Introducing the next phase of our AI Robotics journey Read more
Resources/Resources

Sign up for our newsletter

Get the latest news in AI Robotics, picked just for you

Thom Campbell, Chief Strategy Officer, Capacity
“Covariant designed and delivered a solution that learns, is intelligent, and performs autonomously in a live operational setting. It’s unlike anything else available in the market today, and critically, our teams can rely on it to deliver great outcomes for our clients.”
Pieter Abbeel, Chief Scientist, Covariant
“A quiet revolution is occurring in AI Robotics. AI robots can see, learn, and react to make the right decision based on the current situation. ”
All resources
Introducing the next phase of our AI Robotics journey
We’ve always been driven by a mission to build. This passion for building drove the creation of the Covariant Brain—a gr...
The Research
The power of collaboration: 5 years of KNAPP & Covariant
Five years strong and counting, our partnership has driven remarkable momentum. To date, we’ve gained over 26 unique cus...
The Industry
The key to reliablity: Minimizing human intervention
In AI Robotics, achieving 99% reliability—where human intervention is needed less than 1% of the time—is the critical th...
The Robots
A Covariant Robotic Putwall
Capacity turns to AI Robotics to reliably fulfill customer orders
About Capacity Capacity, a forward-thinking third-party logistics firm with expertise in Health and Beauty products for...
The Robots
RFM-1 update: Higher quality grasp accuracy
Scaling Law in Robotics At Covariant, we see that as we train RFM-1 on more data, our model's performance improves pre...
The Research
RFM-1 update: High-fidelity scene prediction
Scaling Law has been vital to the rapid growth of LLMs over the last few years. Covariant is no stranger to Scaling La...
The Research
Founder’s perspective: Building a truly general AI for robotics must be done in the real world
Each year, NVIDIA hosts GTC (GPU Technology Conference), AI conference, uniting the brightest minds in the field to unve...
The Industry
RFM-1 update: In-context learning to improve grasping
The release of RFM-1, the first commercial Robotics Foundation Model, set a new horizon for AI by giving robots the huma...
The Research
RFM-1: Allowing robots and people to communicate in natural language
By allowing people to instruct robots without needing to re-program, RFM-1 lowers the barriers of customizing AI behavio...
The Research
Introducing RFM-1: Giving robots human-like reasoning capabilities
Andrew Sohn, Anusha Nagabandi, Carlos Florensa, Daniel Adelberg, Di Wu, Hassan Farooq, Ignasi Clavera, Jeremy Welborn, J...
The Research
RFM-1: A world model that understands physics 
In robotics, millimeters can be the difference between “completely unusable” and “superhuman.” The fine-grained predicti...
The Research
What’s Your Problem Podcast: Using AI to build better robots
Peter Chen joins the What’s Your Problem Podcast for a conversation with Jacob Goldstein, former host of NPR’s Planet Mo...
The Industry