Deep learning based head motion prediction for extended reality

An apparatus for predicting head pose of a user in an extended reality system, comprising:

• a processor,
• memory coupled with the processor;
• and
• instructions stored in the memory and executable by the processor to cause the apparatus to:
• train one or more layers of a machine learning network based at least in part on application data associated with the extended reality system and an estimated head motion range associated with the extended reality system;
• receive one or more bias corrected inertial measurement unit measurements based at least in part on a sensor;
• model a relative head pose of the user as a polynomial of time over a prediction interval based at least in part on the one or more bias corrected inertial measurement unit measurements and the trained one or more layers;
• and
• determine a future relative head pose of the user based at least in part on the polynomial.

An apparatus for predicting head pose of a user in an extended reality system, comprising:

• means for training one or more layers of a machine learning network based at least in part on application data associated with the extended reality system and an estimated head motion range associated with the extended reality system;
• means for receiving one or more bias corrected inertial measurement unit measurements based at least in part on a sensor;
• means for modeling a relative head pose of the user as a polynomial of time over a prediction interval based at least in part on the one or more bias corrected inertial measurement unit measurements and the trained one or more layers;
• and
• means for determining a future relative head pose of the user based at least in part on the polynomial.