Vehicle Touchscreen Input Control Under Motion and Vibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle user interfaces, such as touchscreens, suffer from inaccurate user inputs due to lateral, vertical, and longitudinal forces during vehicle movement, leading to incorrect function activation and potential accidents.
Innovation Solution
A computer-implemented method using a user input model that analyzes user interface and sensor data to interpret user inputs, correcting unintended touches through a machine learning algorithm, compensating for offsets and vibrations, and improving touch accuracy by integrating initial personal calibration, generalized augmented touch data, and real-time interaction analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a touchscreen user interface is used in a vehicle, then control functions are simplified and operation is accurate when stationary, but touch accuracy deteriorates during vehicle movement due to lateral, vertical and longitudinal forces causing body movements
Solution Approach 1:
The system performs preliminary calibration by collecting touch data from multiple users at various vehicle positions and creating a predictive model before actual use. This pre-established model predicts and compensates for body movements during vehicle operation, allowing the system to correct touch coordinates in advance based on anticipated motion patterns.
Solution Approach 2:
The system continuously monitors vehicle motion data from sensors and feeds this information back to the predictive model in real-time. The model uses this feedback to dynamically adjust touch coordinate predictions, compensating for ongoing vehicle movements and maintaining touch accuracy throughout operation.
2Device complexity
If touchscreen control elements are used to reduce interior controls, then device complexity is reduced, but reliability deteriorates due to incorrect function activation from inaccurate touches
Solution Approach 1:
The system implements a feedback loop where vehicle motion data from sensors is continuously fed back to the predictive model. This real-time feedback enables the system to detect and correct touch coordinate deviations caused by vehicle movement, ensuring reliable function activation even with reduced physical controls.
Solution Approach 2:
The patent replaces traditional mechanical correction methods with a computational approach. Instead of using additional mechanical components to stabilize the touchscreen, the system uses a machine learning model that processes sensor data and mathematically predicts and corrects touch coordinates, substituting mechanical stabilization with intelligent software-based compensation.
3Measurement precision
If predictive models are trained with personalized calibration data, then touch accuracy for individual users is improved, but data processing complexity increases
Solution Approach 1:
The system creates a universal predictive model that serves multiple functions: it can be trained with personalized data for individual users or used in a generalized mode for all users. This multi-functional model reduces data processing complexity by eliminating the need for separate models for each user while still providing personalized accuracy when needed.
Solution Approach 2:
The system allows dynamic adjustment of model parameters based on available data. When personalized calibration data is available, the model adapts to individual user patterns; when not available, it operates with generalized parameters. This parameter flexibility reduces training complexity while maintaining high accuracy across different usage scenarios.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A computer-implemented method for controlling (100) at least one user interface of a vehicle, comprising: providing user interface data (110) of the at least one user interface; providing user input data (120) of an input of at least one user of the at least one user interface; providing a user input model (130) configured to analyze the user input data based on the user interface data and sensor data of the vehicle; and processing the user interface data (140), the user input data by means of the user input model and generating user interface control data.