Loop closure during SLAM

Simulation of a robot driving around and observing landmarks (objects). When the robot observes a landmark for the second time, it corrects its own position relative to the observed landmark postion; 'loop closure'.

The blue arrow-shaped thingy is the 'actual' robot position. The red arrow-shaped thingy is the 'odometric' position, this is the position where the robot "thinks" it is. Actually the red arrow has the same position change as the blue arrow, only some noise is added.

The robot observes the green dots (landmarks) and puts them on its 'map'. The position of the landmarks on the map are represented by brownish dots with an ellipse around it. The ellipses represent the uncertainties of the positions of the landmarks. The smaller the ellipse, the more certain the robot is about the position of the landmark.

The robot (or actually the red arrow) has its own uncertainty ellipse. This ellipse grows during driving. When the robot observes a previously seen landmark, both the uncertainties of the landmark and the robot are adapted.

The small red dots represent the robot's driven track.

Category:

Howto & Style

Tags:

• robot
• SLAM
• loop
• closure
• loopclosure
• simultaneous
• localisation
• mapping

[heiismail]

nice video if sound was added like comment sound that will help alot