IMU Exercise Detection With Adaptive Thresholds for Rehab Tracking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing exercise tracking systems, particularly those using inertial measurement units (IMUs) and camera systems, struggle to accurately detect a wide range of user exercises and individual user progress due to limited data collection and lack of personalized rehabilitation assessment.

Innovation Solution

A robot equipped with IMU sensors and a processor that adjusts threshold parameters based on user-specific data to detect exercises like squats and cross-leg movements, providing personalized training sessions and rehabilitation progress monitoring through a customizable database and machine learning models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If machine learning approaches are used for exercise detection, then detection accuracy is improved, but data collection requirements and system complexity increase

Engineering Contradiction:

Improveexercise detection accuracyVSAvoiddata collection and processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system dynamically adjusts threshold parameters based on user-specific data and machine learning models. The processor modifies detection thresholds adaptively to improve exercise detection accuracy while managing data processing requirements through parameter optimization rather than increasing overall system complexity

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system implements feedback mechanisms where exercise data is collected, analyzed by machine learning models, and used to refine future detection parameters. This closed-loop approach improves detection accuracy over time while systematically managing data collection needs through iterative learning

Inventive Principle:

Principle #23Feedback

2Device complexity

If static environment camera systems are used, then system simplicity is maintained, but range of motion detection and individual user assessment are limited

Engineering Contradiction:

Improvesystem structureVSAvoidrange of motion detection accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent replaces static camera-based optical detection with dynamic IMU sensor systems that directly measure acceleration, orientation, and movement. This substitution enables accurate range of motion detection and individual user assessment while maintaining reasonable system complexity through compact sensor integration

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transitions from static environment monitoring to dynamic user-specific detection by continuously adapting threshold parameters based on individual user data. This dynamic approach enables accurate range of motion detection and personalized assessment without requiring complex static infrastructure

Inventive Principle:

Principle #15Dynamics

3Adaptability or versatility

If generic exercise detection is implemented, then system versatility is achieved, but individual rehabilitation progress monitoring is lacking

Engineering Contradiction:

Improveexercise detection coverageVSAvoidindividual progress assessment accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The system applies different detection thresholds and parameters tailored to individual user needs and specific rehabilitation goals. By customizing detection criteria for each user rather than using uniform standards, the system achieves both broad exercise detection capability and precise individual progress monitoring

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system collects and analyzes user-specific baseline data before implementing exercise detection. This preliminary data collection enables the machine learning models to establish personalized reference points, allowing the system to later detect both diverse exercise types and track individual rehabilitation progress accurately

Inventive Principle:

Principle #10Preliminary action

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

Enhances the accuracy of exercise detection and rehabilitation assessment by dynamically adjusting threshold parameters, offering targeted training and personalized plans for individual users, thereby improving training effectiveness and monitoring user progress.

Implementation Method 1

obtain first measurement data from at least one inertial measurement unit (IMU) sensor that is arranged at a designated body part of the user, and detect a posture of the user relative to the robot based on the first measurement data

Methodology Applied

Scientific EffectInertial measurement: Accelerometer

Data Source

PatentUS12594461B2User exercise detection method, robot and computer-readable storage medium

Publication Date: 2026.04.07 UBTECH ROBOTICS CORP LTD

AI summary

A user exercise detection method applicable in a robot includes: obtaining first measurement data from at least one inertial measurement unit (IMU) sensor that is arranged at a designated body part of the user, and detecting a posture of the user relative to the robot based on the first measurement data; obtaining second measurement data from the at least one IMU sensor, and determining whether an exercise of the user corresponding to the posture is detected according to a preset threshold parameter and the second measurement data; in response to detection of the exercise, obtaining exercise data when the user performs the exercise multiple times through the at least one IMU sensor; and adjusting the threshold parameter according to the exercise data.