RICHLAND, WA — Researchers at the Department of Energy’s Pacific Northwest National Laboratory (PNNL) are contributing their expertise in artificial intelligence, machine learning, and app development to a project that will ease challenges with urban freight delivery, an experience especially difficult during the holidays.
The entire project—funded with $1.5 million by DOE’s Office of Energy Efficiency and Renewable Energy’s Vehicle Technologies Office and led by the University of Washington’s Urban Freight Lab—will develop, test, and improve technologies aimed at cutting time spent by the driver at the curb, increasing productivity, and reducing time and fuel spent searching for available parking.
Parking constitutes a major headache for urban freight delivery drivers. Restaurants need a constant cycle of fresh produce and meat to feed hungry lunch and dinner customers. Retail establishments depend on delivered products to maintain a steady flow of sales. People living in a city’s apartment buildings expect their Amazon purchases delivered on time, without fail.
Freight companies would benefit from a mechanism that helps drivers identify open parking closest to a delivery location. The sweet spot for a delivery is the “final 50 feet”—where a delivery driver stops to deliver their freight.
"Significant growth in online shopping is causing increasing demand for urban deliveries, whereas space for delivery vehicles to travel and park is limited,” said Anne Goodchild, a researcher at the Urban Freight Lab. “This project is the first attempt to quantify the problems related to a lack of available parking in urban areas and pilot test technologies that can improve the efficiency of the urban delivery system.”
Urban Freight Lab enlisted PNNL in creating an app that will inform drivers of probable open parking spots—helping to reduce double parking, blocked traffic, and parking fines. Working directly with drivers, PNNL developed the app to include features most usable to freight deliverers.
Important to the app’s functionality is making accurate predictions of an open parking spot and curb space. In a second phase of the project, the Urban Freight Lab will contract with a parking sensor company to install sensors in an eight-block study area in downtown Seattle to collect data about parking spots and occupancy. Once the data is collected, PNNL will process and analyze the data and then feed it to the algorithmic model.
“Historical data, like truck size, type of delivery, and how long a truck stays at a location, combined with real-time data from the sensors will allow us to ‘train’ the model,” said PNNL team member John Feo, who will use his AI expertise to inform the app. “We will be working to understand the data the sensors collect and the parameters needed and feed it into the model to inform parking recommendations for the app, so that there is high probability that a space is opening up.”
The Urban Freight Lab also has plans to place lockers near curbside to make delivery more efficient, for example, eliminate the need for drivers to travel up several floors of a building to drop off packages.
In the project’s first of three years, the team is making strides in delivery efficiency in Seattle’s bustling, congested streets.
“Some of the drivers have had their routes for years, they know their routes very well and the parking situations,” said PNNL’s Lyndsey Franklin, one of the designers of the app, who rode along with drivers from Charlie’s Produce and UPS. “I see this app really helping new drivers hired for seasonal conditions, like Christmas. It will also help more seasoned drivers when conditions pop up, like construction hindering access, so they are not taken by surprise.”
- This press release was originally published on the PNNL website. It has been edited for style