Retail now has its very own robot – AndyVision. The robot's designer Priya Narasimhan, a professor at Carnegie Mellon, who heads the Intel Science and Technology Center in Embedded Computing, recently demonstrated AndyVision at an Intel Research Labs event in San Francisco. The robot not only takes inventory but also assists shoppers and is made up of a combination of different types of algorithms, running on a low-power system. It's easier for retailers to implement than RFID tagging, Narasimhan said in a story published on phys.org.
Before designing the robot, Narasimhan's team interviewed retailers to learn about their needs and found that stores lose customers when they run low on high-demand items or when a customer picks up a product but then discards it in a random aisle. The robot, dressed in a red hoodie, has been scanning shelves and generating a real-time interactive map of the Carnegie Mellon university store since May. Customers can browse the inventory via an in-store touchscreen to see if a product is in stock without entering the aisle. The system also displays product information.
AndyVision performs inventory checks, identifying each item on the shelves and alerting employees when items are low or missing. It searches for barcodes and text and uses information about the shape, size, and color of an object to determine identity. The robot can also determine when items should be placed next to each other.
After the campus store test is complete, other retailers will test AndyVision. Watch a the clip below to see AndyVision in action.