Skip to main content
Search

# Doppel

1 related articles

Subscribe to updates
  1. arXiv

    Robots no longer have to guess their own motion: Doppel renders future bodies into a video world model, lifting PSNR by 1.00 dB on unseen trajectories

    Video world models usually take only numerical action vectors, so the model must learn both how joints move the body in the image and how the body changes the scene. Doppel conditions on future robot renderings along a proposed joint trajectory together with the numerical actions, letting a shared model focus on object and environment response. On the Droid, Bridge and RoboMind robot-arm datasets it improves PSNR over an action-only baseline by 1.00 dB on unseen trajectories and 1.20 dB under out-of-distribution evaluation.

You’re all caught up