Weighted Map Data for Stable Autonomous Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicle localization faces challenges due to environmental changes, where maps may need frequent updates and unstable objects like vegetation can decrease alignment operation accuracy, leading to potential failures.
Innovation Solution
The method involves selectively weighting map data units describing geometric elements in an autonomous vehicle's environment, emphasizing more stable objects like roadways and buildings over less stable ones like vegetation, to improve alignment operation performance and availability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If alignment operations use all map data units equally, then the localization process is simple, but the accuracy decreases due to unstable objects like vegetation
Solution Approach 1:
The patent applies local quality by assigning different weights to different map data units based on their stability characteristics. Stable geometric elements (roadways, buildings) receive higher weights while unstable elements (vegetation) receive lower weights. This differential weighting approach improves localization accuracy by emphasizing reliable features without requiring complete system redesign.
2Reliability
If maps are updated frequently to account for environmental changes, then the localization remains accurate, but the time and resources required increase
Solution Approach 1:
The patent implements preliminary action by pre-classifying map data units into stable and unstable categories during map creation or maintenance phases. This advance classification allows the alignment algorithm to automatically prioritize stable features without requiring frequent manual map updates, thereby maintaining localization reliability while reducing the frequency and resource requirements of map maintenance.
3Productivity
If the alignment operation considers all geometric elements, then the process is straightforward, but it fails when unstable objects change significantly
Solution Approach 1:
The patent applies parameter changes by introducing a weight parameter that modulates the influence of each map data unit during alignment operations. By dynamically adjusting these weights based on stability characteristics, the system maintains high alignment success rates even when unstable objects change, while avoiding the need for complex alternative alignment strategies.
4Measurement precision
If stable geometric elements are emphasized in alignment, then the localization accuracy improves, but the system becomes more complex
Solution Approach 1:
The patent implements segmentation by dividing the map data into distinct stable and unstable geometric element categories. This segmentation allows the alignment algorithm to process different types of features with appropriate weights, improving accuracy while keeping the processing framework manageable through clear categorization rather than requiring complex continuous analysis.
Data Source
AI summary
Map data describing various geometric elements in a map used in autonomous vehicle localization is selectively weighted to vary the relative contributions of different geometric elements to an alignment operation. By doing so, the alignment operation may be biased to emphasize geometric elements associated with objects in an environment that are relatively more stable, e.g., roadways, walls, buildings, etc., over objects that are relatively less stable, e.g., vegetation, thereby in many instances improving alignment operation performance and/or availability.