orb_slam_2_ros VS Universal_Robots_ROS_Driver

I have compiled [this repository](https://github.com/appliedAI-Initiative/orb_slam_2_ros) on nvidia jetson nano and it has been successfully built inside my catkin workspace. I have double checked the rosnode list and topics subscribed and published by nodes and they are all good. When I launched the file `roslaunch orb_slam2_ros orb_slam2_d435_rgbd.launch` and try to see the `/orb_slam2_rgbd/pose` topic, the pose looks quite unstable and changing at a faster rate (you can see inside the video attached) while the robot is static. I have attached the tf tree in this issue [frames.pdf](https://github.com/appliedAI-Initiative/orb_slam_2_ros/files/8130863/frames.pdf) and a video link [here](https://drive.google.com/file/d/1nU13ZrD_oXfTAPqC75yUB4uY-FzfR1dC/view?usp=sharing).

They have a section for developer about ROS UR ROS

This is the Ros driver for ur-e series robot. You can simply follow the readme to setup a simulation involving a rviz model and some.basic planning and associated visualisation.

That’s not windows. It uses ROS

Oh no, really? I'm following the directions of this GitHub page which includes features such as "Realtime-enabled communication structure to robustly cope with the 2ms cycle time of the e-Series. " and then says, "To make sure that robot control isn't affected by system latencies, it is highly recommended to use a real-time kernel with the system."