GetMoved: AI-Powered Moving Logistics, Scaled Up on the LUMI-G Supercomputer
THE PROBLEM / CHALLENGE
Organising a home or office relocation is rarely a smooth experience. One of the most persistent pain points is the quotation process: moving companies typically rely on manual surveys or rough customer estimates to price a job, leading to inaccurate quotes, last-minute disputes, and inefficiencies on both sides of the transaction. For a digital platform aiming to streamline this process at scale, the solution lies in computer vision — training AI models to automatically analyse short videos recorded by users and generate structured, reliable inventories of items to be moved. This transforms an inherently subjective process into an objective, data-driven one.
However, building computer vision models that perform accurately across the enormous variety of real-world home environments — different room layouts, lighting conditions, item types and sizes — requires large-scale model training and extensive experimentation. The GPU compute resources needed to develop and refine such models at production quality are well beyond what a growing SME can access locally, creating a bottleneck between a promising prototype and a market-ready product.
SOLUTION
The Montenegrin company CyberCo, developer of the GetMoved platform, was awarded 35,000 GPU hours on the LUMI-G supercomputer (EuroHPC JU, CSC, Finland) through the EuroHPC AI Factory Fast Lane call — with the application process supported by the NCC Montenegro team from the University of Montenegro. GetMoved uses computer vision models to analyse user-recorded videos, automatically detecting and classifying household items to produce structured inventories that moving companies can use to generate accurate, transparent quotes. The LUMI-G allocation allows CyberCo to accelerate model training, run large-scale video processing experiments, and systematically improve the accuracy and robustness of the AI engine across diverse real-world environments — advancing GetMoved from an advanced prototype toward full production-grade readiness.
BENEFITS
- Faster and more accurate AI development: Access to 35,000 GPU hours on LUMI-G enables the level of large-scale training and iterative experimentation needed to meaningfully improve model accuracy across varied home environments — work that would be impractical on locally available hardware.
- Better experience for movers and customers: More reliable AI-generated inventories mean moving companies receive accurate job information upfront, reducing the risk of pricing disputes and enabling a more transparent, trustworthy relocation marketplace.
- Production-grade scalability: The computational capacity of LUMI-G allows CyberCo to stress-test and optimise the platform’s AI engine at a scale that reflects real-world usage, building confidence in the system’s readiness for broad commercial deployment.
- EuroHPC Fast Lane access for a Montenegrin SME: CyberCo’s successful application through the EuroHPC AI Factory Fast Lane call — supported by NCC Montenegro — demonstrates how Montenegrin companies can rapidly access top-tier European GPU infrastructure to accelerate commercial AI product development.
NCC Montenegro, through the University of Montenegro, supported CyberCo in preparing and submitting the successful application to the EuroHPC AI Factory Fast Lane call, enabling this Montenegrin SME to access LUMI-G supercomputing resources for the advancement of its AI-driven logistics platform.