Algorithm Will Tell All UPS Trucks Where to Go

A UPS driver has, on average, 120 stops to make each day. But what’s the most efficient route that driver can take?

The company is hoping its Orion (On-Road Integrated Optimization and Navigation) computer platform will solve this issue for its 55,000 US routes using an algorithm that examines travel costs, distance, and other factors to spit out not necessarily the optimal route, but the most reliably good one, the Wall Street Journal reports.

“Customers and drivers like consistency,” a UPS senior director of process management tells the Journal. “Orion has to know when to give up a penny to make the results more stable.”

This efficiency has become paramount as UPS struggles to compete with FedEx, boost earnings growth, and figure out a way to optimize the many residential stops it now makes.

Rough Patches
The deployment of Orion isn’t always so smooth, though. That is where Mr. Levis comes in. As project manager, he is responsible for getting people and machines to work together. During the earlier stages of writing the Orion algorithm, it was Orion that had to learn to accommodate people.

Jack Levis is the leader of UPS’s Orion project
Jack Levis, leader of UPS’s Orion project, which has been 10 years in the making.
Photo: Matt Roth for The Wall Street Journal

“The project was nearly killed in 2007, because it kept spitting out answers that we couldn’t implement,” Mr. Levis recalls. The earliest versions of Orion focused on getting the best mathematical results, with insufficient regard for the interests of the driver or the customer, who value some level of routine. For example, regular business customers who receive packages on a daily basis don’t want UPS to show up at 10 a.m. one day, and 5 p.m. the next. And a customer who is expecting a shipment of frozen food needs delivery as soon as possible, even if efficiency demands that someone gets priority.

To get the project back on track, UPS chief scientist Ranga Nuggehalli turned to Bob Santilli, a senior project manager, asking him to describe a perfect route. Several weeks later, Mr. Santilli came back with the results of his effort, which produced a model plan of stops for drivers on a route in Lancaster, Pa. The engineering team extracted proprietary rules from the Santilli route and built them into Orion.

“By April or May of 2007, he had the first working version of Orion, which balanced consistency and optimality. It had to do with keeping the driver in a path. The route should flow. That is what we learned. That is what brings consistency. Orion can make exceptions to the flow, but it has to do so in an intelligent manner and it can’t make an unlimited number of exceptions,” Mr. Levis said.

The Wall Street Journal

Here’s how an Orion-driven workday would go: A UPS driver would start by checking out her delivery information acquisition device (DIAD) to see the route Orion has chosen, which the system updates and recalculates based on factors like incoming orders and customer requests for specific delivery times - soon, it may even be able to do that while a driver is on the route.

The system hasn’t caught on with everyone - one driver, for instance, tells the Journal the system calculates routes with more left turns and backing up, which UPS drivers are discouraged from doing. But Orion engineers have been on training ride-alongs with drivers to see how the logic of the system is failing in real-world situations and are correcting the system based on those findings.

CEO David Abney has said that once the system is fully implemented by 2017, it should save up to $400 million a year.

Source: Newser