Robotics Foundation Models for Embodied AI
Over the coming months, labs ship general-purpose robotics model suites that bridge vision-language understanding to physical navigation and manipulation, pushing foundation models into embodied action.
weakening · confidence 83 · -5 7d · -17 30d · Medium term (3-9 months) · tracking since June 18, 2026 · updated October 12, 2026
Score history
Daily conviction score, 0 to 100. Higher means the thesis is more strongly corroborated.
Now 83 · -2 since Oct 11 · ranged 83 to 85
Showing the last few days. Unlock full score history.
Why the conviction moved
- Oct 11Strengthened +1
The RAMMP wheelchair links open vision foundation models to robotic-arm manipulation and navigation. General-purpose perception models are being used for physical action in a funded medical robotics program.
- Oct 7Strengthened +1
A University of Pittsburgh assistive robot uses Meta's SAM 3 and DINOv3 on battery-powered hardware. General-purpose vision foundation models are being reused as the perception layer for physical manipulation.
Showing the last 2 days. Unlock the full record.
Source trail
Supporting · October 11, 2026
Pitt's ARPA-H Robotic Wheelchair Runs Meta's DINO and SAM On-Device for Real-Time 360-Degree Perception
The RAMMP wheelchair links open vision foundation models to robotic-arm manipulation and navigation. General-purpose perception models are being used for physical action in a funded medical robotics program.
Meta AISupporting · October 7, 2026
Meta's open vision models move into national-lab science and assistive robotics
A University of Pittsburgh assistive robot uses Meta's SAM 3 and DINOv3 on battery-powered hardware. General-purpose vision foundation models are being reused as the perception layer for physical manipulation.
Meta AI (University of Pittsburgh)
Unlock full source trail, score history, and daily updates.
60 more sources in the full trail.
Unlock TrendsAffected regions & assets
Townsquare
Argue the thesis in Townsquare.