So the role that magnetometers play in sensor fusion w/ IMU data is for yaw/heading/magnetic north estimation. In short, it aids your orientation (RPY estimate). However, with MagNav, they play a large role in supplying information that allows you to decrease your drift rate.
Yes, we were doing all of that at Apple over ten years ago. I was specifically pointing out that just like WiFi has “texture” that lets you machine learn a position, so does the mag field, letting you determine an absolute position estimate purely from the magnetometer. I was wondering if the sensors and algorithms have advanced on that front.