Automated Driving Lane Detection Using Distance-Based Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing automated driving systems face challenges in reducing the risk of incorrect lane changes, particularly due to camera malfunctions or temporary lane misinterpretations, which can lead to unsafe driving decisions.

Innovation Solution

A method utilizing a camera and evaluation unit to observe lane changes over a specified distance before adopting a new lane, with adjustable distances based on road marking types and vehicle speed, ensuring reliable lane detection even with failure of other sensors or digital maps, and storing previously determined lanes for context awareness.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If the system immediately adopts a new lane when lane markings change, then the responsiveness to actual lane changes is improved, but the risk of incorrect lane changes due to camera malfunctions or temporary markings increases

Engineering Contradiction:
Improveresponsiveness to lane changesVSAvoidaccuracy of lane detection
Core Design Contradiction:
SpeedVSReliability

Solution Approach 1:

The system performs preliminary verification by monitoring lane markings over a predetermined distance before adopting a new lane. This preliminary action allows the system to distinguish between temporary markings and permanent lane changes, reducing false detections while maintaining responsiveness to actual lane changes.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors lane markings and provides feedback by comparing detections over a predetermined distance. This feedback mechanism confirms whether a lane marking change is permanent before executing a lane change, thereby improving reliability without sacrificing responsiveness.

Inventive Principle:
Principle #23Feedback

2Reliability

If the system monitors lane markings over a long predetermined distance, then the reliability of lane detection is improved, but the time required to detect and respond to lane changes increases

Engineering Contradiction:
Improveaccuracy of lane detectionVSAvoidtime to detect lane changes
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system dynamically adjusts the predetermined monitoring distance based on vehicle speed and lane marking type. At higher speeds, the monitoring distance is extended to maintain reliability, while at lower speeds, it can be reduced to minimize time loss. This parameter adaptation resolves the contradiction between reliability and time efficiency.

Inventive Principle:
Principle #35Parameter changes

3Device complexity

If the system uses a fixed monitoring distance for all lane markings, then the system complexity is reduced, but the accuracy decreases when dealing with different lane marking types and speeds

Engineering Contradiction:
Improvesimplicity of monitoring systemVSAvoidaccuracy of lane detection
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The system transitions from a static monitoring distance to a dynamic one that adapts based on vehicle speed and lane marking characteristics. This dynamic adjustment maintains system simplicity while significantly improving detection accuracy for different driving conditions and marking types.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3590791B1Method and device for automated driving of a motor vehicle
Publication Date: 2022.07.20 VOLKSWAGEN AG
  • EP3590791B1 patent drawingFigure 1~2

AI summary

The invention relates to a method and a device (1) for the automated driving of a motor vehicle (20), comprising at least one camera (2) and an evaluation unit (3) for evaluating the data captured by the camera (2), wherein the camera is configured such that lane markings (14, 15, 16, 18, 19) are captured by means of the camera (2) and the evaluation unit (3) is configured such that lanes (11, 12, 13) are determined from the captured data of the camera (2), the evaluation unit (3) is configured such that changes in the lane markings (14, 15, 16, 18, 19) that would lead to the determination of a new lane (17) are observed over a predetermined distance (dgrenz1, dgrenz2), wherein the new lane (17) is only adopted if the changed lane marking (14, 15, 16, 18, 19) is observed over a predetermined distance (dgrenz1, dgrenz2). The specified distance (dgrenz1, dgrenz2) was recorded.