Wrist Motion Recognition via EMG and Acceleration Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion recognition technologies for portable devices struggle with accurately detecting and interpreting complex user motions, especially in intuitive and natural ways, particularly when users interact with gripped objects like pens or pencils, and face challenges with wearable devices due to size constraints and non-intuitive touch-based interfaces.
Innovation Solution
A motion recognition device and method that estimates the state of a gripped object by combining acceleration, EMG, and biomedical signals to track user wrist and joint motions, generating control signals for external devices based on detected writing actions, including sound and grip information, to recognize and interpret written content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Difficulty of detecting and measuring
If acceleration sensors are used to track body motion, then motion detection capability is improved, but measurement precision deteriorates for complex motions involving gripped objects
Solution Approach 1:
The patent combines acceleration sensor data with EMG (electromyogram) signals and sound sensor information to create a multi-modal sensing system. This merging of different sensing modalities allows the system to accurately detect complex motions involving gripped objects, overcoming the limitations of acceleration sensors alone while maintaining ease of motion detection.
Solution Approach 2:
The patent introduces EMG signals as an intermediary to detect muscle activation patterns that precede and accompany object manipulation. By using EMG as a mediator between the user's intent and the actual motion, the system can more precisely interpret complex motions, especially distinguishing between direct hand movements and movements transmitted through gripped objects.
2Measurement precision
If motion sensing cameras are used to analyze user motion, then measurement precision is improved, but device complexity and positioning requirements increase
Solution Approach 1:
The patent replaces the mechanical/optical system of motion sensing cameras with a wearable sensor system comprising acceleration sensors, EMG sensors, and sound sensors. This substitution eliminates the need for complex camera-based tracking systems and their associated positioning requirements, while maintaining the ability to analyze user motion through physiological and physical signal detection.
Solution Approach 2:
The patent segments the motion detection function into multiple independent sensing modalities (acceleration sensing, EMG sensing, sound sensing) that can be independently processed and integrated. This segmentation allows each sensor type to optimize for its specific detection task, reducing overall system complexity compared to a single complex camera system.
3Measurement precision
If multiple sensing modalities are combined to improve motion recognition, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent designs a multi-functional sensing system where the wearable device performs multiple functions: acceleration measurement, EMG signal acquisition, and sound detection. By integrating these diverse sensing capabilities into a single universal platform, the system achieves high motion recognition accuracy without proportionally increasing complexity, as the same hardware platform supports multiple sensing modalities.
Solution Approach 2:
The system uses the user's own physiological signals (EMG) and the acoustic environment (sound of object interaction) as self-provided sensing resources. This self-service approach allows the system to gather additional information without requiring external sensing infrastructure, thereby improving precision while minimizing the addition of external complex components.
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
Enables intuitive and accurate recognition of user motions and content, allowing for seamless control of external devices without the need for specific user interfaces or device positioning, enhancing usability on wearable and small-sized devices.
Implementation Method 1
The estimating of the state of the wrist may include detecting an acceleration according to the writing action, and estimating the state of the wrist according to the acceleration.
Implementation Method 2
The estimating of the joint motion may include detecting electromyogram (EMG) information of the body part related to the wrist according to the writing action, and estimating the joint motion according to the EMG information.
Implementation Method 3
The detecting may include determining that the writing action has started when at least one of a sound generated by the writing action and a grip of an object corresponding to writing is detected.
Data Source
AI summary
A device, a method, and a system recognize a motion using a gripped object. The motion recognition device may estimate a state of a wrist of a user according to a writing action using the gripped object and may estimate a joint motion of a body part related to the wrist according to the writing action. The device may then estimate a state of the gripped object according to the state of the wrist and the joint motion. Additionally, the motion recognition device may control an external device by using a control signal generated by continuously tracking the state of the object.