Vehicle-group-based Crash Risk Prediction and Interpretation on Highways

2024-02-19

AI Summary

Predicting collision risk in multi-vehicle continuous interactions on highways remains challenging due to limitations of conventional segment-level modeling. Method: This paper proposes a dynamic vehicle group (VG)-based risk analysis framework, introducing an influence-driven vehicle grouping strategy and a VG-level risk aggregation model that jointly integrates the improved time-to-collision (iTTC) metric, logistic regression, and graph neural networks (GNNs). To enhance interpretability, GNNExplainer is incorporated to quantify the directional contribution of individual vehicles to group-level risk. Contribution/Results: The proposed framework achieves an AUC exceeding 0.93 for VG-level risk prediction, enabling millisecond-scale real-time collision warnings and fine-grained causal attribution. It establishes a novel paradigm for proactive safety in cooperative connected and autonomous vehicle (CAV) and unmanned aerial vehicle (UAV) systems.

Technology Category

• Planning, Routing, and Scheduling: Model-Based Reasoning
• Computer Vision: Interpretability, Explainability, and Transparency
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Previous studies in predicting crash risks primarily associated the number or likelihood of crashes on a road segment with traffic parameters or geometric characteristics, usually neglecting the impact of vehicles' continuous movement and interactions with nearby vehicles. Recent technology advances, such as Connected and Automated Vehicles (CAVs) and Unmanned Aerial Vehicles (UAVs) are able to collect high-resolution trajectory data, which enables trajectory-based risk analysis. This study investigates a new vehicle group (VG) based risk analysis method and explores risk evolution mechanisms considering VG features. An impact-based vehicle grouping method is proposed to cluster vehicles into VGs by evaluating their responses to the erratic behaviors of nearby vehicles. The risk of a VG is aggregated based on the risk between each vehicle pair in the VG, measured by inverse Time-to-Collision (iTTC). A Logistic Regression and a Graph Neural Network (GNN) are then employed to predict VG risks using aggregated and disaggregated VG information. Both methods achieve excellent performance with AUC values exceeding 0.93. For the GNN model, GNNExplainer with feature perturbation is applied to identify critical individual vehicle features and their directional impact on VG risks. Overall, this research contributes a new perspective for identifying, predicting, and interpreting traffic risks.

Problem

• Collision risk prediction
• Inter-vehicle interaction
• Highway traffic

Innovation

• Vehicle Group Risk Analysis
• Graph Neural Network
• Predictive Modeling