Ramp Metering

Ramp metering, the controlled release of vehicles from on-ramps onto freeways, aims to alleviate traffic congestion and improve overall traffic flow. Current research emphasizes the development and refinement of sophisticated control strategies, leveraging machine learning techniques like reinforcement learning and model predictive control, often within transfer learning frameworks to adapt to diverse traffic conditions and limited sensor data. These advancements focus on improving the accuracy of traffic flow prediction, optimizing throughput while maintaining safety, and enabling coordinated control across large-scale networks, ultimately leading to more efficient and robust traffic management systems.

Papers

November 15, 2023

Reinforcement Learning with Model Predictive Control for Highway Ramp Metering
Filippo Airaldi, Bart De Schutter, Azita Dabiri
Reinforcement Learning Predictive Control Traffic Management Ramp Metering

August 7, 2023

March 12, 2023

Throughput of Freeway Networks under Ramp Metering Subject to Vehicle Safety Constraints
Milad Pooladsanj, Ketan Savla, Petros A. Ioannou
Safety Constraint Traffic Network Worst Case User Throughput Online Merging Ramp Metering Ramp Vehicle

March 4, 2023

Demonstration-guided Deep Reinforcement Learning for Coordinated Ramp Metering and Perimeter Control in Large Scale Networks
Zijian Hu, Wei Ma
Reinforcement Learning Traffic Network Large Scale Network Traffic Dynamic DRL Algorithm Perimeter Defense Traffic Control Ramp Metering

January 28, 2023

Analyzing Robustness of the Deep Reinforcement Learning Algorithm in Ramp Metering Applications Considering False Data Injection Attack and Defense
Diyi Liu, Lanmin Liu, Lee D Han
Deep Reinforcement Learning Native Robustness Deep Q Learning False Data Injection Attack Ramp Metering

July 5, 2022

Ramp Metering to Maximize Freeway Throughput under Vehicle Safety Constraints
Milad Pooladsanj, Ketan Savla, Petros A. Ioannou
Safety Constraint Ramp Metering Ramp Vehicle

Ramp Metering

Papers

Reinforcement Learning with Model Predictive Control for Highway Ramp Metering

A Transfer Learning Framework for Proactive Ramp Metering Performance Assessment

On-ramp and Off-ramp Traffic Flows Estimation Based on A Data-driven Transfer Learning Framework

Throughput of Freeway Networks under Ramp Metering Subject to Vehicle Safety Constraints

Demonstration-guided Deep Reinforcement Learning for Coordinated Ramp Metering and Perimeter Control in Large Scale Networks

Analyzing Robustness of the Deep Reinforcement Learning Algorithm in Ramp Metering Applications Considering False Data Injection Attack and Defense

Ramp Metering to Maximize Freeway Throughput under Vehicle Safety Constraints