Systems and methods for motion measurement drift correction

1. A computer-implemented device for mitigating measurement drift and improving inertial measurement unit (IMU) odometry measurement, the device comprising:

a memory storing instructions; and

at least one processor configured to execute the instructions to:

receive first sensor data from at least one motion sensor;

receive 3-D motion data based on motion detected by at least one camera;

input model input data into a machine learning model configured to generate at least one vector, the model input data being based on the received first sensor data and the received 3-D motion data; and

apply the at least one vector as an offset to at least one of:

the received first sensor data, to create offset first sensor data; or

second sensor data received from the at least one motion sensor, to create offset second sensor data.

2. The computer-implemented device of claim 1 , wherein the model input data comprises at least one of:

a value representing absolute orientation in space;

a value representing a measurement of a gravitational force;

a value representing angular velocity; or

a value representing linear acceleration.

3. The computer-implemented device of claim 1 , wherein the machine learning model is a neural network.

4. The computer-implemented device of claim 3 , wherein the neural network comprises at least one of:

a convolution layer;

a linear layer;

a soft maximum filter;

a drop-out layer; or

a batch normalization layer.

5. The computer-implemented device of claim 3 , wherein the neural network comprises a one-dimensional layer.

6. The computer-implemented device of claim 1 , wherein the at least one vector comprises at least two values, each value corresponding to a different coordinate direction.

7. The computer-implemented device of claim 1 , wherein:

the at least one motion sensor comprises an inertial measurement unit (IMU); and

the received first sensor data comprises position data of the IMU.

8. The computer-implemented device of claim 1 , wherein the device comprises the at least one camera.

9. The computer-implemented device of claim 1 , wherein:

the at least one motion sensor comprises an inertial measurement unit (IMU); and

the IMU is communicably coupled to the computer-implemented device.

10. The computer-implemented device of claim 1 , wherein the first sensor data and the 3-D motion data are generated while the at least one motion sensor or the at least one camera is in contact with a user.

11. The computer-implemented device of claim 1 , wherein the at least one processor is configured to execute an instruction to apply a data transformation to the received first sensor data to generate at least a portion of the model input data.

12. The computer-implemented device of claim 11 , wherein the data transformation comprises at least one of:

a data smoothing operation;

a moving average operation; or

a coordinate frame transformation.

13. The computer-implemented device of claim 1 , wherein:

the first sensor data and the second sensor data comprise time series datasets; and

the at least one processor is configured to execute an instruction to use at least one of the offset first sensor data or the offset second sensor data to adjust a visual representation of one of the time series datasets.

14. The computer-implemented device of claim 13 , wherein the at least one processor is configured to execute an instruction to cause displaying of the adjusted visual representation.

15. The computer-implemented device of claim 1 , wherein the machine learning model is trained to generate the at least one vector, the training being based on model input data sourced with at least one particular contextual attribute.

16. The computer-implemented device of claim 15 , wherein the at least one processor is configured to execute an instruction to select the machine learning model from among a plurality of machine learning models associated with respective contextual attributes.

17. The computer-implemented device of claim 16 , wherein the at least one processor is configured to execute an instruction to select the machine learning model based on at least one input received at the computer-implemented device from a user.

18. The computer-implemented device of claim 1 , wherein the at least one processor is configured to execute an instruction to train the machine learning model using the received first sensor data and the received 3-D motion data.

19. A method for mitigating measurement drift and improving IMU odometry measurement, comprising:

receiving first sensor data from at least one motion sensor;

receiving 3-D motion data based on motion detected by at least one camera;

inputting model input data into a machine learning model configured to generate at least one vector, the model input data being based on the received first sensor data and the received 3-D motion data; and

applying the at least one vector as an offset to at least one of:

the received first sensor data, to create offset first sensor data; or

second sensor data received from the at least one motion sensor, to create offset second sensor data.

20. A computer-implemented device for mitigating measurement drift and improving IMU odometry measurement, the device comprising:

a memory storing instructions; and

at least one processor configured to execute the instructions to:

receive a first data stream of time-series sensor data from at least one motion sensor;

receive a second data stream of time-series 3-D motion data based on motion detected by at least one camera;

input model input data into a machine learning model configured to generate at least one vector, the model input data comprising vectors representing at least one of angular velocity or linear acceleration, the vectors being based on the first data stream and the second data stream; and

apply the at least one vector as an offset to at least one of the first data stream or the second data stream.