Systems and methods for using statistical inference to enhance the precision of sparsified capacitive-touch and other human-interface devices

1. A method comprising, by an electronic device:

receiving sensor data indicative of a touch input from one or more sensors of a human interface-device (HID) of the electronic device, wherein the touch input occurs at a set of actual coordinates with respect to the HID, and wherein the sensor data indicates the touch input occurs at a set of detected coordinates with respect to the HID, wherein the set of detected coordinates is different from the set of actual coordinates, wherein the sensor data indicative of a touch input, the set of actual coordinates, and the set of detected coordinates each comprise a sequence of locations on the HID, each location in the sequence corresponding to a particular time;

determining a context associated with the touch input;

determining, by one or more generative models, context-dependent statistics to apply a delta change to the set of detected coordinates, wherein the context-dependent statistics are based on the context associated with the touch input, and wherein the one or more generative models comprises one or more system parameters and one or more latent parameters, and wherein the delta change corresponds to at least one first location in the sequence of locations of the set of detected coordinates, and the delta change corresponding to the at least one first location is determined based at least on one or more other locations in the sequence of locations of the set of detected coordinates; and

determining a set of time-lapsed predicted coordinates of the touch input with respect to the HID based on the delta change, wherein the set of time-lapsed predicted coordinates are an estimate of the set of actual coordinates.

2. The method of claim 1 , further comprising:

storing the sensor data in a buffer, wherein the buffer is used to remove signal noise associated with the set of detected coordinates from the sensor data, and wherein the context is determined based on the stored data.

3. The method of claim 1 , wherein the one or more sensors of the HID are positioned in a pattern on the HID where a first subset of sensors of the one or more sensors are positioned at least a threshold distance away from a second subset of sensors of the one or more sensors.

4. The method of claim 3 , wherein the pattern comprises a stripe pattern, where the first subset of sensors and the second subset of sensors are positioned along parallel lines with respect to the HID.

5. The method of claim 1 , further comprising:

injecting a plurality of signals into the one or more sensors, wherein the plurality of signals comprise at least a first signal at a first frequency and a second signal at a second frequency; and

detecting, by the one or more sensors, a plurality of attenuated measured signals based on the touch input interfacing the plurality of signals, wherein the plurality of attenuated measured signals are used to generate the sensor data.

6. The method of claim 1 , wherein the one or more sensors comprises one or more of a capacitive sensor or a resistive sensor.

7. The method of claim 1 , further comprising:

displaying, on the HID, an indication of the set of predicted coordinates of the touch input in real-time.

8. An electronic device comprising:

one or more displays;

one or more non-transitory computer-readable storage media including instructions; and

one or more processors coupled to the storage media, the one or more processors configured to execute the instructions to:

receive sensor data indicative of a touch input from one or more sensors of a human interface-device (HID) of the electronic device, wherein the touch input occurs at a set of actual coordinates with respect to the HID, and wherein the sensor data indicates the touch input occurs at a set of detected coordinates with respect to the HID, wherein the set of detected coordinates is different from the set of actual coordinates, wherein the sensor data indicative of a touch input, the set of actual coordinates, and the set of detected coordinates each comprise a sequence of locations on the HID, each location in the sequence corresponding to a particular time;

determine a context associated with the touch input;

determine, by one or more generative models, context-dependent statistics to apply a delta change to the set of detected coordinates, wherein the context-dependent statistics are based on the context associated with the touch input, and wherein the one or more generative models comprises one or more system parameters and one or more latent parameters, and wherein the delta change corresponds to at least one first location in the sequence of locations of the set of detected coordinates, and the delta change corresponding to the at least one first location is determined based at least on one or more other locations in the sequence of locations of the set of detected coordinates; and

determine a set of time-lapsed predicted coordinates of the touch input with respect to the HID based on the delta change, wherein the set of time-lapsed predicted coordinates are an estimate of the set of actual coordinates.

9. The electronic device of claim 8 , wherein the processors are further configured to execute the instructions to:

store the sensor data in a buffer, wherein the buffer is used to remove signal noise associated with the set of detected coordinates from the sensor data, and wherein the context is determined based on the stored data.

10. The electronic device of claim 8 , wherein the one or more sensors of the HID are positioned in a pattern on the HID where a first subset of sensors of the one or more sensors are positioned at least a threshold distance away from a second subset of sensors of the one or more sensors.

11. The electronic device of claim 10 , wherein the pattern comprises a stripe pattern, where the first subset of sensors and the second subset of sensors are positioned along parallel lines with respect to the HID.

12. The electronic device of claim 8 , wherein the processors are further configured to execute the instructions to:

inject a plurality of signals into the one or more sensors, wherein the plurality of signals comprise at least a first signal at a first frequency and a second signal at a second frequency; and

detect, by the one or more sensors, a plurality of attenuated measured signals based on the touch input interfacing the plurality of signals, wherein the plurality of attenuated measured signals are used to generate the sensor data.

13. The electronic device of claim 8 , wherein the one or more sensors comprises one or more of a capacitive sensor or a resistive sensor.

14. The electronic device of claim 8 , wherein the processors are further configured to execute the instructions to:

display, on the HID, an indication of the set of predicted coordinates of the touch input in real-time.

15. A computer-readable non-transitory storage media comprising instructions executable by a processor to:

receive sensor data indicative of a touch input from one or more sensors of a human interface-device (HID) of the electronic device, wherein the touch input occurs at a set of actual coordinates with respect to the HID, and wherein the sensor data indicates the touch input occurs at a set of detected coordinates with respect to the HID, wherein the set of detected coordinates is different from the set of actual coordinates, wherein the sensor data indicative of a touch input, the set of actual coordinates, and the set of detected coordinates each comprise a sequence of locations on the HID, each location in the sequence corresponding to a particular time;

determine a context associated with the touch input;

determine, by one or more generative models, context-dependent statistics to apply a delta change to the set of detected coordinates, wherein the context-dependent statistics are based on the context associated with the touch input, and wherein the one or more generative models comprises one or more system parameters and one or more latent parameters, and wherein the delta change corresponds to at least one first location in the sequence of locations of the set of detected coordinates, and the delta change corresponding to the at least one first location is determined based at least on one or more other locations in the sequence of locations of the set of detected coordinates; and

determine a set of time-lapsed predicted coordinates of the touch input with respect to the HID based on the delta change, wherein the set of time-lapsed predicted coordinates are an estimate of the set of actual coordinates.

16. The media of claim 15 , wherein the instructions are further executable by the processor to:

store the sensor data in a buffer, wherein the buffer is used to remove signal noise associated with the set of detected coordinates from the sensor data, and wherein the context is determined based on the stored data.

17. The media of claim 15 , wherein the one or more sensors of the HID are positioned in a pattern on the HID where a first subset of sensors of the one or more sensors are positioned at least a threshold distance away from a second subset of sensors of the one or more sensors.

18. The media of claim 17 , wherein the pattern comprises a stripe pattern, where the first subset of sensors and the second subset of sensors are positioned along parallel lines with respect to the HID.

19. The media of claim 15 , wherein the instructions are further executable by the processor to:

inject a plurality of signals into the one or more sensors, wherein the plurality of signals comprise at least a first signal at a first frequency and a second signal at a second frequency; and

detect, by the one or more sensors, a plurality of attenuated measured signals based on the touch input interfacing the plurality of signals, wherein the plurality of attenuated measured signals are used to generate the sensor data.

20. The media of claim 15 , wherein the one or more sensors comprises one or more of a capacitive sensor or a resistive sensor.