Steering Wheel Contact Detection for Hand vs Object Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing contact sensors in vehicles, such as capacitive sensors, can only detect whether an electrically conductive object is in contact with the steering wheel, failing to differentiate between a human hand and other objects.
Innovation Solution
A system comprising a processor and memory that uses data from capacitive sensors, cameras, and other sensors to determine the type of object in contact with the steering wheel by analyzing images and depth estimates, and controlling vehicle components based on this information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a capacitive sensor is used to detect contact with the steering wheel, then contact detection capability is improved, but the ability to differentiate between human hand and other objects deteriorates
Solution Approach 1:
The patent combines multiple sensing modalities (capacitive sensors, optical sensors, depth sensors) into an integrated contact detection system. The capacitive sensor detects contact presence while optical and depth sensors provide object characterization, merging their capabilities to simultaneously achieve contact detection and object differentiation without losing information.
Solution Approach 2:
The patent introduces image processing algorithms and machine learning models as intermediaries between the raw sensor data and object identification. These intermediaries process the data from capacitive and optical sensors to extract meaningful object characteristics, enabling differentiation between human hands and other objects while preserving the contact detection capability.
2Loss of information
If multiple sensors and image processing are used to identify object type, then object differentiation capability is improved, but system complexity increases
Solution Approach 1:
The patent designs the contact detection system to perform multiple functions using integrated components. The same sensor array and processing unit that detect contact also characterize objects, and the machine learning model handles both contact validation and object classification, reducing overall system complexity through multi-functionality.
Solution Approach 2:
The system uses its own sensor data and processing capabilities to automatically differentiate objects without requiring external assistance. The machine learning model is trained on data from the system's own sensors and continuously refines its object identification using the data it collects, making the system self-sufficient and reducing complexity.
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 the vehicle to accurately distinguish between a human hand and foreign objects, allowing for appropriate control actions such as messaging, haptic outputs, or speed adjustments, thereby enhancing safety and user interaction.
Implementation Method 1
A contact sensor such as a capacitive sensor can be included in or on a vehicle steering wheel to determine if a user's hand is in contact with the steering wheel
Data Source
AI summary
An object can be detected in contact with a steering wheel of a vehicle. A first image of the steering wheel at a first angle of rotation and a second image of the steering wheel at a second angle of rotation are then obtained. A type of the object is identified based on at least one of the first image or the second image, as one of a human hand or a foreign object. A vehicle component is controlled based on the type of object.