Reserve estimates during resistance training
A time series of raw performance data samples pertaining to performing of a set of repetitions of a movement by a user is collected from a sensor. A set of features is generated from the collected time series of raw performance data samples, including by extracting one or more waveform shape features. The set of features, including the extracted one or more waveform shape features, is provided as input to a model that outputs an estimate of repetitions in reserve.
1 . An exercise machine, comprising:
a sensor;
a memory;
and one or more processors coupled to the memory and configured to:
collect, from the sensor, a time series of raw performance data samples pertaining to performing of a set of repetitions of a movement by a user, the time series of raw performance data comprises a velocity waveform;
generate, from the collected time series of raw performance data samples, a set of features, including extracting one or more waveform shape features, wherein extracting the one or more waveform shape features includes analyzing the velocity waveform and analyzing the velocity waveform comprises performing principal component analysis;
and provide the set of features, including the extracted one or more waveform shape features, as input to a model that outputs an estimate of repetitions in reserve;
wherein the one or more processors are further configured to dynamically adjust torque requested of a motor based at least in part on the estimate of repetitions in reserve output by the model.
2 . The system of claim 1 , wherein the motor provides exercise resistance to an actuator coupled to the motor via a cable.
3 . The system of claim 1 , wherein the sensor senses a position for an actuator that a user exercises against.
4 . The system of claim 1 , wherein generating the set of features comprises generating the set of features according to a set of mappings.
5 . The system of claim 1 , wherein the output of the estimate of repetitions in reserve is done in real-time.
6 . The system of claim 1 , wherein the one or more processors are further configured to identify effective repetitions based at least in part on the estimate of repetitions in reserve output by the model.
7 . The system of claim 1 , wherein: the one or more processors are further configured to identify effective repetitions based at least in part on the estimate of repetitions in reserve output by the model; and identifying the effective repetitions comprises identifying when the estimated repetitions in reserve is below a threshold value.
8 . The system of claim 1 , wherein the one or more processors are further configured to dynamically adjust spotter sensitivity based at least in part on the estimate of repetitions in reserve output by the model.
9 . The system of claim 1 , wherein the one or more processors are further configured to: update the time series of raw performance data samples at least in part by adding raw performance data samples pertaining to a current repetition to raw performance data samples pertaining to one or more prior repetitions; generate an updated set of features based at least in part on the updated time series of raw performance data samples pertaining to the current repetition and the one or more prior repetitions; and provide the updated set of features as input to the model, wherein the model outputs an updated estimate of repetitions in reserve.
10 . The system of claim 1 , wherein the model is run locally at the exercise machine.
11 . The system of claim 1 , wherein the model comprises a gradient-boosted tree model.
12 . The system of claim 1 , wherein the generated set of features includes an inter-repetition feature.
13 . The system of claim 1 , wherein the inter-repetition feature comprises an inter-repetition rest duration.
14 . The system of claim 1 , wherein the one or more processors are further configured to estimate effective volume based at least in part on the estimate of repetitions in reserve output by the model.
15 . A method, comprising:
collecting, from a sensor, a time series of raw performance data samples pertaining to performing of a set of repetitions of a movement by a user, wherein the time series of raw performance data comprises a velocity waveform;
generating, from the collected time series of raw performance data samples, a set of features, including extracting one or more waveform shape features, wherein extracting the one or more waveform shape features includes analyzing the velocity waveform; and analyzing the velocity waveform comprises performing principal component analysis;
and providing the set of features, including the extracted one or more waveform shape features, as input to a model that outputs an estimate of repetitions in reserve;
wherein torque requested of a motor coupled to a user actuator is dynamically adjusted based at least in part on the estimate of repetitions in reserve output by the model.
16 . A computer program product, the computer program product being embodied in a tangible non-transitory computer readable storage medium and comprising computer instructions for:
collecting, from a sensor, a time series of raw performance data samples pertaining to performing of a set of repetitions of a movement by a user, wherein the time series of raw performance data comprises a velocity waveform;
generating, from the collected time series of raw performance data samples, a set of features, including extracting one or more waveform shape features, wherein extracting the one or more waveform shape features includes analyzing the velocity waveform and analyzing the velocity waveform comprises performing principal component analysis;
and providing the set of features, including the extracted one or more waveform shape features, as input to a model that outputs an estimate of repetitions in reserve;
wherein torque requested of a motor coupled to a user actuator is dynamically adjusted based at least in part on the estimate of repetitions in reserve output by the model.