Graph Attention Network for Lane-Wise and Topology-Invariant Intersection Traffic Simulation

arXiv:2404.07446v1 Announce Type: new
Abstract: Traffic congestion has significant economic, environmental, and social ramifications. Intersection traffic flow dynamics are influenced by numerous factors. While microscopic traffic simulators are valuable tools, they are computationally intensive and challenging to calibrate. Moreover, existing machine-learning approaches struggle to provide lane-specific waveforms or adapt to intersection topology and traffic patterns. In this study, we propose two efficient and accurate "Digital Twin" models for intersections, leveraging Graph Attention Neural Networks (GAT). These attentional graph auto-encoder digital …

abstract adapt arxiv attention congestion cs.ai cs.lg dynamics economic environmental flow graph intersection machine network simulation social struggle tools topology traffic traffic congestion type wise