An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems

TL;DR

This paper tackles urban traffic congestion by optimizing two adjustable components of traffic-light schemes: phase combination and phase time allocation. It introduces an offline meta black-box optimization framework that leverages Attentive Neural Processes as a data-driven, uncertainty-aware surrogate and Bayesian optimization for few-shot online adaptation to unseen traffic patterns. By constructing a large offline meta-dataset across diverse traffic patterns and deploying ANP with BO, the approach achieves superior performance over traditional BBO baselines and RL-based methods on realistic networks, including a real-world deployment that boosts throughput by 4.80%. The framework reduces reliance on continuous sensing and online optimization, enabling scalable and practical adaptive design for complex urban road networks.

Abstract

Complex urban road networks with high vehicle occupancy frequently face severe traffic congestion. Designing an effective strategy for managing multiple traffic lights plays a crucial role in managing congestion. However, most current traffic light management systems rely on human-crafted decisions, which may not adapt well to diverse traffic patterns. In this paper, we delve into two pivotal design components of the traffic light management system that can be dynamically adjusted to various traffic conditions: phase combination and phase time allocation. While numerous studies have sought an efficient strategy for managing traffic lights, most of these approaches consider a fixed traffic pattern and are limited to relatively small road networks. To overcome these limitations, we introduce a novel and practical framework to formulate the optimization of such design components using an offline meta black-box optimization. We then present a simple yet effective method to efficiently find a solution for the aforementioned problem. In our framework, we first collect an offline meta dataset consisting of pairs of design choices and corresponding congestion measures from various traffic patterns. After collecting the dataset, we employ the Attentive Neural Process (ANP) to predict the impact of the proposed design on congestion across various traffic patterns with well-calibrated uncertainty. Finally, Bayesian optimization, with ANP as a surrogate model, is utilized to find an optimal design for unseen traffic patterns through limited online simulations. Our experiment results show that our method outperforms state-of-the-art baselines on complex road networks in terms of the number of waiting vehicles. Surprisingly, the deployment of our method into a real-world traffic system was able to improve traffic throughput by 4.80\% compared to the original strategy.

Figures (7)

• Figure 1: Design components of traffic light scheme.
• Figure 2: Overview of our proposed method.
• Figure 3: Illustration of possible phases and combinations.
• Figure 4: Illustration of road networks used for our experiments: (Left) Hangzhou_4$\times$4, (Right) Manhattan_28$\times$7. Figures are taken from wei2019colight.
• Figure 5: Performance comparison between meta BBO methods and our method on Hangzhou Network across online trials. Mean and one standard deviation across three random seeds are reported.