Autonomous Vacuum Cleaner Stereo Vision for Obstacle Shape Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous-traveling vacuum cleaners face challenges in detecting the size and shape of obstacles, limiting their ability to navigate effectively and clean efficiently due to reliance on ultrasonic and infrared sensors that only detect presence, not dimensions.
Innovation Solution
The vacuum cleaner employs a system with multiple cameras positioned on its sides, which capture images of the traveling direction, calculate distances using triangulation, and generate depth images to accurately determine the shape and dimensions of objects, enabling precise obstacle detection and navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ultrasonic sensors and infrared sensors are used for obstacle detection, then obstacle presence can be detected, but the size and shape of obstacles cannot be detected
Solution Approach 1:
The patent replaces ultrasonic and infrared sensors with image pickup means (cameras) to detect obstacles. The image pickup means captures visual information that allows determination of both obstacle presence and their size/shape characteristics, resolving the information loss problem while maintaining detection capability
Solution Approach 2:
The patent introduces a processor as an intermediary that receives image data from the image pickup means and generates obstacle information including size and shape. This intermediary processing step transforms raw image data into useful obstacle characteristics, enabling precise detection without direct sensor contact
2Reliability
If the vacuum cleaner avoids areas where it cannot detect obstacle size and shape, then obstacle avoidance is ensured, but the area to be cleaned is limited causing stagnation in cleaning
Solution Approach 1:
By replacing traditional sensors with image pickup means, the system achieves reliable obstacle detection with size and shape information, enabling the vacuum cleaner to confidently navigate previously restricted areas and improve cleaning coverage without compromising safety
Solution Approach 2:
The patent transitions from binary obstacle detection (present/absent) to multi-dimensional obstacle characterization (size, shape, distance). This dimensional enrichment allows the vacuum cleaner to make informed navigation decisions, entering areas that were previously avoided, thus improving productivity while maintaining reliability
3Measurement precision
If multiple image pickup means are used to detect obstacle shape with high precision, then obstacle detection accuracy improves, but device complexity increases
Solution Approach 1:
The patent employs image pickup means that serve multiple functions: obstacle detection, size measurement, shape recognition, and distance estimation. This multi-functionality reduces the need for separate specialized sensors, achieving high measurement precision while controlling overall device complexity
Solution Approach 2:
The patent combines multiple image pickup means into a unified imaging system processed by a single processor. By merging the detection and processing functions, the system achieves accurate obstacle shape detection while minimizing the complexity increase that would result from completely separate detection systems
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution allows the vacuum cleaner to detect obstacles with high precision, adjust its travel speed and direction accordingly, and maintain efficient cleaning performance by accurately assessing the space around it, thereby improving navigation and cleaning efficiency.
Implementation Method 1
calculate distances using triangulation, and generate depth images
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided is a vacuum cleaner capable of detecting a shape of an object with high precision. A vacuum cleaner (11) includes a main casing, driving wheels, control means (27), a plurality of cameras (51a), (51b), an image generation part (62), and a shape acquisition part (63). The driving wheels enable the main casing to travel. The control means (27) controls drive of the driving wheels to make the main casing autonomously travel. The cameras (51a), (51b) are disposed apart from each other in the main casing to pick up images on a traveling-direction side of the main casing. The image generation part (62) generates a distance image of an object positioned on the traveling-direction side based on the images picked up by the cameras (51a), (51b). The shape acquisition part (63) acquires the shape information of the picked-up object from the distance image generated by the image generation part (62).