Geographic Feature Weighting for Autonomous Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining their location due to environmental conditions such as weather and road construction, which affect the matching process of geographic features with virtual maps.
Innovation Solution
The system identifies and associates geographic features with horizontal or vertical spaces and applies weights to these features based on their space association during comparison with a geographic feature map, accounting for environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If geographic features are matched with virtual maps for vehicle localization, then vehicle position determination is achieved, but accuracy deteriorates under environmental conditions such as weather and road construction
Solution Approach 1:
The patent applies local quality by assigning different weights to different geographic features based on their space association. Vertical space features (e.g., buildings, poles) are given higher weights than horizontal space features (e.g., road markings, curbs) because vertical features are less affected by environmental conditions like weather and road construction. This differential weighting strategy resolves the contradiction by maintaining localization accuracy through selective reliance on more reliable features under adverse conditions.
Solution Approach 2:
The patent implements parameter changes by dynamically adjusting the weights of geographic features based on environmental conditions. The system modifies the importance parameters of different features according to their space association and current environmental context, allowing the localization system to adapt to changing conditions and maintain reliable position determination despite weather or construction impacts.
2Measurement precision
If all geographic features are treated equally in the matching process, then the system is simple to implement, but localization accuracy deteriorates under adverse environmental conditions
Solution Approach 1:
The patent resolves this contradiction by introducing a structured weighting system that assigns different importance levels to features based on their space association. While this increases system complexity, it significantly improves localization accuracy by differentiating between vertical and horizontal features. The complexity is managed through systematic classification rather than ad-hoc adjustments, making the system both accurate and implementable.
Solution Approach 2:
The patent applies dynamics by making the feature weights adjustable and adaptable based on environmental conditions. The system transitions from static equal weighting to dynamic weighted evaluation, allowing it to respond to changing conditions while maintaining a manageable level of complexity through automated weight adjustment based on space association rules.
3Reliability
If vertical space features are prioritized in the matching process, then reliability under environmental conditions improves, but the system becomes more complex
Solution Approach 1:
The patent resolves this contradiction by implementing a clear classification system that categorizes features into vertical and horizontal spaces. This structured approach prioritizes vertical features for improved reliability while managing complexity through systematic classification rules. The space association concept provides a straightforward framework for differentiation without requiring complex analysis.
Data Source
AI summary
A system, device, and methods for autonomous navigation using geographic feature-based localization. An example method includes identifying one or more geographic features based on information received from one or more sensors disposed on a vehicle as the vehicle traverses a route and associating one of a horizontal space and a vertical space with each of the one or more geographic features. The example method further includes comparing the one or more geographic features to a geographic feature map and generating a localized vehicle position based on the comparison between the one or more geographic features and the geographic feature map. Comparing the one or more geographic features to the geographic feature map can include applying weights to the one or more geographic features based in part on the space association for each of the one or more geographic features.