Dongbo Min

PDF

AI summary

Key figure (auto-extracted from paper)
CRASH replaces unrealistic future predictions and distance heuristics with a learning-based, context-aware selection method that generates significantly more realistic high-risk driving scenarios using only past and present data.
Adversarial agent selection Safety-critical simulation Context-aware modeling Autonomous vehicle testing Motion-aware masking Trajectory generation

Problem

Prior safety-critical scenario generation methods rely on infeasible future trajectory predictions and heuristic spatial proximity, producing implausible interactions that misalign with real-world driving dynamics and contextual risk.

Approach

CRASH filters out static agents via Motion-Aware Masking and uses a cross-attention module to probabilistically identify threatening agents based solely on historical and current interactions, jointly optimizing agent selection and trajectory generation.

Key results

  • First learnable framework for adversarial agent selection using only past and present observations
  • Motion-Aware Masking effectively filters static, non-threatening agents to reduce training noise
  • Adversarial agent Selection Module probabilistically estimates collision likelihood via cross-attention
  • Achieves ~65% collision success rate on nuScenes and Waymo, significantly outperforming STRIVE and DiffScene

Why it matters

Enables autonomous vehicle developers to efficiently stress-test safety-critical edge cases with realistic, context-aware simulations that align with real-world temporal constraints.

Abstract

Evaluating the safety of autonomous vehicles requires simulation of safety-critical scenarios such as po- tential collisions, which are difficult to reproduce in real- world environments. Prior methods rely on future trajectory predictions and heuristically select adversarial agents based on spatial proximity to the ego vehicle, often producing unrealistic scenarios that misalign with real-world temporal dynamics and contextual risk. To address these issues, we propose CRASH, the first learning-based adversarial agent selection approach that operates solely on past and present observations. It comprises two key components: (1) a Motion-Aware Masking (MAM) module that filters out static agents unlikely to collide with the ego vehicle due to negligible movement, and (2) an Adver- sarial agent Selection Module (ASM) that models contextual interactions to probabilistically estimate each agent’s likelihood of inducing a collision with the ego vehicle. Experiments on the nuScenes and Waymo datasets demonstrate that CRASH significantly improves the success rate of generating realistic collision scenarios under both replay and rule-based planners, validating the effectiveness of context-aware agent modeling without access to future information.

Index terms

Motion and Path Planning Task and Motion Planning Collision Avoidance

Related papers