RGBD and 2d lidar fusion about rtabmap HOT 1 OPEN

If you use that configuration, it is explained in this paper:

The transformation is computed using the same Motion Estimation approach used by visual odometry (Section 3.1.1), and if accepted, the new link is added to the graph. When a laser scan or a point cloud is available, link’s transformation is refined using the same ICP Registration approach than with lidar odometry (described in Section 3.1.2)

So in your case it is a two steps process:

1. Use RGB-D camera to visually compute localization transform against a node in the map
2. Refine that transform using lidar scan between the two nodes.

The robot can also be localized by only lidar using proximity detection (described in that paper).

Fusing two global localization approaches (not odometry) is more complicated has they would fight each other from their respective map frames.

from rtabmap.