US Pat. No. 10,362,958

SYSTEMS, ARTICLES, AND METHODS FOR ELECTROMYOGRAPHY SENSORS

CTRL-labs Corporation, N...

1. An electromyography (“EMG”) sensor comprising:a first sensor electrode formed of an electrically conductive material, wherein the first sensor electrode comprises a first layer formed of a first electrically conductive material that includes copper and a second layer formed of a second electrically conductive material;
an amplifier; and
a first electrically conductive pathway that communicatively couples the first sensor electrode and the amplifier.

US Pat. No. 10,496,168

CALIBRATION TECHNIQUES FOR HANDSTATE REPRESENTATION MODELING USING NEUROMUSCULAR SIGNALS

CTRL-labs Corporation, N...

1. A computerized system configured to calibrate performance of one or more statistical models used to generate a musculoskeletal representation, the system comprising:a plurality of neuromuscular sensors configured to continuously record a plurality of neuromuscular signals, wherein the plurality of neuromuscular sensors are arranged on at least one wearable device; and
at least one computer processor programmed to:
process at least some of the plurality of neuromuscular signals using a statistical model to generate based, at least in part, on joint angle estimates and/or force estimates output from the statistical model, the musculoskeletal representation;
determine based, at least in part, on at least one aspect of the musculoskeletal representation, that calibration of the statistical model used to generate the musculoskeletal representation is needed;
initiate a calibration session in response to determining that calibration is needed;
update a statistical model configuration based, at least in part, on a plurality of neuromuscular signals recorded by the plurality of neuromuscular sensors and ground-truth data representing position information and/or force information recorded during the calibration session to produce an updated statistical model;
process at least some of the plurality of neuromuscular signals using the updated statistical model to generate an updated musculoskeletal representation;
determine, based, at least in part, on the at least one aspect of the updated musculoskeletal representation whether further calibration of the statistical model is needed; and
end the calibration session in response to determining that further calibration is not needed.

US Pat. No. 10,429,928

SYSTEMS, ARTICLES, AND METHODS FOR CAPACITIVE ELECTROMYOGRAPHY SENSORS

CTRL-labs Corporation, N...

1. A method of fabricating an electromyography (“EMG”) sensor, the method comprising:forming at least a portion of at least one circuit on a first surface of a substrate;
forming a first electrode on a second surface of the substrate, the second surface of the substrate opposite the first surface of the substrate across a thickness of the substrate, wherein the first electrode comprises a first electrically conductive plate;
forming at least a first electrically conductive pathway through the substrate that communicatively couples the first electrode and the at least a portion of at least one circuit;
forming a second electrode on the second surface of the substrate, wherein the second electrode comprises a second electrically conductive plate;
forming at least a second electrically conductive pathway through the substrate that communicatively couples the second electrode and the at least a portion of at least one circuit.

US Pat. No. 10,409,371

METHODS AND APPARATUS FOR INFERRING USER INTENT BASED ON NEUROMUSCULAR SIGNALS

CTRL-labs Corporation, N...

1. A control system, comprising:a plurality of sensors configured to continuously record a plurality of neuromuscular signals from a user; and
at least one computer processor programmed to:
provide as input to a trained statistical model, the plurality of neuromuscular signals and/or information based on the plurality of neuromuscular signals, wherein the trained statistical model was trained based, at least in part, on neuromuscular data recorded during at least one previous performance of a motor action by one or more users and result data indicating an outcome of the motor action performed by the one or more users, wherein the trained statistical model is configured to predict the onset of the motor action prior to completion of the motor action;
predict, based on an output of the trained statistical model, whether an onset of the motor action will occur within a threshold amount of time; and
send a control signal to at least one device based, at least in part, on the prediction, wherein the control signal is sent to the at least one device prior to completion of the motor action by the user to control an operation of the at least one device.

US Pat. No. 10,504,286

TECHNIQUES FOR ANONYMIZING NEUROMUSCULAR SIGNAL DATA

CTRL-labs Corporation, N...

1. A computerized system for anonymizing neuromuscular signals used to generate a musculoskeletal representation, the system comprising:a plurality of neuromuscular sensors configured to continuously record a plurality of neuromuscular signals from a user, wherein the plurality of neuromuscular sensors are arranged on one or more wearable devices; and
at least one computer processor programmed to:
provide as input to a statistical model, the plurality of neuromuscular signals and/or information based on the plurality of neuromuscular signals, wherein:
the plurality of neuromuscular signals and/or information based on the plurality of neuromuscular signals provided as input to the statistical model includes a first personal characteristic of the user, and
the statistical model is trained to remove the first personal characteristic of the user from the plurality of neuromuscular signals and/or information based on the plurality of neuromuscular signals; and
generate the musculoskeletal representation based, at least in part, on position estimates and/or force estimates output from the trained statistical model, wherein:
the musculoskeletal representation is an anonymized musculoskeletal representation from which the first personal characteristic of the user has been removed, and
the statistical model has been trained using an adversarial training approach to remove the first personal characteristic of the user while predicting the position estimates and/or the force estimates associated with the musculoskeletal representation.

US Pat. No. 10,489,986

USER-CONTROLLED TUNING OF HANDSTATE REPRESENTATION MODEL PARAMETERS

CTRL-labs Corporation, N...

1. A computerized system configured to enable a person to select one or more statistical models used to generate a musculoskeletal representation, the one or more statistical models comprising a first statistical model and a second statistical model, the system comprising:a user interface configured to instruct a user to perform at least one gesture while wearing a wearable device having a plurality of neuromuscular sensors arranged thereon; and
at least one computer processor programmed to:
provide as input to the first statistical model and the second statistical model, a plurality of neuromuscular signals recorded by the neuromuscular sensors during performance of the at least one gesture by the user;
generate a first musculoskeletal representation based at least in part by:
outputting from the first statistical model, first position estimates and/or first force estimates associated with the first musculoskeletal representation, and
updating the first musculoskeletal representation based on the first position estimates and/or the first force estimates;
generate a second musculoskeletal representation based at least in part by:
outputting from the second statistical model, second position estimates and/or second force estimates associated with the second musculoskeletal representation, and
updating the second musculoskeletal representation based on the second position estimates and/or the second force estimates;
render a first visual representation based on the first musculoskeletal representation and a second visual representation based on the second musculoskeletal representation;
repeatedly switch between displaying the rendered first visual representation and the rendered second visual representation; and
receive, subsequent to initiation of the displaying, input from the person comprising receiving a selection associated with the first visual representation or the second visual representation.

US Pat. No. 10,528,135

WEARABLE MUSCLE INTERFACE SYSTEMS, DEVICES AND METHODS THAT INTERACT WITH CONTENT DISPLAYED ON AN ELECTRONIC DISPLAY

CTRL-labs Corporation, N...

1. A wearable muscle interface device for controlling navigable content displayed on a wearable head-mounted display, the wearable muscle interface device comprising:a plurality of electromyography sensors to be worn on an arm of a user, the plurality of electromyography sensors for detecting electrical signals of muscle activity corresponding to a gesture performed by the user;
at least one accelerometer for detecting motion of the arm of the user corresponding to the gesture performed by the user;
a first processor, communicatively coupled to the plurality of electromyography sensors and the at least one accelerometer, for:
generating, based on at least the electrical signals detected by the plurality of electromyography sensors and the motion of the arm of the user detected by the at least one accelerometer,
a first interpretation of the gesture performed by the user, and
a second interpretation of the gesture performed by the user, and
generating at least one control signal to request input from the user to select one of the first interpretation of the gesture or the second interpretation of the gesture,
wherein the first interpretation of the gesture and the second interpretation of the gesture represent different gestures selected by the first processor from a set of at least three defined gestures; and
a transmitter communicatively coupled to the first processor, wherein the transmitter transmits the at least one control signal from the wearable muscle interface device directly to a receiver on the wearable head-mounted display,
wherein the at least one control signal causes a second processor of the wearable head-mounted display to execute data and/or instructions stored in a non-transitory computer-readable storage medium of the wearable head-mounted display to effect at least one control interaction including requesting the input from the user to select one of the first interpretation of the gesture performed by the user or the second interpretation of the gesture performed by the user.

US Pat. No. 10,460,455

REAL-TIME PROCESSING OF HANDSTATE REPRESENTATION MODEL ESTIMATES

CTRL-labs Corporation, N...

1. A computerized system for providing a dynamically-updated musculoskeletal representation of a hand, the system comprising:a plurality of neuromuscular sensors configured to continuously record a plurality of neuromuscular signals from a user; and
at least one computer processor programmed to:
provide as input to a trained statistical model, the plurality of neuromuscular signals;
temporally smooth in real-time an output of the trained statistical model;
determine, based on the smoothed output of the trained statistical model:
position information describing a spatial relationship between two or more connected segments of the musculoskeletal representation;
force information describing a force exerted by at least one segment of the musculoskeletal representation; and
update the musculoskeletal representation of the hand based, at least in part, on the position information and the force information.