Vacuum robot with AI and object recognition in the test

Share your love

Anyone who has a vacuum robot knows that good obstacle detection saves many trips to the bot that would otherwise be necessary to free it from wrapped up cables, curtains and socks. Modern robotic vacuum cleaners have a number of sensors to help them find their way around safely. Your lidar and IR or ultrasonic sensors reliably detect large obstacles such as walls, furniture and chair legs. But that doesn’t mean that you can sit back and relax completely. Bots usually overlook small things on the floor, which is why you have to put them away before vacuuming.

Pets are often one of the bosses for robot vacuum cleaners. No matter how thoroughly you checked beforehand, animal residues sometimes appear very suddenly or in places where masters have overlooked them. This is especially a problem if the bots are cleaning time-controlled and unattended. In web forums there are dozens of reports in which dogs and cats had a mishap and then a robot hoover drove over them. The roller brushes smear the manure over a large area on the floor or massage it into carpets. Not only is it gross, it’s expensive too. The vacuum robots in our test should be immune to this worst-case scenario. In addition to the sensors mentioned above, they have cameras that look in the direction of travel during cleaning. Using AI, the vacuum robots try to recognize such obstacles and avoid them without contact.

The test field includes the brand new Deebot T9 AIVI from Ecovacs and Roomba j7 + from iRobot. We would have liked to have the Jetbot AI from Samsung in the test field, but unfortunately no test device was available at the time of going to press. Also in the test is the S6 MaxV from Roborock, which already competed in an individual test against an older vacuum robot with object recognition from Ecovacs. Since it is still available and has learned from several updates, we decided to include it in the test field again – and also because the newer model S7 has not yet been announced in the MaxV version.

  • Access to all heise + content
  • exclusive tests, advice & backgrounds: independent, critically well-founded
  • Read c’t, iX, MIT Technology Review, Mac & i, Make, c’t photography directly in your browser
  • register once – read on all devices – can be canceled monthly
  • first month free, then monthly from € 9.95
  • Weekly newsletter with personal reading recommendations from the editor-in-chief

Start FREE month

Start your FREE month now

Already subscribed to heise +?

Sign up and read

Register now and read articles right away

More information about heise +

Article Source

Read Also   Spatial Audio with Dolby Atmos for your HomePod if you update to version 15.1
Share your love