HD Map Point Annotation for Localization Usefulness
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional maps used by autonomous vehicles lack the precision and accuracy needed for safe navigation, as they are often outdated and created using expensive and time-consuming methods, and vehicle sensors may struggle to detect essential road features due to obstructions or limitations in detection range.
Innovation Solution
The development of high-definition (HD) maps that utilize data from autonomous vehicles themselves to create up-to-date, accurate representations of road conditions, with three-dimensional points annotated for their usefulness in localization, allowing for efficient storage and updating, and enabling safe navigation with low latency and high accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional map creation methods are used, then map data can be obtained, but the maps are outdated and lack precision and accuracy
Solution Approach 1:
The system enables autonomous vehicles to autonomously contribute their sensor data to update HD maps. Vehicles perform self-service mapping by capturing point cloud data during normal operation and automatically contributing it to the map updating process, eliminating the need for dedicated survey vehicles and ensuring maps remain continuously up-to-date with current road conditions
Solution Approach 2:
The system performs preliminary actions by pre-processing point cloud data to identify and annotate useful points before full map updates are performed. By pre-identifying localization-critical points and storing their usefulness measures, the system prepares data in advance for efficient map matching and updating operations
2Measurement precision
If all point cloud data is stored for localization, then localization accuracy improves, but storage requirements increase
Solution Approach 1:
The system extracts only the essential localization information from complete point cloud data by identifying and storing individual points with high usefulness measures. Instead of storing all point cloud data, it extracts and retains only the critical points that contribute most to localization accuracy, significantly reducing storage requirements while maintaining performance
Solution Approach 2:
The system applies local quality by annotating different points in the point cloud with different usefulness measures based on their individual contribution to localization. Rather than treating all points uniformly, it assigns higher importance weights to points that are more useful for localization (such as points on static structures) and lower weights to less useful points, enabling selective storage and processing
3Speed
If vehicle sensors are used to detect road features, then real-time data is obtained, but detection is limited by obstructions and range
Solution Approach 1:
The system merges data from multiple sources by combining real-time sensor data from autonomous vehicles with pre-existing HD map data. By fusing point cloud observations with map information, the system compensates for individual sensor limitations and obstructions, achieving more reliable and complete environmental perception than any single source could provide
Data Source
AI summary
According to an aspect of an embodiment, operations may comprise obtaining a first point cloud that includes a first point. The operations also comprises obtaining a second point cloud that is a copy of the first point cloud and that includes a second point that is a copy of the first point. The operations also comprises moving the second point cloud with respect to the first point cloud according to a first vector. The operations also comprises identifying a closest point of the first point cloud that is closest to the second point of the second point cloud. The operations also comprises determining a second vector between the closest point and the second point. The operations also comprises determining a measure of usefulness of the first point based on the first vector and the second vector. The operations also comprises indicating the measure of usefulness of the first point.