Instacart has acquired Israeli company Arpalus to strengthen its computer vision technology for shelf data in grocery retail. The platform aims to identify more accurately which products are actually available on shelves, so that online orders can be fulfilled more reliably.
Arpalus’ solution turns a short video scan of a shelf into a real-time view of the products that are actually available in store. According to Instacart, the technology can identify individual items on shelves with more than 95 per cent accuracy on average. Using computer vision the solution was built specifically for the complexity of real grocery store environments, including low or unreliable Wi-Fi, inconsistent lighting, and thousands of visually similar products packed tightly together.
Instacart plans to use Arpalus’ technology with its Caper Carts that have external cameras. As the carts move through aisles, they can update shelf inventory insights in real time. Instacart has deployed the Caper technology in almost 100 cities across 15 US-states. This year, Morrisons has become the first British retailer to test the solution, as The Retail Optimiser reported. In 2024, Aldi Süd had tested Caper at its Hofer banner operation in Austria.
Shelf scans shall improve Instacart’s AI models
Arpalus technology also runs on any smartphone or camera-equipped device. Instacart aims for its network of around 600,000 ‘professional shoppers’ to collect shelf data through the app that they already use for each online order. The system can also guide the crowd workers during the scan. It can prompt them to adjust camera angles or distance, so that the shelf is captured more accurately and efficiently.
The E-Food platform hopes for the richer shelf data to improve several of its products. The company states more accurate inventory data could improve the Instacart Marketplace, retailer websites powered by Storefront Pro, Store View and sensor data from Caper Carts.
Real-time visibility into inventory
“Arpalus was founded to solve one of retail’s most fundamental challenges: bridging the gap between what happens in-store and the decisions driving business performance,” said Ofir Zilberberg, Founder and CEO of Arpalus: “We built an AI platform that gives retailers real-time visibility into inventory and store execution, enabling faster and smarter decisions at scale.”
