Lane Directionality Assessment via Sensor Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing driver assistance systems face challenges in accurately determining whether a vehicle is on a directional lane due to outdated or inaccurate map data, temporary changes, and missing information, leading to erroneous localization and activation of assistance functions.

Innovation Solution

A method and device that assess the directionality of a roadway by combining inputs from camera-based, ultrasound, lidar, and radar systems, along with digital maps, to calculate a metric P, which weights environmental detection outputs based on vehicle speed, ensuring reliable detection and activation of assistance functions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If navigation systems use digital maps and GPS localization to determine whether the vehicle is on a directional lane, then the system can provide directional lane information, but the determination may be erroneous due to outdated or inaccurate map data, temporary changes, missing information, or inaccurate vehicle location

Engineering Contradiction:
Improvedirectional lane information accuracyVSAvoidlocalization reliability
Core Design Contradiction:
Loss of informationVSReliability

Solution Approach 1:

The patent combines multiple independent detection systems (camera-based detection, ultrasound detection, lidar detection, radar detection) with digital map data to form a fused assessment of directional lane status. Each detection system provides complementary information about the vehicle environment, and their outputs are integrated with GPS localization and map data to produce a more reliable determination than any single system could achieve alone. This multi-source fusion approach compensates for the weaknesses of individual systems and reduces errors from outdated or inaccurate data.

Inventive Principle:
Principle #5Merging (Combining)

2Device complexity

If the system relies on a single detection method to assess directional lanes, then the system complexity is reduced, but the accuracy and reliability of directional lane detection deteriorates

Engineering Contradiction:
Improvedetection system complexityVSAvoiddirectional lane detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent merges outputs from multiple detection systems (camera, ultrasound, lidar, radar) with digital map data and GPS localization. Each system detects different aspects of the environment, and their combined outputs provide comprehensive information for assessing directional lane status. This multi-system approach achieves high detection accuracy while managing complexity through integrated processing of diverse data sources.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If the system uses multiple detection systems and combines their outputs, then the reliability of directional lane detection is improved, but the device complexity increases

Engineering Contradiction:
Improvedirectional lane detection reliabilityVSAvoiddetection system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent integrates multiple detection systems (camera, ultrasound, lidar, radar) with digital map data and GPS localization into a unified assessment framework. The system processes outputs from all these sources simultaneously to determine directional lane status, achieving high reliability through multi-source validation while managing complexity through systematic data fusion and prioritization of detection outputs.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP2856452B1Carriageway recognition
Publication Date: 2019.08.21 BAYERISCHE MOTOREN WERKE AG
  • EP2856452B1 patent drawingFigure 1~2
  • EP2856452B1 patent drawingFigure 3
  • EP2856452B1 patent drawingFigure 4

AI summary

Disclosed is a method for providing an estimation as to whether a lane is directional or not, involving: establishing a measurement value if a measurement value is yet to be provided prior to performing the method (S401); receiving an output of a device for environment detection (302) of a vehicle, which is based on recognition of the environment at a point in time (S402); assigning a factor to the output, the factor also being based on the speed of the vehicle at a point in time that is assigned to the output (S403); mapping the output in an evaluation value according to a pre-defined mapping rule (S404); assigning the factor to the evaluation value (S405); calculating the measurement value on the basis of a sum that is based on the evaluation value which is weighted with the assigned factor, and on the previously calculated or established measurement value (S406); providing the measurement value (S407).