Amazon unveils updated Just Walk Out technology
In a blog post on Amazon’s corporate website, the global online retailer and on-demand cloud computing provider, announced a significant update to its frictionless checkout technology Just Walk Out.
Jon Jenkins, vice-president, Just Walk Out technology, AWS Applications writes that this new advancement “further increases its accuracy by using the same transformer-based machine learning models underlying many generative AI applications, and applies them to physical stores.”
“We accomplish this by analyzing data from cameras and sensors throughout the store simultaneously, instead of looking at which items shoppers pick up and put back in a linear sequence. For retailers, the new AI system makes Just Walk Out faster, easier to deploy, and more efficient. For shoppers, this means worry-free shopping at even more third-party checkout-free stores worldwide,” he adds.
First launched in 2018, Just Walk Out is used in 170 third-party locations at airports, stadiums, universities, hospitals, and more in the U.S., UK, Australia, and Canada. In Canada, Just Walk Out is deployed at Calgary’s Scotiabank Saddledome and Scotiabank Arena in Toronto. It is also operating at Toronto’s Peason Airport at The Goods Express where travelers can purchase travel essentials, such as drinks, snacks, grab n’ go food, travel accessories, and electronics.
READ: Scotiabank arenas in Calgary and Toronto debut cashierless c-stores
“Just Walk Out technology, which launched in 2018, was built using generative AI and leading-edge machine learning available at the time to figure out ‘who took what,’” writes Jenkins.
“Previously, the AI system analyzed shopper behavior sequentially—their movement and location in the store, what they picked up, and the quantity of each item—each action processed one after another. However, in unusual or novel shopping scenarios (such as if a camera view was obscured due to bad lighting or a nearby shopper), the sequential approach could take time to determine purchases with confidence, and sometimes required manual retraining of the model.”
To overcome this hurdle, the new generation of Just Walk Out uses a multi-modal foundation model to better tackle these real-world shopping scenarios and overcome “variables such as camera obstructions, lighting conditions, and the behavior of other shoppers, while allowing us to simplify the system,” Jenkins continues.
“For example, a shopper might pick up and put down multiple varieties of yogurt, in different combinations, and as they are doing so, another customer might reach for the same item, or the freezer door could fog up, obscuring the cameras’ view. In complex situations like these, the new model can quickly and accurately determine the actual items taken by each shopper.”
