Announcement
PRISM expands four real videos into 256 counterfactual variants for humanoid robot training
A contributor to the work, done at Amazon FAR, says PRISM recovers robot-object trajectories and trains one policy that generalizes across different objects, scales and spatial layouts.
TLDR
A contributor to PRISM says its real-to-sim-to-real approach expands four real videos into 256 counterfactual variants to train humanoid robots to move and handle objects. They say it recovers robot-object trajectories and trains one policy that generalizes across objects, scales and spatial layouts. The work was done at Amazon FAR.
Combined views
30.1K
5 Sources, first seen ago
