Skip to Content

Teleoperated Design Revealed for Assistant Robots

A system lets users manage a team of robots through cloud computing.

Readybot, a research group that last year released videos of a simple prototype cleaning robot, has revealed that the robot is managed through a combination of cloud-based software and skilled remote teleoperators.

Readybot operates autonomously or through remote control. (Courtesy of Readybot)

The company’s Cloud Robotics Collaborative Control (CRCC) system monitors a semi-autonomous robot via a broadband connection. When faced with a particularly tricky task, such as opening a cabinet door, the robot will send a request for a human supervisor to step in and take over. The human operator does this by selecting or refining one of several prepared code of instructions (“scripts”) or writing new ones, according to Readybot’s director, Tom Benson. The CRCC system is designed to let a single user supervise a large team of robots.

“This has the potential to deploy large quantities of robots much sooner, because they’re cheaper and because you aren’t required to build high levels of autonomy,” Benson said. “It’s much more forgiving in the sense of allowing you to have less sophisticated systems and still do the job.” Benson says that Readybots would be best suited for applications like home assist or manual labor.

Using a regular mouse and monitor, a user can switch between 3D simulations of different robots (with a video feed showing the bot’s environment) and can swap between supervising and taking completely control of a robot. Currently, the software can control a single prototype Readybot and up to nine virtual robots.

The company says it took inspiration from video gamers by examining how people playing World of Warcraft, The Sims, and other games and designing the system based on those observations. Gamers who tested out Readybot’s operating software were able to operate it quickly and efficiently, according to the group. People who have played a lot of video games “can manage large amounts of remote devices and can think in that way,” says Benson. “They are capable of managing vast amounts of multitasking.”

Courtesy of Readybot

So far, Readybot can clear a kitchen table, load a dishwasher, transport objects, paint walls, and clean and dry surfaces. The group is currently looking for partners to build more prototypes and to expand the capabilities of CRCC.

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.