Vehicle Self-Position Estimation Using Reliable Road Target Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-position estimation methods for autonomous vehicles are prone to errors due to calibration issues and unstable estimation results, particularly when detecting white lines, which reduces the accuracy of self-position estimation.
Innovation Solution
A self-position estimation method that detects relative positions between targets and the vehicle, stores and filters target position data based on reliability, and compares selected data with map information to estimate the vehicle's current position, using sensors like Laser Range Finders and cameras to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If both white lines are simultaneously detected for self-position estimation, then the vehicle position can be determined, but calibration errors cause steady offset in the detected positions reducing estimation accuracy
Solution Approach 1:
The patent extracts and eliminates unreliable target position data from the set of detected targets. By identifying and removing data with low reliability (such as white lines with calibration errors or inconsistent positions), the system prevents these erroneous measurements from degrading the overall self-position estimation accuracy, thus resolving the contradiction between using multiple targets and maintaining estimation reliability
Solution Approach 2:
The patent changes the parameter of target selection by introducing a reliability criterion. Instead of using all detected targets uniformly, the system evaluates each target's reliability based on detection consistency and calibration accuracy, then selects only those targets that meet the reliability threshold. This parameter change allows the system to maintain measurement precision while filtering out unreliable data that would otherwise reduce estimation stability
2Quantity of substance
If target position data with calibration errors is used, then more data is available for estimation, but the estimation accuracy is reduced due to steady offset errors
Solution Approach 1:
The patent introduces a reliability parameter to evaluate target position data quality. By changing from using all available data to using only data that meets reliability criteria, the system maintains sufficient data quantity for accurate estimation while eliminating data with calibration errors that would reduce precision
Solution Approach 2:
The patent applies different quality standards to different target position data based on their individual reliability characteristics. Rather than treating all data uniformly, the system evaluates each target's local quality (reliability) and selectively uses only those with high quality, thus maintaining overall estimation accuracy while utilizing available data
Data Source
AI summary
A self-position estimation method includes: detecting a relative position between a target present in surroundings of a moving object and the moving object; storing a position where the relative position is moved by the moved amount of the moving object, as target position data; selecting the target position data on the basis of reliability of the relative position of the target position data with respect to the moving object; and comparing the selected target position data with map information including the position information on the target present on a road or around the road, thereby estimating a self-position which is a current position of the moving object.