Localization Layer Alignment Feature Extraction for Automated Driving
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for creating digital localization maps for automated driving lack efficient mechanisms to detect and correct errors in the alignment between the localization and planning layers, which are crucial for accurate vehicle positioning and navigation, especially when layers from different manufacturers or sensor sets are used.
Innovation Solution
A method that involves extracting alignment features from the localization layer, designed to be structurally defined, pattern-based, or statistically derived, allowing for the detection of inadmissible deformations during alignment with the planning layer, thereby enabling error control and ensuring accurate digital localization maps without requiring a complete data set check.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to create digital localization maps without specific alignment detection mechanisms, then the map creation process is simpler, but alignment errors between localization and planning layers cannot be detected, leading to poor localization accuracy
Solution Approach 1:
The method extracts alignment features from the localization layer in advance, before the actual alignment process with the planning layer. This preliminary extraction of features such as road markings, intersections, and landmarks enables subsequent detection of alignment errors without requiring complex real-time analysis during the alignment process itself.
Solution Approach 2:
The method implements a feedback mechanism where alignment errors between the localization layer and planning layer are detected by comparing extracted alignment features. This feedback loop identifies inadmissible deformations and allows for correction, ensuring high localization accuracy while maintaining a manageable system through iterative refinement rather than complex one-step processing.
2Reliability
If complete data sets are checked for alignment accuracy, then alignment errors can be thoroughly detected, but computational complexity and processing time increase significantly
Solution Approach 1:
The method extracts only the essential alignment features from the complete localization layer data, such as key road markings, intersections, and prominent landmarks. This extraction process separates the critical alignment information from the complete dataset, enabling reliable error detection without the computational burden of processing all available data.
Solution Approach 2:
Instead of performing a complete check of all localization layer data for alignment accuracy, the method applies partial action by focusing only on the extracted alignment features. This selective approach provides sufficient reliability for detecting alignment errors while maintaining high productivity by avoiding unnecessary processing of redundant data.
3Adaptability or versatility
If layers from different manufacturers or sensor sets are used, then more data sources and better coverage are achieved, but alignment errors and deformations increase
Solution Approach 1:
The method uses extracted alignment features as intermediaries between the localization layer and planning layer from different sources. These features serve as common reference points that enable comparison and detection of alignment errors, facilitating the integration of data from multiple manufacturers or sensor sets while maintaining alignment precision through systematic error detection.
Data Source
AI summary
A method for forming a localization layer for a digital localization map for automated driving. The method includes: providing the localization layer for a defined region; providing a planning layer for the region; and extracting alignment features from the localization layer that is provided for an alignment with the planning layer, the alignment features being extracted in such a way from the localization layer that an inadmissible deformation of the localization layer may be recognized during the alignment of the planning layer with the localization layer.