Robot Cleaner Visual Positioning for Accurate Cleaning Paths
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current robot cleaners lack precise position recognition and efficient path management, relying on inexpensive control sensors that limit their ability to effectively clean all areas autonomously.
Innovation Solution
Incorporating an image detecting unit, such as an upper camera, to extract and match feature points from images, allowing the robot cleaner to create feature point sets and recognize its position, which enables the creation of optimized cleaning or running paths based on obstacle detection and precise positioning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If an image detecting unit such as an upper camera is used to precisely recognize position, then position recognition precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces traditional mechanical control sensors with an image detecting unit (camera) that uses visual field information and feature point matching to determine position. This substitution of mechanical sensing with optical sensing enables precise position recognition while reducing contact with obstacles and improving reliability.
Solution Approach 2:
The patent introduces feature points as intermediary elements between the camera and the position determination process. By detecting feature points in the visual field and matching them across multiple images, the system achieves precise position recognition without requiring direct mechanical sensing of position.
2Measurement precision
If an image detecting unit is used to detect position, then position recognition precision is improved, but product cost increases
Solution Approach 1:
The patent replaces expensive mechanical control sensors with a camera-based visual sensing system. The camera unit, combined with feature point extraction and matching algorithms, provides precise position information at lower cost compared to traditional mechanical sensing systems.
Solution Approach 2:
The patent uses visual field images as copies or representations of the physical environment. By creating and matching feature point sets from image copies, the system determines position without requiring expensive direct physical measurement devices.
3Manufacturing precision
If feature point matching is performed to recognize position, then cleaning path accuracy is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary extraction and storage of feature points from images before the actual position determination is needed. By pre-processing images to identify and store feature point sets, the system reduces processing time during actual navigation and path correction operations.
Solution Approach 2:
The patent divides the position recognition process into separate stages: feature point extraction from images, creation of feature point sets, matching of feature points between images, and final position determination. This segmentation allows each stage to be optimized independently, improving overall efficiency.
Data Source
AI summary
Disclosed are a robot cleaner and a method for controlling the same. A plurality of images are detected through an image detecting unit such as an upper camera, and two or more feature points are extracted from the plurality of images. Then, a feature point set consisting of the feature points is created, and the feature points included in the feature point set are matched with each other. This may allow the robot cleaner to precisely recognize a position thereof. Furthermore, this may allow the robot cleaner to perform a cleaning operation or a running operation by interworking a precisely recognized position with a map.