System and method for biofeedback including relevance assessment

1. A system for biofeedback, the system comprising:

one or more processors and a memory, the memory being a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions, the one or more processors perform operations of:

obtaining an average of sensor data collected during one or more calibration tasks, resulting in a performance data mean;

acquiring biometric data from a plurality of biometric sensors during performance of a current task, wherein the biometric data comprises an attention biometric, a fatigue biometric, and a stress biometric;

determining a biometric mean value for each biometric in a time window;

determining a correlation between each biometric mean value and the performance data mean;

determining a significance parameter for each correlation, and

when a significance parameter of a biometric crosses a threshold of significance, determining a relevance value of the biometric to the performance of the current task, wherein the relevance value indicates whether the biometric has a positive or a negative correlation with the performance of the current task, and how the biometric should be considered in controlling an automated vehicle system; and

based on at least one relevance value, controlling the automated vehicle system.

2. The system of claim 1 , wherein controlling the automated vehicle system comprises causing a ground-based or aerial vehicle to initiate a physical action.

3. The system of claim 1 , wherein the one or more processors further perform an operation of sending at least one of a visual, audio, or electronic alert.

4. The system of claim 1 , wherein the one or more processors perform operations of, based on the biometric data from each biometric sensor, generating a mental state score, corresponding to each biometric, having a continuous scale, and wherein control of the automated vehicle system has a magnitude that is proportioned based on the mental state score, such that a magnitude of a driving intervention by the automated vehicle system is proportional to the mental state score corresponding to at least one biometric.

5. The system of claim 1 , wherein the one or more processors perform operations of, using sensor data from the one or more calibration tasks, training a biometric model for each biometric.

6. The system of claim 5 , wherein the one or more processors perform operations of:

extracting a set of features from the biometric data from each of the plurality of biometric sensors

analyzing each set of features with a corresponding biometric model, wherein each set of features is analyzed using a machine learning algorithm;

outputting a biometric value for each biometric; and

using each biometric value, generating a mental state score for each biometric.

7. The system of claim 6 , wherein the machine learning algorithm is a generalized linear model.

8. The system of claim 6 , wherein each set of features comprises a power spectral density of a signal from a corresponding biometric sensor.

9. A computer program product for biofeedback, the computer program product comprising:

a non-transitory computer-readable medium having executable instructions encoded thereon, such that upon execution of the instructions by one or more processors, the one or more processors perform operations of:

obtaining an average of sensor data collected during one or more calibration tasks, resulting in a performance data mean;

acquiring biometric data from a plurality of biometric sensors during performance of a current task, wherein the biometric data comprises an attention biometric, a fatigue biometric, and a stress biometric;

determining a biometric mean value for each biometric in a time window;

determining a correlation between each biometric mean value and the performance data mean;

determining a significance parameter for each correlation, and

when a significance parameter of a biometric crosses a threshold of significance, determining a relevance value of the biometric to the performance of the current task, wherein the relevance value indicates whether the biometric has a positive or a negative correlation with the performance of the current task, and how the biometric should be considered in controlling an automated vehicle system; and

based on at least one relevance value, controlling the automated vehicle system.

10. The computer program product of claim 9 , wherein controlling the automated vehicle system comprises causing a ground-based or aerial vehicle to initiate a physical action.

11. The computer program product of claim 9 , wherein the one or more processors further perform an operation of sending at least one of a visual, audio, or electronic alert.

12. The computer program product of claim 9 , wherein the one or more processors perform operations of, based on the biometric data from each biometric sensor, generating a mental state score, corresponding to each biometric, having a continuous scale, and wherein control of the automated vehicle system has a magnitude that is proportioned based on the mental state score, such that a magnitude of a driving intervention by the automated vehicle system is proportional to the mental state score corresponding to at least one biometric.

13. The computer program product of claim 9 , wherein the one or more processors perform operations of, using sensor data from the one or more calibration tasks, training a biometric model for each biometric.

14. A computer implemented method for biofeedback, the method comprising an act of:

causing one or more processers to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:

obtaining an average of sensor data collected during one or more calibration tasks, resulting in a performance data mean;

acquiring biometric data from a plurality of biometric sensors during performance of a current task, wherein the biometric data comprises an attention biometric, a fatigue biometric, and a stress biometric;

determining a biometric mean value for each biometric in a time window;

determining a correlation between each biometric mean value and the performance data mean;

determining a significance parameter for each correlation, and

when a significance parameter of a biometric crosses a threshold of significance, determining a relevance value of the biometric to the performance of the current task, wherein the relevance value indicates whether the biometric has a positive or a negative correlation with the performance of the current task, and how the biometric should be considered in controlling an automated vehicle system; and

based on at least one relevance value, controlling the automated vehicle system.

15. The method of claim 14 , wherein controlling the automated vehicle system comprises causing a ground-based or aerial vehicle to initiate a physical action.

16. The method of claim 14 , wherein the one or more processors further perform an operation of sending at least one of a visual, audio, or electronic alert.

17. The method of claim 14 , wherein the one or more processors perform operations of, based on the biometric data from each biometric sensor, generating a mental state score, corresponding to each biometric, having a continuous scale, and wherein control of the automated vehicle system has a magnitude that is proportioned based on the mental state score, such that a magnitude of a driving intervention by the automated vehicle system is proportional to the mental state score corresponding to at least one biometric.

18. The method of claim 14 , wherein the one or more processors perform operations of, using sensor data from the one or more calibration tasks, training a biometric model for each biometric.