The autonomous devices recognize stock levels and prices on the shelves while scrubbing the floors in all of the company’s 600 stores.
October 31, 2022National big-box retailer Sam’s Club automates on-shelf merchandise management by accurately identifying item, location and price tags using a floor-cleaning robot equipped with computer vision technology. The solution leverages the store’s previous investment in cleaning robots that autonomously navigate aisles, scrub floors while navigating and avoiding obstacles. With the addition of computer vision, stores now have visibility into stock availability on the shelf and where products need to be restocked, removed or adjusted based on analysis of the computer vision images.
Sam’s Club is a members-only retail warehouse club owned and operated by Walmart. Its 600 warehouse clubs are located in 44 states, as well as in Puerto Rico and the US Virgin Islands. The shops known as “clubs” sell goods in bulk. Typically, surplus products are stored on the top shelves rather than in a storage room, while the floor houses salable goods, often sold on pallets. When goods are sold from the bottom, they can then be refilled from the top shelf.
The company’s goal is to equip employees with tools and insights to free up more time to support Sam’s Club members, which it says is a key differentiator from other retailers. So, in late 2018, Sam’s Club explored autonomous floor scrubbing machines that could be manually propelled while still offering the ability to be self-guided. “We thought the concept of autonomous scrubbers would be a tool that would allow staff to reallocate time to members,” says Todd Garner, VP of club product management at Sam’s Club, “so we started with limited testing.”
Time savings for employees
After testing Tennant’s floor scrubber at multiple locations, Garner recalls, “We recognized that autonomous scrubbers brought value to members and staff, and we began rolling them out to all clubs.” the robotic device could provide and looked at inventory, location and management processes. Traditionally, Sam’s Club websites in the United States used a manual inventory tracking method. Staff used pen and paper to keep track of what was properly stocked on the shelves and what needed replenishment.
This was prone to a very time-consuming process, Garner recalls. With the initial paper-based inventory process, the printed reports used by store staff were filled with a large amount of unprioritized data on goods that should be on the shelves. For these employees, inventory management required an exhausting process of reading long lists of inventory details and then prioritizing them. The company’s newer inventory management iteration was digitally oriented, he explains.
“We built this suite of tools,” says Garner, “and our focus was basically to provide better insights and make it easier to act on those insights.” The software tools would prioritize information and provide filters, and they could sometimes activate corrective actions automatically. “But ultimately it was still dependent on the employee finding a problem, diagnosing that problem, and then acting on that problem.” The retailer considered a variety of options to remove manual labor from the process, including drones and fixed cameras before settling on the scrubbers that every store already has in place to get the most consistent, reliable, and accurate data.
Sam’s Club decided that the computer vision functionality would allow him to understand the conditions on the shelves and therefore when to do the restocking. The chosen solution is the T7AMR Shelf Analytics Accessory, made by robotics company Brain Corp. designed and manufactured by Tennant. Tennant built three cameras into each scrubbing robot, along with wireless connectivity to send photos to image processing software, which automatically identifies and marks areas that need attention. All scrubber systems in the company’s 600 stores now include camera vision scanning capability.
Conduct automated inventory counts every night
Typically, the scrubbers are put to work each morning by scanning the opening inventory. The scrubbers have sensors that detect their location within the store, allowing them to detect and avoid obstacles by passing a shopping cart, shelf fixture, or other object that gets in their way. While the robots are pre-programmed to follow a fixed route, they use the sensors to avoid obstacles along the way.
The system includes a tower mounted above the scrubber, which houses three cameras – two in one direction and a third in the opposite direction. One camera is mounted halfway up while another scans the lower shelf level. On the other side of the robot, the third camera is aimed at the top shelf, where surplus goods are stored. The image-based system for scanning shelves begins by capturing image-based data on all three levels of shelves in all aisles.
To scan the shelves, the washer goes through each aisle twice, once in each direction. Cameras capture images that are then linked to the scrubber’s location, and Brain software processes those photos using computer imagery, then translates that data into insights for club employees. These insights can be used to accomplish multiple tasks, Garner says, adding, “A good shopping experience really comes down to making sure items are priced right, making sure items are on sale, making sure items are findable.” are.”
The software can detect correct or incorrect pricing on shelf labels, flagging any pricing discrepancies for staff attention. In addition, the scrubbers can determine inventory levels for each storage unit and highlight products that will soon require a backorder. In addition, the system can detect if a product is in the wrong part of the store or on the wrong shelf.
Providing analytics to employees via an app
Garner says employees have access to insights on their mobile devices using the company’s ecosystem of apps. The first pilot of the scanning solution began in late 2019 at several Sam’s Clubs in California, after which the company began rolling out the solution chain-wide throughout 2021.
Using the scanning capability and the resulting analysis, Garner says, “I strongly believe that Sam’s Club is at the forefront of stationary innovation and that’s why we continue to develop and evolve this.” Other technologies are being considered for future applications, he notes , including UHF RFID tags and readers, to provide accurate quantities of select products such as B. clothing, to definitely identify. “When we complete a use case and solve a problem, we move on to the next and to the next.”
To date, the value of the scanning system is reassurance that products are available on the shelves and prices are properly labeled without the employees having to spend hours and tedious work. “We believe that when we can provide our employees with the right insights at the right time, it’s a better experience for employees and members,” says Garner. “It’s a better experience for everyone and ultimately the true value our members have come to expect from us.”
The central theses:
- Sam’s Club leverages its existing robotic floor scrubber technology to capture inventory data and on-shelf pricing information with the computer vision add-on.
- The technology saves store associates time that would previously have been spent manually checking stock levels and price tags.