When you imagine a retail employee, you probably think of someone at the register or helping a customer. However, employees also spend a lot of time searching warehouses and production floors, fulfilling orders or online orders, and generally trying to keep track of all their inventory.
Tracking inventory takes a long time, in part because retailers don’t always know where everything is. That’s why when you ask a salesperson to check if they have a shirt in your size, it may take them 20 minutes to respond.
Cartesian helps retailers track inventory with technology developed at MIT. The system uses wireless signals from radio frequency identification (RFID) tags attached to items to determine their exact location in the store, from the warehouse to the production floor.
Last year, Cartesian conducted a study with the retailer and found that its platform delivered significant annual savings at the store level by improving inventory tracking, optimizing workflows and improving customer experiences.
“The big problem we’re solving is that about 50 percent of retail hours are spent on inventory management,” says co-founder Fadel Adib SM ’13, PhD ’17, an associate professor at MIT. “This is an approximately $15 billion problem in the United States alone. We use algorithms to decipher indoor locations using wireless signals. The underlying technology enables a new level of indoor location.”
Cartesian is already implemented in over 700 stores in 15 countries and cooperates with one of the largest fashion groups in the world, Inditex, which is the parent company of brands such as ZARA, Pull&Bear and Oysho.
In addition to retailers and warehouses, the Cartesian platform can also improve indoor location tracking for manufacturers, logistics operators and robotics companies.
“The broad vision of what we do is spatial artificial intelligence,” says Adib. “Today, AI is doing exceptionally well in the digital world. Now it needs to move into the physical world. That means enabling machines to perceive their environment in a way that they can interact with it. This is where spatial AI comes in and where the Cartesian comes in.”
From technology to product
Adib, who works jointly in the Media Lab and MIT’s Department of Electrical Engineering and Computer Science, has been researching wireless signals at the Institute for more than 15 years, dating back to his graduate studies.
“My group today is exploring how to use wireless signals to sense the world in ways that weren’t possible before,” Adib says. “We develop the core technology and then build systems around it. Our goal is to deploy these systems in the real world to achieve impact.”
When Adib joined the MIT faculty, the first project he worked on was indoor localization using RFID tags. Isaac Perper ’20, MEnG ’21 later joined his lab as a graduate student, and together they developed machine learning algorithms to process RFID data to translate it into localization patterns, initially focusing on helping robots locate RFID indoors.
In 2021, Adib participated in the National Science Foundation’s I-Corps program, which requires researchers to interview potential customers to find relevant problems to solve with their technology. That’s when he realized what a gigantic problem inventory management was for retailers.
Cartesian was officially founded by Adib and Perper in early 2023 after receiving a diminutive business award from the National Science Foundation. The two worked with MIT’s Office of Technology Licensing to license patents from the Adiba lab. They also received support from MIT’s Venture Mentoring Service.
“Our goal was to reduce the cost of the technology to make it scalable,” Adib recalls. “Isaac focused on simplifying the product, leveraging advances in machine learning, and accelerating performance. At first, this required a lot of iteration and testing.”
For many reasons, retail workers spend most of their time locating items. They may receive an online order to fulfill, restock store shelves, or receive an inquiry from a customer about items in the back.
Stores vary in how they organize inventory. Most separate items by category on specific shelves and bins and then operate barcodes or inventory systems that tend to become dated quickly.
“This is a big problem for stores because customers may simply leave before asking an employee to check their size, or customers may become frustrated and leave if it takes too long,” Adib says. “The co-worker also wastes time searching for items that could be used to perform higher-value work.”
The Cartesian platform works with retailers’ handheld RFID readers that store associates already operate to manage inventory. Each store installs Cartesian software into their existing warehouse applications or uses a custom application that employees have direct access to.
“Thanks to RFID readers, stores inform what is in stock and what is not” – Perper says. “We found a way to take the same scans they already use in the reader, put the generated data into our machine learning algorithms, and generate maps of where everything is located.”
Customers can create analytics powered by Cartesian technology to track inventory levels, show customers maps of where each item is located, and create other services.
“They use our location intelligence platform and create different products based on it,” says Adib. “We can work with any device, any store, any type of RFID. It’s a simple interface. All the sophisticated location algorithms are in the cloud.”
Outside of retail
Cartesian signed its first gigantic contract in 2025 and soon expanded its operations to several hundred stores. One of the advantages of Cartesian is the ability to scale quickly. Perper says he can add a store in about a minute. The Cartesian team doesn’t even have to go to a recent store to turn on the system if they already have a relationship with the company.
“It’s as simple as flipping a switch, preparing the data and sending it to our customers,” says Perper. “One of our first big bets was, ‘Can we build this entirely on existing hardware?’ That bet is starting to pay off.
Cartesian models can also work with Wi-Fi and Bluetooth signals, which the company plans to use with customers in other industries.
“Right now we’re focusing on retail applications, but the technology has a lot of relevance in manufacturing, warehouses and other locations,” Adib says.
The Cartesian team aims to deploy to tens of thousands of stores over the next year and then begin expanding beyond retail into industries such as manufacturing and robotics.
“What’s most exciting to me about Cartesian is that we’ve built a lot of the technology foundation, and now that we have the foundation in place, we hope to build specific application layers,” Perper says. “Then we can ask customers across industries about their problems and apply our technology in different ways to solve them.”