Adding custom odometry to RTABMAP.

[Kavi91]

@matlabbe Sir, Please accept my sincere gratitude for implementing RTABMAP and making it open source for future developments.

So, I am planning to add my version of deep learning-based odometry into RTABMAP. This odometry mainly fused the camera and lidar together to produce a single odometry. Features will also extracted using Deep neural networks for both lidar and RGB.

In order to implement this with current framework.

1. Where I should place my new files
2. which files I should modify to enable custom feature extractions and odometry ?

Thank you in advance.

[matlabbe]

As you are posting this to rtabmap_ros, I assume its for the ROS2 version. If so, I suggest to create your own ros package for the odometry node you want to create. Your node would need to provide at minimum a nav_msgs/Odometry topic and corresponding TF (e.g., odom->base_link). We can then connect that topic and TF to rtabmap node.

If you want to provide visual features to rtabmap, it is also possible by providing a rtabmap_msgs/RGBDImage topic, filled with the features. When launching rtabmap node with subscribe_rgbd:=true, rtabmap will subscribe to that kind of topic.

The lidar can be externally synchronized with subscribe_scan_cloud at the same time, or (for advanced usage) could be provided with the visual data inside a combined rtabmap_msgs/SensorData topic.