🔬 Corporate#71 Emeryville, CA, USA· Est. 2017
Covariant — AI Robotics Research
Building the "AI brain" for warehouse robots using foundation models. Covariant's RFM-1 (Robot Foundation Model) enables robots to pick any object without explicit programming, deployed at Amazon-scale logistics.
robot AI brainwarehouse pickingfoundation modelsgraspinglogistics
Notable achievements
RFM-1 robot foundation model, $222M raised, logistics picking at scale, ABB acquisition discussions, Berkeley BAIR spinout.
Notable work
RFM-1Picking at scale
Recent publications
All papers →Matched by this lab's specialties (keyword overlap + direct affiliation)
LEARNING
📊 0 cites
Artificial Intelligence enhanced smart welding islands: Foundation models revolutionizing manufacturing
Xiwei Wu, Wei Wu, Qiqi Chen +6 more
Robotics and Computer-Integrated Manufacturing · 2026
OTHER
Open access📊 0 cites
Hylos: Operability Contracts for Model-Native Spatial Intelligence
Christopher Da Silva
2026
HRI
Open access📊 0 cites
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains
Rebecca Ramnauth, Drazen Brscic, Brian Scassellati
2026
PERCEPTION
Open access
FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
Zihui Zhang, Zhixuan Sun, Yafei Yang +3 more
2026
LEARNING
Open access
On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning
Thomas Lips, Marco Moletta, Michael C. Welle +2 more
2026
MANIPULATION
Open access
ComPose: When to Trust Hands for Object Pose Tracking
Jisu Shin, Junoh Lee, JunGyu Lee +5 more
2026