Amazon Go knows what a customer has in their cart

In early 2018, the global e-commerce giant Amazon opened its first unmanned Amazon Go store for public use (prior to this, the store without cashiers and staff was available only to company employees for two years). Not surprisingly, Amazon decided to try out the latest AI developments, not only on an automated checkout system for goods without a checkout. All Amazon Go sales departments are equipped with high-tech cameras with an automatic RFID object identification system. Typically, such a system is used in unmanned electric vehicles to track the behavior of passengers in the cabin and automatically process visual information from a computer. But Amazon Go cameras monitor shopper behavior from the moment they enter the store to the moment they pay for the purchase.

The main purpose of the cameras is to determine which items are most in demand, which products customers return to the shelves most often, etc. In addition, Amazon Go cameras detect faces and determine the height, weight, skin color, and other physical characteristics of customers. Subsequently, an AI connected to the video recording system, based on all the data received, not only determines the most popular products for specific consumer groups but also offers options for changing the pricing policy. All this work is performed automatically by a computer without human intervention. The cameras are also connected to the store"s automated warehouse system and shelves equipped with Sensor Fusion sensors. If it is impossible to determine the product taken by the buyer from the shelf, the camera finds it in the warehouse system and coordinates with the weight and motion sensors that are located on each shelf. Let"s say a customer took a carton of milk and started reading the composition of the product, but suddenly saw a familiar brand in the neighborhood and returned the package to its place. Even those few seconds of choice in Amazon Go will be tracked by the camera, touch sensors, and inventory system, and the AI will draw the appropriate conclusions.