Spatio-temporal dual-stage hypergraph MARL for human-centric multimodal corridor traffic signal control

2026-02-18

AI Summary

This study addresses the limitation of conventional traffic signal control strategies that prioritize vehicular efficiency at the expense of multimodal equity. To this end, the authors propose the STDSH-MARL framework, a multi-agent reinforcement learning approach based on centralized training with decentralized execution. The method introduces a novel spatiotemporal two-stage hypergraph attention mechanism, which, for the first time in traffic signal control, explicitly models temporal hyperedges to capture complex interdependencies across time. Furthermore, it employs a hybrid discrete action space to jointly optimize signal phase selection and green duration allocation. Experimental results across five diverse scenarios demonstrate consistent and significant performance gains over state-of-the-art methods, with notable improvements in public transit prioritization. Ablation studies confirm that the incorporation of temporal hyperedges is a key contributor to the observed performance enhancement.

Technology Category

• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Human-centric traffic signal control in corridor networks must increasingly account for multimodal travelers, particularly high-occupancy public transportation, rather than focusing solely on vehicle-centric performance. This paper proposes STDSH-MARL (Spatio-Temporal Dual-Stage Hypergraph based Multi-Agent Reinforcement Learning), a scalable multi-agent deep reinforcement learning framework that follows a centralized training and decentralized execution paradigm. The proposed method captures spatio-temporal dependencies through a novel dual-stage hypergraph attention mechanism that models interactions across both spatial and temporal hyperedges. In addition, a hybrid discrete action space is introduced to jointly determine the next signal phase configuration and its corresponding green duration, enabling more adaptive signal timing decisions. Experiments conducted on a corridor network under five traffic scenarios demonstrate that STDSH-MARL consistently improves multimodal performance and provides clear benefits for public transportation priority. Compared with state-of-the-art baseline methods, the proposed approach achieves superior overall performance. Further ablation studies confirm the contribution of each component of STDSH-MARL, with temporal hyperedges identified as the most influential factor driving the observed performance gains.

Problem

• human-centric traffic signal control
• multimodal transportation
• corridor network
• public transportation priority
• spatio-temporal dependencies

Innovation

• hypergraph attention
• spatio-temporal modeling
• multi-agent reinforcement learning
• multimodal traffic signal control
• hybrid discrete action space