Traffic control cuts delays using dynamic lanes and speed limits
Joint Dynamic Lane Reversal and Variable Speed Limit Control: A Graphormer-Based Approach
Artificial IntelligenceMachine Learning
Summary
Traffic jams could be reduced if roads changed lane directions and speed limits dynamically, but this is tricky because some road changes can cut off parts of the network. The authors created a method that keeps all intersections connected while changing lanes and speeds, using a special attention-based model to learn good control strategies. On a simulated grid of roads, their approach cut traffic delays by 85-90%, showing how smart traffic control could improve rush hour flow. Some parts of the model, like spatial and relational information, were especially important for success.
What this means in practice
- •For traffic control operators: Optimize dynamic lane directions and speed limits in urban road networks to reduce congestion during rush hours while maintaining network connectivity.
- •For urban mobility planners: Design traffic management strategies that integrate frequent lane direction changes and speed adjustments supported by learned policies for better commuter flow.
Tested on simulated data.
Authors
Hamed Araab, Abbas Ahmadi, Mohammad Hossein Basiri
Abstract
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.