Wearable Running Power Estimation Using Underfoot Force Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for determining running power are inconsistent and lack accuracy, particularly in estimating metabolic power which varies with factors like food consumption and caffeine intake, while mechanical power measurements are more accurate but often require specialized equipment.
Innovation Solution
A system and method using force sensors positioned underfoot, combined with inertial measurement units, to calculate mechanical running power through a machine learning model trained on force values, stance time, and running speed, providing accurate and consistent power feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If force sensors and machine learning models are used to determine mechanical running power, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent uses force sensors as intermediary devices positioned between the user's foot and the ground to capture ground reaction forces. These sensors serve as mediators that translate complex biomechanical interactions into measurable electrical signals, enabling accurate power calculation without requiring direct measurement of all physiological parameters.
Solution Approach 2:
The patent replaces complex mechanical power measurement systems (such as instrumented treadmills or motion capture laboratories) with a simpler wearable force sensor system combined with machine learning algorithms. The machine learning model substitutes for complex mechanical analysis by learning patterns from sensor data to directly predict power output.
2Measurement precision
If specialized equipment is used for accurate mechanical power measurement, then measurement precision is improved, but ease of operation deteriorates
Solution Approach 1:
The force sensor system is integrated into footwear or insoles that users already wear, making the measurement device part of the user's existing equipment. The system serves itself by using the user's own foot as the mounting surface, eliminating the need for separate specialized equipment or complex setup procedures.
Solution Approach 2:
The wearable force sensor system is designed to be universally applicable across different locations and activities. The same device can be used outdoors on various terrains, indoors on different surfaces, and for multiple types of activities (running, walking, jumping), replacing the need for location-specific specialized equipment.
Data Source
AI summary
A system, method and computer program product for determining mechanical running power. A plurality of sensor readings is acquired from a plurality of force sensors positioned underfoot. Force values are determined for a plurality of strides using aggregate force data. The slope, a stance time and running speed are determined for each stride. The mechanical running power associated with the plurality of sensor readings is determined by inputting the force values, the slope, the stance time and the running speed to a machine learning model trained to predict the mechanical running power. The mechanical running power can then be provided to the user as feedback or stored for purposes such as later review and analysis. The inputs to the machine learning model can be determined entirely based off of sensor data received from a wearable device worn by the user.