Automatic Load Carrier Localization via Neural Network Vision

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In industrial environments, particularly in warehouses, tracking multiple load carriers such as pallets requires complex sensor systems or trackers, which can be costly and prone to damage or theft, and existing methods fail to efficiently filter out irrelevant information for user-specific queries.

Innovation Solution

A method and system for automatically locating charge carriers in an electronic representation of an industrial environment using user input, where groups of charge carriers are identified, and their positions are displayed on an electronic interface without the need for individual sensors on each load carrier, utilizing a controller, sensor network, and neural networks for data processing and visualization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If sensors or trackers are equipped on each load carrier to enable tracking, then the position of load carriers can be determined, but the cost increases and the risk of damage or theft increases

Engineering Contradiction:
Improveposition determinationVSAvoidsensor equipment
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses optical copying principles where cameras capture images of load carriers and their positions are determined through image processing and neural network analysis, replacing the need for physical sensors or trackers on each load carrier

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces mechanical sensor systems with an optical detection system using cameras and neural networks, transforming the tracking approach from direct physical measurement to optical field-based detection and computational analysis

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

2Loss of information

If all load carriers are tracked individually, then complete information is available, but the information becomes difficult to filter and process for specific user needs

Engineering Contradiction:
Improvetracking informationVSAvoidinformation processing
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent segments the information processing by using neural networks to automatically categorize and filter load carrier data according to user-defined criteria such as charge states, grouping relevant information while excluding irrelevant data

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary layer of neural network-based image processing and data filtering between the raw tracking data and the user interface, automatically processing and filtering information before presentation to users

Inventive Principle:
Principle #24Intermediary (Mediator)

3Productivity

If sensors are installed on load carriers to enable tracking, then position data can be collected, but the risk of damage or theft of sensors increases

Engineering Contradiction:
Improvetracking capabilityVSAvoidsensor durability
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent creates an optical copy of the load carrier information through camera imaging, eliminating the need for physical sensors on load carriers and thereby removing the vulnerability to sensor damage or theft while maintaining full tracking capability

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent introduces cameras and neural networks as intermediary components that perform tracking functions without requiring physical contact with or attachment to load carriers, thereby protecting the system components from damage or theft risks

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4300394A1Automatic localization of a load carrier
Publication Date: 2024.01.03 STILL GMBH
  • EP4300394A1 patent drawingFigure 1
  • EP4300394A1 patent drawingFigure 2
  • EP4300394A1 patent drawingFigure 3a

AI summary

Method (300) for automatically locating at least one charge carrier from a plurality of charge carriers in an electronic representation of an industrial environment, wherein the plurality of charge carriers are arranged in the industrial environment. The charge carriers are assigned to groups of charge carriers. Each group of charge carriers is identifiable by a group identifier.The method (300) comprises the following features: capturing (301) a user input by means of an electronic user interface; detecting (303) a command to display load carriers according to a specific group identification in the captured user input by means of a control device; capturing (305) the position of at least one load carrier from the plurality of load carriers, which is assigned to the group of load carriers identified by the detected group identification, by means of the control device; and displaying (307) the position of the at least one load carrier in the electronic representation of the industrial environment by means of an electronic display controlled by the control device.