Region segmentation apparatus and method for map decomposition of robot

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing robot navigation systems struggle to effectively segment grid maps into regions, particularly in environments with complex graphic characteristics and obstacles, which hinders efficient cleaning or operation.

Innovation Solution

A region segmentation apparatus and method for map decomposition of a robot, which includes a map building unit and a region segmentation unit. The segmentation unit acquires critical points and lines based on obstacle distance maps and topologies, then segments the grid map into regions using these critical lines and inter-label connectivity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional region segmentation methods are used, then the segmentation process is simple, but the segmentation accuracy deteriorates in environments with complex graphic characteristics and obstacles

Engineering Contradiction:
Improveregion segmentation accuracyVSAvoidsegmentation process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the grid map into multiple regions by identifying critical points (obstacle endpoints and intersection points) and critical lines (tangent lines and bisector lines) that divide the space. This hierarchical segmentation approach improves segmentation accuracy by considering both obstacle positions and space division characteristics, resolving the contradiction between simple process and accurate segmentation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension of analysis by computing obstacle distance maps and considering the geometric relationships between obstacles and critical lines. This additional dimensional information (distance relationships and angular relationships) enables more accurate segmentation in complex environments without excessively increasing process complexity.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If region segmentation considers graphic characteristics and obstacles, then segmentation quality improves, but processing time increases

Engineering Contradiction:
Improvesegmentation qualityVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary computations by building an obstacle distance map before segmentation and pre-identifying critical points based on obstacle topology. This preliminary action prepares the data structure in advance, enabling faster and more accurate segmentation when processing complex environments, thus reducing the time penalty for high-quality segmentation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses the obstacle distance map as a computational copy that represents spatial relationships without requiring direct geometric calculations during segmentation. This copying approach allows the system to consider graphic characteristics and obstacles thoroughly while maintaining efficient processing by working with the pre-computed distance representation.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4063986B1Region segmentation apparatus and method for map decomposition of robot
Publication Date: 2025.05.07 MIELE & CO KG
  • EP4063986B1 patent drawingFigure 1
  • EP4063986B1 patent drawingFigure 2
  • EP4063986B1 patent drawingFigure 3

AI summary

The region segmentation apparatus and method for map decomposition of a robot according to the exemplary embodiment of the present disclosure segment the grid map into a plurality of regions in consideration of the graphic characteristic of the space and obstacles disposed in the space.