Simultaneous localization and mapping (SLAM)
The technique a mobile robot uses to build a map of an unknown space while working out its own position on that map at the same time.
Photo: Igor Omilaev / Unsplash
A robot in a new room needs a map to know where it is, and needs to know where it is to draw the map. SLAM solves both together. The robot matches what its sensors see, a LiDAR scan or camera images, against what it has already mapped, and corrects its position estimate with wheel odometry or an IMU, a typical case of sensor fusion.
A mapping robot vacuum is the everyday example. After its first runs, the app shows a floor plan with rooms you can name and areas you can block off. That plan is information about your home: its layout, its size and, once rooms are labeled, how you use them. Whether the map stays on the robot or is uploaded to the maker’s cloud is something to check in the app settings and the privacy policy.
Part of the IoT Glossary. Spotted an error or a missing term? Tell us.