Vehicle Obstacle Mapping With Hierarchical Grid Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional technologies for mobile objects, such as vehicles, struggle to control movement accurately due to the inability to determine the presence or absence of obstacles beyond a certain area size, leading to inadequate navigation, especially in narrow spaces.
Innovation Solution
An information processing device that generates map information indicating the presence or absence of target objects and their detailed positions within areas, allowing for precise control of mobile object movement by setting areas to be avoided based on this information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If map information is generated using fixed-size grid areas to detect obstacles, then the detection process is simple and computationally efficient, but the movement control precision deteriorates because obstacle presence can only be determined at the area level rather than exact position
Solution Approach 1:
The patent divides the detection space into multiple grid areas and further segments each area containing a target object into multiple sub-areas. This hierarchical segmentation allows the system to maintain efficient broad-area scanning while achieving precise localization within specific regions by identifying which sub-areas contain target objects.
Solution Approach 2:
The patent transitions from detecting only the presence/absence of targets in grid areas to detecting detailed positional information by dividing areas into sub-areas. This adds a dimensional layer of precision to the map information, enabling the mobile object to navigate more accurately while maintaining the computational efficiency of grid-based detection.
2Measurement precision
If detailed position information of target objects is obtained by dividing areas into smaller sub-areas, then movement control precision is improved, but the device complexity and computational load increase
Solution Approach 1:
The patent applies segmentation by dividing the detection area into grids and further segmenting only those grids containing target objects into sub-areas. This selective segmentation reduces computational complexity compared to dividing the entire space, as processing is intensified only where necessary for precise navigation.
Solution Approach 2:
The patent implements local quality by applying detailed sub-area division only to specific areas where target objects are detected, rather than uniformly across the entire detection space. This allows high precision where needed while maintaining lower computational complexity in areas without targets.
3Productivity
If only the presence or absence of obstacles in grid areas is detected, then the information processing is simple and fast, but the navigation reliability deteriorates in narrow spaces where precise obstacle positioning is critical
Solution Approach 1:
The patent segments areas containing target objects into multiple sub-areas to determine detailed positions. This allows the system to maintain fast processing through efficient grid-based initial detection while achieving reliable navigation in narrow spaces by identifying precise obstacle locations through sub-area analysis.
Solution Approach 2:
The patent dynamically adjusts the level of detail in map information based on the situation. When target objects are detected in grid areas, the system dynamically generates more detailed map information by dividing those specific areas into sub-areas, allowing adaptive processing speed and reliability based on environmental complexity.
Data Source
AI summary
An information processing device includes processing circuitry. The processing circuitry obtain target information that indicates at least one of a distance to a target object or a position of the target object. The processing circuitry generate, based on the target information, map information of a space including a plurality of areas, the map information indicating presence or absence of the target object in a first area included in the plurality of areas, and a detailed position of the target object in the first area.