Process
SLAM
You might say: simultaneous localisation and mapping
SLAM estimates a robot trajectory and a map together from observations, so the map and pose constrain one another.
- What it does
- Builds a reusable spatial reference when no prior map or reliable absolute position exists.
- Ask
- What representation, loop-closure evidence and uncertainty are acceptable for this environment?
What to look for
- Robot trajectory and map together
- Pose constrained by the map
- Reusable spatial reference
Parts
- Map representation: A map representation is the data structure used to store the world for localization, mapping, and planning.
- Loop closure: Loop closure recognizes a previously visited place and adds a constraint that can correct the trajectory and map.
- Trajectory error (ATE / RPE): Absolute trajectory error (ATE) compares an aligned estimated path with ground truth.
Sources
- Cesar Cadena et al., Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age, Survey of SLAM
Topological mapping drops the metric information and only leverages place recognition to build a graph in which the nodes represent distinguishable places.
- Timothy D. Barfoot, State Estimation for Robotics, Ch. 3, SLAM example
It is an example of simultaneous localization and mapping (SLAM) since we are going to estimate the robot and landmark positions.
Use it on your project
teardown-apply: hold "SLAM" (slam) from the teardown at https://teardownatlas.com/robotics/ against my project
Paste it into a coding agent that has the teardown skills.
An AI agent wrote this map with the teardown skill. It can contain errors: check the sources before you rely on a part. About and legal