This Early-Concept Grants for Exploratory Research (EAGER) project is investigating the emergence, mechanisms, and applications of collective rationality among self-interested vehicle agents in the design of mixed autonomy transportation networks and infrastructure systems. Collective rationality refers to the ability of self-interested members of a group to make consistent, logical decisions that maximize overall, shared benefits. This project will explore and rigorously define the concept of collective rationality in the context of mixed traffic and will explore its application to designing the strategic behaviors of autonomous driving agents in mixed autonomy transportation systems. The core hypothesis is that collective rationality can emerge in broad scenarios even if the involved agents are self-interested. The researchers are leveraging game theory and reinforcement learning to verify this hypothesis theoretically and computationally. The results may help reduce travel cost, uncertainties, and fuel emissions, as well as enhance equity among all road users. Broader applications may include autonomous vehicle behavior design and emergency evacuation.

Principle Investigators:
Jia Li, Civil and Environmental Engineering, WSU
Michael Zhang, Civil and Environmental Engineering, UC Davis

Sponsor: National Science Foundation
Scheduled completion: August 2026

High-quality traffic data are crucial for infrastructure planning, system operations and performance measurement, safety considerations, maintenance activities, and informed analysis and decision-making. That’s why state departments of transportation need comprehensive and cost-effective traffic sensing and data collection systems. The primary goal of this research is to develop machine-learning-based detection algorithms, software, and a mobile hardware system that can utilize existing surveillance video cameras to accurately collect critical traffic information that traditional traffic sensors often cannot capture. This information includes vehicle volumes based on FHWA’s 13-bin classification system, speeds, and road surface conditions. The machine learning process will allow the unit to be trained with real data. The major advantage of this new system will be its ability to collect short-duration count data where geometry and volumes pose safety risks to field staff.

Principal Investigator: Yinhai Wang, Department of Civil and Environmental Engineering, UW
Sponsor: WSDOT
WSDOT Technical Monitor: Natarajan Janarthanan
WSDOT Project Manager: Doug Brodin
Scheduled completion: December 2025

The Washington State Department of Transportation (WSDOT) spends millions of dollars each winter assessing and monitoring the chances of hazardous roadside snow avalanches in Washington’s mountains. For that assessment, dedicated staff hand-dig snow pits, visually evaluate snow conditions, and directly assess avalanche risks to support difficult decisions to open or close roads. The objective of this project is to develop an avalanche sensor for deployment by drone on inaccessible slopes above state roadways that will provide indirect, remote, and real-time information about snow conditions more safely and cost effectively. The research team has already proved the viability of using such sensors to gather temperature, movement, and location data, with a communication range of up to 1,600 feet between them and a base station. In this project, the University of Washington’s STAR Lab will manufacture six to ten sensors for field testing and will place them on a known avalanche path in Snoqualmie Pass. The research team will test the ability of drones to accurately drop and retrieve the sensors. In addition, they will test the communication between the sensors and base station, and they will evaluate the accuracy of the collected snowpack and avalanche information and its value to WSDOT’s avalanche staff.

Principal Investigators:
Yinhai Wang, Civil and Environmental Engineering, UW
Edward McCormack, Civil and Environmental Engineering, UW

Sponsor: WSDOT
WSDOT Technical Monitor: James Morin
WSDOT Project Manager: Doug Brodin
Scheduled completion: June 2025