SLAM & Spatial Mapping

SLAM (Simultaneous Localization and Mapping) lets a robot build a map of an unknown place while working out where it is inside that map.

A robot cannot navigate without a map, and cannot build a map without knowing where it is. SLAM resolves this chicken-and-egg problem by estimating both together from sensor data.

Navigation, inspection, augmented reality, autonomous driving and drones all rely on SLAM. The choice of sensor (camera, LiDAR, IMU, or a mix) and of representation (points, voxels, neural fields, scene graphs) defines most of the subfields.