# Meta's Open Vision Models Run On-Device in a $41.5 Million Robotic Wheelchair Program

Researchers at the University of Pittsburgh say running DINOv3 and the Segment Anything Model (SAM) locally is what lets the system perceive in real time without depending on network connectivity.

- Published: 2026-09-14T06:22:55.303Z
- Canonical: https://polylog.news/ai/2026-09-14/meta-s-open-vision-models-run-on-device-in-a-41-5-million-ro
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/), [Meta AI](https://ai.meta.com/blog/genesis-mission-lawrence-berkeley-national-laboratory-segment-anything-dino/)

Meta published an account of how the Human Engineering Research Laboratories at the University of Pittsburgh, a group affiliated with the United States Department of Veterans Affairs, are using its open vision models in assistive robotics.…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-14/meta-s-open-vision-models-run-on-device-in-a-41-5-million-ro (subscription information: https://polylog.news/pricing).