DynSTGAT: Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control

  title={DynSTGAT: Dynamic Spatial-Temporal Graph Attention Network for Traffic Signal Control},
  author={Libing Wu and Min Wang and Dan Wu and Jia Wu},
  journal={Proceedings of the 30th ACM International Conference on Information \& Knowledge Management},
  • Libing Wu, Min Wang, +1 author Jia Wu
  • Published 12 September 2021
  • Computer Science
  • Proceedings of the 30th ACM International Conference on Information & Knowledge Management
Adaptive traffic signal control plays a significant role in the construction of smart cities. This task is challenging because of many essential factors, such as cooperation among neighboring intersections and dynamic traffic scenarios. First, to facilitate the cooperation of traffic signals, existing work adopts graph neural networks to incorporate the temporal and spatial influences of the surrounding intersections into the target intersection, where spatial-temporal information is usedโ€ฆย Expand


ConSTGAT: Contextual Spatial-Temporal Graph Attention Network for Travel Time Estimation at Baidu Maps
A spatial-temporal graph neural network that adopts a novel graph attention mechanism, which is designed to fully exploit the joint relations of spatial and temporal information, and a computationally efficient model that applies convolutions over local windows to capture a route's contextual information and further employs multi-task learning to improve the performance. Expand
CoLight: Learning Network-level Cooperation for Traffic Signal Control
The proposed model, CoLight, is the first to use graph attentional networks in the setting of reinforcement learning for traffic signal control and to conduct experiments on the large-scale road network with hundreds of traffic signals. Expand
LSGCN: Long Short-Term Traffic Prediction with Graph Convolutional Networks
This paper proposes a novel deep learning framework called Long Shortterm Graph Convolutional Networks (LSGCN) to tackle both traffic prediction tasks and proposes a new graph attention network called cosAtt, and integrates both cosAtt and graph convolution networks ( GCN) into a spatial gated block. Expand
Learning Phase Competition for Traffic Signal Control
A novel design called FRAP is proposed, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Expand
Traffic Signal Control Based on Reinforcement Learning with Graph Convolutional Neural Nets
An RL-based traffic signal control method that employs a graph convolutional neural network (GCNN) that can automatically extract features considering the traffic features between distant roads by stacking multiple neural network layers is developed. Expand
Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control
This paper tackles the problem of multi-intersection traffic signal control, especially for large-scale networks, based on RL techniques and transportation theories and shows that implicit coordination could be achieved by individual control agents with well-crafted reward design thus reducing the dimensionality. Expand
CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenario
A new traffic simulator CityFlow with fundamentally optimized data structures and efficient algorithms that can support flexible definitions for road network and traffic flow based on synthetic and real-world data and provides user-friendly interface for reinforcement learning. Expand
A Survey on Reinforcement Learning Models and Algorithms for Traffic Signal Control
Various RL models and algorithms applied to traffic signal control are reviewed in the aspects of the representations of the RL model (i.e., state, action, and reward), performance measures, and complexity to establish a foundation for further investigation in this research field. Expand
A Survey on Traffic Signal Control Methods
This survey covers the widely acknowledged transportation approaches and a comprehensive list of recent literature on reinforcement for traffic signal control and hopes it can foster interdisciplinary research on this important topic. Expand
MetaLight: Value-Based Meta-Reinforcement Learning for Traffic Signal Control
This paper proposes a novel framework, named as MetaLight, to speed up the learning process in new scenarios by leveraging the knowledge learned from existing scenarios, which improves the-state-of-the-art reinforcement learning model FRAP in traffic signal control by optimizing its model structure and updating paradigm. Expand