US 11,934,578 B1
Apparatus, system, and method for controlling soft fluidic actuators via sensor feedback and machine learning models
Priyanshu Agarwal, Kirkland, WA (US); Nicholas Colonnese, Kirkland, WA (US); Heng Xu, Redmond, WA (US); Benjamin Stephens-Fripp, Redmond, WA (US); and Daniele Piazza, Redmond, WA (US)
Assigned to Meta Platforms Technologies, LLC, Menlo Park, CA (US)
Filed by META PLATFORMS TECHNOLOGIES, LLC, Menlo Park, CA (US)
Filed on May 6, 2021, as Appl. No. 17/313,876.
Claims priority of provisional application 63/072,461, filed on Aug. 31, 2020.
Claims priority of provisional application 63/054,629, filed on Jul. 21, 2020.
Int. Cl. G06F 3/01 (2006.01); G02B 27/01 (2006.01); G06N 3/08 (2023.01)
CPC G06F 3/016 (2013.01) [G02B 27/017 (2013.01); G06F 3/014 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A haptic feedback system comprising:
an actuator;
a supply valve coupled to the actuator;
an exhaust valve; and
a fluidic mass controller communicatively coupled to the supply valve and the exhaust valve, wherein the fluidic mass controller implements a machine learning model that facilitates:
placing the exhaust valve in a state that prevents a fluid from escaping the actuator;
activating the supply valve to fill the actuator with the fluid;
determining that the actuator has filled with a certain amount of the fluid based at least in part on at least one electrical signal received from an electronic pressure sensor; and
in response to determining that the actuator has filled with the certain amount of the fluid, deactivating the supply valve to trap the certain amount of the fluid in the actuator.