Graphormer 动态调节车道方向与限速，仿真中每日延误降低 90%
Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach
把车道换向和限速交给一个 transformer 统一调度，仿真里高峰延误砍了九成，交通方向的做法挺有意思。
论文提出用一个共享 transformer 的 GERASTSA 注意力机制，对全路网执行动态车道换向和可变限速控制。动作解析算法基于图定向理论，保证单向道路调整后路网始终强连通，换向清空车道时交叉口之间也保持可达。策略先做动作条件下的交通预测预训练，再用分道路 PPO 微调。在 6 x 6 网格加早晚高峰的仿真里，约三分之二道路在高峰方向改为单向，日延误比固定配置降低 90%，比调优过的双向负载均衡器降低 85%。消融实验显示去掉关系偏置或空间嵌入会使延误增大约五倍。
Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach
Connected and automated vehicles could allow reassigning lane directions and speed limits on every road frequently, but the benefit hinges on how traffic reroutes, and one-way roads can isolate junctions. We formulate network-wide dynamic lane allocation and directional speed limit control with one-way roads, lane clearing before each reversal, and a navigable graph kept strongly connected at all times. An action-resolution algorithm grounded in graph orientation theory admits a proposal closing a direction only if the network stays strongly connected and otherwise relaxes or reverts it, keeping all junctions mutually reachable within the model, even during clearing. All road controllers share one transformer whose attention, Global Endpoint Relation-Aware Spatio-Temporal Self-Attention (GERASTSA), spans all road-time tokens, biased by the endpoint relations between roads. It is pretrained on action-conditioned traffic forecasting and fine-tuned with per-road proximal policy optimization under a mixed reward that also credits neighboring roads and the network. On a 6 x 6 grid with commuter rush hours, the learned policy makes about two thirds of roads one-way in the peak direction and cuts daily delay by 90% against the initial configuration held fixed and by 85% against a tuned two-way load balancer. Restricted to two-way roads at test time, it gains only about as much as this balancer, whereas its learned speed limits add delay. Pretraining roughly halves the updates needed to surpass the fixed configuration. Of the ablations, only removing the relational bias or the spatial embedding clearly matters, multiplying delay about fivefold.