Road Surface Sensing via Tire Acoustic Feature Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional road surface condition sensing systems for autonomous vehicles are cumbersome and slow to reflect actual road conditions, relying on periodic tire exchanges and weather information, which complicates immediate sensing during driving.
Innovation Solution
A neuromorphic-based road surface condition sensing system that uses acoustic signals from vehicle tires to calculate feature vectors, comparing them with stored patterns to determine road surface conditions and provide real-time feedback to autonomous drive control systems without relying on weather data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If additional wire devices are installed near the tire to sense road surface condition, then road surface condition sensing is enabled, but periodic exchange becomes troublesome
Solution Approach 1:
The patent replaces mechanical wire-based sensing devices with a magnetic field-based sensing system using Hall sensors. This substitution eliminates the need for periodic physical exchange of wire devices while maintaining reliable road surface condition sensing capability through non-contact magnetic field detection.
Solution Approach 2:
The patent introduces magnetic field lines as an intermediary between the tire and the sensing system. By detecting changes in magnetic field caused by tire rotation and road surface interaction, the system enables road surface condition sensing without direct physical contact or wire installation near the tire, thus avoiding periodic exchange requirements.
2Adaptability or versatility
If weather information and temperature data are combined to estimate road surface condition, then sensing coverage is expanded, but immediate reflection of actual road surface situation during driving becomes difficult
Solution Approach 1:
The patent implements continuous real-time detection of road surface conditions through magnetic field sensing during vehicle operation. Unlike periodic weather-based estimation, this system continuously monitors actual road surface conditions through tire-magnetic field interaction, providing immediate and uninterrupted feedback for autonomous driving control.
Solution Approach 2:
The patent establishes a direct feedback loop where magnetic field changes detected during tire rotation immediately inform road surface condition assessment. This real-time feedback mechanism allows the autonomous driving system to respond promptly to actual road conditions without relying on delayed weather information or temperature data.
3Measurement precision
If conventional sensing methods using tire noise are used, then road surface condition can be assessed, but calculation amount increases and reliability decreases due to dependency on weather information
Solution Approach 1:
The patent extracts and utilizes only the essential magnetic field interaction component between the tire and road surface, eliminating the need for complex noise analysis and weather information processing. By focusing solely on magnetic field changes, the system reduces calculation requirements while maintaining or improving measurement precision for road surface condition assessment.
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
This approach minimizes calculation overhead and provides prompt, reliable road surface condition feedback to enhance autonomous driving performance by directly analyzing tire noise, improving sensing accuracy and reducing dependency on weather information.
Implementation Method 1
an acoustic sensing unit for sensing an acoustic signal of a floor of a vehicle
Implementation Method 2
calculating a feature vector by Fourier transforming the sensed acoustic signal
Data Source
AI summary
Disclosed are a road surface condition sensing system and method. The road surface condition sensing system includes an acoustic sensing unit for sensing an acoustic signal of a floor of a vehicle, and a control unit for calculating a feature vector by Fourier transforming the sensed acoustic signal, comparing the calculated feature vector with a plurality of previously stored feature vectors and returning a first feature vector having the smallest relative distance to the calculated feature vector, and outputting a road surface condition corresponding to the first feature vector.


