Robot Map Editing for Moving Obstacle Contour Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing robot mapping technologies generate raw maps with significant noise and inaccurate obstacle contours, requiring manual correction that is time-consuming and costly, often leading to inefficient robot operation.
Innovation Solution
A computer-implemented method and system for automating the editing of raw maps by identifying pixels as moving or fixed obstacles based on color and size, performing dilation and erosion operations, and specifying polygon-based contours to accurately remove noise and correct obstacle boundaries.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual modification is used to correct raw map, then map accuracy is improved, but time consumption and cost increase significantly
Solution Approach 1:
The system performs self-correction by automatically identifying and removing noise pixels, correcting obstacle contours, and classifying obstacles without human intervention. The robot autonomously processes raw map data to generate corrected maps, eliminating the need for manual modification while maintaining high accuracy.
Solution Approach 2:
Manual mechanical editing operations are replaced with automated image processing algorithms. The system uses pixel analysis, contour detection, and classification algorithms to perform corrections that previously required human operators, dramatically reducing time consumption while maintaining or improving accuracy.
2Productivity
If raw map is used as is, then processing time is reduced, but map quality and robot operation efficiency deteriorate
Solution Approach 1:
The system performs preliminary correction of the raw map during the mapping process itself. By automatically removing noise, correcting contours, and classifying obstacles in real-time or near-real-time, the map is prepared for robot navigation before the robot begins its task, ensuring both speed and reliability.
Solution Approach 2:
An automated map correction system acts as an intermediary between raw sensor data and robot navigation. This intermediate processing layer filters out noise, corrects contours, and classifies obstacles, providing clean, reliable map data to the navigation system without significantly delaying processing.
3Measurement precision
If manual noise removal is performed, then map quality is improved, but labor cost and effort increase
Solution Approach 1:
The system autonomously identifies and removes noise pixels through automated algorithms that analyze pixel characteristics such as color, size, and spatial distribution. This self-service capability eliminates the need for human operators to manually inspect and remove noise, dramatically reducing labor costs while maintaining high removal accuracy.
Solution Approach 2:
Manual visual inspection and editing operations are replaced with automated image processing algorithms. The system uses pixel analysis, pattern recognition, and classification to identify and remove noise, performing corrections that previously required human operators at significantly lower cost.
4Device complexity
If moving obstacles are not distinguished from fixed obstacles, then map generation is simpler, but robot navigation accuracy deteriorates
Solution Approach 1:
The system segments obstacles into distinct categories (moving vs. fixed) based on pixel analysis and motion detection. By dividing the obstacle detection task into separate classification stages, the system accurately distinguishes between different obstacle types without overwhelming complexity, enabling precise robot navigation.
Solution Approach 2:
The system uses parameter changes in pixel characteristics (such as color, size, and temporal variations) to differentiate between moving and fixed obstacles. By monitoring how obstacle parameters change over time, the system automatically classifies obstacles without requiring complex manual configuration.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
According to one aspect of the invention, there is provided a method for generating a map for a robot, the method comprising the steps of: acquiring a raw map associated with a task of the robot; identifying pixels estimated to be a moving obstacle in the raw map, on the basis of at least one of colors of pixels specified in the raw map and sizes of areas associated with the pixels; and performing dilation and erosion operations on the pixels estimated to be the moving obstacle, and determining a polygon-based contour of the moving obstacle.