Methods and systems for muscle activity measurement and gesture detection

{
  "publication_number": "US12440123B1",
  "country": "US",
  "kind": "B1",
  "title": "Methods and systems for muscle activity measurement and gesture detection",
  "abstract": "Methods and systems for determining changes in muscle activity patterns based on the optical response of subcutaneous human body structures are presented, along with methods and systems for controlling assistive robotic systems based on the measured muscle activity patterns. Elements of a muscle activity measurement system are mechanically coupled to a wearable structure that fits closely to a portion of the body of a human user. The muscle activity measurement system includes multiple emitters and detectors at different spacing along the skin surface. In some embodiments, the illumination intensity of each measurement channel, the programmable gain of each measurement channel, or both, are calibrated to maximize measurement sensitivity. In some embodiments, optical measurement data is employed to more accurately locate the muscle activity measurement system with respect to the human body. In some embodiments, a muscle activity measurement system tracks changes in muscle structure over time.",
  "claims": [
    "1. A muscle activity measurement system, comprising: an elastic, wearable structure configured to be disposed over a portion of a body of a human user, the portion of the body including one or more subcutaneous muscle structures; a first plurality of optical illumination devices located on the wearable structure, a light emitting surface of each of the first plurality of optical illumination devices facing a direction normal to a surface of the portion of the body of the human user, wherein at least one of the first plurality of optical illumination devices emits illumination light at a different wavelength than another of the plurality of optical illumination devices; a first plurality of photodetectors located on the wearable structure, a photosensitive surface of each of the first plurality of photodetectors facing the direction normal to the surface of the portion of the body of the human user, wherein each of the first plurality of photodetectors generates an output signal indicative of an intensity of light incident on the photosensitive surface; a second optical illumination device located on the wearable structure having a light emitting surface facing a direction parallel to the surface of the portion of the body of the human user; a second photodetector located on the wearable structure having a photosensitive surface facing a direction parallel to the surface of the portion of the body of the human user, wherein the second photodetector generates an output signal indicative of an intensity of light incident on the photosensitive surface of the second photodetector in response to an amount of light provided by the second optical illumination device; a computing system communicatively coupled to the first plurality of optical illumination devices, the second optical illumination device, the first plurality of photodetectors, and the second photodetector, wherein the computing system, communicates an illumination control signal to each of the first plurality of optical illumination devices causing each of the first plurality of optical illumination devices to provide illumination light in response to the illumination control signal, receives the output signal indicative of the intensity of light incident on the photosensitive surface from each photodetector of the first plurality of photodetectors in response to the provided illumination light, determines at least one muscle activity pattern associated with the one or more subcutaneous muscle structures based on the output signals from each of the first plurality of photodetectors, determines a gesture of the human user based on the at least one muscle activity pattern and a trained gesture detection model, wherein the trained gesture detection model is a neural network model, a decision tree model, or a support vector machine model, wherein the at least one muscle activity pattern is an input of the trained gesture detection model and the determined gesture is an output of the trained gesture detection model, and wherein the trained gesture detection model is trained based on a prescribed set of gestures and muscle activity patterns measured while the human user executes the prescribed set of gestures, wherein a motion trajectory of an assistive robot is controlled based on the determined gesture, receives the output signal generated by the second photodetector, and determines a location of the muscle activity measurement system with respect to the body of the human user based on the output signal generated by the second photodetector.",
    "2. The muscle activity measurement system of claim 1, wherein a distance between a first of the first plurality of optical illumination devices and a first of the first plurality of photodetectors is different from a distance between a second of the first plurality of optical illumination devices and a second of the first plurality of photodetectors.",
    "3. The muscle activity measurement system of claim 1, further comprising: a motion sensing module communicatively coupled to the computing system, wherein the motion sensing module includes one or more inertial sensors that measure an orientation of the muscle activity measurement system with respect to a gravitational field.",
    "4. The muscle activity measurement system of claim 1, wherein the illumination control signal causes each of the first plurality of optical illumination devices to provide illumination light sequentially.",
    "5. The muscle activity measurement system of claim 1, wherein the illumination control signal causes at least two of the first plurality of optical illumination devices to provide illumination light simultaneously.",
    "6. The muscle activity measurement system of claim 1, wherein each of the plurality of optical illumination devices is a light emitting diode.",
    "7. The muscle activity measurement system of claim 1, wherein a wearable garment is configured to be disposed between the wearable structure and the portion of the body of the human user."
  ],
  "description_excerpt": "The described embodiments relate to systems and methods for measurement of muscle activity and detection of gestures based on the measured muscle activity.\n\nA significant number of people are affected by musculoskeletal (MSK) injuries or diseases. Unfortunately, relatively few actually complete rehabilitation sessions designed to treat these ailments. Treatment programs and their associated costs are highly variable, and generally, the effectivity of many MSK rehabilitation programs is not well understood. In many cases, there is insufficient quantitative evidence to correlate specific treatment duration with recovery. The lack of data supporting many rehabilitation programs is caused, in part, by lack of patient compliance. As a result, people struggle with lingering pain and disability. This leads to increased overall health costs as health conditions deteriorate and become more complex as time passes.\n\nSystems have been developed to aid post-surgery, at-home exercise. These systems typically utilize motion sensors that are strapped to the body or cameras that point at the patient to check the range of motion of specific limbs as the patient performs a suite of movements under remote supervision of physical therapists. These motion-based systems are very expensive and only collect general movement data. Furthermore, such systems are only useful to patients who are able to generate the specified movements.\n\nSeveral techniques exist to sense specific muscle activation. However, various issues render these techniques impractical for long-term rehabilitation tracking.",
  "cpc": [
    "A61B 5/1107",
    "A61B 2562/0233",
    "A61B 5/0022",
    "A61B 5/0075",
    "A61B 5/0082",
    "A61B 5/1123",
    "A61B 5/1125",
    "A61B 5/6806",
    "A61B 5/7267",
    "A61F 2/70",
    "A61F 2002/704",
    "A61H 2201/1659",
    "A61H 3/00",
    "B25J 13/08",
    "B25J 9/0006",
    "G06F 3/014"
  ],
  "ipc": [
    "A61B 5/00",
    "A61B 5/11",
    "A61F 2/70",
    "A61H 3/00",
    "B25J 13/08",
    "B25J 9/00",
    "G06F 3/01"
  ],
  "assignees": [
    "Manus Robotics Inc"
  ],
  "inventors": [
    "Faye Y. Wu",
    "Haruhiko Harry Asada",
    "Baldin Adolfo Llorens-Bonilla",
    "Sheng Liu"
  ],
  "filing_date": "2019-12-12",
  "publication_date": "2025-10-14",
  "grant_date": "2025-10-14",
  "priority_date": "2018-12-12",
  "application_number": "US-201916712971-A",
  "family_id": "97348781",
  "cited_by_count": 1,
  "citations": [
    "US20070208231A1",
    "US20140107493A1",
    "US20170259428A1",
    "US20180078183A1"
  ]
}