brains/redwood · model record
Redwood AI
160M-parameter vision-language transformer with a diffusion-policy decoder that jointly predicts arm, hand, walking and pelvis commands for mobile manipulation. Runs fully on NEO's embedded GPU at about 5 Hz.
01
Embodiments
robots it has been shown on02
Papers naming this model
from the papers feedNo paper in the current feed names Redwood AI in its title.