Wearable Sensor Autocalibration via Orientation Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Smart wearable devices face performance issues when worn in orientations or positions not optimized for signal detection, leading to suboptimal signal detection and calibration challenges.
Innovation Solution
A wearable device system with sensors and a computer processor that uses autocalibration models, including neural networks, to determine and adjust for the current position and orientation of the device on the user, generating control signals for improved signal processing and system operation without requiring specific user poses or gestures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the wearable device is worn in non-optimized orientations or positions, then the device can be worn more flexibly by users, but signal detection performance deteriorates
Solution Approach 1:
The system dynamically adapts to different wearable orientations by continuously monitoring EMG signal characteristics and automatically selecting or adjusting the appropriate inference model. This allows the device to maintain high measurement precision across multiple orientations without requiring fixed wear positions, thus resolving the contradiction between wear flexibility and signal detection performance.
Solution Approach 2:
The system changes processing parameters based on detected wearable orientation by using autocalibration models to identify orientation state and adjusting the inference model accordingly. This parameter adaptation enables the system to maintain optimal signal detection performance regardless of how the device is oriented on the user's body.
2Measurement precision
If traditional calibration methods are used requiring specific user poses or gestures, then calibration accuracy can be improved, but user convenience and ease of operation deteriorates
Solution Approach 1:
The system performs autocalibration by automatically analyzing EMG signal patterns to determine wearable orientation without requiring user intervention or specific poses. The autocalibration model self-adjusts based on the detected signal characteristics, eliminating the need for users to perform calibration gestures while maintaining calibration accuracy.
Solution Approach 2:
The system performs calibration actions automatically during normal operation by continuously monitoring EMG signals and adjusting the inference model in real-time. This preliminary and ongoing calibration process eliminates the need for separate calibration sessions requiring specific user poses, thereby improving ease of operation while maintaining accuracy.
3Measurement precision
If multiple inference models are used for different orientations, then signal processing accuracy across various positions can be improved, but device complexity increases
Solution Approach 1:
The system uses a single versatile inference model that can process EMG signals across multiple orientations by incorporating orientation detection and adaptive processing. Rather than requiring separate dedicated models for each orientation, this universal approach maintains signal processing accuracy while reducing the number of models needed, thus lowering system complexity.
Solution Approach 2:
The system dynamically selects or adjusts the inference model based on detected wearable orientation. This dynamic adaptation allows a single flexible system to handle multiple orientations effectively, avoiding the need for multiple static models and reducing overall system complexity while maintaining high processing accuracy across all orientations.
Data Source
AI summary
Methods and systems used in calibrating the position and/or orientation of a wearable device configured to be worn on a wrist or forearm of a user, the method comprises sensing a plurality of neuromuscular signals from the user using a plurality of sensors arranged on the wearable device, and providing the plurality of neuromuscular signals and/or signals derived from the plurality of neuromuscular signals as inputs to one or more trained autocalibration models, determining based, at least in part, on the output of the one or more trained autocalibration models, a current position and/or orientation of the wearable device on the user, and generating a control signal based, at least in part, on the current position and/or orientation of the wearable device on the user and the plurality of neuromuscular signals.