用时空图神经网络预测自动驾驶车祸严重程度，精度超97%。
ST-GraphNet: A Spatio-Temporal Graph Neural Network for Understanding and Predicting Automated Vehicle Crash Severity
- 构建细粒度与粗粒度双图结构，融合时空邻近与区域聚合信息。
- 在德州2352起真实事故数据上，模型准确率达97.74%，显著优于基线。
- 适合交通安全部门、智能网联汽车研发者参考，用于高风险区域识别。
理解自动驾驶车辆（AV）事故严重性的时空动态对提升城市交通安全性与基础设施规划至关重要。本文提出ST-GraphNet，一种基于时空图神经网络的框架，通过细粒度与区域聚合的空间图联合建模来预测事故严重程度。利用来自德克萨斯州（2024年）的2,352起真实自动驾驶相关事故报告，包含地理坐标、时间戳、SAE自动化等级及文本描述，我们构建了两种互补图表示：(1) 细粒度图，以单个事故为节点，基于时空邻近性建立边；(2) 粗粒度图，将事故聚类至基于H3网格的空间单元，并通过六边形邻接连接。每个节点融合多模态特征，包括从事故描述中提取的Sentence-BERT文本嵌入。我们评估了GCN、GAT和DSTGCN等不同图神经网络架构，在分类事故严重程度与预测高风险区域方面表现优异。所提出的ST-GraphNet采用基于粗粒度H3图的DSTGCN主干，测试准确率达97.74%，远超最佳细粒度模型（64.7%）。结果表明，空间聚合、动态消息传递与多模态特征融合能有效捕捉自动驾驶事故背后的复杂时空模式。
原文摘要 · Abstract (English)
Understanding the spatial and temporal dynamics of automated vehicle (AV) crash severity is critical for advancing urban mobility safety and infrastructure planning. In this work, we introduce ST-GraphNet, a spatio-temporal graph neural network framework designed to model and predict AV crash severity by using both fine-grained and region-aggregated spatial graphs. Using a balanced dataset of 2,352 real-world AV-related crash reports from Texas (2024), including geospatial coordinates, crash timestamps, SAE automation levels, and narrative descriptions, we construct two complementary graph representations: (1) a fine-grained graph with individual crash events as nodes, where edges are defined via spatio-temporal proximity; and (2) a coarse-grained graph where crashes are aggregated into Hexagonal Hierarchical Spatial Indexing (H3)-based spatial cells, connected through hexagonal adjacency. Each node in the graph is enriched with multimodal data, including semantic, spatial, and temporal attributes, including textual embeddings from crash narratives using a pretrained Sentence-BERT model. We evaluate various graph neural network (GNN) architectures, such as Graph Convolutional Networks (GCN), Graph Attention Networks (GAT), and Dynamic Spatio-Temporal GCN (DSTGCN), to classify crash severity and predict high-risk regions. Our proposed ST-GraphNet, which utilizes a DSTGCN backbone on the coarse-grained H3 graph, achieves a test accuracy of 97.74\%, substantially outperforming the best fine-grained model (64.7\% test accuracy). These findings highlight the effectiveness of spatial aggregation, dynamic message passing, and multi-modal feature integration in capturing the complex spatio-temporal patterns underlying AV crash severity.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。