Robots are helping out this holiday season
Last year the holiday shopping season was like a disaster. Many more people were shopping online because of the pandemic, and millions of packages were delayed or delivered late.
This year could be worse. There are shortages of materials, products, shipping containers and workers. And Deloitte estimates that online sales will jump 11% to 15% this season.
Retailers encourage people to shop as early as possible. In addition, they and the shipping companies are trying out robots that can help them sort the items.
Ken Goldberg is a professor of industrial engineering at the University of California at Berkeley and co-founder of Ambi Robotics, which makes a robot called Ambisort. He said robots are getting better at sorting. The following is an edited transcript of our conversation.
Ken Goldberg: We have come a long way in a year. We understood much better where to grab objects, how to digitize them with faster scanners, all arm movements have been sped up. The system is now ready to do the job. And I think what’s going on is a lot of sellers across the country, they’re all gearing up and trying new things. It will be a great test year for new technologies. Then, those who are working, they will invest very heavily to start in the spring, so that it can solve these problems continuously in the future.
Marielle Segarra: Can you, can you just kind of describe what that looks like to me?
Goldberg: Imagine a large bin on one side, then a blue robot with a clamp at the end, in fact, it [has] suction cups, then cameras all around. On the other side is another robot arm that sort of moves around and drops the packages into this big set of 25 other bins. So it takes up quite a bit of space, the size of a small room, and packages arrive at one end, and they exit at the other end in the smaller bins assigned to each zip code.
Segarra: And how does that speed things up?
Goldberg: Well, it can be really slow for humans to do that, in part because the tubs are actually quite deep so you have to get in, resulting in a lot of back injuries. And then a human has to look at each of them, find where the barcode is, right? This scanning process takes time and then direct it to the appropriate recycle bin. This system therefore speeds up all three aspects. It never gets tired, it can get deep into the trash because of the robot. It’s scanned with many cameras simultaneously, so it can instantly scan, find the barcode, and then drop it in that scanning bin which basically moves it around. As the robot descends to pick up the next item, the first item is dropped into the appropriate bin.
Segarra: Is it intended to replace a person?
Goldberg: Well, it’s meant to complement a person. Actually, you know, I think the analogy is that you’re a journalist, right? And there are probably some jobs that you don’t particularly like doing, and I would imagine something like transcribing an interview like this. But nowadays there are tools that can help you do that, which use [artificial intelligence]. They don’t replace the transcript, you would still have to go and correct it in some places, but it can be a lot of chore for you. It just means that you can focus on the parts of your job that you do best. And that’s exactly the analogy that we think is going to be true for workers and warehouses.
Related links: More information from Marielle Segarra
This story from MIT Tech Review is about the other types of automation you see emerging in warehouses. As if there was a robot from the Covariant firm that was trained to sort bins of random items.
It’s been a big challenge for these machines, as Ken Goldberg told us on the show last year.
And the big picture: We’ve been talking a lot about supply chain shortages and delays, but if you want to know what it really looks like, the New York Times has an article about backing up at a port in Savannah, in Georgia. There are currently 80,000 shipping containers there, 50% more than usual. And the ships wait at sea to unload for nine days.
It is just one link in the chain. Crates of goods are piling up in warehouses because there are not enough truck drivers to transport them.
So robots that sort. They solve a problem, speed up part of the process, but it’s still a bit of a mess overall.