But once these little rectangles start moving by the dozens on nearly unseen wheels, flawlessly gliding around each other, emitting only the faintest whirring sound, they begin to demonstrate their amazing ability to move independently, never once bumping into one another or the many obstacles in this complex warehouse environment.
Remarkably, these autonomous mobile robots (AMRs) have physical strength as well. As one positions itself precisely beneath a 2-meter-tall stack of merchandise and, it slightly expands its width, lifting the stack a few centimeters off the floor and whisks it away to another predetermined spot for humans – or other robots with mechanical arms – to pick out ordered goods.
By blending robotics, automation, and machine learning into the warehousing environment, these floor machines are finding new ways to offset long-standing challenges, such as the shrinking labor market, data collection and the demands of high-velocity e-commerce business models.
Made most famous by Amazon, one of the early versions of these small, boxy warehouse workhorses, created by Massachusetts-based Kiva Logistics, became the symbol of warehouse efficiency when they were first rolled out in 2003.
Rather than rely on humans and a complex arrangement of conveyors belts to move orders through the warehouse, the Kiva AMRs would pick up the stacks or merchandise and bring them to the pickers themselves to reduce walking times. Amazon later purchased Kiva (since renamed Amazon Robotics) in 2012 and now operates more than 100,000 of the little orange units across its vast network.
But logistics companies that think they know everything about robotic warehouse vehicles based on Amazon’s experience may already be behind the curve.
“The market has changed fundamentally in the last few years,” said John Stikes, director of innovation and e-commerce at Germany-based forwarder DB Schenker. The difference, he said, is in the advanced levels of A.I. and machine learning that is being used for advance forecasting. “The items and devices that are being interconnected every year in the internet of things are growing at such a scale that forwarders can now handle an immense assortment of products – it’s a gamechanger.”
Today, several logistics companies, such as DB Schenker, XPO Logistics, DHL Supply Chain and others, are collaborating with dozens of robotics firms to blend innovative, autonomous logistics technology into their operations.
As robotics continues to pave new inroads in the logistics environment, these systems, paired with these forwarders’ inventory management systems, are making warehouses faster, smarter and more efficient than ever. These systems may also help determine what warehouses will look like five to years from now.
“Heavy acceleration of adoption of the technology is where you get the democratization of robotics,” Stikes said. “It now makes sense.”
The market for robotics is already responding to these advances. According to a new report published by Allied Market Research, the global warehouse robotics market was valued at $2.44 billion in 2016 and is expected to reach $5.19 billion by 2023, sustaining a compound annual growth rate of 11.6%.
Last year, XPO Logistics sent ripples through the forwarding industry by announced an exclusive partnership with AMR manufacturer GreyOrange Pte. Ltd., to operate their robot vehicles in North America, the United Kingdom and eight European countries. “We call them cobots,” said Mario Harik, chief information officer at Connecticut-based XPO, “because they work with our human pickers in the warehouse.”
The initial $450 million plan, XPO said, was that it would begin deploying 5,000 of the GreyOrange AMRs over the next year or so to, essentially, bring the cargo to the pickers rather than sending the pickers to the cargo. Each AMR can move a mobile rack weighing approximately 450 to 1,500 kilograms from the storage area it to a station where a worker can fulfill up to 48 orders simultaneously.
Controlled by XPO’s warehouse management system, the AMRs are intended to work together, as a hive mind, bringing priority overnight orders to the front and sequencing other orders as they are made in real-time, while moving other racks back into storage. As with most AMRs, the units are equipped with sensors that enable it to recognize its location in the warehouse and avoid static obstacles, like pallets, and dynamic obstacles, like forklifts and other AMRs as they perform their warehouse floor ballet.
This mobility “allows us to dramatically improve fulfillment time and cut costs,” said Bradley Jacobs, CEO of XPO. “These are important benefits for our customers – particularly in the e-commerce and omnichannel retail sectors, where order speed and accuracy are essential ways to compete.”
This year, RK Logistics Group, a California-based 3PL, which operates 14 warehousing centers totaling nearly 1 million square feet of commercial distribution and fulfillment space in the Bay Area, said it has completed a three-year testing program of AMR systems called CartConnect, which used cylinder-shaped versions of the classic AMR box. Made by Fetch Robotics, in San Jose, the CartConnect units can pick up different-sized carts designed to carry larger boxes and totes, and then autonomously deliver the cart to a destination.
When an employee finishes loading a cart, it can summon the CartConnect AMR, which then picks up the cart and proceeds to its directed location. At its destination, the CartConnect AMR separates from the cart, and issues an audible signal, notifying a worker that the cart has arrived. The worker then rolls the cart to a nearby workspace to complete the shipping process. This also relieves the worker from having to physically lift boxes from the cart and carry them any distance in the shipping area.
With workers collecting items six times an hour – walking an average of four minutes to each consolidation area – each worker can save 24 minutes an hour by eliminating the walking, according to RK Logistics.
RK has also utilized Fetch’s HMIShelf robots for the past three years, which works in tandem with a warehouse worker. These units have a fixed-capacity cart attached and typically can take up to a dozen multiple small parcels, boxes or totes. It is operated by an on-board touch screen, so when the human operator is finished loading the AMR, one of several options is selected on the touch screen, and the robot is sent off on its route. At destination, another employee unloads the cart and then, using the touch screen, sends the robot back to its origin.
The new CartConnect AMRs do not have fixed carts attached. These units are more flexible and can pick up different-sized, higher-capacity carts designed to carry larger boxes and totes, and then autonomously deliver the cart to a destination. These units can be operated remotely by any web-enabled device, such as a hand scanner or through direct integration with warehouse systems.
The Fetch robotics platforms are also being deployed by DHL for a Netherlands-based warehouse operated by Finnish power systems client Wärtsilä. The company’s 37,000-square-meter Central Distribution Center in Kampen, Netherlands, had sent more than 870,000 items to customers in 2015 and was interested in working with DHL to automate the process.
“Our robotic system is up and running and has already saved our operators walking up to 32 kilometers per day,” said Bastiaan Snaterse, project manager for DHL Supply Chain consultancy and innovation. “What is quite impressive is the flexibility of the solution and how easy it is to adjust to our needs.”
DHL also noted that, without any programming experience, the operators were able to modify the paths and schedules of the robots as well as designate restricted areas, demonstrating that the robots are able to adapt to their specific warehouse environments.
At DB Schenker, the robotics tactic involves AMRs, but also includes a mechanical arm to pick certain merchandise from warehouses. In a partnership with IAM Robotics, the forwarder has deployed IAM robotic units that move between rows of merchandise and pick out items from shelves as orders come in and store them in a bin carried by the unit.
“This is an exciting time for the logistics industry, where a lot of great technologies and solutions are emerging,” said Joel Reed, CEO at IAM Robotics.
Whenever the subject of robots comes up, the issue of their effects of the human workforce must be addressed. Automation in the warehouse, after all, can make picking activities four to five time more efficient than if they were performed by humans.
However, as many logistics companies insist, the use of autonomous robotics is having little effect on the numbers of workers they have hired and retained. Rather, the systems merely make the workers’ jobs less labor-intensive and therefore more attractive to the average worker.
“The real benefit of AMRs is that they relieve employees from tedious, low-value work, such as walking a cart full of items from order assembly areas to shipping, and then walking back,” explained Rock Magnan, president of RK Logistics. “It improves the workplace experience for the employee, makes them more efficient, and frees up time for them to focus on more higher-value activity.”
In fact, Magnan said, RK has historically had trouble finding people willing to do warehouse work, especially in the Bay Area. “We continually have dozens of positions open,” he said. “The AMRs help improve the workplace experience for our warehouse associates, enabling us to focus them on work that’s more thoughtful and stimulating, and makes the best use of their talent. This technology has proven to be a positive recruiting advantage for us.”
“RK is a great example of a company innovating its way out of a tough employment market,” said Melonee Wise, CEO of Fetch Robotics. “Robots don’t take jobs, they take tasks.”
“These robots carry all the weight of the products and they get you the goods, you reduce travel time, you reduce bending down to pick up products – it just improves safety,” agreed XPO’s Harik. “It’s more of a risk aversion solution.”
While Harik says XPO does not have to hire as many temporary workers during peak periods, due to the efficiency savings, he said the company is adding more data scientists and machine-learning people to service the robots. “There’s definitely an increase in focus on technology overall,” he added.
In the next few years, expect the need for data scientists in logistics to continue rising steadily. “We have data running out of our ears,” said DB Schenker’s Stikes. As a 2018 article from Forbes noted, about 90% of all data that’s ever been created in the world was created in just the previous two years, and the industry is doing its best to keep up.
“Moore’s Law is alive and well in the robotics industry,” Stikes said, referring to the common observation that integrated circuitry in computers become twice as fast every two years.
So, what can we expect to do with this immense amount of data? If it’s crunched the right way, and the machine-learning functions have worked, we can accurately predict the future, some of the 3PLs said, and plan accordingly.
“If you can imagine we have e-commerce customers that are selling cell phones, and we know that whenever somebody buys this brand of cell phone, they always buy the headset with it,” said Harik. By knowing this, he added, XPO can position certain stock-keeping units (SKUs) that go together, in close proximity in the warehouse.
“The key thing about these robots is that they are going to not only line up multiple shelves of products in front of the pickers but put them in sequence,” he added. “So it’s not just you, as a picker, taking a product from Shelf A and then you wait for the robot #2 to go get Shelf B. They would all be lined up in front of you. So the intelligence is more how you sequence it all – especially through e-commerce, where the customer expects next-day shipment.”
Stikes, however, challenges the notion that warehouse automation is mostly an e-commerce concern. “The process in a warehouse is not fundamentally different whether I’m shipping to stores or to individual homes,” he said. “Industrial clients are increasingly looking at how they can better build kits. How do we build rainbow assortments going to retailers so you get to the point where you can eliminate the back room in a store?”
This is where advanced machine learning and A.I. comes in, Stikes continued. “Ýou can begin to goal-shift and then change what the system is looking for and search for anomalies.”
For instance, you can teach the system to look for traffic jams in the warehouse. If two SKUs are too popular in one location, you separate them across two different aisles to improve product flow. Or, he added, if you see that “on the third Tuesday of the fourth month,” you’re going to move a lot of a particular item, the automated systems can rearrange the warehouse for those items before the next shift begins.
Eventually, Stikes said, with enough trending data collected from these AMRs, logistics companies will be able to make fundamental changes in now warehouses are managed, organized and restocked, and even how the footprint is designed to meet the needs of the customers.
Not bad for an army of little silicon boxes.