by Shaun McGillis
October 5th 2018
Share
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.”