
Amazon is rolling out new AI technology to help delivery drivers work more efficiently. The company's Vision-Assisted Package Retrieval (VAPR) system uses computer vision to highlight packages for each stop, potentially saving drivers significant time and effort.
VAPR projects a green circle onto packages meant for the current delivery stop and a red X on others. This visual cue, combined with audio feedback, allows drivers to quickly identify the right items without manually sorting or checking labels.
"Before, it could take me anywhere between 2 and 5 minutes to empty a tote and organize packages for the next stops. Now, with VAPR, this whole step just takes me about a minute," said Bobby Garcia, a driver testing the system in North Boston.
Amazon plans to install VAPR in 1,000 of its Rivian electric delivery vans by early 2025. The company says early tests show a 67% reduction in perceived physical and mental effort for drivers, saving over 30 minutes per route.
The technology adapts Amazon's warehouse robotics systems for use in delivery vehicles. It uses machine learning models trained to recognize various package types and labels in different lighting conditions.
While finding packages only takes a few minutes per stop, Amazon says this can add up significantly for drivers making over 100 deliveries daily. By streamlining this process, the company aims to improve delivery accuracy and allow drivers to focus more on customer service.
VAPR's development, which began in 2020, required addressing unique challenges of the delivery environment, including limited space and variable lighting in vans.
With hundreds of thousands of drivers and vans in its global fleet, Amazon sees VAPR as a way to boost efficiency at scale across its massive delivery network.