Digital Twin UAV Inventory Counting With Real-Time Path Calibration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing inventory counting methods in automated warehousing systems face issues such as high labor costs, low efficiency, high energy consumption, and difficulty in accurately capturing goods located far from the stacking machine, leading to inaccurate stocktaking, especially in double-extension stereoscopic warehouses.

Innovation Solution

A rotary-wing UAV stocktaking method based on a digital twin, which involves building a digital twin model of the logistics warehouse, synchronizing warehouse tasks, generating a UAV cruising path, and using epipolar geometry to calibrate the actual UAV's position relative to the virtual UAV, enabling accurate photo comparison and stocktaking without human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If a stacking machine carries a camera to traverse the entire warehouse for stocktaking, then stocktaking can be automated, but energy consumption increases and operation time becomes long

Engineering Contradiction:
Improveautomation of stocktakingVSAvoidenergy consumption of stacking machine
Core Design Contradiction:
Extent of automationVSUse of energy by moving object

Solution Approach 1:

The patent creates a digital twin (virtual copy) of the warehouse and its contents, allowing stocktaking to be performed on the virtual model rather than requiring physical traversal by the stacking machine. This copying approach enables automated inventory verification without the energy consumption and time costs of moving heavy equipment throughout the warehouse.

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical traversal system (stacking machine physically moving through the warehouse) with a computational system that processes images and updates the digital twin. This substitution eliminates the need for mechanical movement during stocktaking operations, significantly reducing energy consumption.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If a stacking machine traverses the entire warehouse to capture all goods, then stocktaking coverage improves, but operation time increases

Engineering Contradiction:
Improvestocktaking coverageVSAvoidoperation time for stocktaking
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by continuously capturing images during normal warehouse operations and pre-processing them to update the digital twin. This preliminary data collection and processing eliminates the need for time-consuming comprehensive traversals during actual stocktaking, as the virtual warehouse is already populated with inventory information.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements continuous image capture and processing during normal warehouse operations, maintaining an up-to-date digital twin without interrupting workflow. This continuous action approach ensures complete stocktaking coverage is achieved progressively over time rather than requiring a single lengthy operation.

Inventive Principle:
Principle #20Continuity of useful action

3Measurement precision

If manual stocktaking is performed by workers on the stacking machine, then goods verification can be done, but labor costs increase and safety risks arise

Engineering Contradiction:
Improvegoods verification accuracyVSAvoidsystem complexity with human operators
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs self-service by automatically capturing images, processing them through algorithms, updating the digital twin, and generating stocktaking reports without human intervention. This automation eliminates the need for workers to physically access goods on the stacking machine, reducing both labor costs and safety risks while maintaining verification accuracy.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces human operators with an automated computational system that uses image processing algorithms to verify goods. This substitution eliminates the complexity of coordinating human safety and operations while improving consistency and accuracy of verification.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Measurement precision

If multiple sensing devices are installed on the UAV for stocktaking, then data acquisition capability improves, but system cost and energy consumption increase

Engineering Contradiction:
Improvedata acquisition capabilityVSAvoidnumber of sensing devices
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the UAV camera multi-functional by using it for both navigation (path following) and stocktaking (inventory verification) purposes. This universal approach eliminates the need for separate specialized sensors, reducing system complexity and cost while maintaining comprehensive data acquisition capability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The image processing system performs multiple functions including object detection, recognition, and inventory verification using the same camera data. This multi-functionality approach maximizes the utility of minimal sensing devices, reducing overall system complexity while maintaining high measurement precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4722837A1Digital twin-based rotor unmanned aerial vehicle inventory counting method and apparatus, and storage medium
Publication Date: 2026.04.08 RIAMB (BEIJING) TECH DEV CO LTD
  • EP4722837A1 patent drawingFigure 1
  • EP4722837A1 patent drawingFigure 2~3
  • EP4722837A1 patent drawingFigure 4

AI summary

A rotary-wing UAV stocktaking method and apparatus based on the digital twin, and a storage medium are provided, which are applied to the technical field of logistics & warehousing. By building a digital twin model of a logistics warehouse, warehouse-in and warehouse-out tasks are synchronized in the digital twin model, to implement virtuality-reality synchronization of goods. Meanwhile, virtual and actual UAVs are controlled to move forward according to a planned path. Cameras are used to take photos of goods on shelf grids for virtuality and reality comparison, thereby determining the accuracy of the goods on the shelf grids. In addition, in the cruising process of the UAVs, coordinate offsets of the virtual and actual UAVs are determined by an epipolar geometry algorithm, so that the position of an actual UAV is calibrated in actual time based on the position of a virtual UAV, which can avoid gradual deviation of the actual UAV from the original planned path due to external interference and improve instantaneity of a path of a UAV. Human participation is not required; the quantity of sensors involved is small, so energy consumption is low; and photos are taken independently for each shelf so that the photos have high clarity.