Road Weather Detection Using Laser Intensity Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in accurately determining road conditions such as wet or snowy surfaces, which can affect safe operation, as existing systems may not effectively utilize sensor data to differentiate between dry and wet conditions.

Innovation Solution

A method and system that utilize laser data to determine average intensity and distribution of road surfaces, comparing these to threshold values and expected conditions under dry weather, along with additional data from cameras and precipitation sensors, to estimate road conditions and make informed driving decisions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If laser data intensity is used to detect road conditions, then measurement precision is improved, but device complexity increases due to multiple sensors and data processing requirements

Engineering Contradiction:
Improveroad condition detection accuracyVSAvoidsensor system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent combines laser sensors, cameras, and precipitation sensors into an integrated road condition detection system. Multiple data sources (laser intensity data, camera images, precipitation sensor readings) are merged and processed together to determine road conditions, achieving higher measurement precision through sensor fusion while managing complexity through unified processing architecture.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The laser sensor system is designed to perform multiple functions: detecting wet road conditions through intensity analysis, identifying snowy conditions through intensity distribution, and providing data for various driving decisions. This multi-functionality improves measurement precision across different road conditions while avoiding the need for separate dedicated sensors for each condition.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If multiple data sources are processed to improve road condition identification, then reliability is improved, but loss of time increases due to extensive data processing

Engineering Contradiction:
Improveroad condition assessment reliabilityVSAvoiddata processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary processing of laser data by continuously calculating intensity averages and distributions, and pre-processing camera images and precipitation sensor data. This preliminary action ensures that when road condition determination is needed, the data is already prepared and organized, reducing the time required for final assessment while maintaining high reliability through comprehensive data analysis.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses feedback from multiple data sources to continuously refine road condition assessments. Laser intensity data, camera images, and precipitation sensor readings provide ongoing feedback that allows the system to update its understanding of road conditions in real-time, improving reliability while the feedback loop is optimized to minimize processing delays.

Inventive Principle:
Principle #23Feedback

3Ease of operation

If laser intensity threshold comparison is used to identify wet roads, then ease of operation is improved, but measurement precision deteriorates due to simple thresholding

Engineering Contradiction:
Improveroad condition identification simplicityVSAvoidwet road detection precision
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system enhances the simple threshold comparison by adding another dimension of analysis: intensity distribution. Instead of relying solely on average intensity thresholds, the system also evaluates how intensity values are distributed across different ranges. This dimensional expansion improves measurement precision by providing more nuanced detection of wet road conditions while maintaining the operational simplicity of threshold-based methods.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system dynamically adjusts threshold values based on environmental conditions and road surface characteristics. Rather than using fixed thresholds, the system modifies intensity thresholds according to contextual information from multiple sensors, improving measurement precision while keeping the threshold comparison approach operationally simple through automated parameter adaptation.

Inventive Principle:
Principle #35Parameter changes

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 accurate identification of wet or snowy road conditions, allowing for improved driving decisions and safety by processing multiple data sources to assess road conditions and adjust vehicle operation accordingly.

Implementation Method 1

receiving laser data collected for a roadway as a vehicle is driven along the roadway, wherein the laser data includes a plurality of laser data points

Methodology Applied
Scientific EffectLIDAR (Light Detection and Ranging): LIDAR

Implementation Method 2

evaluating the reflected radiation

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3284645B1Detecting road weather conditions
Publication Date: 2021.11.03 WAYMO LLC
  • EP3284645B1 patent drawingFigure 1
  • EP3284645B1 patent drawingFigure 2
  • EP3284645B1 patent drawingFigure 3A

AI summary

The invention relates to detecting road weather conditions, namely an at least partly snow covered road. Vehicle sensors including a laser 310, 311, precipitation sensors 340, and/or cameras 320, 322 may be used to detect information such as the brightness of the road, variations in the brightness of the road, brightness of the world, current precipitation, as well as the detected height of the road. Information received from other sources such as networked based weather information (forecasts, radar, precipitation reports, etc.) may also be considered. The combination of the received and detected information may be used to estimate the probability of precipitation such as water, snow or ice in the roadway. This information may then be used to maneuver an autonomous vehicle 101 (for steering, accelerating, or braking) or identify dangerous situations.