Shelf Article Identification Using Weight and Distance Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional article identification systems fail to accurately identify multiple articles picked up simultaneously from different positions on the same shelf, leading to inaccuracies in tracking and inventory management.
Innovation Solution
The system employs a combination of weight sensors and distance sensors to estimate the position and accuracy of picked-up articles, using an information processing device to calculate corrected accuracy based on both weight measurement data and distance data, enabling precise identification of articles picked up from the shelf.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If weight sensors are used to estimate picked-up articles, then the system can detect weight changes, but it cannot accurately identify multiple articles picked up simultaneously from different positions
Solution Approach 1:
The system divides the shelf into multiple measurement regions, each with its own weight sensor. This segmentation allows the system to independently detect weight changes at different positions, enabling accurate identification of multiple articles picked up simultaneously from different locations on the shelf
Solution Approach 2:
The patent introduces distance sensors as intermediary devices that detect the position of the user's hand or body relative to the shelf. This intermediary measurement helps disambiguate which article was picked up when multiple articles are removed, resolving the limitation of weight-only detection
2Measurement precision
If the system estimates article position based on weight sensor data, then it can identify picked-up articles, but the accuracy decreases when multiple articles are picked up from the same shelf
Solution Approach 1:
The system transitions from one-dimensional weight measurement to two-dimensional position estimation by combining weight sensor data with distance sensor data. This dimensional enhancement allows the system to accurately determine both the vertical position (from weight change) and horizontal position (from distance measurement) of picked-up articles
Solution Approach 2:
The patent replaces pure mechanical weight-based estimation with a hybrid system that incorporates optical or electromagnetic distance measurements. This substitution provides more precise position information without being limited by the ambiguities of weight-only detection
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 approach allows for accurate identification of articles picked up simultaneously from different positions, enhancing the accuracy and reliability of inventory tracking and management systems.
Implementation Method 1
a weight sensor that measures a weight of an article, the weight sensor being installed on a shelf on which the article is placed
Implementation Method 2
a distance sensor that includes the shelf and a predetermined area in front of the shelf in a measurement range and measures a distance to an object to be measured that is present in the measurement range
Data Source
AI summary
An article identification system includes a weight sensor, a distance sensor, and an article identification device including an information processing device. The information processing device calculates, based on weight measurement data detected by the weight sensor, a first item picked up position of a plurality of picked up estimated items and a degree of accuracy indicating a degree of correctness of the estimation of the picked up estimated items. The information processing device obtains a second item picked up position based on the distance data of the person obtained by the distance sensor. The information processing device calculates a correction certainty by correcting the certainty of the estimated picked up items based on the first item picked up position and the second item picked up position, and identifies the picked up items based on the correction certainty.


