Multi-Context enhanced Lane-Changing prediction using a heterogeneous Graph Neural Network

• Published in: Expert systems with applications Vol. 264; p. 125902
• Main Authors: Dong, Yiqing, Han, Chengjia, Zhao, Chaoyang, Madan, Aayush, Mohanty, Lipi, Yang, Yaowen
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 10.03.2025
• Subjects: Attention mechanism; Heterogeneous graph neural network; Lane-changing prediction; Microscopic traffic load simulation; Multiple contexts; Transformer; Microscopic traffic load simulation; Attention mechanism; Lane-changing prediction; Transformer; Heterogeneous graph neural network; Multiple contexts

Lane-changing Prediction (LCP) is crucial in defining vehicle movement in Microscopic Traffic Load Simulation (MTLS), impacting the distribution of traffic load on bridge decks. Despite their simplicity, existing physics-based approaches are subjective and deterministic, resulting in low fidelity in...