User interface control of responsive devices
Inventors
Ang, Dexter W. • Cipoletta, David O • Karnes, Samuel J. • Kowalczyk, Michael P. • Patel, Salil H. • Trambert, Steven D.
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11543887-B2
Publication Date
2023-01-03
Expiration Date
Abstract
Among other things, a user interface device has a sensor configured to detect, at a wrist of a human, nerve or other tissue electrical signals associated with an intended contraction of a muscle to cause a rapid motion of a finger. An output provides information representative of the nerve or other tissue electrical signals associated with the intended contraction of the muscle to an interpreter of the information.
Core Innovation
The invention provides a system for gesture control using a wearable device configured to be worn at a wrist of a person. The wearable device includes a biopotential sensor configured to obtain biopotential data indicating nerve or other tissue electrical signals associated with an intended contraction of a muscle, and a wrist motion sensor configured to obtain wrist motion data indicating motion of the person's wrist.
The system further includes a second device in communication with both the wearable device and a third device comprising a machine learning classifier. The second device obtains second device data using an interface of the second device, where the second device data is distinct from the biopotential data and the wrist motion data. The wearable device transmits the biopotential data and the wrist motion data to the second device, and the second device transmits the biopotential data, the wrist motion data, and the second device data, or derivatives, to the third device.
At the third device, the machine learning classifier processes each of the biopotential data, the wrist motion data, and the second device data, or derivatives of any of these. The machine learning classifier generates an interpreted output based on a combination of the biopotential data, the wrist motion data, and the second device data, or derivatives. The interpreted output is produced from combined processing of the multiple data sources that originate from the wrist wearable device and the second device interface.
Claims Coverage
The partial content provides two independent claims: an apparatus/system claim and a method claim. Each independent claim centers on obtaining wrist biopotential data and wrist motion data from a wearable device, obtaining distinct second device data at a second device, and using a machine learning classifier to generate an interpreted output based on a combination of these data sources or derivatives.
Wrist-worn biopotential and motion acquisition
A wearable device worn at a wrist obtains biopotential data from a biopotential sensor indicating nerve or other tissue electrical signals associated with an intended contraction of a muscle, and obtains wrist motion data from a wrist motion sensor indicating motion of the person's wrist.
Second device obtains distinct second device data
A second device in communication with the wearable device and a third device obtains second device data using an interface of the second device, where the second device data is distinct from the biopotential data and the wrist motion data.
Classifier-driven interpreted output from combined data (apparatus)
Transmit the biopotential data and wrist motion data from the wearable device to the second device, then transmit from the second device to the third device comprising a machine learning classifier each of the biopotential data, the wrist motion data, and the second device data, or derivatives; process each input or derivative and generate an interpreted output based on a combination of the inputs or derivatives.
Wireless gesture control method with classifier fusion (method)
Obtain biopotential data indicating nerve or other tissue electrical signals associated with an intended contraction of a muscle and obtain wrist motion data indicating motion of the person's wrist using a wearable device; wirelessly transmit the biopotential data and wrist motion data to a second device; obtain second device data distinct from the biopotential data and the wrist motion data; wirelessly transmit the biopotential data, wrist motion data, and the second device data, or derivatives, to a third device comprising a machine learning classifier; process each input or derivative and generate an interpreted output based on a combination.
Across both independent claims, the inventive scope is the combination of wrist biopotential data indicating intended muscle contraction with wrist motion data, plus distinct second device data obtained via a separate device interface, where a machine learning classifier processes the multiple data streams or derivatives to generate an interpreted output based on their combination.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?