IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
This work addresses the challenge of semantic consistency in action spaces for foundation models in embodied AI, enabling human-to-robot knowledge transfer, though it appears incremental as it builds on existing latent action and world model concepts.
The paper tackles the problem of learning a unified action space for embodied AI by introducing Image-GOal Representations (IGOR), which compresses visual changes into latent actions to enable knowledge transfer between human and robot data, resulting in capabilities like cross-domain motion migration and language-aligned robot control.
We introduce Image-GOal Representations (IGOR), aiming to learn a unified, semantically consistent action space across human and various robots. Through this unified latent action space, IGOR enables knowledge transfer among large-scale robot and human activity data. We achieve this by compressing visual changes between an initial image and its goal state into latent actions. IGOR allows us to generate latent action labels for internet-scale video data. This unified latent action space enables the training of foundation policy and world models across a wide variety of tasks performed by both robots and humans. We demonstrate that: (1) IGOR learns a semantically consistent action space for both human and robots, characterizing various possible motions of objects representing the physical interaction knowledge; (2) IGOR can "migrate" the movements of the object in the one video to other videos, even across human and robots, by jointly using the latent action model and world model; (3) IGOR can learn to align latent actions with natural language through the foundation policy model, and integrate latent actions with a low-level policy model to achieve effective robot control. We believe IGOR opens new possibilities for human-to-robot knowledge transfer and control.