What is SLAM in robotics?
SLAM (simultaneous localization and mapping) lets a robot build a map of an unknown space while tracking where it is inside that map.
Updated:
Definition
SLAM means a robot estimates its pose and a map of the environment at the same time, usually from lidar, cameras or both.
How it works
As the robot moves, sensors see overlapping features. Algorithms match them, update the pose, and grow a consistent map — correcting drift when loops close. On warehouses and robotaxis, SLAM is the backbone of navigation when GPS is weak or absent.
Why it matters
Without knowing "where am I?" a mobile robot cannot plan. SLAM turned AMRs and autonomous vehicles from fixed-path machines into systems that explore and adapt.
Frequently asked questions
Do robotaxis use SLAM?
Many do, often fused with HD maps and GNSS. Indoor AMRs and drones rely on SLAM even more.
Lidar or vision SLAM?
Both exist. Lidar SLAM is robust outdoors; visual SLAM is cheaper but sensitive to lighting.
How does it relate to LiDAR?
[LiDAR](/{L}/glossary/lidar) point clouds are a common input to modern SLAM stacks.
Newsletter
Robrief Weekly
One email a week with the robotics news that matters. Free, unsubscribe anytime.