The movement of goods throughout the supply chain is complex, fraught with uncertainties, and not without room for improvement. Portland State University recently received a $167,000 grant to support research investigating the development and evaluation of an intelligent freight transportation matching system. The system could improve freight and trucking networks critical to supply chain performance by reducing inefficient capacity—the problem of keeping trucks full of cargo while they’re on the road.

The National Science Foundation awarded the grant to civil and environmental engineering associate professor Avinash Unnikrishnan and co-investigators Stephen Boyles and Sanjay Shakkottai of the University of Texas at Austin. The research team will develop algorithms that match the needs of shippers and carriers using a type of reinforcement learning technique called bandit optimization. Such algorithms are often used to deliver personalized content recommendations on Amazon or Netflix. The “smart” matching algorithms will use data input into the system to continually improve how it connects organizations in need of freight capacity with those that supply it. Unnikrishnan and his colleagues will validate the system using real-world freight data. If successful, the system could increase the efficient use of freight capacity, reduced costs, fuel consumption, emissions, and reduce the number of empty trucks on the road.

"Transportation is a critical component of the supply chain," said Unnikrishnan, whose research focuses on optimizing the planning and operations of traffic, transit, and freight networks.

"Freight is an integral part of the economy. But there’s a lot of inefficient use of capacity out there. If we can develop a system that matches shippers to carriers considering the various constraints each may have, then we can reduce inefficiency and improve the system."

WHAT'S NEXT?

The research approach further extends traditional algorithms and heuristics for stochastic multi-armed bandit problems and the vehicle routing problem. A freight match problem is characterized by the arrival of stochastic demands that are queued for service and the need to estimate the costs a match would impose on a carrier, which serves as reserve prices for carriers for particular requests. The model represents this by extending the traditional multi-armed bandit problem to allow the set of "arms" to vary over time, as carriers enter and leave the system. Different from a traditional vehicle routing problem, efficiently and robustly estimating changes in routing costs from incorporating freight jobs is more important in the freight matching problem than deriving detailed routing plans at a fine-grained level.

Through 2019, the research team will investigate new algorithms in both of these areas, implementing them in a simulation framework and testing them with real-world data, to test the hypothesis that the queueing bandit approach can outperform auctions and alternative market mechanisms.

RELATED RESEARCH

To learn more about this and other TREC research, sign up for our monthly research newsletter.

• Connected Streetcar Project
• Exploring Data Fusion Techniques to Derive Bicycle Volumes on a Network
• Social-Transportation Analytic Toolbox (STAT) for Transit Networks

The Transportation Research and Education Center (TREC) at Portland State University is home to the National Institute for Transportation and Communities (NITC), the Initiative for Bicycle and Pedestrian Innovation (IBPI), and other transportation programs. TREC produces research and tools for transportation decision makers, develops K-12 curriculum to expand the diversity and capacity of the workforce, and engages students and young professionals through education.