Will Drones and AI Manage Your Future Retail Inventory?

Tech firm says its new system can prevent out-of-stocks.

September 05, 2019

AUSTIN, Texas—Using the human eyeball as the primary means of tracking retail inventory may soon be a thing of the past, reports Stores.org. According to Richard Schwartz, president and founder of Pensa Systems Inc., his Austin-based company has created a system that combines autonomous drones, computer vision and artificial intelligence to manage in-store inventory.

Being out of stock on store shelves has long been a bane of the retail industry, with more than one in eight products often unavailable on shelves at any given time, Schwartz says. Retail analysts at IHL Group estimate that in 2018 out-of-stocks caused retailers to lose $984 billion in revenue worldwide, including $145 billion in North America.

Shoppers often postpone making purchases when the products they want are not on the shelves. “That’s a very material loss for the retailer on the revenue level and profitability level,” said Schwartz.

The core of the Pensa platform is the deployment of small, camera-equipped drones that capture stock conditions on store shelves. The drones are self-guided and automatic, acting as “a roving pair of eyes for staring at the shelves,” said Schwartz, adding that it’s on the back end where retailers can enjoy the primary benefits.

Stock information captured by the drones’ cameras are forwarded in real-time and stored in the cloud, giving stores immediate visibility into their stock situation. The AI architecture then learns and analyzes information from the shelves, such as recognizing how products are managed while drawing conclusions about inventory status.

The drone operations are designed to be quiet in a retail store environment and are far less intrusive than the recent inventory tracking robots that have launched in some retail stores, Schwartz said.

The drones operate automatically and are set to deploy during hours when stores are closed or during store hours on aisles that are free of shoppers. In testing the technology during store hours, Schwartz found that nearly half of the shoppers were unaware of the technology’s presence.

Using AI, computers can be trained to recognize products on the shelves almost to the individual item level, Schwartz said. “We train the computer not only literally to look at the shelves, but effectively to recognize things the same way people do.”

Currently, Pensa Systems is working with major retail chains and large manufacturers to move this technology into store environments.

For more on how artificial intelligence and innovation are shaping the retail landscape, see “Mapping Innovation" in the April 2019 issue of NACS Magazine, plus “Revolutionizing Retail” in the August 2018 issue  and “What’s Minding the Store” in the October 2018 issue.