Detecting contactless gestures using radio frequency
The present disclosure provides for detection of input to a wireless device, such as earbuds or other wearable devices, based on RF signals between the earbuds and/or between an earbud and other devices, such as a host device. For example, gestures may be detected using signal strength, such as by using a received signal strength indicator (RSSI), between two earbuds and/or between an earbud and a host device.
1. A method for detecting input, the method comprising:
receiving a machine-learned model, the machine-learned model trained based on:
training user input gestures, the training user input gestures including at least one training user input gesture received by a first device; and
a detected change in a training signal strength during the reception by the first device of the at least one training user input gesture;
detecting, by the first device, a first signal strength between the first device and a second device that is wirelessly coupled to the first device;
identifying, by the first device, a change in the detected first signal strength; and
determining, by the first device based on the change in the detected first signal strength and using the machine-learned model trained based on the at least one training user input gesture received by the first device and the detected change in the training signal strength, a user input gesture corresponding to the change in the detected first signal strength.
2. The method of claim 1 wherein the first device is a first earbud of a pair of earbuds and the second device is a second earbud of the pair of earbuds.
3. The method of claim 1 , further comprising:
detecting, by the first device, a second signal strength between the first device and a host device; and
identifying, by the first device, a change in the detected second signal strength;
wherein determining the user input gesture is further based on the change in the detected second signal strength.
4. The method of claim 1 , wherein the user input gesture is a non-contact gesture.
5. The method of claim 4 , wherein the non-contact gesture includes one of a swipe gesture or a hold gesture near the first device.
6. The method of claim 1 , further comprising:
detecting, by one or more sensors of the first device, the user input gesture; and
correlating the detection of the user input gesture by the one or more sensors with the identified change in the detected first signal strength.
7. The method of claim 6 , wherein the one or more sensors include at least one of a touch sensor or an infrared sensor.
8. The method of claim 1 , further comprising updating the stored indication and detected changes in the detected first signal strength when a subsequent user input gesture is received.
9. A system comprising:
a wearable wireless device comprising a memory, one or more processors, and a wireless interface for wirelessly communicating with at least one second device, wherein the one or more processor processors of the wearable wireless device are configured to:
receive a machine-learned model, the machine-learned model trained based on:
training user input gestures, the training user input gestures including at least one training user input gesture received by the wearable wireless device; and
a detected change in a training signal strength during the reception by the wearable wireless device of the at least one training user input gesture;
detect a first signal strength between the wearable wireless first device and the at least one second device that is wirelessly coupled to the wearable wireless first device;
identify a change in the detected first signal strength; and
determine, based on the change in the detected first signal strength and using the machine-learned model trained based on the at least one training user input gesture received by the wearable wireless device and the detected change in the training signal strength, a user input gesture corresponding to the change in the detected first signal strength.
10. The system of claim 9 , wherein the wearable wireless device is a first earbud of a pair of earbuds and the at least one second device is a second earbud of the pair of earbuds.
11. The system of claim 9 , wherein the one or more processors of the wearable wireless device are further configured to:
detect a second signal strength between the wearable wireless device and a host device; and
identify a change in the detected second signal strength;
wherein determining the user input gesture is further based on the change in the detected second signal strength.
12. The system of claim 9 , wherein the user input gesture is a non-contact gesture.
13. The system of claim 12 , wherein the non-contact gesture includes one of a swipe gesture or a hold gesture near the first device.
14. The system of claim 9 , wherein the wearable wireless device further comprises one or more sensors, and wherein the one or more processors of the wearable wireless device are further configured to:
detect, using the one or more sensors, the user input gesture; and
correlate the detection of the user input gesture by the one or more sensors with the identified change in the detected first signal strength.
15. The system of claim 14 , wherein the one or more sensors include at least one of a touch sensor or an infrared sensor.
16. The system of claim 9 , wherein the one or more processors of the wearable wireless device are further configured to update the stored indication and detected changes in the detected first signal strength when a subsequent user input gesture is received.
17. A non-transitory computer-readable medium storing instructions executable by one or more processors for performing a method for detecting input, the method comprising:
receiving a machine-learned model, the machine-learned model trained based on:
training user input gestures, the training user input gestures including at least one training user input gesture received by a first device; and
a detected change in a training signal strength during the reception by the first device of the at least one training user input gesture;
detecting, by the first device, a first signal strength between the first device and a second device that is wirelessly coupled to the first device;
identifying, by the first device, a change in the detected first signal strength; and
determining, by the first device based on the change in the detected first signal strength and using the machine-learned model trained based on the at least one training user input gesture received by the first device and the detected change in the training signal strength, a user input gesture corresponding to the change in the detected first signal strength.
18. The non-transitory computer-readable medium of claim 17 , wherein the first device is a first earbud of a pair of earbuds and the second device is a second earbud of the pair of earbuds.
19. The non-transitory computer-readable medium of claim 17 , the method further comprising:
detecting, by the first device, a second signal strength between the first device and a host device; and
identifying, by the first device, a change in the detected second signal strength;
wherein determining the user input gesture is further based on the change in the detected second signal strength.
20. The non-transitory computer-readable medium of claim 17 , wherein the user input gesture is a non-contact gesture.