Washington State Safe System Champion Award
The Yakama Smart Project Team received the Washington State Traffic Safety Commission recognition for its work advancing data-driven roadway safety in tribal communities.
Technology Transfer
From Research to Real-World Impact
Translating transportation research into deployable technologies, agency practice, commercial products, and safer, smarter infrastructure.
Research → Practice
Technology Transfer as a Core Research Goal
A central goal of Prof. Wang's research is to move promising ideas beyond papers and laboratory demonstrations. Working through the UW STAR Lab, PacTrans, transportation agencies, tribal communities, industry partners, and entrepreneurial pathways, the research team develops technologies that can be tested in the field, improved through real-world use, and ultimately implemented at scale.
This approach has led to field-deployed sensing and edge-AI systems, operational transportation data tools, truck-parking technologies, safety applications, connected-transportation systems, and the launch of a University of Washington spin-off company, AIWaysion.
01
Research
New concepts, algorithms, sensing methods, and system architectures
→
02
Prototype
Integrated hardware, software, AI, edge computing, and communications
→
03
Field Deployment
Testing with transportation agencies and communities in real conditions
→
04
Implementation
Operational systems, commercialization, and broader technology adoption
UW Spin-Off
AIWaysion: Translating STAR Lab Innovation into Practice
AIWaysion was launched as a University of Washington spin-off to commercialize and deploy intelligent transportation technologies developed through research at the UW STAR Lab.
The company's core technology grew from the Mobile Unit for Sensing Traffic (MUST), an integrated smart-infrastructure platform that combines sensing, data fusion, edge AI, analytics, and communication in a field-deployable roadside unit.
MUST has evolved from university research into a practical platform for multimodal traffic sensing, roadway and weather monitoring, safety analysis, V2X applications, infrastructure monitoring, and real-time transportation intelligence.
Commercial Deployment
AIWaysion Wins the 2026 DC Autonomous Vehicle Observation Challenge
2026
Independent Infrastructure-Based Observation of Autonomous Vehicles
In 2026, AIWaysion was selected by US Ignite, the District Department of Transportation, and the Southwest Business Improvement District as the winner of Washington, DC's Autonomous Vehicle Observation Zone Challenge.
Working with Parsons Corporation, AIWaysion will deploy MUST technology to detect and track autonomous vehicles, generate high-resolution trajectory data, and analyze AV behavior and interactions in mixed urban traffic. The pilot is scheduled to begin in 2027.
This deployment represents a new application pathway for technology that began as university transportation sensing research: using intelligent roadside infrastructure to independently understand how automated vehicles operate on public streets.
Read the US Ignite announcement →Recognition
Awards for Research Implementation & Technology Transfer
CUTC Technology Transfer Leadership Award
Under Prof. Wang's leadership as PacTrans Director, PacTrans received the Council of University Transportation Centers Technology Transfer Leadership Award. The recognition highlighted the center’s sustained commitment to knowledge dissemination, practical applications, agency partnerships, and moving university transportation research into implementation.
Read the PacTrans award story →FHWA Build a Better Mousetrap — Innovative Project Award
The MUST deployment with Yakama Nation received the national Innovative Project Award for monitoring traffic, detecting dangerous events, and providing real-time roadway safety information.
AASHTO High-Value Research Award
The WSDOT truck-parking research received an AASHTO High-Value Research Award, recognizing the practical value of work on real-time truck-parking information, visualization, and prediction.
National Research to Practice
NCHRP 17-100 Highlighted by TR News
2026
Leveraging AI and Big Data to Enhance Safety Analysis
Prof. Wang's NCHRP 17-100 research was highlighted in the Spring 2026 issue of TR News, the Transportation Research Board's quarterly magazine. The article, authored by Yinhai Wang and Mehrdad Nasri, summarizes the research that led to NCHRP Research Report 1152: Leveraging Artificial Intelligence and Big Data to Enhance Safety Analysis: A Guide.
The project demonstrates how artificial intelligence, machine learning, and emerging data sources can be translated into practical safety-analysis tools for transportation agencies. Pilot demonstrations included automated streetlight inventory using imagery with the Oregon Department of Transportation and intersection video analytics in Bellevue, Washington, for extracting vehicle turning speeds and trajectories.
Beyond the pilots, the project produced applied workflows for connected vehicle data, lidar, roadway video, traffic-sign recognition, pedestrian detection, roadway-surface condition analytics, and other safety applications. The practitioner-focused guide is designed to help agencies move from data acquisition and model development to validation, deployment, performance monitoring, and broader implementation.
Research in Practice
Selected Field Deployments & Operational Applications
Yakama Nation — US 97
MUST technology was installed to collect real-time traffic, roadway-surface, and environmental data and support data-driven safety planning in a corridor with serious crash challenges.
UW CEE: Fighting fatalities with facts →WSDOT Truck Parking Information & Management System
Research on sensing, machine-learning-based availability prediction, system calibration, data integration, and APIs has been developed into an operational framework for improving truck-parking information.
Read the TRAC project story →Real-Time Visibility & Road Condition Monitoring
STAR Lab research has tested MUST-based roadside systems for real-time traffic and environmental sensing, visibility detection, warning activation, and safety applications under real roadway conditions.
Read the TRAC project story →Active Transportation Sensing & I2X
AI-based sensing built on MUST has been used to connect roadway users, infrastructure, transportation agencies, and real-time information systems for multimodal safety and infrastructure-to-everything applications.
Read the TRAC project story →Curbside Monitoring
MUST and edge-video analytics were deployed in a Bellevue curbside pilot to evaluate curb utilization and demonstrate how university research can support local transportation operations.
Read the PacTrans success story →Washington, DC AVO Zone
AIWaysion's commercial MUST platform will be deployed to observe, measure, and analyze autonomous-vehicle operations and interactions in dense urban traffic.
Read the challenge announcement →In the News
Research Moving Beyond the University
External reporting and agency project stories document how STAR Lab research and AIWaysion technologies have progressed from university prototypes to field demonstrations, operational systems, and commercial deployments.
NCHRP 17-100 Featured in TR News
Yinhai Wang and Mehrdad Nasri summarize how AI, machine learning, and emerging data can be moved from research into practical transportation safety analysis.
Read the TR News article →AIWaysion Wins DC's Autonomous Vehicle Observation Zone Challenge
US Ignite / District Department of Transportation
Read story →MUST Technology Continues Expanding into Real-World Safety Applications
AIWaysion project and deployment updates
View AIWaysion updates →PacTrans Receives Technology Transfer Leadership Award
Pacific Northwest Transportation Consortium
Read story →STAR Lab Launches Spin-Off Company AIWaysion
Pacific Northwest Transportation Consortium
Read story →Innovation Pathways
Research, Intellectual Property & Commercialization
Technology transfer can take many forms. Some research is implemented directly through agency projects and operational systems. Other work advances through prototypes, patents, licensing, startup activity, and commercial deployment.
The STAR Lab's experience with MUST and AIWaysion demonstrates how sustained university research, public-agency partnerships, technology validation, and entrepreneurship can work together to move innovation from concept to implementation.
Technology Transfer Pathways
- Agency-funded applied research
- Field pilots and demonstrations
- Technology validation with users
- Patents and intellectual property
- University commercialization support
- Spin-off company formation
- SBIR-supported product development
- Commercial deployment and scaling
Impact
Research Is Most Valuable When It Reaches Practice
Technology transfer is not a final step after research; it is part of the research process itself. Real-world deployment reveals new problems, creates better data, improves technology, and helps ensure that research addresses the actual needs of transportation agencies and communities. Professor Wang and his research team aim to create innovations that are technically advanced, cost-effective, deployable, and capable of making a measurable difference in transportation safety, mobility, and infrastructure management.