CityLight: A Universal Model for Coordinated Traffic Signal Control in City-scale Heterogeneous Intersections

2024-06-04

AI Summary

To address challenges in city-scale heterogeneous intersection cooperative signal control—including inconsistent phase semantics and complex modeling of adjacency effects—this paper proposes a reinforcement learning–based framework for universal representation and neighborhood fusion. Methodologically: (1) a semantics-driven phase re-indexing module unifies state representation and aligns observations across heterogeneous intersections; (2) a novel attention-based neighborhood fusion mechanism models relative traffic influence spatially while explicitly capturing competitive relationships among adjacent intersections; (3) a neighborhood-integrated reward function is introduced to enhance collaborative optimization. Extensive experiments across networks ranging from hundreds to tens of thousands of intersections demonstrate that the proposed method improves overall traffic throughput by 11.68% and cross-scenario transfer performance by 22.59%, significantly outperforming state-of-the-art approaches.

Technology Category

• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Planning/Scheduling and Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

The increasingly severe congestion problem in modern cities strengthens the significance of developing city-scale traffic signal control (TSC) methods for traffic efficiency enhancement. While reinforcement learning has been widely explored in TSC, most of them still target small-scale optimization and cannot directly scale to the city level due to unbearable resource demand. Only a few of them manage to tackle city-level optimization, namely a thousand-scale optimization, by incorporating parameter-sharing mechanisms, but hardly have they fully tackled the heterogeneity of intersections and intricate between-intersection interactions inherent in real-world city road networks. To fill in the gap, we target at the two important challenges in adopting parameter-sharing paradigms to solve TSC: inconsistency of inner state representations for intersections heterogeneous in configuration, scale, and orders of available traffic phases; intricacy of impacts from neighborhood intersections that have various relative traffic relationships due to inconsistent phase orders and diverse relative positioning. Our method, CityLight, features a universal representation module that not only aligns the state representations of intersections by reindexing their phases based on their semantics and designing heterogeneity-preserving observations, but also encodes the narrowed relative traffic relation types to project the neighborhood intersections onto a uniform relative traffic impact space. We further attentively fuse neighborhood representations based on their competing relations and incorporate neighborhood-integrated rewards to boost coordination. Extensive experiments with hundreds to tens of thousands of intersections validate the surprising effectiveness and generalizability of CityLight, with an overall performance gain of 11.68% and a 22.59% improvement in transfer scenarios in throughput.

Problem

• Modeling heterogeneous intersections for traffic signal control
• Incorporating neighborhood influence in universal traffic policies
• Addressing computational challenges in city-scale traffic coordination

Innovation

• Neighbor Influence Encoder models traffic flow relations
• Neighbor Influence Aggregator attentively aggregates neighbor influences
• Universal policy for heterogeneous intersections with neighborhood inclusion