Vehicle Control Grid Mapping for Clear Drivable Region Boundaries
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing in-vehicle control systems face challenges in accurately determining the traveling region of a vehicle due to the dispersion of detected objects, which leads to unclear boundary information and the need to avoid uncertain regions.
Innovation Solution
An in-vehicle control device that includes an object detection unit, an object information storage unit, an information processing unit, and a road surface region determination unit. The device generates a determination grid map by complementing object unoccupied regions with object occupied regions, and then determines a road surface region as a closed space surrounded by object occupied regions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If the occupied grid map is created by spreading the object occupied region according to the degree of intensity, then the contrast between occupied and unoccupied regions is improved, but the clarity of position information at the boundary is lowered
Solution Approach 1:
The patent divides the grid map processing into two distinct stages: first creating a pre-processing grid map with spread occupied regions for contrast enhancement, then generating a determination grid map that preserves boundary clarity. This segmentation allows each map to serve its specific purpose without compromising the other.
Solution Approach 2:
The determination grid map acts as an intermediary between the pre-processing grid map and the final traveling region determination. It receives the complemented occupied regions from the pre-processing map while maintaining clear boundaries, thereby mediating between the need for contrast enhancement and position precision.
2Loss of information
If the object occupied region is spread to clarify the contrast, then the occupied region becomes more distinct, but the traveling region must be set in a narrow area avoiding uncertain regions
Solution Approach 1:
The patent segments the grid map into pre-processing and determination stages, allowing the occupied region to be spread for distinctness in the first stage while preserving the original boundary information in the second stage to maximize traveling region area.
Solution Approach 2:
The patent applies different processing qualities to different parts of the grid map: the occupied regions are complemented and spread to enhance distinctness, while the boundary regions are preserved with high precision to ensure accurate traveling region determination and maximize available area.
3Loss of information
If the boundary of the traveling region is determined from the pre-processing grid map with spread occupied regions, then the contrast is improved, but the determination accuracy is reduced due to dispersion
Solution Approach 1:
The patent segments the processing into two maps: the pre-processing grid map provides contrast improvement through region spreading, while the determination grid map maintains boundary accuracy by using the complemented regions without further dispersion, allowing accurate boundary determination.
Solution Approach 2:
The patent creates a determination grid map that copies and complements the occupied regions from the pre-processing grid map, preserving the contrast enhancement benefits while maintaining the positional accuracy needed for precise boundary determination.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
The present invention clearly and easily determines the region in which a vehicle can travel without changing the clarity in the position information of the object detected by a sensor. An in-vehicle control device includes an object detection unit that detects a position of an object in front of an own vehicle from image information captured by an image pickup device, an object information storage unit that stores a pre-processing grid map in which a position where the object detection unit has detected an object is set as an object occupied region and a position where no object has been detected is as an object unoccupied region, an information processing unit that generates a determination grid map in which a part of the object unoccupied region of the pre-processing grid map is replaced with the object occupied region, and a road surface region determination unit that generates an automatic driving grid map in which a closed space surrounded by the object occupied region of the determination grid map is set as a road surface region.