Back to results
US 12,714,911 B2Granted
Condition detection
AssigneeTonal Systems, Inc.
InventorsBryan James, Brandt Belson
Life of this patent
Estimating the term…
Abstract
An exercise device includes an actuator that provides resistance to a user. It further includes a sensor that senses the state of the actuator over time. It further includes an emergency event handler that receives a stream of information from the sensor and determines, based at least in part on the stream of information, a potential occurrence of an emergency condition.
Claims3
An exercise device, comprising:
- an actuator configured to provide resistance to a user;
- a plurality of sensors configured to sense a state of the actuator over time, wherein the plurality of sensors includes two or more of the following:
- a sensor to measure position of the actuator, a sensor to measure position of a motor, a sensor to measure voltage and/or current being consumed by the motor, a sensor to measure how much force is being applied to the actuator by the user, or a sensor used to measure an acceleration and a rate of rotation of the actuator;
- and
- an emergency event handler configured to:
- receive a stream of information from the plurality of sensors;
- and
- determine, based at least in part on the stream of information, a potential occurrence of an emergency condition, comprising to:
- determine a baseline usage pattern of the exercise device based on the stream of information, wherein the baseline usage pattern comprises one or more of the following:
- an average of observed ranges of motion, an average of observed times between repetitions, an average of observed number of times that the user is spotted, an average of observed cable velocity, or an average of observed asymmetry between first and second cables of the exercise device, wherein the baseline usage pattern is determined using a model, wherein the model implements a machine learning technique, and wherein the model is trained using labeled training data, and wherein the baseline usage pattern is determined for an exercise based on historical workout data associated with the user;
- compare an observed pattern of usage of the exercise device with the baseline usage pattern to obtain a deviation, comprising to:
- receive first sensor information from a first sensor of the plurality of the sensors and second sensor information from a second sensor of the plurality of the sensors;
- combine the first sensor information and the second sensor information to obtain the observed pattern of usage, wherein the combining includes to aggregate the first sensor information and the second sensor information to obtain the observed pattern of usage;
- determine the baseline usage pattern based on a first exercise or a second exercise;
- and
- compare the observed pattern of usage with the baseline usage pattern to obtain the deviation;
- and
- in response to a determination that the deviation is equal to or greater than a variation threshold:
- activate a third sensor to obtain third sensor information, wherein the third sensor includes one or more of the following:
- a camera or a microphone;
- evaluate a likelihood of the emergency condition has occurred based on the third sensor information;
- and
- in the event that the likelihood of the emergency condition is below an emergency threshold, adjust the variation threshold.
20 more elements
A method, comprising:
- receiving a stream of sensor information from a plurality of sensors configured to sense a state of an actuator configured to provide resistance to a user, wherein the actuator is associated with an exercise device, wherein the plurality of sensors includes two or more of the following:
- a sensor to measure position of the actuator, a sensor to measure position of a motor, a sensor to measure voltage and/or current being consumed by the motor, a sensor to measure how much force is being applied to the actuator by the user, or a sensor used to measure an acceleration and a rate of rotation of the actuator;
- and
- based at least in part on the stream of sensor information, determining a potential occurrence of an emergency condition, comprising:
- determining a baseline usage pattern of the exercise device based on the stream of information, wherein the baseline usage pattern comprises one or more of the following:
- an average of observed ranges of motion, an average of observed times between repetitions, an average of observed number of times that the user is spotted, an average of observed cable velocity, or an average of observed asymmetry between first and second cables of the exercise device, wherein the baseline usage pattern is determined using a model, wherein the model implements a machine learning technique, and wherein the model is trained using labeled training data, and wherein the baseline usage pattern is determined for an exercise based on historical workout data associated with the user;
- comparing an observed pattern of usage of the exercise device with the baseline usage pattern to obtain a deviation, comprising:
- receiving first sensor information from a first sensor of the plurality of the sensors and second sensor information from a second sensor of the plurality of the sensors;
- combining the first sensor information and the second sensor information to obtain the observed pattern of usage, wherein the combining includes aggregating the first sensor information and the second sensor information to obtain the observed pattern of usage;
- determining the baseline usage pattern based on a first exercise or a second exercise;
- and
- comparing the observed pattern of usage with the baseline usage pattern to obtain the deviation;
- and
- in response to a determination that the deviation is equal to or greater than a variation threshold:
- activating a third sensor to obtain third sensor information, wherein the third sensor includes one or more of the following:
- a camera or a microphone;
- evaluating a likelihood of the emergency condition has occurred based on the third sensor information;
- and
- in the event that the likelihood of the emergency condition is below an emergency threshold, adjusting the variation threshold.
16 more elements
A computer program product embodied in a non-transitory computer readable storage medium and comprising computer instructions for:
- receiving a stream of sensor information from a plurality of sensors configured to sense a state of an actuator configured to provide resistance to a user, wherein the actuator is associated with an exercise device, wherein the plurality of sensors includes two or more of the following:
- a sensor to measure position of the actuator, a sensor to measure position of a motor, a sensor to measure voltage and/or current being consumed by the motor, a sensor to measure how much force is being applied to the actuator by the user, or a sensor used to measure an acceleration and a rate of rotation of the actuator;
- and
- based at least in part on the stream of sensor information, determining a potential occurrence of an emergency condition, comprising:
- determining a baseline usage pattern of the exercise device based on the stream of information, wherein the baseline usage pattern comprises one or more of the following:
- an average of observed ranges of motion, an average of observed times between repetitions, an average of observed number of times that the user is spotted, an average of observed cable velocity, or an average of observed asymmetry between first and second cables of the exercise device, wherein the baseline usage pattern is determined using a model, wherein the model implements a machine learning technique, and wherein the model is trained using labeled training data, and wherein the baseline usage pattern is determined for an exercise based on historical workout data associated with the user;
- comparing an observed pattern of usage of the exercise device with the baseline usage pattern to obtain a deviation, comprising:
- receiving first sensor information from a first sensor of the plurality of the sensors and second sensor information from a second sensor of the plurality of the sensors;
- combining the first sensor information and the second sensor information to obtain the observed pattern of usage, wherein the combining includes aggregating the first sensor information and the second sensor information to obtain the observed pattern of usage;
- determining the baseline usage pattern based on a first exercise or a second exercise;
- and
- comparing the observed pattern of usage with the baseline usage pattern to obtain the deviation;
- and
- in response to a determination that the deviation is equal to or greater than a variation threshold:
- activating a third sensor to obtain third sensor information, wherein the third sensor includes one or more of the following:
- a camera or a microphone;
- evaluating a likelihood of the emergency condition has occurred based on the third sensor information;
- and
- in the event that the likelihood of the emergency condition is below an emergency threshold, adjusting the variation threshold.
16 more elements
Dependencies are inferred from the claim text.