Touch Input Force Estimation from Heatmaps Without Physical Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing touch interfaces lack force-sensing functionality, which is beneficial for enhancing user experience but adds cost and size to computing systems, and existing solutions using a single force sensor are inaccurate in multi-touch scenarios.
Innovation Solution
A machine-learning model trained on data from a plurality of force sensors simulates force-sensing functionality by analyzing touch heatmaps, allowing computing systems without force sensors to estimate touch input forces accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If force sensors are added to the touch interface, then force-sensing functionality is achieved, but system cost and size increase
Solution Approach 1:
The patent creates a virtual copy of force sensor functionality through machine learning. Instead of physically adding force sensors to every device, a trained ML model copies the force-sensing behavior by analyzing touch heatmap patterns from existing touch sensors, producing force estimation outputs that mimic what actual force sensors would measure.
Solution Approach 2:
The patent replaces the mechanical/physical force sensing system with a computational approach. The ML model substitutes physical force sensors by processing electrical signals from touch sensors through algorithmic analysis, transforming a hardware-based measurement system into a software-based estimation system.
2Device complexity
If a single force sensor is used, then system size is reduced, but measurement accuracy deteriorates in multi-touch scenarios
Solution Approach 1:
The patent segments the touch interface into multiple virtual force sensor locations corresponding to different regions of the touch screen. The ML model processes touch heatmap data to estimate force at multiple discrete locations simultaneously, enabling accurate multi-touch force detection without requiring multiple physical sensors.
Solution Approach 2:
The patent transitions from a single-point force measurement (one-dimensional) to a distributed multi-point force estimation (two-dimensional). By analyzing spatial patterns in the touch heatmap, the ML model generates force estimates across the entire touch surface, adding spatial dimensionality to the force sensing capability.
Data Source
AI summary
Examples are disclosed herein relating to simulating force-sensing functionality for a touch interface using a machine-learning model that is trained based at least on training data generated by a training touch interface including a plurality of force sensors. In one example, a computing system includes a touch interface configured to output a touch heatmap based at least on touch input detected by a plurality of touch sensors of the touch interface. The computing system is configured to execute a machine-learning model that is configured to receive the touch heatmap, output a force estimation of the touch input based at least on analyzing the touch heatmap, and execute a computing operation based at least on the force estimation. The machine-learning model is trained based at least on training data generated by a training touch interface including a plurality of force sensors.