A fleet of robots at the headquarters of “Google” for cleaning work

Google revealed a project aimed at hiring a “fleet of robots” to carry out various forms of cleaning work inside the company’s headquarters.

The company said in a statement, “The project called (Everyday Robots), which was developed by a team within the experimental (X Labs) dedicated to creating a general-purpose educational robot, has moved some of its model machines from the lab to the Google Bay Area campus (the headquarters complex of the two Google companies). and Alphabet) to carry out some light cleaning tasks,” according to the American “The Verge” website.

“Over the coming months, employees may see robots doing various cleaning tasks, such as scanning tables after lunch in breakout areas, or opening conference room doors to check if the room needs tidying or if there are missing seats,” she added.

Alphabet is putting its prototype robots to work cleaning up around Google’s offices https://t.co/7jmqjPaXPS pic.twitter.com/EF9oKnnWq7

— The Verge (@verge) November 19, 2021

The company explained that the robots come primarily in the form of arms on wheels, with a multi-purpose clutch at the end of a flexible arm connected to a central tower, and there is a head on top of the tower equipped with cameras and vision sensors, and what looks like a rotating lidar unit on the side with sensors for navigation and navigation.

“We now operate a fleet of more than 100 robots, autonomously performing a range of useful tasks around our desks,” says Hans-Peter Brondmo, Senior Project Officer. Cups to open doors.

“These robots were first seen sorting trash for recycling when the company assigned the Everyday Robot team in 2019,” Brondmo added.

“The big promise made by the company (along with many other startups and competitors) is that machine learning will finally enable robots to do more cleaning as well as work in unstructured environments such as homes and offices.”

“Right now, we’re very good at building machines that can perform repetitive tasks in factories, but we get baffled when we try to get them to repeat simple tasks like cleaning the kitchen or folding clothes, and that’s a problem we’ve been working on for a while,” Brondmo added. .

“By using a combination of machine learning techniques such as reinforcement learning, cooperative learning, and demo learning, robots have significantly gained a better understanding of the world around them and become more adept at performing everyday tasks,” he noted.