Self-Learning Threshold for Vacuum Cleaner Flooring Type Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cordless vacuum cleaners struggle to accurately distinguish between different flooring types, leading to suboptimal suction power and runtime performance on soft versus hard floors.
Innovation Solution
A computer-implemented method that iteratively updates a threshold value for distinguishing between flooring types using sensor data obtained only during hard-floor mode, employing a hard-floor self-learning threshold to enhance accuracy and stability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a threshold value is updated using sensor data from both soft-floor and hard-floor modes, then the threshold may adapt to more floor types, but the threshold becomes less accurate and more sensitive to noise because soft-floor data introduces variability
Solution Approach 1:
The patent segments the sensor data into two distinct categories: data from hard-floor mode and data from soft-floor mode. By separating these data sources, the system can selectively use only hard-floor data for threshold updates, thereby maintaining high detection accuracy while avoiding the noise and variability introduced by soft-floor data.
Solution Approach 2:
The patent applies local quality by assigning different qualities to different portions of the sensor dataset. Specifically, hard-floor sensor data is treated as high-quality data suitable for threshold updates, while soft-floor sensor data is excluded from the update process. This selective approach ensures that only reliable data influences the threshold, maintaining precision without sacrificing adaptability.
2Adaptability or versatility
If the threshold value is updated frequently, then the system adapts quickly to environmental changes, but the threshold becomes less stable and more sensitive to noise
Solution Approach 1:
The patent implements preliminary action by establishing a minimum dataset size requirement before allowing threshold updates. The system accumulates sensor data over time and only permits threshold updates when the dataset reaches a predetermined size, ensuring that updates are based on sufficient data. This preliminary accumulation phase stabilizes the threshold while still allowing eventual adaptation to environmental changes.
Solution Approach 2:
The patent uses feedback mechanisms to monitor the quality and quantity of sensor data before allowing threshold updates. The system continuously evaluates whether the accumulated data meets the minimum size criterion and only proceeds with updates when the criterion is satisfied. This feedback loop balances adaptability with stability by preventing premature updates while enabling updates when sufficient data is available.
3Adaptability or versatility
If sensor data from soft-floor mode is included in threshold updates, then the threshold may become more versatile, but cleaning performance deteriorates because the threshold becomes less reliable for distinguishing flooring types
Solution Approach 1:
The patent extracts and isolates the problematic soft-floor sensor data from the threshold update process. By taking out the soft-floor data component entirely from the update equation, the system maintains threshold reliability for flooring type distinction while preventing the degradation that would result from incorporating noisy soft-floor measurements.
Solution Approach 2:
Instead of including all available sensor data (both hard-floor and soft-floor) in the threshold update, the patent inverts the approach by explicitly excluding soft-floor data. This inversion strategy prioritizes reliability over versatility, ensuring that the threshold remains a dependable indicator for flooring type detection while still maintaining sufficient adaptability through the use of hard-floor data.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A mechanism for defining a threshold for use in discriminating between on which of a plurality of different categories of flooring a nozzle of a vacuum cleaner is positioned. A threshold value is (iteratively) updated using sensor data obtained only when the vacuum cleaner operates in a hard-floor mode, such that the threshold value is a hard-floor self-learning threshold.