Robot Cleaner Position Recognition Using 3D Feature Point Matching

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robot cleaners lack precise position recognition and mapping capabilities, relying on inexpensive control sensors that limit their ability to efficiently clean all areas autonomously, especially in complex environments.

Innovation Solution

A robot cleaner equipped with an image detecting unit, feature point extracting and matching units to create 3D coordinates information from 2D feature points, and a control unit that verifies positions using similarity calculations and moving distance measurements, allowing for precise navigation and path correction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If an image detecting unit with feature point extraction and matching is used, then position recognition precision is improved, but device complexity increases

Engineering Contradiction:
Improveposition recognition precisionVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces traditional mechanical control sensors with an image detecting unit that uses optical fields (cameras) to capture images and extract feature points. This substitution enables precise position recognition through image processing and feature matching algorithms, achieving higher measurement precision while reducing reliance on complex mechanical sensing systems.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces feature points as intermediary elements between the image detecting unit and the position recognition system. By extracting and matching feature points from images, the system creates a bridge that translates visual information into precise position data, resolving the contradiction between using simple sensors and achieving high precision.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If feature point extraction and matching is implemented, then cleaning efficiency in complex environments is improved, but processing time increases

Engineering Contradiction:
Improvecleaning efficiencyVSAvoidprocessing time
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-extracting and storing feature points from images before the actual position recognition and path planning processes. This preprocessing step allows the robot to quickly match features during navigation, reducing real-time processing time and improving overall cleaning efficiency in complex environments.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses itself to generate the data it needs for navigation. The image detecting unit captures images, the feature extraction unit processes them, and the extracted features are immediately used for position recognition and path correction, creating a self-sufficient system that minimizes external processing delays.

Inventive Principle:
Principle #25Self-service

3Manufacturing precision

If 3D coordinates information is created from 2D feature points, then mapping accuracy is improved, but computational complexity increases

Engineering Contradiction:
Improvemapping accuracyVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent applies dimensionality change by transforming 2D feature points from images into 3D coordinates in the mapping process. This transformation enables accurate three-dimensional mapping and position recognition by adding depth information through coordinate system conversion, achieving high mapping accuracy while managing computational complexity through efficient mathematical transformations.

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

Data Source

PatentEP3360456B1Robot cleaner and controlling method of the same
Publication Date: 2020.03.04 LG ELECTRONICS INC
  • EP3360456B1 patent drawingFigure 1
  • EP3360456B1 patent drawingFigure 2~3
  • EP3360456B1 patent drawingFigure 4~5

AI summary

Disclosed are a robot cleaner and a method for controlling the same. The robot cleaner is capable of recognizing a position thereof by extracting one or more feature points having 2D coordinates information with respect to each of a plurality of images, by matching the feature points with each other, and then by creating a matching point having 3D coordinates information. Matching points having 3D coordinates information are created to recognize a position of the robot cleaner, and the recognized position is verified based on a moving distance measured by using a sensor. This may allow a position of the robot cleaner to be precisely recognized, and allow the robot cleaner to perform a cleaning operation or a running operation by interworking the precisely recognized position with a map.