# Meta Puts Segment Anything and DINO Into Assistive Robotics at the University of Pittsburgh

Researchers are using Meta's open vision foundation models to help a robotic system perceive and act, an application of promptable perception to physical assistance.

- Published: 2026-07-28T05:31:39.988Z
- Canonical: https://polylog.news/ai/2026-07-28/meta-puts-segment-anything-and-dino-into-assistive-robotics
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/)

Meta describes work with the University of Pittsburgh using its Segment Anything and DINO vision models in assistive robotics, aimed at helping people with mobility limitations. The application pairs promptable segmentation with self-superv…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-07-28/meta-puts-segment-anything-and-dino-into-assistive-robotics (subscription information: https://polylog.news/pricing).