Mobile-Body Position Estimation from Lane Division Endpoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing self-position estimation methods struggle to accurately specify the distance in the traveling direction of a vehicle using lane division lines, such as white lines, due to their continuous nature and varying lengths in the front-rear direction, leading to inaccuracies in position estimation.
Innovation Solution
A self-position estimation device that calculates a difference value between predicted and measured positions of lane division line end points, correcting the predicted position using a coefficient based on the interval of scanning positions, enhancing accuracy by adjusting the Kalman gain according to scanning position intervals and the number of detected scan lines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a continuously-provided structure such as a white line, a curbstone, and a guardrail is measured in the self-position estimation, then a distance in a lateral direction can be measured, but a distance in a traveling direction cannot be accurately specified
Solution Approach 1:
The patent extracts the end points of lane division lines from the continuous lane markings as discrete measurement targets. By focusing on these specific extracted features rather than the continuous line itself, the system can obtain precise position information in the traveling direction, resolving the contradiction between measuring lateral distance and specifying traveling direction position.
Solution Approach 2:
The patent segments the continuous lane division line into discrete end point features that can be independently measured and tracked. This segmentation allows the system to use these discrete points for accurate position estimation in the traveling direction, overcoming the limitation of continuous structures.
2Reliability
If a lane division line in a dashed line shape is used for position estimation, then the structure is detectable, but the length of the lane division line to be detected in a front-rear direction is changed, making the position in the traveling direction cannot be accurately specified
Solution Approach 1:
The patent performs preliminary identification and tracking of lane division line end points before using them for position estimation. By pre-establishing the positions and characteristics of these end points, the system can accurately specify traveling direction position even when the detected length of lane division lines varies, maintaining both detection reliability and measurement precision.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Improves the accuracy of self-position estimation in both lateral and traveling directions by refining the estimation process with coefficients tailored to scanning position intervals and detected lane division line characteristics.
Implementation Method 1
a measurement unit which is mounted on the mobile body and which measures the measured position by performing scanning at a plurality of scanning positions with a light in a predetermined direction
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A self-position estimation device is mounted on a mobile body and acquires a predicted position of the mobile body. Additionally, the self-position estimation device calculates a difference value between a predicted position of an end point of a lane division line that is obtained based on information on the end point of the lane division line acquired from map information and a measured position of the end point of the lane division line measured in such a manner that a measurement unit mounted on the mobile body performs scanning with a light in a predetermined direction. The self-position estimation device estimates a self-position of the mobile body by correcting the predicted position with a value obtained by multiplying the difference value by a coefficient. Further, the self-position estimation device corrects the coefficient based on an interval of scanning positions of the measurement unit at a position where the end point of the lane division line is detected.