Landmark Position Correction in Point Cloud Self-Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional self-position estimation techniques for automatic driving systems suffer from reduced accuracy due to large observation errors in landmark detection, which are not adequately addressed by existing methods.
Innovation Solution
A self-map generation device that includes a landmark detection unit, a landmark information accumulation unit, a landmark position correction unit, and a self-map generation unit to correct landmark positions based on error distribution, thereby improving the accuracy of self-position estimation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional self-position estimation techniques are used, then the system can operate in various environments, but the accuracy of self-position estimation becomes insufficient when the observation error of the landmark is large
Solution Approach 1:
The system performs frequency distribution of observation position information to detect error distributions, then uses this feedback to correct landmark positions. The correction amount is calculated based on the detected error distribution characteristics, creating a closed-loop feedback mechanism that continuously improves estimation accuracy despite initial observation errors.
Solution Approach 2:
The system changes the parameter representation of landmark positions by introducing correction amounts based on error distribution analysis. Instead of using raw observation positions directly, the system transforms them into corrected positions by applying parameter adjustments derived from frequency distribution patterns, thereby improving measurement precision.
2Manufacturing precision
If landmarks are registered on the map with high accuracy for automatic driving, then the quality of self-generated map improves, but the complexity of the system increases due to error distribution analysis and correction processes
Solution Approach 1:
The system performs self-correction by automatically analyzing its own observation errors through frequency distribution and autonomously correcting landmark positions based on detected error patterns. This self-service mechanism eliminates the need for external manual correction processes while maintaining high map quality, thereby managing system complexity through automation rather than human intervention.
Solution Approach 2:
The system performs preliminary error distribution analysis and landmark position correction during the map generation process itself, rather than as a separate post-processing step. By integrating the correction action into the primary workflow, the system achieves high map quality without requiring additional complex external correction systems.
Data Source
AI summary
Provided are a self-map generation device and a self-position estimation device with which it is possible to achieve high-accuracy self-position estimation even when an observation error due to a sensor is large by estimating an error amount of a landmark serving as an observation point and improving the quality of a self-generated point group map. This self-map generation device generates a point group map from point group data of external information obtained by a vehicle-mounted sensor mounted in a vehicle, and comprises: a landmark detection unit that detects a landmark from the point group map; a landmark information accumulation unit that accumulates observation position information of the detected landmark; a landmark position correction unit that corrects the position of the landmark on the basis of point group coordinates extracted from an error distribution detected when the observation position information of the landmark has been frequency-distributed; and a self-map generation unit that saves, as a self-generated map, a corrected map obtained by correcting the position of the landmark and obtained from the landmark position correction unit.