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

2026-04-23

AI Summary

This work addresses the lack of high-fidelity, safety-critical scenarios in autonomous driving validation that accurately reflect the topological complexity of real-world accidents. We propose a novel method that, for the first time, integrates OpenStreetMap’s precise road network, the reasoning capabilities of large language models for inferring vehicle initial states, and NHTSA’s semi-structured crash reports to automatically reconstruct both the topological structure and dynamic progression of real traffic incidents. These reconstructions are then instantiated as high-fidelity simulation scenarios in CARLA. Leveraging this approach, we introduce an open-source benchmark suite comprising 52 diverse collision types, road topologies, and pre-crash maneuvers, offering a realistic and challenging testbed for evaluating autonomous driving systems.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Sampling/Simulation-based Search
• Application Domains: Transportation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization

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.

Problem

• Autonomous Vehicles
• Accident Reconstruction
• Road Topology
• Safety-critical Scenarios
• CARLA Simulation

Innovation

• topology-aware reconstruction
• CARLA simulation
• Large Language Models
• autonomous vehicle evaluation
• accident benchmarking