Deep Learning Terrain Mode Control via Road Friction Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional terrain mode control technologies require human intervention to determine road surface conditions, which hinders the development of advanced autonomous driving capabilities and increases vehicle manufacturing costs due to the need for dedicated physical buttons.
Innovation Solution
A deep learning-based method that uses camera-obtained road surface data to estimate the road friction coefficient and automatically control in-vehicle modules, eliminating the need for driver intervention and physical buttons by determining optimal terrain modes and providing autonomous driving assistance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If conventional terrain mode control technology is used with manual driver determination, then the system can control terrain mode, but it requires additional driver manipulation and dedicated physical buttons which increases device complexity and reduces ease of operation
Solution Approach 1:
The system uses the vehicle's existing camera to capture road surface images and automatically determines terrain mode without requiring driver intervention. The processor analyzes the captured images to identify road surface characteristics and autonomously selects the appropriate terrain mode, allowing the system to serve itself rather than requiring manual operation.
Solution Approach 2:
The existing camera system, originally designed for general vehicle functions, is repurposed to perform terrain mode determination. This multi-functional approach eliminates the need for dedicated physical buttons or separate determination devices, reducing device complexity while maintaining ease of operation.
2Extent of automation
If conventional terrain mode control technology is used with manual driver determination, then the system can control terrain mode, but it requires human intervention which hinders autonomous driving capabilities
Solution Approach 1:
The processor automatically analyzes road surface images captured by the camera and determines terrain mode without any driver intervention. This autonomous determination process enhances the extent of automation by eliminating manual input requirements while maintaining ease of operation through automatic system response.
3Ease of manufacture
If dedicated physical buttons are provided for terrain mode selection, then the system can control terrain mode, but it increases manufacturing costs and reduces interior design flexibility
Solution Approach 1:
The camera system serves multiple functions including its original purpose and terrain mode determination. This eliminates the need for dedicated physical buttons, simplifying manufacturing processes and reducing device complexity while lowering manufacturing costs and improving interior design flexibility.
Solution Approach 2:
The terrain mode determination function is extracted from the need for physical buttons and implemented through software processing of camera images. This removes the physical hardware requirement, easing manufacturing constraints and reducing device complexity.
Data Source
AI summary
The present disclosure in some embodiments provides a method and apparatus which utilize a learning model based on deep learning for enabling a vehicle to autonomously estimate a road surface condition by using a deep learning-based learning model, determine a terrain mode optimized for the road surface being traveled by the vehicle, and control respective in-vehicle modules and thereby automatically control the terrain mode.