Systems and methods for a compressed controller for an active exoskeleton
A system to augment motion via a battery-powered active exoskeleton boot is provided. The system can include a controller and an electric motor that generates torque about an axis of rotation of an ankle joint of the user. The controller can receive sensor data associated with activity of the exoskeleton boot during a first time interval. The controller can determine, based on the sensor data input into a model trained via a machine learning technique associated with one or more users performing one or more physical activities, one or more commands for a second time interval. The controller can transmit the one or more commands generated based on the model to the electric motor to cause the electric motor to generate torque about the axis of rotation of the ankle joint of the user in the second time interval.
1. A system to augment motion via an exoskeleton of a foot-ankle, comprising:
a shin pad of a foot-ankle exoskeleton configured to couple to a shin of a user below a knee of the user;
an actuator located below the knee of the user and coupled to the shin pad, the actuator configured to generate torque about an axis of rotation of an ankle joint of the user; and
a controller, comprising memory and one or more processors, to:
receive sensor data associated with activity of the exoskeleton during a first time interval;
input the sensor data into a model trained via a machine learning technique using historical motion data associated with one or more users performing one or more physical activities;
generate a set of candidate parameters from a candidate torque profile based on the sensor data input into the model;
modify the model based on a comparison of the set of candidate parameters and a set of target parameters generated from a target torque profile generated prior to receipt of the sensor data;
determine, for a second time interval subsequent to the first time interval, one or more commands to match the set of candidate parameters; and
transmit the one or more commands generated based on the model to the actuator to cause the actuator to generate torque about the axis of rotation of the ankle joint of the user in the second time interval.
2. The system of claim 1 , comprising:
a battery holder coupled to the shin pad, the battery holder to receive a battery module configured to provide power to at least one of the controller or the actuator.
3. The system of claim 1 , comprising:
a housing enclosing the actuator, the housing located below the knee of the user and coupled to the shin pad; and
an output shaft coupled to the actuator and extending through a bore in the housing.
4. The system of claim 1 , comprising:
a housing that encloses the controller, the housing located below the knee of the user and coupled to the shin pad.
5. The system of claim 1 , comprising:
one or more housings that enclose the controller and the actuator, the one or more housings located below the knee of the user and coupled to the shin pad.
6. The system of claim 1 , wherein the controller is further configured to:
generate a candidate trajectory based on the set of candidate parameters; and
generate a target trajectory based on the set of target parameters.
7. The system of claim 1 , wherein the controller is further configured to:
select the set of candidate parameters based on the sensor data into the model.
8. The system of claim 1 , wherein the historical motion data corresponds to data collected via the exoskeleton in a plurality of states, the plurality of states comprising at least one of an unpowered state, a partially powered state, or a fully powered state.
9. The system of claim 1 , wherein the controller is further configured to:
receive, via a network, the model from a command modelling system that trains the model based on the historical motion data, wherein the command modelling system:
receives the historical motion data comprising historical sensor data;
provides, for display via a display device communicatively coupled to the command modelling system, a visual indication of the historical motion data;
receives, via a user interface, an indication of the candidate torque profile corresponding to the visual indication of the historical motion data; and
train, using the machine learning technique and based on the indication of the candidate torque profile received via the user interface, the model to cause the model to output the one or more commands responsive to the sensor data.
10. The system of claim 1 , wherein:
the historical motion data comprises at least one of inertial measurement unit data, goniometer data, infrared reflector data, or force plate data; and
the sensor data comprises at least one of ankle joint data, inertial measurement unit data, or battery data.
11. A method of augmenting motion via an exoskeleton of a foot-ankle, comprising:
receiving, by a controller comprising memory and one or more processors, sensor data associated with activity of a foot-ankle exoskeleton during a first time interval;
inputting, by the controller, the sensor data into a model trained via a machine learning technique using historical motion data associated with one or more users performing one or more physical activities;
generating, by the controller, a set of candidate parameters from a candidate torque profile based on the sensor data input into the model;
modifying, by the controller, the model based on a comparison of the set of candidate parameters and a set of target parameters generated from a target torque profile generated prior to receipt of the sensor data;
determining, by the controller, for a second time interval subsequent to the first time interval, one or more commands to match the set of candidate parameters; and
transmitting, by the controller, the one or more commands generated based on the model to an actuator to cause the actuator to generate torque about an axis of rotation of an ankle joint of a user in the second time interval,
wherein the actuator is located below a knee of the user and coupled to a shin pad of the exoskeleton, and the shin pad couples to a shin of the user below the knee of the user.
12. The method of claim 11 , comprising:
generating, by the controller, a candidate trajectory based on the set of candidate parameters; and
generating, by the controller, a target trajectory based on the set of target parameters.
13. The method of claim 11 , comprising:
selecting, by the controller, the set of candidate parameters based on the sensor data into the model.
14. The method of claim 11 , comprising:
receiving, by the controller via a network, the model from a command modelling system that trains the model based on the historical motion data, wherein the command modelling system:
receives the historical motion data comprising historical sensor data;
provides, for display via a display device communicatively coupled to the command modelling system, a visual indication of the historical motion data;
receives, via a user interface, an indication of the candidate torque profile corresponding to the visual indication of the historical motion data; and
train, using the machine learning technique and based on the indication of the candidate torque profile received via the user interface, the model to cause the model to output the one or more commands responsive to the sensor data.
15. A method, comprising:
providing a shin pad of a foot-ankle exoskeleton to couple to a shin of a user below a knee of the user;
providing an actuator located below the knee of the user and coupled to the shin pad, the actuator configured to generate torque about an axis of rotation of an ankle joint of the user; and
providing a controller, comprising memory and one or more processors, the controller configured to:
receive sensor data associated with activity of the exoskeleton during a first time interval;
input the sensor data into a model trained via a machine learning technique using historical motion data associated with one or more users performing one or more physical activities;
generate a set of candidate parameters from a candidate torque profile based on the sensor data input into the model;
modify the model based on a comparison of the set of candidate parameters and a set of target parameters generated from a target torque profile generated prior to receipt of the sensor data;
determine, for a second time interval subsequent to the first time interval, one or more commands to match the set of candidate parameters; and
transmit the one or more commands generated based on the model to the actuator to cause the actuator to generate torque about the axis of rotation of the ankle joint of the user in the second time interval.
16. The method of claim 15 , comprising:
providing a battery holder coupled to the shin pad, the battery holder to receive a battery module configured to provide power to at least one of the controller or the actuator.
17. The method of claim 15 , comprising:
providing a housing enclosing the actuator, the housing located below the knee of the user and coupled to the shin pad; and
providing an output shaft coupled to the actuator and extending through a bore in the housing.
18. The method of claim 15 , comprising:
providing a housing that encloses the controller, the housing located below the knee of the user and coupled to the shin pad.