Since AI 2026 / 6–8 Nov / Turku

From 3D scan to
intelligent
field service.

A room becomes more useful when you can understand what is in it, find the right equipment, and know what to inspect next.

The idea

See the room.
Understand the work.

Industrial context is scattered across physical spaces, device readings and maintenance documents. Scan2Work brings those pieces into a shared 3D environment.

  1. 01

    Scan

    Start with the supplied 3D Gaussian-splat capture of an industrial boiler room.

    The physical context
  2. 02

    Understand

    Frame individual assets and connect them to synthetic equipment records, conditions and telemetry.

    The equipment context
  3. 03

    Work

    Follow a technician’s route, surface nearby equipment and review evidence for the next inspection step.

    The service context

The Valmet Automation challenge

Industrial Metaverse: Semantic 3D Scene Understanding & Autonomous Field-Service Copilot

Built at the Since AI 2026 hackathon in Turku, Finland, 6–8 November 2026, for Valmet Automation’s challenge.

About the hackathon
01 / Scene understanding

Give objects an identity

Extract and frame assets from the supplied scene so equipment can be selected and understood in context.

02 / Data integration

Connect the records

Map the provided synthetic Excel equipment, telemetry, alarm and service data to the extracted assets.

03 / Spatial simulation

Make the route matter

Simulate obstacle-aware technician navigation and show nearby assets as the technician moves through the room.

04 / Grounded guidance

Explain the next step

Use device conditions and supplied troubleshooting documentation to support diagnostics with traceable evidence.

The people behind the prototype

Built together.

Five people, one shared challenge. Meet the team that came together to explore what industrial spatial intelligence could become.

Explore the prototype

Find the right machine.
Know the next step.

Open interactive demo