Virtual Track Guidance for Vehicle Contour Localization
Find Innovative SolutionsGenerate 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
Engineering 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
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.
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.
2Ease of manufacture
If virtual lane guidance is implemented, then ease of track modification is improved, but navigation accuracy deteriorates when contour comparison fails
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.
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.
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
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.
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
Implementation Method 2
A contour detection sensor (14) detects a respective contour of a surrounding area of the vehicle
Data Source
Figure 1~2.
Figure 3~4
Figure 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).