Traffic Flow Theory

Traffic flow theory aims to understand and optimize the movement of vehicles, aiming to alleviate congestion and improve efficiency in transportation networks. Current research focuses on developing data-driven models, such as reinforcement learning and physics-informed deep learning, often integrated with graph neural networks for multi-agent control (e.g., coordinated platooning and traffic signal optimization). These advancements leverage real-world traffic data and incorporate principles from traffic flow theory to create more realistic and effective control strategies, impacting both the design of intelligent transportation systems and the development of autonomous vehicle technologies.

Papers

April 3, 2024

Traffic Divergence Theory: An Analysis Formalism for Dynamic Networks
Matin Macktoobian, Zhan Shu, Qing Zhao
Dynamic Network Network Traffic Dynamic Traffic Analysis Formalism Traffic Flow Theory

November 27, 2023

A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
Jianxiong Li, Shichao Lin, Tianyu Shi, Chujie Tian, Yu Mei, Jian Song, Xianyuan Zhan, Ruimin Li
Offline Reinforcement Learning Data Driven Approach Traffic Simulator Sample Efficient Offline Reinforcement Learning Traffic Flow Theory

October 17, 2023

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control
Xianyue Peng, Hang Gao, Hao Wang, H. Michael Zhang
Reinforcement Learning Multi Agent Reinforcement Learning Traffic Signal Control Traffic Flow Platoon Control Heterogeneous Setting Congestion Mitigation Traffic Flow Theory

February 23, 2023

Physics Informed Deep Learning: Applications in Transportation
Archie J. Huang, Shaurya Agarwal
Financial Application Transportation System Physic Informed Deep Learning Traffic State Estimation Traffic Flow Theory

December 21, 2022

Continual Interactive Behavior Learning With Traffic Divergence Measurement: A Dynamic Gradient Scenario Memory Approach
Yunlong Lin, Zirui Li, Cheng Gong, Chao Lu, Xinwei Wang, Jianwei Gong
Catastrophic Forgetting Continual Learning Trajectory Prediction Multi Scenario Vehicle Trajectory Prediction Traffic Flow Theory

October 6, 2022

Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning
Chaolun Ma, Bruce Wang, Zihao Li, Ahmadreza Mahmoudzadeh, Yunlong Zhang
Reinforcement Learning Lyapunov Function Traffic Signal Control Adaptive Traffic Signal Control Heterogeneous Traffic Traffic Flow Theory

May 30, 2022

Vehicle Route Planning using Dynamically Weighted Dijkstra's Algorithm with Traffic Prediction
Piyush Udhan, Akhilesh Ganeshkar, Poobigan Murugesan, Abhishek Raj Permani, Sameep Sanjeeva, Parth Deshpande
Practical Algorithm Traffic Prediction Dijkstra Algorithm Traffic Flow Theory

Traffic Flow Theory

Papers

Traffic Divergence Theory: An Analysis Formalism for Dynamic Networks

A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning

Combat Urban Congestion via Collaboration: Heterogeneous GNN-based MARL for Coordinated Platooning and Traffic Signal Control

Physics Informed Deep Learning: Applications in Transportation

Continual Interactive Behavior Learning With Traffic Divergence Measurement: A Dynamic Gradient Scenario Memory Approach

Lyapunov Function Consistent Adaptive Network Signal Control with Back Pressure and Reinforcement Learning

Vehicle Route Planning using Dynamically Weighted Dijkstra's Algorithm with Traffic Prediction