I think the scan localization node writes the result to the pose tree, so any component can access the result, but Nvidia doesn’t document which components read from the pose tree.
For the ParticleFilterLocalization, it says: “For every tick the particle distribution is updated based on an ego motion estimate read from the pose tree”. Does it mean if we use IMU and use “DifferentialBaseWheelImuOdometry”, we are basically using IMU in the prediction step of the Particle filter? I would appreciate if someone clears this problem for me. Thanks