Vehicle LiDAR Road Boundary Detection Grid Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Inaccurate object detection by LiDAR systems can compromise the reliability and safety of autonomous driving, particularly in determining road boundaries, due to point noise and errors from moving objects, reflection distance, and angle.
Innovation Solution
A vehicle LiDAR system and object detection method that sets grids based on lane width, calculates road boundary candidates using occupation percentages and freespace point data, and corrects road boundary information using previous time point data and lateral speed, reducing errors by identifying static and moving objects and refining road boundary detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If LiDAR sensor is used to obtain surrounding object information, then autonomous driving function is assisted, but detection accuracy decreases due to point noise and errors from moving objects, reflection distance, and angle
Solution Approach 1:
The patent segments the detection space into multiple lanes based on lane width, and further divides each lane into longitudinal grids. This segmentation allows the system to process and analyze point cloud data in smaller, manageable regions, improving measurement precision by focusing computational resources on specific areas where road boundaries need to be detected.
Solution Approach 2:
The patent applies local quality by calculating occupation percentages of objects within each lane grid and analyzing freespace point data distributions specifically in boundary regions. By treating different spatial regions with different analysis methods (e.g., focusing on static objects in lane grids near boundaries), the system improves detection accuracy in critical areas without compromising overall system reliability.
2Measurement precision
If road boundary detection is performed using traditional LiDAR methods, then basic navigation is achieved, but detection accuracy decreases due to errors from moving objects and environmental factors
Solution Approach 1:
The patent performs preliminary actions by first setting up lane grids and identifying static objects before detecting road boundaries. By pre-processing the point cloud data to filter out moving objects and establish a stable reference frame using static objects, the system reduces the impact of environmental factors on boundary detection accuracy.
Solution Approach 2:
The patent uses feedback by calculating occupation percentages of objects in each lane grid and using this information to identify potential road boundary regions. The system continuously monitors the distribution of freespace point data and adjusts boundary detection based on the accumulated information from multiple measurements, improving precision while managing complexity through iterative refinement.
3Measurement precision
If occupation percentages and freespace point data are analyzed to calculate road boundary candidates, then detection accuracy improves, but computational complexity increases
Solution Approach 1:
The patent segments the computational task by dividing the detection area into lanes and further into longitudinal grids. Instead of analyzing the entire point cloud at once, the system calculates occupation percentages within each small grid cell, significantly reducing the computational power required while maintaining high measurement precision for road boundary detection.
Solution Approach 2:
The patent applies partial action by focusing computational resources only on lane grids that are likely to contain road boundaries, identified through the occupation percentage analysis. Rather than processing all possible regions equally, the system concentrates computational power on critical areas where boundary detection is most needed, improving efficiency without sacrificing accuracy.
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
The method effectively reduces errors in road boundary detection, improving the accuracy and confidence of road boundary information, thereby enhancing the reliability of autonomous driving systems.
Implementation Method 1
A Light Detection And Ranging (LiDAR) has been developed in the form of constructing topographic data
Implementation Method 2
obtain information on a surrounding object, such as a target vehicle, by using a LiDAR sensor
Data Source
AI summary
An object detection method of a vehicle LiDAR system includes setting grids including a host vehicle lane according to a lane width on a grid map which is generated based on freespace point data and object information, and calculating a road boundary candidate based on occupation percentages of objects by lane calculated based on the object information and distributions of the freespace point data; and outputting road boundary information by correcting the calculated road boundary candidate based on information on a road boundary candidate determined at a previous time point.