Phantom: Training Robots Without Robots Using Only Human Videos

Marion Lepert, Jiaying Fang, Jeannette Bohg

Keywords: Learning from Human Videos, Imitation Learning

TL;DR: We present a scalable method for training robot manipulation policies directly from human videos—without any robot data—achieving zero-shot deployment and up to 92% success on diverse tasks.

Abstract: Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale. We present a scalable framework for training manipulation policies directly from human video demonstrations, requiring no robot data. Our method converts human demonstrations into robot-compatible observation-action pairs using hand pose estimation and visual data editing. We inpaint the human arm and overlay a rendered robot to align the visual domains. This enables zero-shot deployment on real hardware without any fine-tuning. We demonstrate strong success rates—up to 92%—on a range of tasks including deformable object manipulation, multi-object sweeping, and insertion. Our approach generalizes to novel environments and supports closed-loop execution. By demonstrating that effective policies can be trained using only human videos, our method broadens the path to scalable robot learning. Videos are available at https://phantom-training-robots.github.io.

Submission Number: 289