Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline

TL;DR

This paper introduces a new dataset and a strong baseline model for multi-intersection traffic signal control, leveraging deep reinforcement learning with graph-based encoding to handle complex urban traffic scenarios effectively.

Contribution

It presents a novel dataset combining synthetic and real traffic data, and proposes a deep RL model with graph convolutional encoder-decoder architecture for multi-intersection traffic optimization.

Findings

The model outperforms several competitive methods on synthetic data.

It effectively captures multi-intersection relations using graph convolution.

The approach reduces model complexity while maintaining high performance.

Abstract

The control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. However, it is challenging since traffic dynamics are complicated in real-world scenarios. Because of the high complexity of the optimisation problem for modelling the traffic, experimental settings of existing works are often inconsistent. Moreover, it is not trivial to control multiple intersections properly in real complex traffic scenarios due to its vast state and action space. Failing to take intersection topology relations into account also results in inferior solutions. To address these issues, in this work we carefully design our settings and propose a new dataset including both synthetic and real traffic data in more complex scenarios. Additionally, we propose a novel baseline model with strong performance. It is based on deep reinforcement learning with an encoder-decoder structure: an edge-weighted graph convolutional encoder to excavate multi-intersection relations; and an unified structure decoder to jointly model multiple junctions in a comprehensive manner, which significantly reduces the number of the model parameters. By doing so, the proposed model is able to effectively deal with the multi-intersection traffic optimisation problem. Models are trained/tested on both synthetic and real maps and traffic data with the Simulation of Urban Mobility (SUMO) simulator. Experimental results show that the proposed model surpasses multiple competitive methods.