Visual SLAM
Visual SLAM (simultaneous localization and mapping) solves the problem of knowing where the robot is relative to some fixed pose. Robots can tell where they are relative to where they started through use of odometry such as kinematic odometry (e.g. ticks from wheel encoders), visual odometry (e.g. tracking visual features as you move relative to them), or inertial odometry (e.g. integrating IMU readings. Odometry inevitably begins to drift, however, because small errors when estimating motion between any two moments accumulate.
By building a graph of landmarks (distinct identifiable visual features on a map) from one or multiple cameras, Visual SLAM can recognize when it has visited the same location again (closing the loop). This allows for an accurate localization to correct for any accumulating drift.
- cuVSLAM
- List of Useful Visualizations
- Saving a Map
- Loading and Localizing in a Map
- Coordinate Frames
- Repositories and Packages
- Examples