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

Abstract

Evaluating the safety of autonomous vehicles requires simulation of safety-critical scenarios such as potential 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 Adversarial 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.