Point Cloud Filtering for Fresh HD Maps in Autonomous Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately navigating due to sensor limitations and outdated or inaccurate map data, which can lead to safety issues and inefficiencies in updating road information.
Innovation Solution
Generation of high-definition (HD) maps using sensor data from vehicles to create precise, up-to-date maps that include dynamic and static object identification, enabling efficient storage and low-latency navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional maps are created using survey teams with high resolution sensors, then map accuracy is improved, but the cost and time required to create and update maps increases significantly
Solution Approach 1:
The patent uses multiple vehicles equipped with sensors to collect map data, creating copies of the mapping function distributed across many units. This allows simultaneous data collection from multiple locations, dramatically increasing map update speed while maintaining accuracy through aggregation of data from numerous sensor sources.
Solution Approach 2:
The patent combines sensor data from multiple vehicles into a single consolidated map. By merging data streams from numerous sources, the system achieves both high accuracy (through data aggregation) and high productivity (through parallel data collection), resolving the contradiction between map quality and update speed.
2Area of stationary object
If GPS systems are used for location determination, then coverage area is improved, but location accuracy deteriorates to over 100 meters error
Solution Approach 1:
The patent combines GPS data with sensor-collected map data to create a hybrid positioning system. This merging allows the system to maintain GPS's broad coverage while achieving centimeter-level accuracy through sensor fusion, resolving the contradiction between wide coverage and precision location determination.
3Loss of time
If survey fleets with many cars are deployed to keep maps up to date, then map freshness is improved, but the complexity and cost of the system increases
Solution Approach 1:
The patent enables vehicles to automatically contribute their sensor data to map updates without requiring centralized coordination or special survey operations. This self-service approach allows continuous, automatic map refreshing using existing vehicle infrastructure, reducing system complexity while improving map freshness.
Data Source
AI summary
According to one or more embodiments, operations may relate to a point cloud being generated based at least on filtering out points from a first point cloud based at least on an analysis of which of the filtered out points correspond to respective points of one or more second point clouds different from the first point cloud.