Exosuit activity transition control
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for an exosuit activity transition control structure. In some implementations, sensor data for a powered exosuit is received. The sensor data is classified depending on whether the sensor data is indicative of a transition between different types of activities of a wearer of the powered exosuit. The classification is provided to a control system for the powered exosuit. The powered exosuit is controlled based on the classification.
1 . A computer-implemented method comprising:
receiving, by one or more computing devices, a first set of sensor data from one or more sensors in a powered exosuit;
predicting, by the one or more computing devices, based on the received first set of sensor data, that a wearer of the powered exosuit is performing a first type of activity with a first confidence score;
receiving, by the one or more computing devices, a second set of sensor data from the one or more sensors in the powered exosuit;
predicting, by a transition detection model of the one or more computing devices, based on the received second sensor data, that the wearer of the powered exosuit has transitioned from the first type of activity to a second type of activity with a second confidence score;
determining, by the one or more computing devices, a plurality of actions to be performed based on the transition;
detecting, by the one or more computing devices, that the second confidence score exceeds a threshold value corresponding to at least one action of the plurality of actions; and
triggering, by the one or more computing devices, the at least one action upon detecting that the second confidence score exceeds the threshold value, wherein the plurality of actions includes:
changing a threshold value corresponding to another action of the plurality of actions,
changing a maximum amount of force or torque allowed to be applied by an actuator of the powered exosuit,
adjusting a maximum allowed flex at a hinge of the powered exosuit,
activating one or more safety rules that include at least one of: locking a joint, restricting rotation of the joint, and altering assistive force output,
adjusting a maximum speed of movement allowed for the powered exosuit, and
changing, based on the transition, an active control program in the powered exosuit that operates the powered exosuit to a control program associated with the second type of activity;
detecting, by the one or more computing devices, that the second confidence score exceeds a second threshold value, wherein the second threshold value is greater than the threshold value; and
based on the detection, activating a second set of one or more safety rules and deactivating, based on the detection, the one or more safety rules.
2 . The method of claim 1 , wherein the first type of activity includes one of: sitting, walking, falling, standing, climbing stairs, or running.
3 . The method of claim 1 , wherein the one or more sensors comprises at least one of:
a position sensor, a motion sensor, an accelerometer, a potentiometer, an electrogoniometer, a pose detection sensor, a joint angle sensor, an encoder, a load sensor, a pressure sensor, a force sensor, a torque sensor, a strain gauge, a piezoresistive sensor, a gyroscope, an electromyographic (EMG) sensor, an electroencephalography (EEG) sensor, or an electrooculography sensor.
4 . The method of claim 1 , wherein the first set of sensor data and the second set of sensor data from the one or more sensors incudes at least one of: a force currently applied to a right knee joint of the wearer and a pressure on a foot of the wearer.
5 . The method of claim 1 , wherein the first set of sensor data and the second set of sensor data from the one or more sensors indicates at least one of:
parameters of the powered exosuit,
physiological parameters for the wearer, or
indications of interactions of the wearer with the powered exosuit.
6 . The method of claim 1 , wherein the one or more computing devices are configured to normalize the first set of sensor data and the second set of sensor data from the one or more sensors based on characteristics of the wearer.
7 . The method of claim 6 , wherein the characteristics of the wearer includes a weight and a height of the wearer.
8 . The method of claim 1 , wherein the triggering the at least one action is based at least in part on a control program of the one or more computing devices; and wherein the method further comprises receiving, from a remote management system via an onboard receiver, instructions to change the control program.
9 . A system comprising:
one or more sensors;
a processor; and
one or more computer-readable media storing instructions that, when executed, cause the processor to:
receive a first set of sensor data from one or more sensors in a powered exosuit;
predict, based on the received first set of sensor data, that a wearer of the powered exosuit is performing a first type of activity with a first confidence score;
receive a second set of sensor data from the one or more sensors in the powered exosuit;
predict, based on the received second sensor data, that the wearer of the powered exosuit has transitioned from the first type of activity to a second type of activity with a second confidence score;
determine a plurality of actions to be performed based on the transition;
detect that the second confidence score exceeds a threshold value corresponding to at least one action of the plurality of actions; and
trigger the at least one action upon detecting that the second confidence score exceeds the threshold value, wherein the plurality of actions includes:
changing a threshold value corresponding another action of the plurality of actions,
changing a maximum amount of force or torque allowed to be applied by an actuator of the powered exosuit,
adjusting a maximum allowed flex at a hinge of the powered exosuit,
activating one or more safety rules that include at least one of: locking a joint, restricting rotation of the joint, and altering assistive force output,
adjusting a maximum speed of movement allowed for the powered exosuit, and
changing, based on the transition, an active control program in the powered exosuit that operates the powered exosuit to a control program associated with the second type of activity;
detecting that the second confidence score exceeds a second threshold value, wherein the second threshold value is greater than the threshold value; and
based on the detection, activating a second set of one or more safety rules and deactivating, based on the detection, the one or more safety rules.
10 . The system of claim 9 , wherein the first type of activity includes one of: sitting, walking, falling, standing, climbing stairs, or running.
11 . The system of claim 9 , wherein the one or more sensors comprises at least one of:
a position sensor, a motion sensor, an accelerometer, a potentiometer, an electrogoniometer, a pose detection sensor, a joint angle sensor, an encoder, a load sensor, a pressure sensor, a force sensor, a torque sensor, a strain gauge, a piezoresistive sensor, a gyroscope, an electromyographic (EMG) sensor, an electroencephalography (EEG) sensor, or an electrooculography sensor.
12 . The system of claim 9 , wherein the first set of sensor data and the second set of sensor data from the one or more sensors incudes at least one of: a force currently applied to a right knee joint of the wearer and a pressure on a foot of the wearer.
13 . The system of claim 9 , wherein the first set of sensor data and the second set of sensor data from the one or more sensors indicates at least one of:
parameters of the powered exosuit,
physiological parameters for the wearer, or
indications of interactions of the wearer with the powered exosuit.
14 . The system of claim 9 , wherein processor is configured to normalize the first set of sensor data and the second set of sensor data from the one or more sensors based on characteristics of the wearer.
15 . The system of claim 14 , wherein the characteristics of the wearer includes a weight and a height of the wearer.
16 . The system of claim 9 , wherein the triggering the at least one action is based at least in part on a control program; and wherein the instructions further cause the processor to receive, from a remote management system via an onboard receiver, instructions to change the control program.
17 . One or more non-transitory computer-readable media storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
receiving, by one or more computing devices, a first set of sensor data from one or more sensors in a powered exosuit;
predicting, by the one or more computing devices, based on the received first set of sensor data, that a wearer of the powered exosuit is performing a first type of activity with a first confidence score;
receiving, by the one or more computing devices, a second set of sensor data from the one or more sensors in the powered exosuit;
predicting, by the one or more computing devices based on the received second sensor data, that the wearer of the powered exosuit has transitioned from the first type of activity to a second type of activity with a second confidence score;
determining, by the one or more computing devices, a plurality of actions to be performed based on the transition;
detecting, by the one or more computing devices, that the second confidence score exceeds a threshold value corresponding to at least one action of the plurality of actions; and
triggering, by the one or more computing devices, the at least one action upon detecting that the second confidence score exceeds the threshold value, wherein the plurality of actions includes:
changing a threshold value corresponding to another action of the plurality of actions,
changing a maximum amount of force or torque allowed to be applied by an actuator of the powered exosuit,
adjusting a maximum allowed flex at a hinge of the powered exosuit,
activating one or more safety rules that include at least one of: locking a joint, restricting rotation of the joint, and altering assistive force output,
adjusting a maximum speed of movement allowed for the powered exosuit, and
changing, based on the transition, an active control program in the powered exosuit that operates the powered exosuit to a control program associated with the second type of activity;
detecting, by the one or more computing devices, that the second confidence score exceeds a second threshold value, wherein the second threshold value is greater than the threshold value; and
based on the detection, activating a second set of one or more safety rules and deactivating, based on the detection, the one or more safety rules.
18 . The computer-readable media of claim 17 , wherein the first type of activity includes one of: sitting, walking, falling, standing, climbing stairs, or running.
19 . The computer-readable media of claim 17 , wherein the one or more sensors comprises at least one of:
a position sensor, a motion sensor, an accelerometer, a potentiometer, an electrogoniometer, a pose detection sensor, a joint angle sensor, an encoder, a load sensor, a pressure sensor, a force sensor, a torque sensor, a strain gauge, a piezoresistive sensor, a gyroscope, an electromyographic (EMG) sensor, an electroencephalography (EEG) sensor, or an electrooculography sensor.
20 . The computer-readable media of claim 17 , wherein the first set of sensor data and the second set of sensor data from the one or more sensors incudes at least one of: a force currently applied to a right knee joint of the wearer and a pressure on a foot of the wearer.