IMU-Based Gait Phase Detection for Precise FES Timing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately determine and predict the phase of the human gait cycle, particularly for applications involving robotic devices and rehabilitation through functional electrical stimulation (FES), necessitating improved methods for precise muscle activation timing.
Innovation Solution
Utilizing inertial measurement units (IMUs) with accelerometers and gyroscopes, combined with neural networks, to estimate gait phases from sensor data, enabling precise determination and prediction of gait phases for targeted muscle activation, such as through FES, and integrating this data into a control strategy for robotic limbs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pressure sensors are used to determine gait phase events, then gait phase determination can be achieved, but measurement precision and reliability are insufficient for accurate muscle activation timing
Solution Approach 1:
The patent replaces pressure sensors with inertial measurement units (IMUs) that use accelerometers and gyroscopes to detect gait phase. This substitution from mechanical pressure detection to inertial measurement provides more accurate and reliable data for determining gait phase and timing muscle activation, directly resolving the contradiction between measurement precision and reliability.
2Measurement precision
If neural networks are implemented to predict gait phase, then gait phase prediction accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements neural networks that are pre-trained offline to predict gait phase from IMU data. By performing the complex training and model development in advance rather than in real-time operation, the system achieves high prediction accuracy while keeping the runtime device complexity manageable. The pre-trained model can be deployed to embedded systems with limited computational resources.
3Reliability
If functional electrical stimulation is applied based on predicted gait phase, then rehabilitation effectiveness is improved, but control system complexity increases
Solution Approach 1:
The patent implements a feedback control system where IMU data continuously monitors gait phase, the neural network predicts current and future gait phases, and the FES controller adjusts stimulation timing based on these predictions. This closed-loop feedback mechanism ensures accurate muscle activation timing for effective rehabilitation while managing system complexity through efficient integration of the prediction algorithm.
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 accurate identification of gait phases, allowing for effective muscle targeting and control strategies in rehabilitation and robotic motion, enhancing precision and effectiveness of interventions.
Implementation Method 1
IMUs as used in embodiments of the invention comprise at least one accelerometer and at least one gyroscope
Implementation Method 2
IMUs as used in embodiments of the invention comprise at least one accelerometer and at least one gyroscope
Implementation Method 3
a neural network stored on a device that has been trained to accurately predict the subject's phase of gait from IMU data
Implementation Method 4
the application of an electrical charge to the muscles of a subject for the purposes of rehabilitation and injury prevention
Data Source
AI summary
An aspect of the invention providing a method for determining the phase of gait of a subject is provided, the method comprising: transmitting from at least one motion sensor, data corresponding to motion of a part of a lower limb of the subject to a control unit; estimating a gait phase of the subject using the control unit; and sending an input signal based on the estimated gait phase to a controller; based on the input signal, executing a pre-determined instruction or action.