Robot Edgewise Walking Termination Using Map Contour Unit Regions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for controlling robot edgewise walking termination are inefficient due to cumulative sensor errors and complex room layouts, leading to repeated sweeping and reduced working efficiency.

Innovation Solution

A map region contour-based setting method is employed, where a robot acquires a map of the working region and sets rectangular regions around corner points to define unit regions for edgewise walking. The robot then determines whether to stop edgewise walking by checking if it has covered all or repeatedly walked through a set of these unit regions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a robot learns to recognize objects and determine their placement positions through repeated learning, then the robot can adapt to various objects, but the time required for learning increases and productivity decreases

Engineering Contradiction:
Improverobot adaptability to various objectsVSAvoidlearning time
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary actions by pre-acquiring three-dimensional map data of the storage location and processing it into contour information before the robot begins its learning process. This pre-processing of spatial information allows the robot to start with a head start, reducing the time needed to learn object placements by having environmental context already available.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a simplified copy of the complex three-dimensional environment by generating two-dimensional contour maps that represent the essential spatial features. This contour map serves as a simplified representation that the robot can process more efficiently than full three-dimensional data, enabling faster learning while maintaining adaptability to different objects and locations.

Inventive Principle:
Principle #26Copying

2Measurement precision

If the robot learns by repeatedly observing object placements, then the robot can improve its recognition accuracy, but the learning process takes excessive time

Engineering Contradiction:
Improveobject recognition accuracyVSAvoidlearning duration
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary processing of the storage location into contour information before the robot begins learning. This pre-acquisition and pre-processing of spatial data provides the robot with immediate contextual information, allowing it to achieve accurate object recognition without requiring extensive repeated observation and learning trials.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system transforms the three-dimensional spatial information into two-dimensional contour parameters, changing the dimensional representation to create a more efficient data structure for learning. This parameter transformation from 3D to 2D contour maps reduces the complexity of information the robot must process, enabling faster acquisition of recognition accuracy.

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If the robot uses complex three-dimensional map data for learning, then the robot can achieve accurate spatial understanding, but the processing time and computational load increase

Engineering Contradiction:
Improvespatial understanding accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system creates a simplified two-dimensional contour map copy from the original three-dimensional storage location data. This contour map retains the essential spatial relationships and boundary information needed for accurate understanding while reducing the data complexity and processing requirements, allowing the robot to achieve the same spatial comprehension with less computational burden and faster processing.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The system extracts only the essential contour information from the complete three-dimensional map data, separating the critical spatial boundary elements from the full volumetric information. This extraction of essential contour features provides sufficient spatial understanding for object placement recognition while eliminating redundant data that would increase processing time and computational load.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentEP4521185A1Map area contour-based setting method and robot edge end control method
Publication Date: 2025.03.12 AMICRO SEMICONDUCTOR CO LTD
  • EP4521185A1 patent drawingFigure 1
  • EP4521185A1 patent drawingFigure 2
  • EP4521185A1 patent drawingFigure 3

AI summary

A map region contour-based setting method and a method for controlling robot edgewise walking termination. The method for controlling robot edgewise walking termination includes: a robot setting a plurality of unit regions to be subjected to edgewise walking by executing a setting method; then, the robot performing edgewise walking in a working region (S302); when the robot walks through all unit regions to be subjected to edgewise walking, the robot stopping walking along the edge (S306); and when the robot repeatedly walks through the same batch of unit regions to be subjected to edgewise walking, the robot stopping walking along the edge (S307), wherein the same batch of unit regions to be subjected to edgewise walking are a preset number of unit regions to be subjected to edgewise walking that are different from each other, and the number of unit regions to be subjected to edgewise walking set by using the setting method is greater than the preset number.