AI 中文总结
研究异构道路网络交通信号控制接口，用共享图神经网络为交通流分配分数，经确定性关联矩阵转换为信号相位集，通过PPO实验评估，在合成网格和城市图上测试，为该控制接口的可行性提供了证据。
AI 中文摘要
我们提出了一种交通信号控制接口，其中共享图神经网络为各个交通流分配分数。每个路口使用确定性关联矩阵将这些分数转换为其自身可变大小的合法信号相位集。有向走廊节点提供交通上下文，而交通流节点表示通过路口的受控输入到输出路径。类型化均值聚合为每个交通流生成一个标量；相位定义和信号定时保留在学习网络之外。这使得图大小和特定于路口的动作数量与学习参数形状无关。PPO实验在未见的合成网格几何形状、改变的信号覆盖范围和五个异构城市图上评估该接口。在合成网格族内未见的几何形状上，策略保持了性能，而信号覆盖范围的变化暴露了对信号覆盖分布变化的敏感性。在所有五个城市图上执行单个训练的城市策略实例，结果各异。这些结果提供了可行性证据，而非对转移到任意道路网络的一般估计。
英文摘要
We present a traffic-signal control interface in which a shared graph neural network assigns scores to individual traffic movements. Each junction converts these scores into its own variable-sized set of legal signal phases using a deterministic incidence matrix. Directed corridor nodes provide traffic context, while movement nodes represent controlled input-to-output paths through junctions. Typed mean aggregation produces one scalar per movement; phase definitions and signal timing remain outside the learned network. This makes graph size and junction-specific action count independent of the learned parameter shapes. PPO experiments evaluate the interface on unseen synthetic grid geometries, altered signal coverage, and five heterogeneous city graphs. The policies retained performance across unseen geometries within the synthetic grid family, while changes in signal coverage exposed sensitivity to a signal-coverage distribution shift. A single trained city-policy instance executed across all five city graphs, with heterogeneous outcomes. These results provide feasibility evidence rather than a general estimate of transfer to arbitrary road networks.
Comments9 pages, including 3 appendix pages, 5 figures. Code: https://github.com/BertilBraun/GNN-Traffic-Signal-Control
