Our technology
Physical AI
Small vision and decision models that perceive and act in the physical world: robots, machines, screens and sites, on your own hardware.
Physical AI means models that see through your cameras, read your HMIs and drive decisions on the floor. We build them small and specialised, so they run on the compute already in the cell or the vehicle.
Every model is validated hardware-in-the-loop on the Test Automation Stand: real devices, real cameras, overnight regression before anything reaches production.
Research on arXiv
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- PaLM-E: An Embodied Multimodal Language Model
- OpenVLA: An Open-Source Vision-Language-Action Model
Used in
See it on your own data
We start with an MVP on your screens, devices or tickets. Request an MVP and bring a real use case.
Request MVP