sEMG Signal Detection for AI Prosthetic Motion Intent Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately mapping human user intentions to electronic device actions, particularly for amputees controlling prosthetics, due to limited and variable training data from sensor placement and difficulty in labeling hand kinematics.
Innovation Solution
Positioning a plurality of sensors at specific body positions, using a sleeve with alignment indicators, and employing an AI regression model trained through mimicked and mirrored training to continuously improve the mapping of neuromuscular movements to motion intents, allowing intuitive control of electronic devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensors are positioned at specific body positions to capture neuromuscular signals, then measurement precision is improved, but device complexity increases due to multiple sensor placements
Solution Approach 1:
The system divides the body into multiple segments (e.g., upper arm, forearm, hand) and places sensors at specific positions on each segment. This segmentation allows precise capture of neuromuscular signals from different muscle groups while organizing the complexity through structured placement zones.
Solution Approach 2:
The patent introduces an intermediary processing layer that receives signals from multiple sensors positioned at different body locations. This intermediary system processes and integrates the signals, managing the complexity of multiple sensor placements while maintaining high measurement precision through centralized signal handling.
2Ease of operation
If training data is collected from limited sensor placements, then ease of operation is improved, but measurement precision deteriorates due to variable and limited data
Solution Approach 1:
The system performs preliminary actions by collecting training data from multiple sensor positions during a setup phase before actual operation. This preliminary data collection from diverse positions creates a comprehensive training dataset that improves mapping accuracy while keeping the actual operation simple, as the system is already trained on varied placements.
Solution Approach 2:
The patent changes parameters by collecting training data across multiple sensor positions and configurations rather than relying on a single fixed placement. This parameter variation in the training phase creates more robust models that maintain high precision during operation, resolving the contradiction between ease of operation and measurement precision.
3Adaptability or versatility
If continuous variable mapping is used to map electric signals to motion intents, then adaptability is improved, but device complexity increases due to AI model requirements
Solution Approach 1:
The patent replaces traditional mechanical or rule-based control systems with an AI regression model that performs continuous variable mapping. This substitution enables high adaptability and flexibility in interpreting neuromuscular signals and translating them to motion intents, while the AI model handles the complexity internally, providing flexible control without requiring complex user-side mechanisms.
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
The system provides improved accuracy and continuous learning for intuitive device control by leveraging continuous variable mapping and separate training sessions, enhancing user control over electronic devices like prosthetics.
Implementation Method 1
positioning a plurality of sensors at a plurality of particular positions on a human body for sensing electric signals (also referred to as surface electromyographic signals and/or sEMG signals) from the human body
Data Source
AI summary
A method for training an artificial intelligence (AI) model for allowing a user to intuitively control an electronic device includes positioning a plurality of sensors at a plurality of particular positions on a human body for sensing electric signals. The method also includes recording a first set of electric signals from each of the plurality of sensors in a continuous manner. At the same time, a first set of motion intents associated with a first sequence of body movement is also recorded in a continuous manner. An AI regression model is trained using a neural network to map the first set of electric signals to the first set of motion intents. In response to receiving a second set of electric signals from the plurality of sensors in a continuous manner, the AI regression model predicts a motion intent, causing the electronic device to perform an action.