traffic | National Center for Sustainable Transportation

Network Sensor Error Quantification and Flow Reconstruction Using Deep Learning

Research Product Type

Dissertation / Thesis

This study approaches the problem of quantifying the network sensor errors as a supervised learning problem and leveraging deep neural networks to map observed traffic flow counts to the systematic errors in the sensors. The author aims at building a model that could reconstruct the erroneous flow irrespective of the level of random noise in the sensors, which is unknown in the real-world.

Network-wide Emissions Estimation Using the Macroscopic Fundamental Diagram

Principal Investigator Rafegh Aghamohammadi
Georgia Institute of Technology

Estimation of emissions and energy consumption using MOVES (Motor Vehicle Emission Simulator) model is cumbersome for large-scale network and intractable for real-time analysis and control purposes

Project Status

Complete

Network-wide Emissions Estimation Using the Macroscopic Fundamental Diagram

Research Product Type

Research Report

This report presents a review of the studies incorporating the Macroscopic Fundamental Diagram (MFD) dynamics for emissions estimation using various microscopic estimation frameworks.

Optimization of Safe and Cost-Effective Driving Strategies with Connected and Autonomous Vehicles through Driving Simulator Tests

Principal Investigator Fengxiang Qiao, Ph.D.
Texas Southern University

This project will evaluate the design, operation, and impacts of advanced optimization strategies for traffic operations over transportation networks with Connected and Automated Vehicles (CAVs) under complicated dynamic traffic conditions.

Project Status

In Progress

Perception Learning, Prediction and Motion Planning for Energy Efficient Driving of Connected and Automated Vehicles

Research Product Type

Dissertation / Thesis

This dissertation developed predictive models and trajectory planning algorithms using machine learning and optimization techniques to address four key challenges of energy efficient driving of connected and automated vehicles.

Personalized Coordinated Routing with Utility Learning

Research Product Type

Research Brief

This research proposes a utility learning mechanism to estimate drivers' routing preferences for coordinated routing systems. This research brief discusses the results and effectiveness of the coordinated routing system and the utility learning mechanism.

Planning for Sustainable and Equitable Goods Movement: Identifying Barriers, Best Practices and a Path Forward

Principal Investigator Gregory Rowangould, Ph.D.
University of Vermont

The objective of this research is to understand the limitations and barriers to more effective regional goods movement planning and the implications for understanding and addressing sustainability and equity concerns.

Project Status

In Progress

Reconstructing Fundamental Diagrams of Heterogeneous Traffic from Trajectory Data

Principal Investigator Di Chen
University of California, Davis

This research will focus on reconstructing fundamental diagrams of heterogeneous traffic from trajectory data.

Project Status

Complete

Reducing Truck Emissions and Improving Truck Fuel Economy via ITS Technologies

Principal Investigator Petros Ioannou, Ph.D.
University of Southern California

This project proposes using intelligent transportation system (ITS) technologies that take into account the presence of trucks in the traffic flow. The researchers anticipate that this will improve impact on the environment by reducing fuel consumption and pollution levels in areas where the truck volume is relatively high.

Project Status

Complete

Selection of the Speed Command Distance for Improved Performance of a Rule-Based VSL and Lane Change Control

Research Product Type

Associated Publication

This paper discusses the impact of Variable Speed Limit sign distance on the effectiveness and performance of VSL control. It proposes a rule-based VSL strategy that matches the outflow of the upstream VSL zone with the bottleneck capacity based on a multi-section Cell Transmission Model.