Wearable electromyography-based controllers for human-computer interface

• US 8,170,656 B2
• Filed: 03/13/2009
• Issued: 05/01/2012
• Est. Priority Date: 06/26/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Tan, Desney, Saponas, T. Scott, Morris, Dan, Turner, Jim
• Primary Examiner(s): Hlndenburg, Max
• Assistant Examiner(s): DOUGHERTY, SEAN PATRICK
• Application Number:
  US12/404,223
• Publication Number:
  US 20090326406A1
• Time in Patent Office: 1,145 Days
• Field of Search: 345/157, 345/158, 600/372, 600/382, 600/384, 600/546, 600/595, 702/150, 715/863
• US Class Current: 600/546
• CPC Class Codes: A61B 5/389 Electromyography [EMG]
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06F 3/015 Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883

Abstract

A “Wearable Electromyography-Based Controller” includes a plurality of Electromyography (EMG) sensors and provides a wired or wireless human-computer interface (HCl) for interacting with computing systems and attached devices via electrical signals generated by specific movement of the user'"'"'s muscles. Following initial automated self-calibration and positional localization processes, measurement and interpretation of muscle generated electrical signals is accomplished by sampling signals from the EMG sensors of the Wearable Electromyography-Based Controller. In operation, the Wearable Electromyography-Based Controller is donned by the user and placed into a coarsely approximate position on the surface of the user'"'"'s skin. Automated cues or instructions are then provided to the user for fine-tuning placement of the Wearable Electromyography-Based Controller. Examples of Wearable Electromyography-Based Controllers include articles of manufacture, such as an armband, wristwatch, or article of clothing having a plurality of integrated EMG-based sensor nodes and associated electronics.

Claims

1. A human-computer interface, comprising:

an arbitrarily positionable wearable device having a plurality of sensor nodes, wherein each sensor node further includes one or more Electromyography (EMG) sensors;

a module for activating the wearable device following receipt of an explicit indication provided by the user;

a module for automatically measuring muscle generated electrical signals using one or more of the EMG sensors;

a module for automatically determining which muscle generated electrical signals correspond to one or more specific user gestures; and

a module for causing one or more computing devices to automatically execute one or more specific commands corresponding to one or more of the specific user gestures.

2. The human-computer interface of claim 1 further comprising a calibration phase which automatically identifies one or more specific user muscles which generate the electrical signals measured by one or more specific EMG sensors.

3. The human-computer interface of claim 2 wherein the user performs one or more specific gestures as part of a training phase for the calibration.

4. The human-computer interface of claim 1 wherein a subset of the EMG sensors is identified by an automated multiplexing process which determines which EMG sensors are sufficient to measure the muscle generated electrical signals that are associated with one or more of the specific user gestures.

5. The human-computer interface of claim 4 further comprising a module for automatically disabling all EMG sensors not included in the subset of EMG sensors.

6. The human-computer interface of claim 1 further comprising a module for automatically determining an approximate position of the wearable device on the surface of the skin of the user'"'"'s body.

7. The human-computer interface of claim 1 further comprising a module for automatically determining relative positions of the sensor nodes to each other.

8. The human-computer interface of claim 1 wherein the wearable device communicates wirelessly with one or more of the computing devices.

9. The human-computer interface of claim 1 further comprising a module which provides automatic feedback to the user for directing the user to refine placement of a position of the wearable device on the surface of the user'"'"'s skin.

10. The human-computer interface of claim 1 further comprising a module for providing automatic feedback to the user to indicate whether one or more of the specific commands were successfully executed in response to one or more specific user gestures.

11. The human-computer interface of claim 1 further comprising a module for deactivating the wearable device following receipt of an explicit indication provided by the user.

12. A process for sending commands to one or more computing devices, comprising:

arbitrarily positioning a wearable device in contact with an outer surface of a user'"'"'s skin, said wearable device having a plurality of Electromyography (EMG) sensors for measuring muscle generated electrical activity via the skin of the user;

performing an automated positional localization process to automatically determine an approximate position of the wearable device on the surface of the skin of the user'"'"'s body;

automatically evaluating muscle-generated electrical signals of the user measured via one or more of the EMG sensors to automatically identify one or more specific gestures of the user from a predefined set of gestures; and

automatically directing one or more computing devices to execute one or more specific commands corresponding to one or more of the identified gestures.

13. The process of claim 12 further comprising performing an initial calibration process which evaluates muscle generated electrical signals associated with a subset of gestures to determine expected muscle generated electrical signals for the complete set of gestures.

14. The process of claim 12 wherein commands associated with one or more of the gestures of the set of gestures is user definable.

15. A system for providing a human-computer interface (HCI), comprising:

a user-wearable device having a plurality of Electromyography (EMG) sensors, said user-wearable device being placed on an outer surface of the user'"'"'s skin in an approximate position on a pre-determined body part of the user;

an automated self-calibration process which maps muscle generated electrical signals corresponding to one or more specific user gestures to one or more specific commands, said muscle generated electrical signals being measured by one or more of the EMG sensors;

an automated process for identifying a subset of the EMG sensors as being sufficient to measure muscle generated electrical signals to accurately identify the specific commands mapped the specific user gestures;

an automated process for disabling all EMG sensors not included in the subset;

an automated process for using the subset of EMG sensors to evaluating muscle generated electrical signals associated with one or more user gestures to identify the commands associated with those user gestures; and

a process for transmitting specific commands associated with one or more specific user gestures to one or more computing devices.

16. The system of claim 15 further comprising an automated positional localization process which determines an approximate position of the user-wearable device on the body of the user.

17. The system of claim 16 further comprising an automated process for directing the user to refine the approximate position of the user-wearable device.

18. The system of claim 15 wherein the user-wearable device includes a wireless interface to one or more of the computing devices.