Gesture control using biopotential-based analog front end
Inventors
Stern, Kenneth • Wang, Tanya • McLaurin, Tristan • Cipoletta, David • Ang, Dexter
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11914791-B2
Publication Date
2024-02-27
Expiration Date
Abstract
Disclosed are methods, systems and non-transitory computer readable memory for gesture control. For instance, a system may include a wearable device configured to be worn on a portion of an arm of a user. The wearable device may include a plurality of electrodes disposed on an interior of the wearable device and configured to obtain biopotential signals from the user's arm; and a biopotential chip. The biopotential microchip may be configured to output, directly or indirectly, biopotential data, acceleration data, and/or angular rate data, or derivatives thereof (“gesture data”), to a machine learning classifier. The machine learning classifier may be configured to generate, based on the gesture data, a gesture output indicating a gesture performed by the user. In some cases, the plurality of electrodes may include one or more wristband electrodes and/or a plurality of hub electrodes in a hub. In some cases, the hub may be curved.
Core Innovation
A wearable device is configured to be worn on a portion of an arm of a user and includes a plurality of electrodes disposed on an interior of the wearable device to obtain biopotential signals from the user's arm. The wearable device includes a biopotential microchip with one or more analog inputs coupled to receive the biopotential signals from the plurality of electrodes, and at least one analog input is coupled to a respective differential amplifier configured to amplify differences in signals between pairs of electrodes.
The biopotential microchip includes one or more analog-to-digital converters configured to convert the biopotential signals to biopotential data. The biopotential microchip also includes an accelerometer disposed onboard the biopotential microchip to output acceleration data indicating an acceleration of the portion of the user's arm, and a gyroscope disposed onboard the biopotential microchip to output angular rate data indicating an angular rate of the portion of the user's arm.
The biopotential microchip is an integral unit and has all of the processor, the gyroscope, the accelerometer, the one or more analog inputs, and the ADCs located on a common unitary substrate. The biopotential microchip is configured to output, directly or indirectly, combined data including the biopotential data, the acceleration data, the angular rate data, or derivatives thereof, to a machine learning classifier that generates an output indicating a parameter of the user based on the data.
The biopotential microchip comprises either a first low-power state where the ADCs and differential amplifiers are not enabled but the accelerometer and the gyroscope are enabled, or a second low-power state where the accelerometer and the gyroscope are powered down but at least the ADCs are active.
Claims Coverage
The independent claims cover a wearable system and corresponding method, plus a corresponding biopotential microchip architecture, centered on an integral biopotential microchip on a common unitary substrate that combines electrode-based biopotential data with onboard inertial sensor data and outputs combined data to a machine learning classifier to generate an output indicating a parameter of the user, with defined low-power state behavior.
Biopotential wearable with electrode-pair differential amplification and onboard inertial sensing
A wearable device worn on a portion of an arm includes a plurality of electrodes disposed on an interior to obtain biopotential signals, with a biopotential microchip having analog inputs coupled to receive the biopotential signals and a respective differential amplifier configured to amplify differences in signals between pairs of electrodes.
Integrated common-substrate biopotential microchip including ADCs, accelerometer, and gyroscope
The biopotential microchip is an integral unit with all of the processor, the gyroscope, the accelerometer, the one or more analog inputs, and the ADCs located on a common unitary substrate.
Machine learning classifier output for a user parameter based on combined biopotential and motion data
The biopotential microchip outputs biopotential data from the ADCs, acceleration data from the accelerometer, and angular rate data from the gyroscope, or derivatives thereof, to a machine learning classifier configured to generate, based on the data, an output indicating a parameter of the user.
Low-power state behavior for ADC/differential amplifier enablement versus inertial sensing enablement
The biopotential microchip comprises either a first low-power state in which the one or more ADCs and the differential amplifiers are not enabled but the accelerometer and the gyroscope are enabled, or a second low-power state in which the accelerometer and the gyroscope are powered down but at least the one or more ADCs are active.
Method receiving biopotential signals, converting to biopotential data, obtaining motion data, and processing for classifier output
A method receives biopotential signals from a plurality of electrodes via one or more analog inputs of a biopotential microchip with differential amplification between electrode pairs, converts the biopotential signals to biopotential data via one or more ADCs, obtains and outputs acceleration data via an onboard accelerometer and angular rate data via an onboard gyroscope, processes the biopotential, acceleration, and angular-rate data by a processor, and outputs combined data to a classifier configured to generate an output indicating a parameter of the user.
Biopotential microchip architecture outputting combined data to a classifier with defined low-power modes
A biopotential microchip includes one or more analog inputs coupled to receive biopotential signals from a plurality of electrodes with differential amplification between electrode pairs, one or more ADCs to convert to biopotential data, an onboard accelerometer outputting acceleration data, an onboard gyroscope outputting angular rate data, and a processor processing the outputs, where all of the processor, gyroscope, accelerometer, analog inputs, and ADCs are located on a common unitary substrate and the microchip outputs combined data to a classifier; the microchip comprises either a first low-power state disabling ADCs and differential amplifiers while enabling accelerometer and gyroscope, or a second low-power state powering down accelerometer and gyroscope while keeping at least the ADCs active.
Overall, the independent claims define an integrated biopotential microchip integral unit on a common unitary substrate that performs electrode-pair differential amplification, digitizes biopotential signals with ADCs, and combines that biopotential data with onboard accelerometer and gyroscope data for a machine learning classifier that outputs an indication of a user parameter, under explicit low-power state configurations.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?