Point Cloud Map Change Point Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for estimating self-position using map information are prone to reduced accuracy when the actual situation differs from the map information, and they lack effective techniques to identify change points where the map information is outdated.
Innovation Solution
An estimation apparatus that acquires point cloud data and map information, divides the data into regions, calculates association ratios between data points and map information, and identifies change points by analyzing the correlation between shifted ratio values in different regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If point cloud data is collated with map information to estimate self-position, then position estimation is achieved, but accuracy is reduced when actual situation differs from map information
Solution Approach 1:
The system performs preliminary detection of change points by analyzing associations between point cloud data and map information before final position estimation. By identifying regions where the map information diverges from actual situation in advance, the system can exclude these unreliable regions from position calculation, thereby maintaining high accuracy even when map information is outdated in certain areas.
2Ease of operation
If map information is used for position estimation, then estimation can be performed, but change points where map information is outdated cannot be identified
Solution Approach 1:
The system establishes a feedback mechanism where association results between point cloud data and map information are continuously analyzed to detect change points. The association ratio and correlation strength serve as feedback signals that indicate whether map information accurately reflects the actual situation. When degradation is detected, the system adjusts its position estimation strategy by excluding unreliable map regions, thus maintaining operational capability while identifying information loss.
3Measurement precision
If association ratio is calculated for each region, then change point detection is enabled, but computational complexity increases
Solution Approach 1:
The system segments the point cloud data and map information into multiple regions, calculating association ratios independently for each region. This segmentation approach enables parallel processing of different spatial areas, reducing the computational burden on single processors. By dividing the large-scale data processing task into smaller regional units, the system achieves accurate change point detection across the entire environment while managing computational complexity through distributed calculation.
Data Source
AI summary
The first acquisition unit (110) acquires point cloud data at a plurality of timings obtained by a sensor mounted on a moving body. A second acquisition unit (130) acquires map information. The division unit (150) divides each point cloud data item acquired by the first acquisition unit (110) into a plurality of predetermined regions. The ratio value calculation unit (170) calculates, for a first region and a second region different from the first region, a ratio value indicating an association ratio between each data point and the map information in each region. The estimation unit (190) identifies an estimated change point where a content of the map information is estimated to be different from an actual situation, using a strength of a correlation between a ratio value of the first region shifted in time or position and a ratio value of the second region.