Curve Alignment for Detecting Changes in Vehicle Map Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles rely on accurate and up-to-date pre-stored map information to navigate, but real-time changes in the environment can be difficult to detect and interpret, affecting the vehicle's ability to make safe driving decisions.
Innovation Solution
The vehicle's computing devices analyze detected objects by comparing their location coordinates to pre-stored map information, dividing curves into segments, and adjusting their positions based on tolerance constraints to determine the likelihood of changes, allowing for the identification of feature changes and updates in the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the vehicle uses pre-stored map information for navigation, then navigation accuracy is improved, but the ability to detect real-time environmental changes deteriorates
Solution Approach 1:
The system performs preliminary actions by dividing curves into line segments in advance and establishing tolerance constraints before comparison. This preprocessing enables efficient real-time detection by having the segmentation and constraint framework ready, allowing the system to quickly assess whether detected features match expected map features within acceptable tolerances.
Solution Approach 2:
The patent applies segmentation by dividing curves from map information into multiple line segments. This segmentation allows for more granular comparison with detected features, enabling the system to identify specific changes in the environment while maintaining overall navigation accuracy through systematic segment-by-segment verification.
2Measurement precision
If the vehicle divides curves into multiple line segments for comparison, then detection precision of feature changes is improved, but computational complexity increases
Solution Approach 1:
The patent divides curves into line segments to enable precise feature change detection. By breaking down complex curves into manageable segments, the system achieves high detection precision while keeping computational tasks manageable through systematic processing of individual segments rather than attempting to analyze entire curves at once.
Solution Approach 2:
The system applies local quality by establishing tolerance constraints specific to each line segment or group of segments. This allows the patent to apply different levels of scrutiny and tolerance to different portions of the environment, improving detection precision where needed while reducing computational complexity in areas with stable features.
3Reliability
If the vehicle applies tolerance constraints to line segments, then reliability of change detection is improved, but the system's responsiveness to actual changes may be reduced
Solution Approach 1:
The patent applies dynamics by making the tolerance constraints adaptive rather than fixed. The system can adjust tolerance levels based on the type of feature being detected and the confidence level of matches, allowing it to be more responsive to actual changes when confidence is low while maintaining reliability through stricter constraints when confidence is high.
Solution Approach 2:
The system changes parameters by adjusting tolerance constraint values based on feature types and detection confidence. This parameter adaptation allows the patent to balance reliability and responsiveness dynamically, tightening constraints to improve reliability for critical features while loosening them to maintain responsiveness for less critical changes.
Data Source
AI summary
Aspects of the disclosure relate to determining whether a feature of map information. For example, data identifying an object detected in a vehicle's environment and including location coordinates is received. This information is used to identify a corresponding feature from pre-stored map information based on a map location of the corresponding feature. The corresponding feature is defined as a curve and associated with a tag identifying a type of the corresponding object. A tolerance constraint is identified based on the tag. The curve is divided into two or more line segments. Each line segment has a first position. The first position of a line segment is changed in order to determine a second position based on the location coordinates and the tolerance constraint. A value is determined based on a comparison of the first position to the second position. This value indicates a likelihood that the corresponding feature has changed.