TRACE: Topology-aware Reconstruction of Accidents in CARLA for AV Evaluation

arXiv cs.RO / 4/27/2026

💬 OpinionDeveloper Stack & InfrastructureTools & Practical UsageModels & Research

共有:

Key Points

The TRACE pipeline reconstructs real NHTSA crash reports into high-fidelity CARLA simulations to better cover rare, safety-critical AV scenarios.
It preserves real-world road topology by retrieving site-specific OpenStreetMap data, avoiding overly simplified or abstract geometry used in prior benchmarks.
TRACE uses Large Language Models to infer each involved vehicle’s initial state from road geometry and pre-crash maneuvers described in reports.
From semi-structured crash-report information, it generates simulation trajectories and curates an open-source benchmark of 52 diverse accident scenarios for AV evaluation.
The resulting dataset is intended to provide a more challenging and realistic testbed for assessing AV systems against real-world failure modes.

Abstract

Validating Autonomous Vehicles (AVs) requires exposure to rare, safety-critical scenarios, infrequent in routine driving data. Existing benchmarks address this by generating synthetic conflicts or mapping accident descriptions to abstract road geometries, failing to capture the topological complexity of real-world crashes. We introduce TRACE , a pipeline that automates the reconstruction of NHTSA crash reports into high-fidelity CARLA simulations by (1) retrieving site-specific OpenStreetMap data to preserve exact road topology, (2) leveraging Large Language Models to infer vehicles' initial state from road geometry and pre-crash maneuvers, and (3) generating simulation trajectories from semi-structured report data. Using this pipeline, we curated a benchmark of 52 diverse accident scenarios covering varied collision types, road topologies, and pre-crash maneuvers, providing a challenging open source resource for testing AV systems against real-world failures.