Mobility Augmentation Control Using Machine-Learned Motor Intent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional mobility aids such as crutches, canes, wheelchairs, exoskeletons, and functional electrical stimulation (FES) systems are not personalized to the user and fail to optimize mobility augmentation based on available information, limiting their effectiveness for individuals with mobility disabilities.
Innovation Solution
A mobility augmentation system that uses machine learning to monitor muscle electroactivity, kinematics, and kinetics to predict intended movements, applying personalized actuation strategies and optimizing them through real-time feedback loops.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional mobility aids (crutches, canes, wheelchairs, exoskeletons, FES systems) are used, then basic mobility support is provided, but the system cannot personalize or optimize mobility augmentation based on user-specific movement data
Solution Approach 1:
The system collects and stores movement data from multiple users during calibration sessions before actual use. This preliminary data collection enables the system to pre-compute personalized movement patterns and predictions, so that when a user needs mobility assistance, the system already has their specific movement characteristics ready to optimize assistance immediately without requiring complex real-time analysis during critical moments
Solution Approach 2:
The system creates simplified representations (models) of complex user movement patterns by collecting training data and generating predictive models. These copied models capture essential movement characteristics without storing all raw sensor data, enabling personalized assistance while managing computational complexity through data abstraction and model-based prediction
2Measurement precision
If machine learning models are trained on generalized movement data from multiple users, then the system can provide initial mobility assistance, but the predictions are not optimized for individual user characteristics
Solution Approach 1:
The system performs calibration during scheduled sessions before normal use, collecting and processing user-specific movement data in advance. This preliminary calibration establishes personalized predictive models that improve prediction accuracy for that specific user, while the models are then ready for rapid deployment during actual mobility tasks without requiring additional calibration time during critical moments
Solution Approach 2:
The system dynamically adapts its predictive models by continuously updating them with new user data collected during calibration sessions. The model evolves from a generalized population-based prediction to a personalized user-specific prediction through iterative refinement, allowing the system to balance between quick deployment and progressively improving accuracy over time
3Ease of operation
If the system applies actuation strategies based on predicted movements, then mobility assistance is provided, but the system cannot optimize actuation parameters for individual user needs
Solution Approach 1:
The system implements a closed-loop control architecture where movement predictions are continuously compared with actual user movements. The differences (errors) between predicted and actual movements are fed back to adjust and refine the predictive models and actuation strategies. This feedback mechanism enables automatic optimization of actuation parameters for individual users without requiring complex manual tuning, as the system self-adjusts based on performance feedback
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 personalized and optimized mobility assistance by predicting intended movements and adjusting actuation strategies to minimize differences between intended and actual movements, enhancing user independence and mobility.
Implementation Method 1
By monitoring muscle electroactivity, the system can determine what movement the user intends to make before the user makes it
Data Source
AI summary
A mobility augmentation system monitors a user's motor intent data and augments the user's mobility based on the monitored motor intent data. A machine-learned model is trained to identify an intended movement based on the monitored motor intent data. The machine-learned model may be trained based on generalized or specific motor intent data (e.g., user-specific motor intent data). A machine-learned model initially trained on generalized motor intent data may be re-trained on user-specific motor intent data such that the machine-learned model is optimized to the movements of the user. The system uses the machine-learned model to identify a difference between the user's monitored movement and target movement signals. Based on the identified difference, the system determines actuation signals to augment the user's movement. The actuation signals determined can be an adjustment to a currently applied actuation such that the system optimizes the actuation strategy during application.