MIT Technology Review Subscribe

Car makers are testing a way for humans to team up with dangerous robots

If Veo Robotics is successful, human factory workers will eventually work with robots the way farmers work with horses.

Car manufacturers have been using robots in factories for decades. But these huge industrial machines are too dumb and dangerous for humans to work anywhere close to. That’s a problem being addressed by Veo Robotics, a startup helping to create robot factory workers that can work safely alongside their human coworkers.

But while Veo might be a startup, its robots can’t simply move fast and break things—because the things they’d be breaking would be people, VP of engineering Clara Vu explained at MIT Technology Review’s EmTech conference today. That’s why it’s so impressive that several major manufacturing firms are already testing Veo’s technology and beginning to imagine scenarios in which humans and industrial workers can work safely alongside each other.

Advertisement

Manufacturers—particularly car makers—need robots because they are far better and more efficient than humans at welding or lifting and moving heavy parts. Humans, however, are far better than robots at tasks like fastening small parts together, which requires precision, fine manipulation, and sensitivity to feedback. So whereas welding has been almost completely automated, the final assembly line—the last phase before a car can roll off the factory floor—still looks mostly the way it did 100 years ago, said Vu, with “hundreds of people doing hundreds of tasks almost completely manually.”

This story is only available to subscribers.

Don’t settle for half the story.
Get paywall-free access to technology news for the here and now.

Subscribe now Already a subscriber? Sign in
You’ve read all your free stories.

MIT Technology Review provides an intelligent and independent filter for the flood of information about technology.

Subscribe now Already a subscriber? Sign in

In theory, if humans and their robotic counterparts could work side by side, things like final assembly could be achieved more efficiently. But at the moment the risk of human injury is too great, and safety standards require that robots be kept segregated—often in cages. Veo is using 3-D sensors, advanced computer vision, and software that builds representations of its immediate environment so it can spot and avoid people (see “This company tames killer robots”).

Vu said the company has recently partnered with three major manufacturers—an automaker, a manufacturer of consumer packaged goods, and a tier-one automotive supplier—on “early prototype trials” to test Veo’s systems. 

But it’s not just about making safer robots: the humans need some reassurance too. “For a line worker to be able to approach that robot, it not only has to be safe; it has to feel safe,” she said. So Veo is working on human-robot collaboration models that are similar to the way a farmer can work with a horse, she explained: “That horse can hurt you, but you know it won’t, because you know how it thinks and you know how to interact with it.”

This is your last free story.
Sign in Subscribe now

Your daily newsletter about what’s up in emerging technology from MIT Technology Review.

Please, enter a valid email.
Privacy Policy
Submitting...
There was an error submitting the request.
Thanks for signing up!

Our most popular stories

Advertisement