Retired Professor Tries To Teach Robots To Sew Clothes Atlanta company SoftWear is trying to create a robot that can sew. If the project succeeds, it could have a huge effect on the global economy, and clothing manufacturing could return to the U.S.
NPR logo

Retired Professor Tries To Teach Robots To Sew Clothes

  • Download
  • <iframe src="https://www.npr.org/player/embed/489584328/489584329" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript
Retired Professor Tries To Teach Robots To Sew Clothes

Retired Professor Tries To Teach Robots To Sew Clothes

Retired Professor Tries To Teach Robots To Sew Clothes

  • Download
  • <iframe src="https://www.npr.org/player/embed/489584328/489584329" width="100%" height="290" frameborder="0" scrolling="no" title="NPR embedded audio player">
  • Transcript

Atlanta company SoftWear is trying to create a robot that can sew. If the project succeeds, it could have a huge effect on the global economy, and clothing manufacturing could return to the U.S.

DAVID GREENE, HOST:

Robots have gotten very good at a lot of things, from building cars in factories to moving boxes around warehouses. What's next, hosting a radio program? Well, for decades, one repetitive industrial task has remained surprisingly difficult, and that is sewing clothes. Jacob Goldstein from our Planet Money podcast has the story of one man's quest to teach robots to sew.

JACOB GOLDSTEIN, BYLINE: Steve Dickerson is an emeritus professor at Georgia Tech and an inventor. He started a computer vision company that sold for a lot of money and had some other ideas that did not do as well.

(SOUNDBITE OF ARCHIVED BROADCAST)

GOLDSTEIN: Did you get a patent on a self-making bed?

STEVE DICKERSON: Yes, I did.

GOLDSTEIN: (Laughter).

DICKERSON: But I've never commercialized that, even though I think it's a great one to do.

GOLDSTEIN: Dickerson's current project, teaching robots to sew, could have major economic consequences. It could bring industrial sewing back to the United States. But Dickerson says it's a very hard technical problem for a really simple reason.

(SOUNDBITE OF ARCHIVED BROADCAST)

DICKERSON: Fabric, by definition, is very flexible.

GOLDSTEIN: Robots are really good at dealing with things that are not flexible. You give a robot a giant piece of steel, tell it to cut some incredibly complicated pattern, the robot will get it exactly right every time. But if you try and do that with a piece of fabric, the fabric wrinkles or bends as it's going through the machine. The robot doesn't see that, and it gets all messed up. A few years back, Dickerson had an idea. You could teach robots to sew by teaching them to see in a new way. He realized you could build cameras into the robot and use the cameras to track every single thread in a piece of fabric.

(SOUNDBITE OF ARCHIVED BROADCAST)

DICKERSON: It is counting the threads at the needle...

GOLDSTEIN: Right.

DICKERSON: ...As they pass. You have to take a thousand pictures per second. And you process that image a thousand times a second, and you get a count of the threads that have passed.

GOLDSTEIN: Now when the fabric starts to stretch or bunch up, the camera will instantly see that. It'll send a signal to some robot hand or whatever to fix the fabric. Not long after that initial insight, Dickerson joined up with a few other people and decided to start a company.

(SOUNDBITE OF ARCHIVED BROADCAST)

DICKERSON: We got together. And we just sat around a conference room and said, what should we call this company? And that's where the name SoftWear came out.

GOLDSTEIN: SoftWear - W-E-A-R - like clothes. It's a pun.

(SOUNDBITE OF ARCHIVED BROADCAST)

DICKERSON: Yes. And software is how we run it.

GOLDSTEIN: I - no, I get it.

DICKERSON: It runs on software (laughter).

GOLDSTEIN: I get the joke. I get it.

DICKERSON: (Laughter) OK.

GOLDSTEIN: They got a few grants, some venture capital and set up shop in a little brick building in Atlanta. A few weeks ago, I went to visit. Barry Clark, the company's head of R&D, showed me around.

(SOUNDBITE OF ARCHIVED BROADCAST)

GOLDSTEIN: So these are the robots?

BARRY CLARK: These are the robots. That's right.

GOLDSTEIN: We're standing in front of this big table with two separate machines on it. One is this robot arm.

CLARK: It has a vacuum attached to it so it can suck. And so what we do is we use it to actually pick up the pant leg.

GOLDSTEIN: The other machine is a modified sewing machine. Clark shows me how the machines can sew a leg of a pair of jeans together. The vacuum arm picks up the fabric...

(SOUNDBITE OF VACUUM RUNNING)

GOLDSTEIN: ...Moves it over to the sewing machine, which then sews them together.

(SOUNDBITE OF SEWING MACHINE STITCHING)

CLARK: And now we finished sewing the piece, and so we eject it.

GOLDSTEIN: The company's robots can't sew an entire pair of jeans or a T-shirt yet, but they're getting close. Steve Dickerson, who founded the company, says when they get there, factories that sew clothes will start sprouting up in the U.S. again.

(SOUNDBITE OF ARCHIVED BROADCAST)

DICKERSON: That's almost a guarantee. If we can meet our targets on cost and performance, it will happen.

GOLDSTEIN: And so those factories will not look at all like the factories that closed up 40 years ago.

DICKERSON: If you took the broad picture and looked at the factory production floor, the only thing that would be different is very few people, if any.

GOLDSTEIN: Yes. That is a - not a trivial difference. There used to be a person running the sewing machine, and now it will be a computer.

DICKERSON: That is correct.

GOLDSTEIN: You will need some people to work in the factory, mostly to take care of the robots, fewer jobs, requiring a fair bit of education and probably paying decent wages. This is what manufacturing looks like in America now, not factories where you can walk in the door straight out of high school with no special training and have a solid lifelong job. Those jobs are not coming back. Jacob Goldstein, NPR News.

Copyright © 2016 NPR. All rights reserved. Visit our website terms of use and permissions pages at www.npr.org for further information.

NPR transcripts are created on a rush deadline by Verb8tm, Inc., an NPR contractor, and produced using a proprietary transcription process developed with NPR. This text may not be in its final form and may be updated or revised in the future. Accuracy and availability may vary. The authoritative record of NPR’s programming is the audio record.