Ecommerce stores warehouse

How CoEvolution Robotics Software Handles Warehouse Automation

The large robot extends upwards, standing more than four meters. He pulls out a plastic tote box and bends over to place it on a lower shelf, before retreating. Then a shorter robot rolls up, removes the bag, turns around, and delivers it to a human staff member.

All around the warehouse, the scene repeats itself – several robots performing different tasks simultaneously without ever colliding. Yet they were made by different manufacturers and use different operating systems.

What keeps the warehouse running smoothly – fast and efficient order processing – is not the hardware, but the software.

Developed by Chinese smart logistics start-up CoEvolution, the software platform is able to communicate with all the different systems in the warehouse, giving it what CoEvolution founder Lijun Zhu, 39, calls a “God’s sight”, which then makes it possible to orchestrate all the different robots, proactively setting tasks for them while making sure they don’t get in the way of each other.

“Robots don’t communicate with each other, they communicate with our platform system,” Zhu explains. “We have an open platform that can coordinate with different types of robots. It’s very hard to do actually, but we built it.

He says the growing availability of relatively inexpensive and reliable robots means the software element will be what sets the best logistics solutions apart. He anticipates a “big trend” to adopt robots in logistics.

The warehouse described above is in the southern city of Guangzhou and is owned by a leading MRO supply distributor MYMRO, the former Chinese subsidiary of Grainger.

Robots help warehouses maintain high inventory levels

In order to provide a premium customer experience with adequate inventory, the warehouse keeps hundreds of thousands of products in stock. By using CoEvolution, the company was able to store most of its inventory on high shelves and through order data, the robot’s control system would automatically move in-demand products to lower shelves in advance so that they can be selected for dispatch by other robots. This means that the picking area in the warehouse can be reduced by half while also reducing human labor by approximately 50%, representing significant cost savings.

“The analogy is like a computer hard drive and computer memory. You have most of your inventory on high shelves, like all the data on a hard drive. But then when you need it, you load everything into your memory, which is the lower level of the shelf, and the other robots will bring the products to that lower level to the human operator. It’s very efficient and high-density,” Zhu says.

It may be a software solution, but Zhu says she was born from long hours of visiting the MYMRO warehouse and seeing how it works – and before that, years of experience learning the “pain points” in the logistics industry. Zhu had an interesting career – after earning a doctorate. A graduate in the US, he went to investment bank Goldman Sachs before joining Amazon and working on supply chain optimization, which first sparked his interest in logistics. His interest in the internet then led him to move to Facebook, after which he returned to China and started in the logistics arm of Alibaba, working on the integration of artificial intelligence and machine learning into the logistics. In 2019, he left the Chinese e-commerce giant to found CoEvolution.

“So it’s a very traditional field, you move real things around with very interesting and advanced mathematical models and software. I could see the value of that, you impact the world, real things,” says -he.

“But my experience in the internet industry is also valuable because it made me feel that by applying advanced techniques you can create a lot of value.”

Zhu goes to great lengths to point out that creating a robot control system is not like imagining an algorithm to use online. Working in the real world means unforeseen issues that the platform must be robust enough to absorb and keep running. Too much complexity and sophistication can be as detrimental as too little.

“You have to really go to the warehouse, work with people, get really tired and have all these different issues, and then you figure out how to control the right level of complexity, the right level of sophistication in your models.”

Long Wong is a satisfied customer. He is the founder and chairman of ProA Supply Chain, the logistics subsidiary of China’s leading e-commerce beauty brand eBeauty Group (also known as UCO Cosmetics), which has achieved over $3 billion in sales of cosmetics last year.

According to MIT-educated Wong, ProA first tried using automated guided vehicles (AGVs) to bring goods from shelves to warehouse workers in 2018, but was disappointed with the standard implementation of the technology. Black Box. Workers had to wait a long time between picking, and the AGVs didn’t integrate well with other warehouse processes. The overall result, he says, was a warehouse 20% less efficient than equivalent manual operations.

Intelligent Logistics Platform Improves Warehouse Efficiency

In contrast, the use of CoEvolution’s intelligent logistics software platform has enabled: better robot routing allowing fewer robots to be used; integrating processes with the overall flow of warehouse operations, which improves the overall efficiency of human worker throughput; and the ability to integrate robots from multiple vendors to handle different specialized tasks.

“I think CoEvolution’s technology is unique,” ​​says Wong. “Not only does it integrate robots from multiple vendors, but it also orchestrates the tasks and movements performed by the robots. I think this will be the future of warehouse automation.

Communicating with different robots is one thing, reacting to change is another – and that’s where Zhu says his background in artificial intelligence and machine learning comes in.

Change is hard in logistics, which requires planning — an e-commerce business can plan a supply chain to last about three years and find that after a year the business has changed, he says. Third-party logistics providers are at even greater risk: one day they may provide warehousing solutions for consumer packaged goods, the next it may be electronics.

“It really illustrates the biggest problem for customers and technology vendors. You give your solution to the customer and a year later everything has changed, it’s really a headache,” he says.

That’s why CoEvolution focuses on developing the software’s ability to react to change rather than predict it, Zhu says.

For example, a typical warehouse may have an area with wide aisles where the hottest products are stored, making them easier to access. If customers then move on in droves to buy something else, for example following a celebrity endorsement, suddenly everything is in the wrong place. But CoEvolution’s software platform can react as soon as order data starts coming in by rearranging inventory so that in-demand products are in the right place for quick selection. This happens automatically and requires no human intervention, Zhu explains.

So far, it’s a solution that works well for both e-commerce and traditional retail in China, where demand has fluctuated more widely than in the US and Europe – at least until now. as the Covid pandemic hits, disrupting supply chains and causing an increase in online shopping. in the West.

Logistics Lessons from Warehouse Automation Deployment in China

For Wong, the Chinese experience offers valuable insights: “Supply chain professionals in the West can leverage the hard lessons we’ve learned and leap forward by leveraging software and hardware that have been developed in China.

Meanwhile, Zhu is eyeing new markets — CoEvolution is working on a project in South Korea and wants to expand further — as well as different business sectors and the latest advancements in robotics technology.

He wants to integrate the platform with other types of automated equipment such as robotic arms. Technologies such as computer vision could be applied in warehouses, he says, with robots recognizing and choosing individual products rather than boxes in one location.

Explaining to potential customers what CoEvolution does is a challenge, he says, because it can be difficult for them to conceptualize. But he is confident that the company will prove its worth.

“Having such an adaptive solution is the future, which provides the core value to customers,” he says.

“We were in this industry, we feel the pain. All your plans are disrupted and you have to reschedule everything. It is very hard and tiring. We are trying to solve this problem with our technology.

Hill Thurber is a freelance producer at the BBC. In 2008, when he started out as a journalist, he lived in China. He is based in London.