Radar Curb And Lane Feature Extraction for Adverse-Weather Localization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing localization systems in autonomous vehicles face challenges in accurately determining vehicle position, especially in adverse weather conditions, due to limitations of optical sensors like cameras and lidar, and GPS/IMU systems have low accuracy under certain conditions.

Innovation Solution

Utilizing radar to detect metallic particles in lane and curb markings, enabling precise localization by determining range and azimuth angles, which can be fused with GNSS or RTK information for enhanced positioning accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If optical sensors (cameras and lidar) are used for localization, then the system can detect lane markings and curb features, but the accuracy deteriorates in adverse weather conditions

Engineering Contradiction:

Improvelocalization accuracy in adverse weatherVSAvoiddetection accuracy of lane markings

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent replaces optical sensing mechanisms (cameras and lidar) with radar-based detection. Radar uses electromagnetic waves in the microwave frequency range, which are not scattered or absorbed by rain, fog, or snow in the same way optical signals are. This substitution enables reliable detection of metallic particles in lane markings and curb features under adverse weather conditions, resolving the contradiction between reliability and measurement precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If GPS/IMU systems are used for positioning, then the system can provide location data, but the accuracy is low under certain conditions

Engineering Contradiction:

Improvepositioning accuracyVSAvoidpositioning reliability under certain conditions

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent combines radar-based detection of lane markings and curb features with GPS/IMU positioning data. The radar system provides accurate relative position information by detecting metallic particles in road markings, while GPS/IMU provides absolute location data. By merging these complementary data sources, the system achieves high positioning accuracy and reliability even when GPS signal quality deteriorates, resolving the contradiction between measurement precision and reliability.

Inventive Principle:

Principle #5Merging (Combining)

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

Radar-based localization provides accurate vehicle positioning in adverse weather conditions, improving lane keeping and decision-making capabilities of autonomous vehicles by overcoming visibility limitations of optical sensors.

Implementation Method 1

radar to detect metallic particles in lane and curb markings

Methodology Applied

Scientific EffectRadar: Radar

Implementation Method 2

determining range and azimuth angles

Methodology Applied

Scientific EffectElectromagnetic radiation reflection: Reflection

Data Source

PatentUS12466427B2Curb-based feature extraction for localization and lane detection using radar

Publication Date: 2025.11.11 MOTIONAL AD LLC

AI summary

Provided are methods, systems, and computer program products for lane keep tracking and/or localization of a vehicle using a radar to detect metallic particles in paint applied to lane markings or curb markings. An example method may include: causing a radar system of a vehicle to output radio waves; receiving a radar image from the radar system corresponding to returned radio waves; determining a portion of the radar image includes lane or curb markings, wherein the lane or curb markings are embedded with metallic particles; and determining a location of the vehicle based at least in part on the determined portion of the radar image that includes the lane or curb markings.