EMG Training System Using Joint Position Mapping for Full Hand Movement Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current EMG systems are limited in decoding the full range of hand movements, making them insufficient for able-bodied use cases, as they can only recognize a fixed number of pre-trained movements.
Innovation Solution
A computing device processes EMG signals from a device like the NeuroLife sleeve and joint position signals from a capturing device to create a mapping, training a decoding algorithm that can predict the full range of hand movements, enabling control of virtual or robotic hands.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a decoding algorithm is trained to recognize a fixed number of pre-trained movements, then the system can reliably control a small number of grips for individuals with motor impairments, but the system becomes insufficient for able-bodied use cases due to limited movement recognition
Solution Approach 1:
The system transitions from a static, fixed set of pre-trained movements to a dynamic, continuous movement space. By mapping EMG signals to joint angles in three-dimensional space, the system can adapt to any movement within the captured range, allowing able-bodied users to perform unlimited movements while maintaining reliability through the structured mapping framework.
Solution Approach 2:
The patent extends the movement recognition from discrete classified movements to continuous three-dimensional joint angle space. By incorporating multiple joint angles (wrist, elbow, shoulder) as dimensions, the system creates a comprehensive movement vocabulary that captures the full range of human motion, transforming the limitation of fixed movements into a versatile continuous control system.
2Device complexity
If the system uses traditional EMG decoding with a limited set of pre-trained movements, then the device complexity remains manageable, but the system cannot accurately decode the full range of hand movements
Solution Approach 1:
The system segments the complex task of full-range movement decoding into manageable components by capturing multiple joint angles (wrist, elbow, shoulder) separately and mapping them to corresponding virtual or robotic hand movements. This segmentation allows the system to handle complex full-range motion through simpler, modular joint-level control, maintaining manageable device complexity while achieving high measurement precision.
3Adaptability or versatility
If the system is designed for able-bodied use cases requiring full range of motion, then the adaptability increases, but the traditional EMG approach becomes insufficient for accurate decoding
Solution Approach 1:
The system creates a universal decoding framework that works for both able-bodied users requiring full range of motion and individuals with motor impairments. By mapping EMG signals to continuous three-dimensional joint angle space, the system provides a multi-functional solution that adapts to different user needs and movement capabilities, achieving both high adaptability and reliable decoding accuracy across diverse applications.
Data Source
AI summary
EMG training systems, devices and methods are disclosed. In an approach, a computing device may receive a first input and a second input. The first input may be from an EMG device, such as the NeuroLife® sleeve provided by Battelle. A second input may be from a joint position capturing device. The computing device may create a mapping between the first input and the second input and then train a decoding algorithm based on the mapping. The decoding algorithm may be used to determine a position of the EMG device based on input received from the EMG device.