UAV Inventory Tracking With Machine Learning Put-Away Verification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for tracking inventory inside warehouses are operationally expensive, time-consuming, and lack accuracy in put-away processes, particularly those using drones, leading to inefficiencies and delays.
Innovation Solution
A system utilizing an unmanned aerial vehicle (UAV) equipped with an image capturing device and machine learning models to identify rack bays and inventory items, correlating historical data to determine empty spaces and mismatches, and providing real-time alerts for improved put-away accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If existing drone-based systems are used to track inventory, then coverage area is improved, but put-away accuracy deteriorates
Solution Approach 1:
The patent segments the warehouse into multiple predefined spaces, each with specific rack bays and inventory items. The system processes images of these segmented areas separately through machine learning models, allowing for focused analysis and improved accuracy in each zone while maintaining comprehensive coverage across the entire warehouse.
Solution Approach 2:
The patent introduces machine learning models as intermediary processing layers between the drone's image capture and the final put-away verification. These models act as mediators that analyze images, identify rack bays and inventory items, and determine put-away accuracy, thereby improving measurement precision without requiring the drone to physically interact with each item.
2Measurement precision
If manual inventory tracking methods are used, then measurement precision is improved, but labor cost and time consumption increase
Solution Approach 1:
The patent replaces manual mechanical inspection processes with an automated system consisting of drones for image capture and machine learning models for analysis. This substitution eliminates human labor while maintaining high measurement precision through computer vision and pattern recognition algorithms, simultaneously improving both accuracy and productivity.
Solution Approach 2:
The system performs self-service by automatically capturing images, processing them through machine learning models, identifying rack bays and inventory items, and determining put-away accuracy without requiring human intervention. The system monitors itself and provides real-time alerts for mismatches or empty spaces, eliminating the need for manual verification while maintaining high accuracy.
3Measurement precision
If comprehensive manual inspection is performed, then measurement precision is improved, but time consumption increases
Solution Approach 1:
The patent implements continuous monitoring where the drone systematically captures images of predefined spaces and the machine learning models continuously process these images to verify put-away accuracy. This continuous action eliminates gaps in inspection and provides real-time verification without requiring periodic manual interruptions, thereby reducing time loss while maintaining high precision.
Solution Approach 2:
The system performs preliminary actions by pre-defining warehouse spaces, pre-identifying rack bays and inventory items, and pre-processing images through machine learning models before actual verification is needed. This preliminary setup enables rapid real-time verification without requiring time-consuming manual inspections during the actual put-away process.
Data Source
AI summary
A system for tracking inventory inside a warehouse with put-away accuracy is provided. The system 100 includes unmanned aerial vehicle (UAV) 102 including image capturing device 102A, warehouse 104, inventory tracking unit 106, user device 108, cloud server 110, and network 112. The UAV 102 is configured to capture media contents of pre-defined space within the warehouse 104 using image capturing device 102A. The pre-defined space includes rack bays with unique rack bay identifier and inventory items stocked on rack bays with pallet identifier that is similar to corresponding unique rack bay identifier. The inventory tracking unit 106 determines inventory data including empty space, inventory mismatch, and inventory record by processing the media contents using machine learning models 106A-B. The inventory tracking unit 106 sends empty space alert and mismatch alert to user and transmits inventory data to cloud server 110 and user device 108 through network 112.