Hybrid FES Control for Noisy Volitional Intent Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing functional electrical stimulation (FES) systems face challenges in accurately decoding volitional intent due to noise, invasive implantation issues, and interpatient variability, leading to errors and reduced effectiveness in neurological injury rehabilitation.
Innovation Solution
A hybrid FES system combining volitional intent-based control through EEG, iEEG, or EMG decoding with a user interface (UI) for precise control, allowing users to switch between modes and contexts, minimizing errors and enhancing intuitive operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If volitional intent decoding is used to control FES, then control precision is improved, but error rates increase due to noise and signal interference
Solution Approach 1:
The patent combines volitional intent decoding (BCI/EMG) with traditional UI control mechanisms into a hybrid FES control system. The system integrates neural signal processing with user interface elements, allowing the user to switch between volitional control mode and UI control mode. This merging approach enables the system to leverage the high precision of intent decoding while using the UI as a backup mechanism to reduce errors caused by noise and signal interference.
Solution Approach 2:
The system implements feedback mechanisms where the user can monitor the decoded volitional intent and correct errors through the UI interface. The control system provides feedback about the detected intent to the user, allowing real-time correction of misinterpretations. This feedback loop helps reduce error rates by enabling users to verify and adjust the decoded commands before they are executed.
2Measurement precision
If invasive electrodes are implanted for iEEG recording, then measurement precision is improved, but device complexity and surgical risk increase
Solution Approach 1:
The patent segments the control system into multiple functional components: invasive iEEG recording pathway, non-invasive EEG/EMG recording pathway, and UI control pathway. This segmentation allows the system to offer different levels of invasiveness as optional modes. Users can select between highly precise invasive recording or less invasive non-invasive alternatives, thereby reducing the mandatory complexity of implantation while maintaining the option for high precision when needed.
Solution Approach 2:
The FES control system is designed with multi-functionality to accommodate different user needs and medical conditions. It can operate with invasive iEEG electrodes for maximum precision, or switch to non-invasive EEG/EMG sensors for simpler implementation. The system universally supports both invasive and non-invasive recording methods, allowing flexibility in deployment based on patient suitability and clinical requirements.
3Adaptability or versatility
If machine learning components are used for intent decoding, then adaptability to individual patients is improved, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary calibration and training of machine learning models before actual FES control operations. During calibration sessions, the system collects data about the patient's neural patterns and learns optimal decoding parameters. This preliminary action prepares the ML model in advance, reducing the computational burden during real-time control operations. The trained models can then make faster predictions with lower computational complexity.
Solution Approach 2:
The patent implements dynamic adaptation where the machine learning components can adjust their complexity and processing requirements based on operational context. The system can switch between different decoding algorithms and processing intensities depending on the task requirements and available computational resources. This dynamic approach allows high adaptability to individual patients while managing computational complexity through context-aware algorithm selection.
4Ease of operation
If multiple control modes are provided for different contexts, then ease of operation is improved, but device complexity increases
Solution Approach 1:
The control interface is segmented into distinct operational modes (volitional control mode, UI control mode, hybrid mode) that can be independently configured and activated. Each mode handles specific contextual requirements, allowing the system to present simplified controls appropriate to each situation. This segmentation reduces overall complexity by organizing the interface into manageable, context-specific modules rather than a monolithic complex system.
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 hybrid system provides refined control with reduced error rates, increased movement options, and context awareness, improving neurological rehabilitation by enabling users to directly control their anatomy with enhanced precision and responsiveness.
Implementation Method 1
determining the volitional intent of the associated user by applying at least one machine learning (ML) component to the acquired neural signals
Implementation Method 2
control the FES stimulator to apply the operating mode-specific FES stimulation to the anatomical region of the associated user via the electrodes of the stimulation garment
Implementation Method 3
at least one neural signal amplifier configured to acquire neural signals indicative of motor cortex activity of the associated user
Implementation Method 4
electromyography (EMG) signals are measured using the electrodes of the electrical stimulation garment
Data Source
AI summary
A functional electrical stimulation (FES) system includes a stimulation garment with electrodes arranged to contact skin of an anatomical region worn on the anatomical region, an FES stimulator, an FES control user interface (UI) device configured to present an FES control UI, and a hardware processor programmed to: set the FES system in a user-selected operating mode based on user inputs from the FES control UI, determine an operating mode-specific FES stimulation based at least on the user-selected operating mode, and control the FES stimulator to apply the operating mode-specific FES stimulation to the anatomical region of the user via the electrodes.