Virtual Track Guidance for Vehicle Contour Localization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing navigation systems for driverless vehicles face challenges in reliability and robustness, particularly with contour-based localization methods, where map inaccuracies and environmental changes can lead to incorrect position estimation and navigation errors, which are often only noticed during productive use.

Innovation Solution

A method that evaluates the reliability of position and pose determination by comparing recorded contours with reference information, using a quality measure to identify potential navigation failures and allowing for early intervention, incorporating a virtual lane guidance system that learns from a physical track and uses contour detection sensors to correct vehicle pose along a predetermined trajectory.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If contour-based localization is used for navigation, then flexibility and freedom from physical tracks are improved, but reliability and robustness deteriorate due to map inaccuracies and environmental changes

Engineering Contradiction:
Improvenavigation flexibilityVSAvoidlocalization reliability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system performs preliminary actions by creating and storing reference contours during a learning phase before actual navigation. These reference contours are captured in advance and stored in memory, allowing the vehicle to compare current sensor readings against pre-established data during operation, thereby improving localization reliability without physical tracks.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback by continuously comparing current contour measurements with stored reference contours and using the comparison results to correct position and orientation estimates. This closed-loop feedback mechanism compensates for environmental changes and maintains reliable localization despite the flexibility of contour-based methods.

Inventive Principle:
Principle #23Feedback

2Ease of manufacture

If virtual lane guidance is implemented, then ease of track modification is improved, but navigation accuracy deteriorates when contour comparison fails

Engineering Contradiction:
Improvetrack modification easeVSAvoidposition estimation accuracy
Core Design Contradiction:
Ease of manufactureVSMeasurement precision

Solution Approach 1:

The system creates accurate copies of the physical track environment by capturing reference contours during a learning phase and storing them as virtual representations. These copied reference contours serve as the basis for virtual lane guidance, enabling easy track modifications through software updates without physical changes, while maintaining position estimation accuracy through precise contour matching.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system handles track modifications by changing parameters of the stored reference contours rather than physical track elements. When track modifications are needed, the reference contour data is updated with new measurements, and the vehicle adapts to the changed parameters through contour comparison, maintaining measurement precision while achieving ease of modification.

Inventive Principle:
Principle #35Parameter changes

3Extent of automation

If map data is used for position determination, then navigation autonomy is improved, but error accumulation deteriorates when contour comparison is ignored

Engineering Contradiction:
Improvenavigation autonomyVSAvoidposition determination reliability
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system maintains continuous contour comparison throughout navigation operation, rather than ignoring it during autonomous phases. By continuously comparing current contours with reference contours and correcting position estimates in real-time, the system prevents error accumulation while maintaining high navigation autonomy through the learned virtual track.

Inventive Principle:
Principle #20Continuity of useful action

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

This approach enhances navigation reliability by identifying weak points in localization before they affect operation, enabling proactive measures to improve system availability and maintaining navigation accuracy by displaying reliability measures and suggesting remedial actions.

Implementation Method 1

A contour detection sensor (14) detects a respective contour of a surrounding area of the vehicle

Methodology Applied
Scientific EffectLight reflection: Reflection

Implementation Method 2

A contour detection sensor (14) detects a respective contour of a surrounding area of the vehicle

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Data Source

PatentEP3875908B1Vehicle navigation and virtual track guidance device
Publication Date: 2022.02.23 SICK AG
  • EP3875908B1 patent drawingFigure 1~2.
  • EP3875908B1 patent drawingFigure 3~4
  • EP3875908B1 patent drawingFigure 5

AI summary

A method for navigating a vehicle (10) along a trajectory defined by a track (12) is described, in which a contour detection sensor (14) detects the contour of the vehicle's (10's) surroundings and determines the vehicle's (10's) position and/or pose based on this contour. A reliability measure is determined to assess the accuracy of the position and/or pose determination, and this reliability measure is assigned to a position along the track (12).