18205476. ESTIMATING VERTICAL OSCILLATION AT WRIST simplified abstract (Apple Inc.)

ESTIMATING VERTICAL OSCILLATION AT WRIST

Organization Name

Apple Inc.

Inventor(s)

Richard A. Fineman of Campbell CA (US)

Adeeti V. Ullal of Emerald Hills CA (US)

Allison L. Gilmore of Redwood City CA (US)

Gabriel A. Blanco of San Francisco CA (US)

Karthik Jayaraman Raghuram of Foster City CA (US)

Mark P. Sena of Larkspur CA (US)

Maryam Etezadi-amoli of Santa Clara CA (US)

James J. Dunne of San Francisco CA (US)

Po An Lin of San Jose CA (US)

ESTIMATING VERTICAL OSCILLATION AT WRIST - A simplified explanation of the abstract

This abstract first appeared for US patent application 18205476 titled 'ESTIMATING VERTICAL OSCILLATION AT WRIST

Simplified Explanation

The patent application describes a method for estimating vertical oscillation (VO) at the wrist using a wearable device. Here are the key points:

• The wearable device collects sensor data, including acceleration and rotation rate, from the user's wrist.
• Centripetal acceleration is estimated based on the user's acceleration and rotation rate.
• The estimated centripetal acceleration is subtracted from the user's acceleration to calculate a modified user's acceleration.
• The arm swing component of the modified user's acceleration is decoupled to estimate the center of mass (CoM) acceleration.
• A machine learning model is used with the CoM acceleration as input to compute the vertical oscillation of the user's CoM.
• Alternatively, the vertical acceleration derived from the CoM acceleration and a gravity vector can be integrated to calculate the vertical oscillation.

Potential applications of this technology:

• Fitness tracking: The method can be used to accurately measure vertical oscillation during activities like running or jumping, providing valuable data for fitness tracking and performance analysis.
• Rehabilitation monitoring: By monitoring vertical oscillation at the wrist, the method can assist in tracking the progress of rehabilitation exercises and assessing the recovery of patients.
• Biomechanical analysis: Researchers and coaches can utilize this technology to study and analyze the vertical oscillation patterns of athletes, helping to optimize training techniques and prevent injuries.

Problems solved by this technology:

• Accurate measurement: The method provides a more accurate estimation of vertical oscillation by taking into account factors like centripetal acceleration and decoupling the arm swing component.
• Wrist-based measurement: By estimating vertical oscillation at the wrist, the method eliminates the need for additional sensors or devices attached to other parts of the body.
• Real-time monitoring: The wearable device allows for real-time monitoring of vertical oscillation, enabling immediate feedback and adjustments during physical activities.

Benefits of this technology:

• Improved performance tracking: Athletes and fitness enthusiasts can gain insights into their vertical oscillation patterns, helping them optimize their movements and improve performance.
• Enhanced rehabilitation monitoring: Healthcare professionals can track the progress of patients' rehabilitation exercises more accurately, leading to better treatment plans and outcomes.
• Convenient and non-intrusive: The wearable device worn on the wrist provides a convenient and non-intrusive way to measure vertical oscillation, without interfering with the user's movements.

Original Abstract Submitted

Enclosed are embodiments for estimating vertical oscillation (VO) at the wrist. In some embodiments, a method comprises: obtaining, with a wearable device worn on a wrist of a user, sensor data indicative of the user's acceleration and rotation rate; estimating centripetal acceleration based on the user's acceleration and rotation rate; calculating a modified user's acceleration by subtracting the estimated centripetal acceleration from the user's acceleration; estimating center of mass (CoM) acceleration by decoupling an arm swing component of the user's acceleration from the modified user's acceleration; and computing vertical oscillation of the user's CoM using a machine learning model with at least the CoM acceleration as input to the machine learning model, or by integrating vertical acceleration derived from the CoM acceleration and a gravity vector.