Next-Gen 3D streaming of industrial twins as a source for AI agents
| Reference number | |
| Coordinator | Epicz Lab AB |
| Funding from Vinnova | SEK 150 000 |
| Project duration | January 2026 - April 2026 |
| Status | Ongoing |
| Venture | Advanced digitalization - Industrial needs-driven innovation |
| Call | Collaborations with the US in AI, digital infrastructure and cyber security |
Important results from the project
Yes, the project goals were met. We explored the feasibility of 3D streaming digital twin components with contextual data and created a mockup of such a user experience. Through the work and at NVIDIA´s GTC conference in the U.S., our understanding of the challenge deepened significantly. We identified NVIDIA as a potential key partner and laid the groundwork for a Phase 2 with deeper technical development and industrial pilots.
Expected long term effects
The project is expected to lead to a new type of industrial AI infrastructure based on real-time streaming of digital twins that AI agents can interpret and act on. In the long term, this can enable autonomous factories, improved production optimization, and reduced climate footprint. Collaborations with U.S. actors such as NVIDIA strengthen Swedish competitiveness in industrial AI.
Approach and implementation
The project had three phases: preparation with technical mapping and streaming validation, a US visit where Klaudia Mur and Jesper Lundbäck attended NVIDIA´s GTC conference with meetings, demos and workshops with potential partners, and a post-visit phase with deeper analysis and Phase 2 preparation. Work was split into four packages: technical definition, mockup and demonstrator, partner identification, and realization planning.