Foundation Models
CrossFormer
CrossFormer is a cross-embodiment robot policy from UC Berkeley (Doshi et al., 2024), a transformer trained on 900K trajectories spanning single-arm and bimanual manipulation, quadruped locomotion, and navigation without requiring a shared observation or action space. Variable observation tokens and per-embodiment action readouts let one architecture control drastically different robots, matching specialist policies while enabling transfer across embodiments.
Why it matters for physical AI
CrossFormer demonstrated that one policy can span manipulation, navigation, and locomotion without aligning action spaces, strengthening the case for unified generalist models over per-platform specialists.
Build physical AI
Put these concepts to work on real hardware
Axol is a dual-arm robot built for physical AI — teleoperate it, collect demonstrations, and deploy learned policies out of the box.