Steering Wheel Hands-On Detection Using Control Input Signals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting contact between a driver's hands and a vehicle's steering wheel are not robust enough, as they rely on limited input variables, which can lead to inaccurate hands-on detection, affecting the activation and deactivation of driver assistance systems.
Innovation Solution
A method and device that utilize a trained machine learning approach, specifically a deep neural network, to determine hand contact by incorporating actuation data from control elements on the steering wheel, along with steering system status data, to generate a decision signal, enhancing the robustness of hands-on detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional sensor-based or rule-based methods are used for hands-on detection, then the system complexity remains low, but the detection reliability and accuracy deteriorate due to limited input variables
Solution Approach 1:
The patent transitions from traditional 2D sensor arrays to a 3D spatial mapping approach, creating a virtual representation of the steering wheel surface with depth information. This dimensional enhancement allows the system to detect hand contact more reliably by analyzing spatial coordinates and pressure distribution in three dimensions, improving detection accuracy without proportionally increasing system complexity
Solution Approach 2:
The patent combines multiple sensing technologies (capacitive sensors, force sensors, and machine learning algorithms) into a composite detection system. This integration creates a synergistic effect where each component contributes its strengths, resulting in more reliable hands-on detection than any single method could achieve alone, while the unified system architecture manages complexity
2Measurement precision
If more input variables are considered in hands-on detection, then the detection accuracy improves, but the processing time and computational complexity increase
Solution Approach 1:
The patent pre-processes sensor data during normal operation to build and maintain a virtual 3D model of the steering wheel surface, including pressure distribution maps and spatial coordinate systems. This preliminary preparation allows the hands-on detection algorithm to quickly compare current sensor readings against the pre-established model, achieving high accuracy without requiring extensive real-time computation when a hand contact event occurs
Solution Approach 2:
The patent replaces complex mechanical signal processing with machine learning algorithms that can rapidly analyze multiple input variables simultaneously. The trained neural network model processes spatial coordinates, pressure values, and sensor patterns in parallel, achieving high detection accuracy with reduced processing time compared to traditional sequential analysis methods
Data Source
Figure 1
AI summary
The invention relates to a method for detecting contact between hands and a steering wheel (52) of a vehicle (50), wherein, based on at least detected and/or received state data (10) of a steering system (51) of the vehicle (50), a decision (20) is made by means of at least one trained machine learning method (3) as to whether at least one hand is in contact with the steering wheel (52) or not, wherein the actuation of at least one control element (54-x) arranged on the steering wheel (52) is taken into account as an input variable (11) of the at least one trained machine learning method (3), and wherein a decision signal (21) is generated and provided. Furthermore, the invention relates to a device (1) for detecting contact between hands and a steering wheel (52) of a vehicle (50).