US 12,228,642 B2
Characterising wave properties based on measurement data using a machine-learning model
Thomas Robert Swanson, Sunnyvale, CA (US); and Riva Gulassa, Sunnyvale, CA (US)
Assigned to TidaIX AI Inc., Mountain View, CA (US)
Filed by TidalX AI Inc., San Ramon, CA (US)
Filed on Aug. 1, 2023, as Appl. No. 18/363,506.
Application 18/363,506 is a continuation of application No. 17/869,050, filed on Jul. 20, 2022, granted, now 11,754,707.
Claims priority of provisional application 63/242,639, filed on Sep. 10, 2021.
Prior Publication US 2024/0192363 A1, Jun. 13, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G01S 15/87 (2006.01); G01S 15/89 (2006.01); G06N 20/00 (2019.01)
CPC G01S 15/872 (2013.01) [G01S 15/8952 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, by an underwater camera device, inertial measurement unit (IMU) data that reflects motion of the underwater camera device over a period of time;
generating, by the underwater camera device, particular model input data based at least on the IMU data;
providing, by the underwater camera device, the particular model input data to a machine learning model that is trained to output estimated wave properties based on model input data;
receiving, by the underwater camera device, a particular estimated wave property; and
determining, by the underwater camera device, a future device position for the underwater camera device after receiving the particular estimated wave property.