Advanced Tool for Traffic Crash Analysis: An AI-Driven Multi-Agent Approach to Pre-Crash Reconstruction

2025-11-13

AI Summary

Traditional traffic accident reconstruction relies heavily on expert knowledge, resulting in poor consistency and limited robustness when processing fragmented, multimodal, and often conflicting scene data—including textual reports, structured tables,现场 photographs, and event data recorder (EDR) time-series measurements. This paper proposes a two-stage multi-agent AI framework that integrates natural language generation with deep causal reasoning to enable automatic, interpretable reconstruction of pre-collision scenarios. Our method resolves conflicts across heterogeneous EDR sources, achieving 100% accuracy in both event identification and collision role assignment—surpassing human expert performance. Evaluated on 39 complex rear-end collisions, the framework demonstrates high precision and strong robustness: it maintains reliable inference even under significant data incompleteness or measurement errors. The approach advances automated forensic analysis by unifying symbolic reasoning, probabilistic causality, and multimodal fusion within an explainable, agent-based architecture.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Traffic collision reconstruction traditionally relies on human expertise, often yielding inconsistent results when analyzing incomplete multimodal data. This study develops a multi-agent AI framework that reconstructs pre-crash scenarios and infers vehicle behaviors from fragmented collision data. We present a two-phase collaborative framework combining reconstruction and reasoning phases. The system processes 277 rear-end lead vehicle deceleration (LVD) collisions from the Crash Investigation Sampling System, integrating textual crash reports, structured tabular data, and visual scene diagrams. Phase I generates natural-language crash reconstructions from multimodal inputs. Phase II performs in-depth crash reasoning by combining these reconstructions with temporal Event Data Recorder (EDR).For validation, we applied it to all LVD cases, focusing on a subset of 39 complex crashes where multiple EDR records per collision introduced ambiguity (e.g., due to missing or conflicting data).The evaluation of the 39 LVD crash cases revealed our framework achieved perfect accuracy across all test cases, successfully identifying both the most relevant EDR event and correctly distinguishing striking versus struck vehicles, surpassing the 92% accuracy achieved by human researchers on the same challenging dataset. The system maintained robust performance even when processing incomplete data, including missing or erroneous EDR records and ambiguous scene diagrams. This study demonstrates superior AI capabilities in processing heterogeneous collision data, providing unprecedented precision in reconstructing impact dynamics and characterizing pre-crash behaviors.

Problem

• Reconstructs pre-crash scenarios from fragmented multimodal collision data
• Infers vehicle behaviors using AI-driven multi-agent collaborative framework
• Processes incomplete data including missing EDR records and ambiguous diagrams

Innovation

• Multi-agent AI framework reconstructs pre-crash scenarios from fragmented data
• Two-phase system combines multimodal reconstruction with temporal reasoning
• Achieves perfect accuracy in complex crash analysis surpassing human experts