US 11,914,762 B2
Controller position tracking using inertial measurement units and machine learning
Doruk Senkal, Kirkland, WA (US); and Sheng Shen, Shoreline, WA (US)
Assigned to META PLATFORMS TECHNOLOGIES, LLC, Menlo Park, CA (US)
Filed by META PLATFORMS TECHNOLOGIES, LLC, Menlo Park, CA (US)
Filed on Dec. 17, 2021, as Appl. No. 17/555,126.
Claims priority of provisional application 63/131,242, filed on Dec. 28, 2020.
Prior Publication US 2022/0206566 A1, Jun. 30, 2022
Int. Cl. G06F 3/01 (2006.01); G06F 3/0346 (2013.01); G06N 3/044 (2023.01); G06N 3/08 (2023.01); G06N 3/045 (2023.01); G06T 7/70 (2017.01); G06N 3/04 (2023.01)
CPC G06F 3/012 (2013.01) [G06F 3/0346 (2013.01); G06N 3/04 (2013.01); G06T 7/70 (2017.01); G06F 3/011 (2013.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 2207/20084 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
a first component configured to be positioned at a first portion of a user's body, the first component comprising at least a first inertial measurement unit (IMU) configured to generate first measurements indicating motion of the first component;
a second component configured to be positioned at a second portion of the user's body, comprising a least a second IMU configured to generate second measurements indicating motion of the second component, wherein a set of potential positions of the first component and the second component is determined by physiological constraints of the first portion and the second portion of the user's body; and
a controller configured to:
receive first measurements from the first IMU and the second measurements from the second IMU, and
predict, using a trained neural network model trained using the set of potential positions, a position of the first component relative to the second component corresponding to an expected future position of the first component relative to the second component at a future time.