All posts by trac

Environmental DNA: From Knowledge to Action for Management

Transportation agencies are frequently required to conduct analyses of the biological elements of ecosystems as part of their work in constructing and repairing roads and culverts. However, measuring ecosystems—and particularly the impacts of construction projects on those ecosystems—is not a straightforward or standardized process. The goal of this project was to demonstrate a widely applicable, rigorous, quantitative method for reporting on environmental impact using environmental DNA.

... Read More about Environmental DNA: From Knowledge to Action for Management
Linear Scheduling Evaluation and Best Practices Development

This project evaluated the importance of the use of the linear scheduling method (LSM) for planning and conducting linear construction projects, including large, complex transportation-related construction such as highway, tunnel, and bridge projects. Two off-the-shelf LSM software programs demonstrated potential to support the implementation of LSM for the Washington State Department of Transportation (WSDOT).

... Read More about Linear Scheduling Evaluation and Best Practices Development
WSDOT Truck Parking 2026-2027 Continual Learning for Predicting Truck Parking Availability

Insufficient availability of safe and accessible truck parking forces professional truck drivers to choose between adherence to federal hours-of-service regulations and parking in unsafe or unauthorized locations, including highway shoulders, ramps, and local streets. Challenges to developing an effective Truck Parking Information and Management System (TPIMS) for tracking commercial truck parking availability and informing drivers include non-stationary parking demand patterns, sparsity of data, and imperfect conditions for sensor reliability. The goal of this research is to develop a robust, adaptive, and deployable truck parking prediction framework, together with a practical Prediction Improvement Toolkit, that can maintain reliable TPIMS performance over time despite the challenges commonly observed in real-world deployments. Building on operational experience from WSDOT’s TPIMS, this research is focusing on advancing prediction methodologies and translating them into reusable tools, guidelines, and evaluation resources that will support long-term TPIMS stability, trust, and scalability throughout the system’s lifecycle.

Principle Investigator: Yinhai Wang, Civil and Environmental Engineering, UW
Sponsor: WSDOT
WSDOT Technical Monitor: Matt Neeley
WSDOT Project Coordinator: David Strich
Scheduled completion: July 2027

An Application of AI-Driven Edge Computing Technology for Traffic Sign Detection and Asset Management

Effective management and maintenance of traffic signs are essential for ensuring road safety and operational efficiency. However, traditional, manual methods for assessing traffic sign conditions are labor-intensive, time-consuming, expensive, often inconsistent, and they can pose safety risks for personnel. To address these challenges, the researchers have developed a novel Automatic Traffic Sign Detection and Assessment System (ATSDAS). The ATSDAS uses video logs and GPS data and leverages AI-driven edge computing, deep learning models, and feature extraction to identify, classify, and evaluate the condition of traffic signs in real time. It also organizes and stores traffic sign data dynamically, enabling effective asset management for transportation agencies. The focus of this project is to validate and refine the previously developed system for onboard traffic sign detection and condition assessment by using an edge device. This work will transition the system from a laboratory setting to practical field applications, emphasizing its robustness, reliability, and scalability for real-world asset management. By integrating this innovation into statewide operations, Washington state will not only improve road safety and operational efficiency but also position itself as a leader in leveraging AI-driven solutions for transportation infrastructure.

Principle Investigator: Yinhai Wang, Civil and Environmental Engineering, UW
Sponsors: WSDOT / FHWA STIC
WSDOT Technical Monitor: Trevor McCain
WSDOT Project Coordinator: David Strich
Scheduled completion: April 2027

Enhancing Active Transportation User Safety Through Cooperative Multi-Task Sensing and Infrastructure-to-Everything (I2X) Technologies

Existing traffic management systems lack the ability to effectively detect, track, and predict the movements and potential conflicts faced by active transportation users, such as pedestrians, cyclists, and people in wheelchairs, especially in complex urban environments. Moreover, current systems lack a unified platform to facilitate communication among vehicles, infrastructure, and vulnerable road users. This project, focused on developing a cooperative multi-task sensing system, aims to detect and track all road users to optimize signal control for all and predict and mitigate user conflicts. Through infrastructure-to-everything (I2X) technologies, crucial information about road user behavior and interactions will be generated and disseminated to various agents, enhancing situational awareness across the transportation network. Moreover, the integration of personal identification devices will allow active transportation users to communicate directly with drivers and infrastructure. This communication will facilitate a more responsive and adaptive traffic management system, with the potential to reduce user conflicts, especially with vulnerable, non-motorized users.

Principle Investigator: Yinhai Wang, Civil and Environmental Engineering, UW
Sponsor: WSDOT
WSDOT Technical Monitor: Scott Davis
WSDOT Project Coordinator: David Strich
Scheduled completion: December 2027

2050 Transportation Scenario Visualization

With the state’s population projected to rise sharply by 2050, within the next 25 years numerous factors will affect transportation mobility, economic vitality, and quality of life in Washington state. To aid in planning, this project developed a data-driven, web-based visual tool, called Mobility Washington 2050: The Future in Motion, that is intended to make complex, disparate transportation data accessible and actionable for both policymakers and the public.

... Read More about 2050 Transportation Scenario Visualization
Smart and Cooperative Truck Parking Monitoring and Calibration System Empowered by Machine Learning

Truck parking information management systems (TPIMS) are intended to help monitor, identify, and broadcast the real-time availability of truck parking stalls to commercial vehicle operators. This study developed a framework for improving TPIMS by better detecting anomalies in collected parking data and better calibrating counting systems to improve the reliability of truck parking occupancy information.

... Read More about Smart and Cooperative Truck Parking Monitoring and Calibration System Empowered by Machine Learning
Analysis of Lane Departure Crashes with Emerging Data, Machine Learning, and Field Evaluation

Vehicle lane departure is a primary cause of roadway crashes, and it leads to serious driver injuries and fatalities in Washington state and beyond. This study characterized the leading factors that contribute to lane departure crashes in Washington, looking particularly at lane markings, by developing an analysis framework and leveraging new types of data.

... Read More about Analysis of Lane Departure Crashes with Emerging Data, Machine Learning, and Field Evaluation
Improving Mobility for Suburban and Rural Communities through Innovative Transit Approaches: A Comparative Cost Evaluation

With limited funding, transit agencies search for ways to more cost effectively serve their riders, particularly in low-density communities. Transit incorporating mobility-on-demand (TIMOD) is one possibility, but how does it compare to services such as fixed transit or ride-hailing services? This study compared the cost-effectiveness of TIMOD to that of other modes in suburban and rural settings.

... Read More about Improving Mobility for Suburban and Rural Communities through Innovative Transit Approaches: A Comparative Cost Evaluation
Truck Parking Information and Management System (TPIMS)

Truck parking availability for commercial drivers traveling through Washington state is limited. To help truck drivers plan their trips and maximize the use of available parking, the University of Washington STAR Lab developed a self-learning and optimizing truck parking information and management system (TPIMS) for installation at state-owned truck parking facilities such as weigh stations and safety rest areas.

... Read More about Truck Parking Information and Management System (TPIMS)