Steering Wheel Grip Intensity Estimation Beyond Sensor Zones
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle systems that estimate grip intensity using pressure sensors on the steering wheel are costly, complex, and unreliable, especially during atypical driving scenarios due to limited dimensionality from modeling.
Innovation Solution
A detection system that computes grip intensity using image data of an operator's hand grasp, relying on inexpensive pressure sensors in limited areas for calibration, and utilizing a learning model trained offline with test images to estimate grip intensity accurately outside sensor areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pressure sensors are installed throughout the steering wheel to improve grip intensity detection accuracy, then measurement precision is improved, but manufacturing cost and device complexity increase
Solution Approach 1:
The steering wheel is divided into two functional zones: set areas with pressure sensors for calibration and outside set areas without sensors for operational use. This segmentation allows the system to achieve accurate grip intensity measurement through a hybrid approach using both sensor data and image processing, reducing overall sensor requirements while maintaining detection accuracy.
Solution Approach 2:
The learning model is trained offline using test images and sensor data from set areas before actual operation. This preliminary training phase allows the system to learn the relationship between image features and grip intensity, enabling accurate predictions during actual driving without requiring sensors throughout the entire steering wheel.
2Measurement precision
If pressure sensors are installed throughout the steering wheel to improve grip intensity detection accuracy, then measurement precision is improved, but manufacturing cost increases
Solution Approach 1:
The steering wheel is divided into two functional zones: set areas with pressure sensors for calibration and outside set areas without sensors for operational use. This segmentation allows the system to achieve accurate grip intensity measurement through a hybrid approach using both sensor data and image processing, reducing overall sensor requirements while maintaining detection accuracy.
Solution Approach 2:
The system uses image data as a virtual copy or representation of the physical grip state. By training a learning model to map image features to grip intensity values, the system creates a computational model that replicates the measurement function, reducing dependence on extensive physical sensor coverage.
3Reliability
If pressure sensors are used to estimate grip intensity, then grip intensity can be detected, but the system produces unreliable estimates during atypical driving scenarios due to limited dimensionality
Solution Approach 1:
The system transitions from relying solely on one-dimensional pressure sensor data to using multi-dimensional image data including hand position, grip posture, and contact area information. This dimensional enrichment allows the learning model to capture diverse gripping patterns and maintain reliability across various driving scenarios, including atypical ones.
Solution Approach 2:
The system uses grip measurements from pressure sensors in set areas to provide feedback for calibrating and validating the learning model. This feedback mechanism ensures the model's predictions remain accurate and reliable by continuously comparing model outputs with actual sensor measurements during calibration phases.
4Reliability
If pressure sensors are installed on the steering wheel to detect grip intensity, then grip information can be obtained, but the system increases bulk and reduces available space
Solution Approach 1:
The steering wheel is divided into two functional zones: set areas with pressure sensors for calibration and outside set areas without sensors for operational use. This segmentation allows the system to achieve accurate grip intensity measurement through a hybrid approach using both sensor data and image processing, reducing overall sensor requirements while maintaining detection accuracy.
Solution Approach 2:
The system extracts the essential measurement function from physical sensors throughout the steering wheel and concentrates it into localized sensor arrays in set areas combined with external imaging. This extraction allows the bulk of the steering wheel to remain free of sensors while preserving detection capability through the hybrid measurement approach.
Data Source
AI summary
Systems, methods, and other embodiments described herein relate to implementing and calibrating a learning model for inferring operator intent by estimating grip intensity. In one embodiment, a method includes estimating, using a learning model during a driving scenario, first grip intensity on a steering device for a vehicle according to initial image data depicting a hand of an operator gripping outside the set areas that have pressure sensors. The method also includes calibrating the learning model for the operator and the steering device using grip measurements and additional image data acquired from gripping inside the set areas. The method also includes computing, using the learning model during the driving scenario, second grip intensity outside the set areas on the steering device according to hand images acquired about the operator. The method also includes adapting a vehicle parameter of the vehicle according to the second grip intensity.