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

TL;DR

TRACE is a pipeline that converts real-world crash reports into detailed CARLA simulations by leveraging map data and language models, creating a valuable benchmark for autonomous vehicle safety testing.

Contribution

It introduces a novel method for reconstructing real-world accidents into high-fidelity simulations using map data and language models, enabling better AV evaluation.

Findings

Curated a benchmark of 52 diverse accident scenarios.

Reconstructed accidents with accurate topologies and vehicle states.

Provided an open-source resource for AV safety validation.

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.