Phase Action Space for cross-embodiment Representation (PHASOR for short) introduces a universal action representation that maps different humanoid embodiments in a shared motion space, making robot behavior more transferable, interpretable, and scalable across platforms.
At OpenMind, our deployments involve mixed fleets that operate on one brain. PHASOR helps our team run shared interpretable actions that are transferable across devices without a need for additional re-training.
PHASOR is a collaboration with
@AIMSafety_,
@LGE_Global, Seoul National University and MAUM AI.
Read the research here: