Power-efficient processing of neuromuscular signals to confirm occurrences of user gestures, and systems and methods of use thereof

1 . A method of power-efficient processing of neuromuscular signals to confirm occurrence of a predetermined event, the method comprising:

obtaining a first set of neuromuscular signals from a neuromuscular-signal sensing component of a wearable device;

determining, using a low-power detector of the wearable device, that a respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that a predetermined in-air hand gesture has been performed at the wearable device:

processing the first set of neuromuscular signals using a high-power detector of the wearable device to generate processed neuromuscular signals, the high-power detector configured to detect a first set of in-air hand gestures while consuming a first amount of power from the wearable device and the low-power detector configured to detect a second set of in-air hand gestures while consuming a second amount of power from the wearable device, the second set of in-air hand gestures includes less in-air hand gestures than the first set of in-air hand gestures and the second amount of power is less than the first amount of power; and

in accordance with a determination, based on the processed neuromuscular signals that the predetermined in-air hand gesture did occur, registering an occurrence of the predetermined in-air hand gesture;

receiving a second set of neuromuscular signals from the neuromuscular-signal sensing component of the wearable device; and

after determining, based on a respective neuromuscular signal of the second set of neuromuscular signals and using the low-power detector and not using the high-power detector, that a different predetermined in-air hand gesture, distinct from the predetermined in-air hand gesture, was performed at the wearable device:

performing an action in response to the different predetermined in-air hand gesture at the wearable device.

2 . The method of claim 1 , wherein:

the predetermined in-air hand gesture includes a wake gesture followed by another in-air hand gesture; and

registering the occurrence of the predetermined in-air hand gesture includes:

registering an occurrence of the wake gesture to cause the high-power detector to remain in an active state; and

registering an occurrence of the another in-air hand gesture to cause the wearable device to execute a function that corresponds to the another in-air hand gesture performing an action within a user interface.

3 . The method of claim 1 , wherein:

the neuromuscular-signal sensing component includes a plurality of neuromuscular-signal sensors that correspond to the high-power detector;

while the high-power detector is in an active state, data from the plurality of neuromuscular-signal sensors is processed by the high-power detector; and

while the high-power detector is in an inactive state, data from the plurality of neuromuscular-signal sensors is stored at the wearable device and not processed by the high-power detector.

4 . The method of claim 1 , wherein, prior to determining that the respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that the predetermined in-air hand gesture has been performed at the wearable device, the high-power detector is in an inactive state; and

the method further comprises, in accordance with determining that the respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that the predetermined in-air hand gesture has been performed at the wearable device, transitioning the high-power detector to an active state.

5 . The method of claim 1 , wherein:

the low-power detector operates in a default active state to process detected neuromuscular signals from the neuromuscular-signal sensing component; and

the high-power detector operates in a default inactive state in which it does not process neuromuscular signals in the absence of a trigger signal.

6 . The method of claim 1 , further comprising:

prior to using the low-power detector to determine that the respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that the predetermined in-air hand gesture has been performed at the wearable device:

transitioning the low-power detector from an inactive state to an active state based on muscular activity detected via the neuromuscular-signal sensing component satisfying a muscular-activity wake-up criterion.

7 . The method of claim 6 , further comprising:

while the low-power detector is in the active state:

in accordance with a determination that data from the neuromuscular-signal sensing component indicates that the muscular-activity wake-up criteria are no longer satisfied, transitioning the low-power detector to the inactive state.

8 . The method of claim 1 , further comprising:

after performing the action in response to the different predetermined in-air hand gesture at the wearable device, transitioning both the high-power detector and the low-power detector to inactive states in accordance with a predetermined amount of time having elapsed.

9 . The method of claim 8 , wherein, during the predetermined amount of time, no respective neuromuscular signal is determined to require further processing to confirm that an in-air hand gesture has been performed at the wearable device.

10 . The method of claim 1 , further comprising:

determining, using the low-power detector, that another different predetermined in-air hand gesture was performed at the wearable device, the determining based on a respective neuromuscular signal of a third set of neuromuscular signals, wherein the another different predetermined in-air hand gesture is distinct from the different predetermined in-air hand gesture and the predetermined in-air hand gesture; and

in response to determining that the another different predetermined in-air hand gesture was performed at the wearable device, performing another action at the wearable device, the another action being distinct from the action.

11 . The method of claim 1 , further comprising:

before registering the occurrence of the predetermined in-air hand gesture, evaluating data from a second sensor of the wearable device to confirm that the predetermined in-air hand gesture occurred at the wearable device, wherein the second sensor is distinct from the neuromuscular-signal sensing component.

12 . A non-transitory, computer-readable storage medium including instructions that when executed by a system including a wearable, cause the system to:

obtain a first set of neuromuscular signals from a neuromuscular-signal sensing component of a wearable device;

determine, using a low-power detector of the wearable device, that a respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that a predetermined in-air hand gesture has been performed at the wearable device:

process the first set of neuromuscular signals using a high-power detector of the wearable device to generate processed neuromuscular signals, the high-power detector configured to detect a first set of in-air hand gestures while consuming a first amount of power from the wearable device and the low-power detector configured to detect a second set of in-air hand gestures while consuming a second amount of power from the wearable device, the second set of in-air hand gestures includes less in-air hand gestures than the first set of in-air hand gestures and the second amount of power; and

in accordance with a determination, based on the processed neuromuscular signals that the predetermined in-air hand gesture did occur, register an occurrence of the predetermined in-air hand gesture;

receive a second set of neuromuscular signals from the neuromuscular-signal sensing component of the wearable device; and

after determining, based on a respective neuromuscular signal of the second set of neuromuscular signals and using the low-power detector and not using the high-power detector, that a different predetermined in-air hand gesture, distinct from the predetermined in-air hand gesture, was performed at the wearable device:

perform an action in response to the different predetermined in-air hand gesture at the wearable device.

13 . The non-transitory, computer-readable storage medium of claim 12 , wherein:

registering the occurrence of the predetermined in-air hand gesture includes:

registering an occurrence of the wake gesture to cause the high-power detector to remain in an active state; and

registering an occurrence of the another in-air hand gesture to cause the wearable device to execute a function that corresponds to the another in-air hand gesture performing an action within a user interface.

14 . The non-transitory, computer-readable storage medium of claim 12 , wherein:

the neuromuscular-signal sensing component includes a plurality of neuromuscular-signal sensors that correspond to the high-power detector;

while the high-power detector is in an active state, data from the plurality of neuromuscular-signal sensors is processed by the high-power detector; and

while the high-power detector is in an inactive state, data from the plurality of neuromuscular-signal sensors is stored at the wearable device and not processed by the high-power detector.

15 . The non-transitory, computer-readable storage medium of claim 12 , wherein:

the low-power detector operates in a default active state to process detected neuromuscular signals from the neuromuscular-signal sensing component; and

the high-power detector operates in a default inactive state in which it does not process neuromuscular signals in the absence of a trigger signal.

16 . The non-transitory, computer-readable storage medium of claim 12 , further including instructions that cause the system to:

prior to using the low-power detector to determine that the respective neuromuscular signal of the first set of neuromuscular signals requires further processing to confirm that the predetermined in-air hand gesture has been performed at the wearable device:

transition the low-power detector from an inactive state to an active state based on muscular activity detected via the neuromuscular-signal sensing component satisfying a muscular-activity wake-up criterion.

17 . The non-transitory, computer-readable storage medium of claim 16 , further including instructions that cause the system to:

while the low-power detector is in the active state:

in accordance with a determination that data from the neuromuscular-signal sensing component indicates that the muscular-activity wake-up criteria are no longer satisfied, transition the low-power detector to the inactive state.

18 . The non-transitory, computer-readable storage medium of claim 12 , further including instructions that cause the system to:

after performing the action in response to the different predetermined in-air hand gesture at the wearable device, transition both the high-power detector and the low-power detector to inactive states in accordance with a predetermined amount of time having elapsed.

19 . The non-transitory, computer-readable storage medium of claim 18 , wherein, during the predetermined amount of time, no respective neuromuscular signal is determined to require further processing to confirm that an in-air hand gesture has been performed at the wearable device.

20 . The non-transitory, computer-readable storage medium of claim 12 , further including instructions that cause the system to:

before registering the occurrence of the predetermined in-air hand gesture, evaluate data from a second sensor of the wearable device to confirm that the predetermined in-air hand gesture occurred at the wearable device, wherein the second sensor is distinct from the neuromuscular-signal sensing component.