# Pittsburgh Researchers Build Assistive Robotics on Meta's Segment Anything and DINO Models

The RAMMP prototype uses SAM 3.1 and DINOv3 for real-time scene understanding, so the device can recognize obstacles and objects it was never trained on.

- Published: 2026-08-23T06:19:43.709Z
- Canonical: https://polylog.news/ai/2026-08-23/pittsburgh-researchers-build-assistive-robotics-on-meta-s-se
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Meta AI](https://ai.meta.com/blog/assistive-robotics-university-of-pittsburgh-sam-dino/), [University of Pittsburgh Rehabilitation and Neural Engineering Laboratory](https://www.rnel.pitt.edu/research/neuroprosthetics/intracortical-brain-computer-interfaces)

A team at the University of Pittsburgh is integrating Meta's SAM 3.1 and DINOv3 into an assistive robotics prototype called RAMMP, using the models for real-time perception of an environment that no fixed label set can anticipate. The examp…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-23/pittsburgh-researchers-build-assistive-robotics-on-meta-s-se (subscription information: https://polylog.news/pricing).