Smart warehouses and distribution centers are addressing the challenges of asset tracking by increasing the use of technologies such as machine vision, artificial intelligence and the Internet of things, as well as autonomous and supervised robotics.
Recent trends pose major challenges to warehouses and distribution centers. According to the U.S. Census Bureau and the Department of Commerce, the share of e-commerce in retail sales has increased from 10.5% in early 2019 to 13% in the past quarter, and will soar to 15.7% in the second quarter of 2020. This growth has put pressure on these facilities to improve efficiency and speed.
At the same time, the warehouse department has been struggling with labor shortage. According to the Bureau of labor statistics, throughout 2021, job vacancies in the U.S. warehousing sector reached or exceeded 5% of the total number of jobs in the sector, which means that about 75000 jobs have not been filled.
There are differences between warehouses and distribution centers: the former is used for long-term storage and inventory construction, while the latter is more suitable for high-speed and rapid turnover operation. The bottom line of both is to know where their things are, where they need to go, and how to get them there.
"At a basic level, it's asset tracking. If you think about it, about 70% of the use cases in the Internet of things world revolve around tracking the location of something," said srini samudrala, senior vice president of digital and Internet of things at zyter, a company based in Rockville, Maryland“
Both facilities are addressing this tracking challenge by increasing the use of "intelligent" technologies such as machine vision, artificial intelligence and the Internet of things, as well as autonomous and supervised robotics. According to the data of ABI research, a market research company, by 2025, more than 4 million commercial robots will be installed in more than 50000 warehouses, which is a great increase compared with the 4000 robot warehouses tracked by the company in 2018.
Seize the opportunity
New and old companies, large and small, are trying to establish themselves in the smart warehouse and distribution center market. For example, Honeywell launched its Honeywell universal robot controller (hurc) in 2020, after the company had launched an autonomous robot unloader. Thomas Evans, chief technology officer of Honeywell robotics, recalled: "Hey, we're trying to make these robots different from other robots in terms of hardware, so we don't have to make these robots universal. Then we're making these robots into one or more control systems. In this way, we don't have to make these robots universal."
In a white paper entitled "breakthrough robotics empowering distribution centers", Honeywell pointed out five key technologies. The progress of these technologies makes a new generation of robots in the storage and distribution industry possible.
● sensors and vision, including three-dimensional (3D) cameras and lidar.
● machine learning and artificial intelligence (AI), allowing robots to solve problems independently.
● connect through the cloud.
● computing power.
● mobility.
Our idea is that with these technologies, robots will be able to solve the warehouse problem by themselves, while humans will continue to guide the training operation. Honeywell believes that the tasks performed by the robot include loading and unloading, picking items, sorting and placing them on pallets.
Evans said: "The product we just released is an intelligent flexible unloader. The products come in on the pallet; they can be products that look the same or products that look completely different. The robot system uses machine vision to distinguish between two packages and says, 'I just want to pick this one and put it on the conveyor belt'. It will also learn from it; it says, 'I succeeded in picking this time, and the image of my success looks like this 。 It builds an information base from which the robot can draw more inferences. "
Another company active in this area is Qualcomm, whose smart city accelerator program is part of a strategic partnership with zyter's smartspaces Internet of things platform. "We don't make equipment at all," explains samudrala of zyter. "That's where the relationship with Qualcomm is good for both of us."
Other members of Qualcomm's program provide trackers, cameras and sensors that zyter uses to implement smart warehouses.
"We have a platform with many different components, but we don't just bring in one platform. We integrate with some devices in advance and convert their data and protocols into our growing data model.". Zyter's platform currently hosts more than 200 different devices in its ecosystem. " Samudrala said.
Like Honeywell's hurc, zyter's smartspaces are modular. "It's just a bunch of Lego blocks that you can put together and build any solution you want," he said If all you want is basic asset tracking, zyter can give it to you; Here is the device, here is the application. This is one of our basic modules. We also do automation. We also do automated inventory management: know how many things you have in the warehouse and, more importantly, where they are stored., "Said samudrala." We've implemented indoor navigation, so you can go out and find them and tell you whether the objects are not in the right place, when they enter inventory, when they leave, and whether this should happen. "
Smartspaces uses analytics to help the warehouse go beyond simply understanding the content and location of items and predicting future needs. Samudrala said: "some of the analyses we do today, from descriptive to predictive and even prescriptive, are mainly driven by the analytical and supervised learning process“
An example of the warehouse project that Qualcomm and zyter are working on is the current work for onescreen, a provider of video collaboration products in San Diego, California. The project will involve autonomous mobile robots, augmented and virtual reality tools and IOT sensors, all of which work together with the warehouse management system. Onescreen's question is "how do we track all the inventory in the warehouse?" samudrala said, "and how can we better manage these inventory based on incoming orders, the history of all orders, etc. We know how much inventory they have to complete an order. We are also obtaining data from the order to determine whether the inventory can meet the incoming order, and then start to fulfill the project. "
Smart and transparent
As for the future of this category, Evans of Honeywell said: "obviously, robotics will become more complex. Customers are constantly changing the way they operate, not the choice. They want to see the performance of the software: Data dashboard and user interface. We need to be very flexible to hurc to ensure that we provide the correct updates to the software."
