LiDAR Road Surface Recognition for Weather-Resilient Height Profiling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional road surface recognition technologies using cameras are prone to inaccuracies due to variations in illuminance and weather conditions, making it difficult to accurately determine road surface conditions.

Innovation Solution

Utilizing LiDAR to generate point cloud data, which is less affected by environmental conditions, and integrating this data with motion-related data to create a point cloud map, allowing for accurate road surface recognition through local mapping and height profile generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If camera-based road surface recognition technology is used, then the system can obtain road surface information, but the recognition accuracy deteriorates under varying illuminance and weather conditions

Engineering Contradiction:

Improveroad surface recognition accuracyVSAvoidilluminance and weather condition variations

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the optical camera-based system with a LiDAR-based system that uses laser ranging to measure road surface height. This substitution of the sensing mechanism eliminates the dependency on visible light conditions, as LiDAR actively emits its own light source and measures the reflected light's time of flight, providing accurate measurements regardless of ambient illuminance or weather conditions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent changes the measurement parameter from optical intensity-based detection (camera) to time-of-flight-based distance measurement (LiDAR). By measuring the time it takes for laser pulses to travel to and from the road surface, the system obtains direct height information that is independent of lighting conditions, thereby resolving the contradiction between measurement precision and environmental sensitivity.

Inventive Principle:

Principle #35Parameter changes

2Device complexity

If monocular camera technology is used, then the system structure is simple, but road surface information cannot be obtained when the vehicle is stationary

Engineering Contradiction:

Improvesystem structureVSAvoidroad surface information acquisition

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent replaces the passive optical camera system with an active LiDAR system that emits laser pulses and measures the reflected light. This active sensing mechanism allows the system to obtain road surface height information regardless of vehicle motion state, as the LiDAR actively probes the environment rather than passively capturing light, thereby ensuring reliable information acquisition whether the vehicle is moving or stationary.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If stereo vision technology is used, then road surface recognition can be achieved through correlation analysis, but feature point extraction is greatly affected by image quality

Engineering Contradiction:

Improveroad surface recognition capabilityVSAvoidfeature point extraction accuracy

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent replaces the stereo vision system that relies on feature point extraction from images with a LiDAR system that directly measures three-dimensional spatial coordinates. This substitution eliminates the intermediate step of feature point extraction and correlation analysis, providing direct and accurate road surface height measurements that are not dependent on image quality or the presence of distinguishable features.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates a direct three-dimensional point cloud representation of the road surface using LiDAR measurements, bypassing the need to extract and match feature points from two-dimensional images. This direct copying of spatial information into a 3D format preserves all measurement information without the losses inherent in feature point extraction methods.

Inventive Principle:

Principle #26Copying

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 precise road surface recognition regardless of environmental factors, improving the accuracy and reliability of road surface condition detection.

Implementation Method 1

Light Detection and Ranging (LiDAR)

Methodology Applied

Scientific EffectLight reflection: Reflection

Implementation Method 2

point cloud data generated by use of LiDAR

Methodology Applied

Scientific EffectTime of flight measurement: Time of Flight

Data Source

PatentUS12420802B2Method and system for recognizing road surface

Publication Date: 2025.09.23 HYUNDAI MOTOR CO LTD

AI summary

A road surface recognition method may include extracting first point cloud data in a front road surface region of a vehicle from point cloud data generated by LiDAR of the vehicle, generating a point cloud map by use of a local map and the first point cloud data, determining a predicted driving route of the vehicle based on motion-related data of the vehicle; and generating a road surface height profile of the predicted driving route based on the point cloud map and the predicted driving route.