Inventory Interaction Detection Using Weight and Non-Weight Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing inventory management systems face challenges in accurately tracking interactions and quantity changes of items in a materials handling facility, particularly when multiple types of items are stored in partitioned areas, as weight changes alone may not suffice to identify specific items due to similar weights and distributions.
Innovation Solution
The system employs weight sensors to gather data, which, combined with hypotheses based on item and physical configuration data, scores and ranks potential interactions to determine the most accurate change, using a subset of hypotheses within threshold values and activity data from non-weight sensors like cameras to identify item picks or placements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If weight sensors are used to track item quantity changes, then measurement capability is provided, but accuracy deteriorates when multiple item types have similar weights and distributions
Solution Approach 1:
The system segments the inventory monitoring task into multiple independent measurement components: weight sensors provide weight data, while non-weight sensors (optical, radar, RFID) provide spatial and identification data. This segmentation allows each sensor type to focus on specific characteristics, and the combined data enables accurate item type differentiation even when weights are similar.
Solution Approach 2:
The patent merges weight data from weight sensors with non-weight data from other sensors (optical, radar, RFID) to create a comprehensive monitoring system. By combining multiple data sources, the system overcomes the limitations of weight-only measurement and achieves accurate item identification and quantity tracking across different item types.
2Measurement precision
If multiple sensors are deployed to improve tracking accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The system employs a multi-functional sensor architecture where different sensor types (weight, optical, radar, RFID) serve multiple purposes: identifying item types, tracking quantity changes, detecting user interactions, and monitoring item locations. This multi-functionality reduces the need for separate dedicated systems and manages overall complexity.
Solution Approach 2:
The patent introduces a data processing system as an intermediary that receives data from multiple sensor types, correlates the information, and produces unified monitoring results. This intermediary layer simplifies the system architecture by centralizing data fusion logic and presenting a unified interface for inventory management.
3Device complexity
If weight data alone is used for inventory tracking, then system simplicity is maintained, but reliability deteriorates due to inability to distinguish similar-weight items
Solution Approach 1:
The system implements feedback mechanisms where sensor data continuously updates inventory records, and the system responds to detected changes (picks, placements, movements) by updating quantity counts and triggering appropriate actions. This feedback loop ensures reliable tracking while maintaining system responsiveness without excessive complexity.
Data Source
AI summary
An inventory location, such as a shelf, may be used to stow different types of items in different areas of the shelf. Interactions may take place, such as the pick or place of items from the shelf. Weight data acquired from weight sensors at the shelf may be used to generate a set of hypotheses to describe types and quantities of items added to or removed from the shelf during an interaction. One or more of these hypotheses may be eliminated from consideration or selected as a solution based on activity data related to the shelf. The activity data is based on non-weight data from a non-weight sensor associated with the shelf. As an example, image data from a camera directed to the shelf can help identify presence of a user or a change in appearance at an area of the shelf to help evaluate hypotheses.