SLAM builds maps while tracking position.
SLAM builds a map while estimating the robot pose: approaches EKF-SLAM, particle filters (FastSLAM), graph optimisation (GTSAM), visual SLAM (ORB-SLAM) and lidar SLAM (LOAM, Cartographer). Loop closure corrects drift. Maps: occupancy grids, feature maps, point clouds.
A vacuum robot maps rooms with lidar SLAM.
Localisation and mapping let a robot know where it is and what the environment looks like, which is essential for autonomous movement.
SLAM builds maps while tracking position.
Localisation and mapping let a robot know where it is and what the environment looks like, which is essential for autonomous movement.
Simultaneous localisation and mapping, the problem of building a map while estimating the robot position within it.
Lidar, cameras, wheel odometry and inertial sensors, which are often combined for robustness.
Typical applications include building a map of a warehouse as a robot drives through it, localising a robot against a known map using lidar and estimating the position of a drone in a building without GPS.
Study "Mobile robots" first (topic 65 of 102 in Manufacturing, Robotics & Systems). It covers the groundwork this topic builds on.
Data association. Loop closure. Scan matching (ICP).
A vacuum robot maps rooms with lidar SLAM.
The next topic is "Path planning", which builds directly on this one.
It is classed as Intermediate in Manufacturing, Robotics & Systems (topic 66 of 102). It is an intermediate topic. Work through the beginner topics in Manufacturing, Robotics & Systems first.
Want to practise? Open the interactive course for quick checks, quizzes, simulations and progress tracking.