Lane Boundary Section Identification Using Orientation and Line Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing vehicle systems face challenges in accurately identifying sections belonging to a single lane boundary, especially in environments with construction sites or outdated high-definition maps, which hinders driver assistance systems and navigation.

Innovation Solution

A method that captures section information of lane boundaries, determines orientation relative to a reference line, and uses a line determination algorithm to verify if sections are aligned within a tolerance range, identifying sections as belonging to one lane boundary only if they are coincidentally oriented and aligned.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If multiple sections of lane boundaries are detected from sensor data or maps, then the vehicle can identify lane boundaries even in complex environments, but it becomes difficult to determine which sections belong to the same lane boundary

Engineering Contradiction:
Improvelane boundary identification reliabilityVSAvoidsection allocation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the lane boundary identification process into distinct steps: first detecting individual sections independently, then allocating them to lane boundaries based on geometric relationships. This segmentation allows complex detection to be broken down into manageable processing stages, resolving the contradiction between reliable identification and processing complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces orientation information as an additional dimension for section allocation. By considering not only spatial position but also orientation relative to a reference line, the system can reliably determine which sections belong to the same lane boundary. This dimensional addition transforms the allocation problem from a purely spatial matching task to a geometric relationship assessment, improving reliability while providing clear allocation criteria.

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

2Adaptability or versatility

If the vehicle detects lane boundaries in environments with construction sites or outdated maps, then it can adapt to short term changes, but the accuracy of identifying sections belonging to one lane boundary decreases

Engineering Contradiction:
Improveenvironmental adaptabilityVSAvoidsection orientation measurement precision
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent performs preliminary detection of individual lane boundary sections before attempting to allocate them to complete lane boundaries. This preliminary action allows the system to capture all available section information from sensor data and maps, then systematically allocate them using geometric criteria. This approach maintains adaptability to environmental changes while improving measurement precision through structured processing.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces orientation information as an intermediary criterion for allocating sections to lane boundaries. This intermediary measurement helps bridge the gap between detecting scattered sections and forming complete, accurate lane boundary representations. By using orientation as a mediating factor, the system can adapt to environmental changes while maintaining precision in identifying which sections belong together.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If the vehicle uses orientation information and line determination algorithms to verify section alignment, then section allocation accuracy improves, but computational complexity increases

Engineering Contradiction:
Improvesection alignment precisionVSAvoidcomputation algorithm complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the computational process into distinct algorithmic steps: determining orientation information for each section, comparing orientations to identify candidate sections, and verifying alignment using line determination algorithms. This segmentation of computation allows the system to achieve high precision while managing complexity through structured processing stages rather than monolithic computation.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4475093A1Method for identifying sections belonging to one lane boundary of a lane of a road
Publication Date: 2024.12.11 VOLKSWAGEN AG
  • EP4475093A1 patent drawingFigure 1~2
  • EP4475093A1 patent drawingFigure 3
  • EP4475093A1 patent drawingFigure 4

AI summary

The invention relates to a method for identifying sections (13) belonging to one lane boundary (10) of a lane (11) on a road (12) comprising: providing (S3) multiple section information (22) each describing a section (13); for each section information (22) determining (S4) an orientation information (28) describing an orientation of the section (13) relative to a reference line (26); if the orientation information (28) of at least three adjacent sections (23, 24, 25) coincide within a tolerance range (29), verifying (S6) if these sections (23, 24, 25) are all on one line by applying a line determination algorithm (30) on the section information (22); only if the sections (23, 24, 25) are all on one line, identifying (S7) the sections (23, 24, 25) as belonging to one lane boundary (36); providing (S8) a lane boundary information (37) that describes the one lane boundary (36).