HMI Input Surface Sensing for Glove- and Moisture-Robust Touch Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Capacitive touch interfaces in HMI systems are susceptible to false readings due to moisture or gloves, limit touch surfaces to non-conductive materials, and struggle to accurately detect user intent and touch location, press intensity, and gesture types, lacking a universal methodology for recognizing user interactions involving pressure and proximity.
Innovation Solution
A method and system using integrated sensors with signal processing, feature extraction, classification, and machine learning algorithms to detect and classify physical inputs on an HMI input structure, employing techniques like Gaussian noise removal, event detection, and machine learning models to determine input location and intent.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If capacitive touch interfaces are used to detect physical inputs, then the interface can register user intent through capacitance changes, but the system becomes susceptible to false readings from moisture or gloves and cannot discern user intention
Solution Approach 1:
The system segments the detection process into multiple independent measurement dimensions (capacitance, conductance, impedance, phase, frequency, time-domain characteristics) rather than relying on a single capacitive measurement. This segmentation allows the system to cross-validate readings and distinguish genuine touch inputs from false triggers caused by moisture or gloves.
Solution Approach 2:
The system changes the electrical parameters being measured beyond simple capacitance detection. By measuring conductance, impedance, phase, and frequency characteristics simultaneously, the system creates a multi-parameter fingerprint for each touch event, enabling discrimination between intentional touches and environmental interference.
2Measurement precision
If capacitive touch interfaces rely on capacitance changes to identify physical inputs, then the interface can detect finger presence, but the system cannot work when the user is wearing gloves
Solution Approach 1:
The system implements a universal detection mechanism that functions across multiple conditions (bare finger, gloved finger, moisture exposure). By measuring multiple electrical characteristics simultaneously and using machine learning to recognize patterns, the system achieves multi-functional capability to detect various types of physical inputs regardless of the user's hand condition.
Solution Approach 2:
The system changes from single-parameter capacitive detection to multi-parameter electrical characterization. By measuring conductance, impedance, phase, and frequency in addition to capacitance, the system creates a richer signal profile that remains detectable even when gloves or moisture alter the capacitive properties of the touch interface.
3Adaptability or versatility
If infrared and/or ultrasound are used to overcome capacitive interface limitations, then the system can detect user presence with gloves, but the system cannot determine the intention behind an input or precise touch location
Solution Approach 1:
The system merges the advantages of capacitive sensing (precise location and intensity detection) with the glove-detection capability of alternative technologies. By combining multiple sensing modalities and their corresponding signal processing pipelines, the system achieves both accurate touch localization and glove compatibility simultaneously.
Solution Approach 2:
The system uses machine learning algorithms as an intermediary that processes raw sensor signals from multiple modalities and translates them into accurate touch location and gesture type classifications. This intermediary layer enables the system to interpret complex multi-source data and produce precise spatial and semantic information about user inputs.
4Measurement precision
If non-capacitive touch sensing is used with extensive mapping and iterative design processes, then the system can achieve desired performance, but the development time and complexity increase significantly
Solution Approach 1:
The system performs preliminary characterization of sensor responses during the manufacturing process, storing reference data for different touch conditions, locations, and intensities. This pre-characterization creates a library of expected sensor behaviors that can be directly compared against actual inputs during operation, eliminating the need for time-consuming iterative field testing and calibration.
Solution Approach 2:
The system uses machine learning algorithms to automatically characterize and adapt to the specific sensor array's behavior patterns without requiring manual calibration or extensive engineering iteration. The algorithm self-adjusts to account for manufacturing variations and environmental conditions, reducing the need for manual tuning and extending the design process.
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 accurate detection and classification of user inputs on various surfaces, independent of hardware configuration or mechanical variations, reducing the need for iterative design cycles and enhancing user interaction recognition.
Implementation Method 1
Capacitive touch interfaces may be susceptible to false readings when moisture or gloves are involved
Implementation Method 2
signal processing, feature extraction, classification, and function mapping
Data Source
AI summary
Systems and methods for detecting and classifying types of physical inputs on an input surface of a human machine interface (HMI) input structure are disclosed. In response to a physical input on the input surface, one or more sensor signals are received from respective sensors associated with the HMI input structure. One or more features are determined for each received sensor signal. Based on the one or more features for each sensor signal, a position on the input surface is determined by classifying the one or more sensor signals. The classification of the one or more sensor signals can be performed by one or more machine learning algorithms. Based on a classification of the physical input, an action associated with the determined location is executed.