Multi-context enhanced lane-changing prediction using a heterogeneous graph neural network

• Main Authors: Dong, Yiqing, Han, Chengjia, Zhao, Chaoyang, Madan, Aayush, Mohanty, Lipi, Yang, Yaowen
• Other Authors: School of Civil and Environmental Engineering
• Format: Article
• Language: English
• Published: 2025
• Subjects: Engineering; Lane-changing prediction; Microscopic traffic load simulation
• Online Access: https://hdl.handle.net/10356/182263
• Institution: Nanyang Technological University

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...