Wrist-Worn Wearable Device for Vertical Oscillation Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for calculating vertical oscillation in runners require additional wearable sensors, which are inconvenient and costly for average runners, as they typically only have a wrist-worn smartwatch or fitness band.
Innovation Solution
A method using a wrist-worn wearable device to estimate vertical oscillation by processing acceleration and rotation rate data through centripetal acceleration estimation, arm swing decoupling, and machine learning models to compute center of mass acceleration and vertical oscillation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a sensor is attached to the torso or foot to calculate vertical oscillation, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The wrist-worn device performs multiple functions: it measures vertical oscillation, tracks fitness activities, and monitors health metrics. By making the wrist device universal, it eliminates the need for separate torso or foot sensors, resolving the contradiction between measurement precision and device complexity
Solution Approach 2:
The wrist acts as an intermediary location between the foot (where vertical oscillation originates) and the torso (where it is traditionally measured). The device processes wrist acceleration data through algorithms that estimate centripetal acceleration and decouple arm swing components to derive torso vertical oscillation, achieving accurate measurement without direct torso contact
2Measurement precision
If additional wearable sensors are purchased for professional training, then measurement precision is improved, but cost increases
Solution Approach 1:
The existing wrist-worn smartwatch or fitness band is designed to perform multiple functions including vertical oscillation measurement, eliminating the need to purchase additional dedicated sensors and reducing overall device quantity
Solution Approach 2:
The wrist-worn device uses its own existing sensors (accelerometer and gyroscope) to measure vertical oscillation, making the system self-sufficient and eliminating dependency on external specialized equipment
3Ease of operation
If a sensor is attached to the wrist, then ease of operation is improved, but measurement precision deteriorates due to distance from center of mass
Solution Approach 1:
The wrist serves as an intermediary measurement point that, through sophisticated signal processing including centripetal acceleration estimation and arm swing decoupling, allows accurate inference of torso vertical oscillation despite the distance from the center of mass
Solution Approach 2:
The patent replaces direct mechanical measurement at the torso with a computational model that processes wrist acceleration data. The system substitutes physical proximity with mathematical transformation, using machine learning models to convert wrist sensor readings into accurate vertical oscillation estimates
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables the determination of vertical oscillation using a single wrist-worn device, avoiding the need for additional sensors and providing accurate estimates of running efficiency without the added cost or inconvenience of torso or foot-worn devices.
Implementation Method 1
obtaining, with at least one processor of a wearable device worn on a wrist of a user, sensor data indicative of the user's acceleration
Implementation Method 2
sensor data indicative of the user's acceleration and rotation rate
Data Source
AI summary
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.


