RFM-1

Multimodal Any-to-Any Sequence Model

It incorporates images, video, joint angles, force reading, suction cup strength, and more into its prediction engine to produce images, videos, or a series of commands for a robot.

Covariant | Powering the Future of Automation, Today

Covariant builds and delivers Robotics Foundation Models into the real world, meeting the reliability and flexibility required by the world’s leading retailers and logistics providers.

https://covariant.ai/insights/introducing-rfm-1-giving-robots-human-like-reasoning-capabilities/

Covariant Announces a Universal AI Platform for Robots

The robotics foundation model is built on tons of warehouse data

https://spectrum.ieee.org/covariant-foundation-model

RFM-1

Multimodal Any-to-Any Sequence Model

Recommendations