Amazon reroutes drivers in real time
Amazon is enhancing delivery drivers’ ability to avoid traffic and road hazards.
Over the past two years, the e-tail giant has been developing and piloting a new technology called Fleet Edge to automatically detect changes in roads, traffic signs, and highways. Fleet Edge continuously refreshes on-road information into Amazon’s mapping software, providing the most up-to-date routing data for drivers delivering packages.
Previously, when a driver faced a challenge like a recent road closure due to construction, it might have taken several weeks for that update to make it into Amazon’s routing software, adding more time required on behalf of for the driver to navigate around the closure.
The Fleet Edge solution features an in-vehicle computer, street-view camera, and GPS receiver that are designed to keep up with the rapidly changing road environment and capture changes that day, so drivers have fewer disruptions during their delivery experience.
How it works
When a driver is en route, the Fleet Edge system detects newly constructed roads, traffic signs, closures, and buildings, automatically and continuously updating the navigation for future routes with a more comprehensive and current map of the area. Over the past few months, more than 33,000 new signs have been added to Amazon’s mapping system.
By providing up-to-date information on road conditions, drivers can avoid challenging driving maneuvers, reduce the need for U-turns, and bypass road hazards. Additionally, Amazon says the accuracy of GPS location has increased by 260% in the test areas, improving navigation safety by announcing upcoming turns sooner.
"With the help of drivers and DSPs, we identified the need to improve safety and provide more precise and accurate routes that better reflect the constantly changing on-road environment," said Beryl Tomay, VP of Amazon Last Mile Delivery technology. "By investing in Fleet Edge, we're creating a more safe and seamless experience for drivers’ and eliminating on-road navigation challenges that add time to routes."
Amazon partners with MIT to optimize routes
In other efforts to maximize delivery efficiency, Amazon’s Last Mile team, which develops planning software for the e-tail giant’s delivery fleet, collaborates with the MIT Center for Transportation & Logistics (CTL) to incorporate driver know-how into route optimization models. In February 2022, the two groups began sponsoring a competition, called the Amazon Last Mile Routing Research Challenge, in which academic teams will train machine learning models to predict the delivery routes chosen by experienced drivers.
Amazon is providing the training data for the models and will be evaluating submissions, with technical support from MIT CTL scientists. The historical data provided by Amazon will include approximate delivery locations, package dimensions, and travel times and distances between locations, all information that is used by existing route optimization algorithms.
However, Amazon will also provide more than 4,000 traces of driver-determined routes, which encode the drivers’ know-how. Using both sources of information, contestants will be able to build models that identify and predict drivers’ deviations from routes computed in the traditional manner.