Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
For robot learning researchers, this work addresses the embodiment gap in human-to-robot skill transfer, offering a practical action representation that improves transfer efficiency.
This paper proposes a bridging action representation—relative wrist translation in the initial head-camera frame—to transfer manipulation skills from humans to bi-manual robots, achieving far more effective transfer than noisy 6DoF human actions and scaling with human data volume.
We study whether we can learn novel manipulation skills from human actions to a bi-manual robot with parallel grippers. Human action data is cheap, abundant, and diverse, making it one of the most promising resources for scaling up robot learning. Yet transferring skills from humans to robots remains hard: most prior work treats humans as just another bi-manual 6DoF embodiment, where hand-pose estimates are noisy and the contact patterns of human fingers differ fundamentally from those of a parallel gripper. We argue that learning rotation-inclusive action signals from human data is therefore sub-optimal, and instead propose a bridging action representation: the relative wrist translation within the initial head-camera frame, an action space shared by humans and robots. To handle the potential absence of certain action components in different embodiments, we build a $π_0$-like vision-language-action model with interleaved action tokens and attention masking. On a suite of novel bi-manual manipulation tasks, our bridging action transfers human manipulation knowledge to robots far more effectively than noisy 6DoF human actions and scales with the amount of human data.