A cleaning robot uses cameras as its main sensors to navigate and clean floors without getting stuck. The vision-first approach relies on rich visual data and backend algorithms to make smart decisions about where to go and what to clean.
The design of the robot, very, very unique. We haven't seen anything like this before in basically any of the robot markets. How do you design this so that it works, it cleans, and it doesn't get stuck?
So for us, I think we knew we were going to build a system based on cameras, and there's a lot of advantages to that. Cameras are very powerful sensors. You get a lot of information. And so if you build the right algorithms on the backend, you can use that information to take meaningful decisions.
