Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11449150-B2
Publication Date
2022-09-20
Expiration Date
Abstract
Systems and methods for gesture-based control are provided. In some embodiments, a system may include a wearable device configured to be worn on a person's wrist. The wearable device may include a plurality of biopotential channels, a location sensor, and a processor. The system may be configured to generate a data stream based on the outputs from the biopotential channels and/or the location sensor. The system may be configured to enter a first state in which the output from the location sensor is processed according to a first set of logical rules. The system may be configured to classify a gesture, and, based on the gesture classification, transition to a second state in which the output from the location sensor is processed according to a second set of logical rules that is different than the first set of logical rules.
Core Innovation
The invention relates to gesture-based control using a wearable device configured to be worn on a person's wrist and comprising a plurality of biopotential channels and a location sensor. The biopotential channels each include a pair of electrodes and output signals indicating biopotentials at a respective location on a body part, where at least the first biopotential channel varies in response to motions or intended motions of an index finger.
The system generates a data stream based on the outputs from the plurality of biopotential channels and/or the location sensor and partitions the data stream into a plurality of windows. Gesture classification is performed by analyzing the plurality of windows to detect a sequence in biopotential amplitude behavior, including a first window showing baseline amplitude, a second window showing an increase in amplitude relative to the baseline, and a third window showing maintained amplitude in an elevated state relative to the baseline amplitude, and determining that a time between the second window and the third window is greater than a threshold period of time.
Based on the gesture classification, the system transitions to a lift-and-hold state in which the output from the location sensor is processed according to a second set of logical rules different from the first set of logical rules. In the lift-and-hold state, the location-sensor processing can produce direction-based movement commands to move an application object or a selector in a first direction relative to a frame of reference of the person.
The invention also includes selecting targets for application operations by determining, based on at least the output from the location sensor, a directional vector intended by the person and using that directional vector together with the output from one or more biopotential channels. When a gesture indicating the intention to make a selection is detected, a target indicated by the directional vector is selected.
Claims Coverage
The partial content provides two independent claims: a system claim and a method claim. Both independent claims share the same core inventive structure of window-based gesture classification from biopotential amplitude behavior combined with state-based processing of location-sensor output, including a transition into a lift-and-hold state based on specified timing and amplitude conditions.
Wrist wearable with biopotential channels and location sensor for gesture-based control
A system having a wearable device worn on a person's wrist with a plurality of biopotential channels, each with a pair of electrodes outputting biopotential signals at respective locations, with the output of at least the first biopotential channel varying in response to motions or intended motions of an index finger, and a location sensor outputting data indicating a location of the body part, together with a processor.
Windowed gesture classification from biopotential amplitude sequence and time threshold
Generating a data stream based on outputs from the plurality of biopotential channels and/or the location sensor, partitioning the data stream into a plurality of windows, and classifying a gesture by determining a first window baseline amplitude, a second window amplitude increase relative to the first window, a third window maintained elevated-state amplitude relative to the first window, and that a time between the second window and the third window is greater than a threshold period of time.
State transition to lift-and-hold with different logical rules for location-sensor processing
Transitioning to a lift-and-hold state based on the gesture classification so that the output from the location sensor is processed according to a second set of logical rules different than the first set of logical rules.
Method for gesture-based control using the same windowed classification and logical-rule transition
A method that generates a data stream from outputs of a plurality of biopotential channels and/or a location sensor of a wearable device on a person's wrist, partitions the data stream into a plurality of windows, classifies a gesture using the baseline amplitude, amplitude increase, elevated maintained amplitude, and time-between-windows condition relative to a threshold, and transitions the system to a lift-and-hold state where the output from the location sensor is processed according to a second set of logical rules different than the first set of logical rules.
Across the independent claims, the inventive concept is a state-based gesture control framework: windowed analysis of biopotential amplitude behavior drives a transition into a lift-and-hold state where location-sensor output is processed using a different logical-rule set. The independent method claim mirrors the same steps for gesture-based control.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?