Interactive Attention-Based Graph Transformer for Multi-intersection Traffic Signal Control

With the exponential growth in motor vehicle numbers, urban traffic congestion has become a pressing issue. Traffic signal control plays a pivotal role in alleviating the problem. In modeling multi-intersection, most studies focus on communication with regional intersections. They rarely consider the cross-regional. To address the above limitation, we construct an interactive attention-based graph transformer network for traffic signal control (GTLight). Specifically, the model considers correlations between cross-regional intersections using an interactive attention mechanism. In addition, the model designs a phase-timing optimization algorithm to solve the problem of overestimation of Q-value in signal timing strategies. We validate the effectiveness of GTLight on different traffic datasets. Compared to the recent graph-based reinforcement learning method, the average travel time is improved by 28.16%, 26.56%, 25.79%, 26.46%, and 19.59%, respectively.