Occupancy Grid Route Control With Selective Obstacle Expansion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies for autonomously moving bodies often fail to prevent collisions with objects in their environment.
Innovation Solution
A control device that recognizes the position of objects around a moving body using image data, generates an occupancy grid diagram to map the environment, and expands regions around detected objects to generate a safe route for the moving body.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a moving body autonomously moves to a preset destination using conventional occupancy grid mapping, then the moving body can navigate the environment, but the moving body may come into contact with objects due to insufficient collision prevention
Solution Approach 1:
The occupancy grid is segmented into multiple regions based on distance from the moving body: a first region (closer) where objects are expanded by adding buffer grid cells, and a second region (farther) where objects are not expanded. This segmentation allows collision prevention to be applied selectively, improving reliability while managing complexity.
Solution Approach 2:
Different processing qualities are applied to different spatial locations. Objects in the first region receive expanded protection buffers, while objects in the second region maintain original boundaries. This local differentiation optimizes collision prevention where it matters most without unnecessarily complicating the entire occupancy grid.
2Reliability
If the occupancy grid diagram is expanded uniformly around all detected objects, then collision prevention is improved, but the route generation becomes less efficient due to increased computational load
Solution Approach 1:
The space around the moving body is segmented into a first region and a second region based on distance thresholds. Only objects in the first region undergo expansion processing, while objects in the second region are left unchanged. This selective approach maintains collision prevention effectiveness while significantly reducing computational load compared to uniform expansion.
Solution Approach 2:
Instead of applying expansion to all detected objects uniformly, the system applies partial expansion only to objects in the critical first region where collision risk is highest. This partial action approach provides sufficient protection without the excessive computational burden of processing every object equally.
Data Source
AI summary
A control device includes a recognition part that recognizes a position of an object present around a moving body based on an image obtained by imaging a state around the moving body, an occupancy grid diagram generation part that generates an occupancy grid diagram including a plurality of grid cells based on the position of the object present around the moving body, and a route generation part that generates a route, which the moving body follows, based on the occupancy grid diagram, and the occupancy grid diagram generation part determines whether the object is present for each of the plurality of grid cells in the occupancy grid diagram based on the position of the object present around the moving body, and the occupancy grid diagram generation part expands a first region including a grid cell in which it is determined that the object is present.