Methods and apparatus for power expenditure and technique determination during bipedal motion
Training at the proper level of effort is important for athletes whose objective is to achieve the best results in the least time. In running, for example, pace is often monitored. However, pace alone does not reveal specific issues with regard to running form, efficiency, or technique, much less inform how training should be modified to improve performance or fitness. A sensing system and wearable sensor platform described herein provide real-time feedback to a user/wearer of his power expenditure during an activity. In one example, the system includes an inertial measurement unit (IMU) for acquiring multi-axis motion data at a first sampling rate, and an orientation sensor to acquire orientation data at a second sampling rate that is varied based on the multi-axis motion data.
1. A watch configured to be worn on a wrist of a user, the watch comprising:
a sensor platform comprising:
an inertial measurement unit (IMU) for acquiring multi-axis motion data while the user is engaging in a physical activity; and
a pressure sensor for acquiring an air pressure data while the user is engaging in the physical activity;
one out more output devices including at least one of a display, a speaker, or a vibration element;
memory; and
a processor operable to:
receive the multi-axis motion data from the IMU;
receive the air pressure data from the pressure sensor;
estimate, during the physical activity, power expended by the user based on at least:
the air pressure data;
a speed determined, in part, from the multi-axis motion data;
a change in speed determined, in part, from the multi-axis motion data; and
a scaling factor based on measurements of one or more users; and
based on the estimated power, generating feedback via the one or more output devices.
2. The watch of claim 1 , wherein the processor is further operable to estimate wind resistance experienced by the user based on the air pressure data, and wherein estimating the power expended by the user includes accounting for the wind resistance.
3. The watch of claim 1 , wherein the processor is further operable to estimate an incline of a path of the user based on at least one of the air pressure data and the multi-axis motion data, and wherein estimating the power expended by the user includes accounting for the incline.
4. The watch of claim 1 , wherein the sensor platform further comprises a satellite receiver; and the speed is determined, in part, based on a signal received from the satellite receiver.
5. The watch of claim 1 , wherein the scaling factor is a first scaling factor, and the processor is further operable to decompose the multi-axis motion data into horizontal motion components and vertical motion components, wherein the power is estimated based on the horizontal motion components and the vertical motion components.
6. The watch of claim 1 , wherein the watch further includes a heart rate sensor for acquiring heart rate data during the physical activity, and the processor is operable to:
receive the heart rate data from the heart rate sensor; and
based on the heart rate data and the estimated power, generating a fitness metric.
7. The watch of claim 6 , wherein the fitness metric is one of fatigue or a power-heart rate relationship.
8. The watch of claim 1 , wherein the one or more users includes the user.
9. A watch configured to be worn on a wrist of a user, the watch comprising:
an inertial measurement unit (IMU) for acquiring multi-axis motion data while the user is running;
a pressure sensor for acquiring an air pressure data while the user is running;
a satellite receiver for acquiring geolocation data while the user is running;
a heart rate sensor for acquiring heart rate data while the user is running;
a speaker;
a vibration element;
a display;
memory; and
a processor operable to:
receive the multi-axis motion data from the IMU;
receive the air pressure data from the pressure sensor;
estimate, while the user is running, an incline of a path of the user based on the air pressure data;
estimate, while the user is running, power expended by the user based on at least:
the air pressure data;
a speed determined from at least one of the multi-axis motion data or the geolocation data;
the estimated incline based on the air pressure data; and
a scaling factor based on measurements of one or more users; and
generate feedback while the user is running, based on the estimated power, via at least one of the display, the speaker, or the vibration element.
10. The watch of claim 9 , wherein the processor is further operable to estimate wind resistance experienced by the user based on the air pressure data, and wherein estimating the power expended by the user includes accounting for the wind resistance.
11. The watch of claim 9 , wherein estimating the power is further based on a change in speed determined based on the multi-axis motion data.
12. The watch of claim 9 , wherein the estimated power is displayed on the display while the user is running.
13. The watch of claim 9 , wherein the processor is further operable to:
based on the heart rate data and the estimated power, determine a fatigue state; and
display a fatigue indicator based on determining the fatigue state.
14. A method for estimating power by a watch worn by a user, the method comprising:
measuring, using an inertial measurement unit (IMU) of the watch, motion of the watch while the watch is worn by the user engaging in a physical activity to produce multi-axis motion data;
measuring, using a pressure sensor of the watch, an air pressure while the user is engaging in the physical activity to produce air pressure data;
receiving, by a processor, a signal that includes the multi-axis motion data and a signal that includes the air pressure data;
estimating, by the processor, power expended by the user, based, at least in part, on:
the air pressure data;
at least one of a speed or a change in a speed determined, in part, from the multi-axis motion data; and
a scaling factor, the scaling factor being empirically determined based on measurements of one or more users; and
generating, via an output device of the watch, feedback based on the estimated power while the user is engaging in the physical activity.
15. The method of claim 14 , further comprising estimating, based on the multi-axis motion data, at least one of a stride length or ground contact time.
16. The method of claim 14 , estimating an incline of a path of the user based on at least one of the air pressure data and the multi-axis motion data, and wherein estimating the power expended by the user includes accounting for the incline.
17. The method of claim 14 , further comprising detecting, by machine learning techniques, at least one action of interest during the physical activity.
18. The method of claim 14 , wherein the speed is determined, in part, based on a signal received from a satellite receiver in the watch.
19. The method of claim 14 , further comprising:
receiving heart rate data in from a heart rate sensor in the watch;
based on the heart rate data and the estimated power, determining a fatigue state; and
generating a fatigue indicator based on determining the fatigue state.
20. The method of claim 14 , wherein the one or more users includes the user.