Vehicle Position Validation via Map-Sensor Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle positioning systems face errors and inaccuracies due to noisy sensor data and complex measurement conditions, which can compromise safety during autonomous or highly automated driving.
Innovation Solution
A computer-implemented method using a digital map and multiple statistically independent validators to validate vehicle position estimates by comparing sensor-detected features with expected map features, ensuring low statistical uncertainties and minimizing false positives through feature grouping and rejection based on predetermined criteria.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If validation is performed using sensor data and digital maps to confirm vehicle position, then the reliability of position determination is improved, but the statistical uncertainty of validation remains high due to ambiguous feature assignments
Solution Approach 1:
The patent segments the validation process into multiple independent validators, each responsible for validating specific features or aspects of the vehicle position. This segmentation allows each validator to operate with reduced statistical uncertainty while collectively providing comprehensive validation coverage, thereby improving overall reliability without propagating high uncertainty across all validation dimensions.
Solution Approach 2:
The patent introduces an intermediary feature assignment mechanism that mediates between sensor-detected features and digital map features. This intermediary layer resolves ambiguities by establishing statistically significant correspondences between features, reducing the statistical uncertainty in validation while maintaining high reliability through rigorous comparison protocols.
2Reliability
If multiple validators are used to assess position validity, then the reliability is improved, but the complexity of the validation system increases
Solution Approach 1:
The validation system is segmented into multiple independent validators, each handling specific validation tasks. This modular segmentation improves reliability through redundancy and specialized focus while managing complexity by dividing the overall system into manageable, independently developable components that can be optimized separately.
Solution Approach 2:
The patent designs validators with universal applicability across different validation scenarios and feature types. Each validator is constructed to handle multiple related validation tasks, reducing the need for highly specialized components and thereby managing system complexity while maintaining high reliability through multi-functional validation capabilities.
3Quantity of substance
If features with large lateral extent are included in validation, then more map features can be used for comparison, but the number of false positives increases due to ambiguous assignments
Solution Approach 1:
The patent applies local quality by evaluating features based on their specific spatial characteristics and contextual properties. Features are selectively included in validation based on their local suitability, where features with large lateral extent are scrutinized through localized validation criteria that account for their ambiguous nature, thereby reducing false positives while maximizing the use of available features.
Solution Approach 2:
An intermediary validation mechanism is introduced that mediates between the quantity of available features and the reliability of validation results. This intermediary layer filters and prioritizes features based on their discriminative capability, allowing maximum feature utilization while preventing ambiguous features with large lateral extent from causing false positives through rigorous intermediate validation checks.
Data Source
AI summary
A method for determining the validity of an estimated position of a vehicle includes receiving the estimated position; receiving sensor information relating to a vehicle environment; detecting a number of first features in the digital map and a number of second features in the sensor information, wherein the features indicate at least one object beside a road; grouping the first features into a number of first feature groups and grouping the second features into a number of second feature groups; rejecting first and/or second feature groups; assigning at least some of the first feature groups which have not been rejected to a particular second feature group which has not been rejected; and determining the validity of the estimated position based on a comparison of positions of a number of the first feature groups which have not been rejected with positions of the respectively assigned second feature groups.