Occupancy Grid Control Using Chromaticity and Elevation Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for updating occupancy grids in mobile industrial robots are inefficient, particularly when dealing with complex environments containing objects of varying heights, transparent or reflective surfaces, and dark objects, which can lead to inaccurate navigation and potential collisions.
Innovation Solution
The method involves using a color-depth sensor to generate an occupancy grid by identifying globally dominant chromaticity values and combining them with elevation data to determine the occupancy status of cells, thereby reducing the time required to generate an accurate occupancy grid.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional occupancy grid updating methods are used, then the robot can navigate environments, but the processing time is excessive and accuracy is reduced for complex objects
Solution Approach 1:
The patent segments the occupancy grid update process into distinct phases: processing dominant chromaticity values separately from elevation data. By dividing the complex environment into chromaticity-based regions and then applying elevation filtering, the system achieves both speed and accuracy without processing all data points uniformly
Solution Approach 2:
The patent changes the parameter representation by using chromaticity values (color space parameters) instead of raw RGB values. This transformation enables more efficient comparison and grouping of similar surfaces, reducing processing time while maintaining accuracy for identifying objects with varying heights and materials
2Measurement precision
If detailed sensor data is processed for all cells, then accuracy improves, but processing complexity and time increase significantly
Solution Approach 1:
The patent extracts and processes only the most relevant features (dominant chromaticity values and elevation data) rather than analyzing all sensor data for every cell. This selective extraction reduces processing complexity while maintaining detection accuracy by focusing computational resources on discriminative features
Solution Approach 2:
The patent performs preliminary processing by identifying dominant chromaticity values and filtering elevation data before final occupancy determination. This preliminary action prepares the data in advance, reducing the complexity of the final decision-making process and enabling faster, more accurate occupancy grid generation
Data Source
Figure 1~3
Figure 2
Figure 4~5
AI summary
A robot (210) movable on a substrate (220) is controlled on the basis of an occupancy grid (230) of cells (231), where each cell is associated with an occupancy probability that some physical object (240, 241, 242) is present in the cell. From an elevation map and a chromaticity map, an occupancy probability may be assigned as follows: a first partial occupancy probability px is derived from a mean elevation of each cell; a distribution of the chromaticity is estimated and dominant chromaticity values are identified; a rule is applied that assigns a lower second partial occupancy probability p2 to a cell when the chromaticity of the cell if its chromaticity is one of dominant chromaticity values in the chromaticity map; and the occupancy probability is obtained by merging the first and second partial occupancy probabilities.