Case Histories
Standardization of intralogistics flows
Problem
In the logistics sector, having objective, real-time data is essential to ensure an efficient and traceable flow of goods, optimize delivery times, reduce errors, and improve vehicle load management.
By leveraging computer vision and AI systems for reading identification labels and measuring the height of merchandise stacks, it becomes possible to implement load optimization algorithms, leading to significant savings and efficiency improvements.
Starting point
The client is a major logistics operator needing to objectify material flows based on real-time data. Since goods are always transported on Euro pallets, the key variable influencing vehicle storage optimization is the height of the merchandise stack, which may consist of multiple pallets from different orders. Currently, label reading, pallet counting, and height estimation are manually performed by operators.
Solution Implemented
An AI-powered vision system, AI-go, has been developed to automatically acquire and analyze information related to merchandise stacks. Image acquisition systems, mounted on mobile carts and equipped with illuminators and distance sensors, capture images even in low-light conditions and with high positioning variability.
Advanced computer vision and AI algorithms enable:
– automatic detection and reading of identification labels
– extraction and decoding of Data Matrix codes to ensure pallet traceability
– counting of transported pallets and detection of any load anomalies
– precise height measurement of the stack, optimizing the arrangement of goods in transport vehicles and storage areas.
The developed solution integrates with the company’s ERP/MES and WMS systems, enabling automatic data storage and transmission, enhancing coordination between handling, storage, and distribution.
Results
The implemented solution fully automates a previously manual and error-prone process, improving logistics efficiency, reducing handling times, and increasing the accuracy of goods traceability.
Key results include:
– complete automation of pallet stack identification, eliminating manual entries and reducing operational errors;
– accurate identification and reading of labels, ensuring full traceability;
– precise height measurement of stacks, improving load balancing in transport and storage spaces;
– seamless integration with ERP/MES and WMS systems, providing real-time, objective data for optimized logistics management.
