Guardado en:
Detalles Bibliográficos
Autores principales: Chen, Xiaoyu, Guo, Junliang, He, Tianyu, Zhang, Chuheng, Zhang, Pushi, Yang, Derek Cathera, Zhao, Li, Bian, Jiang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2411.00785
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917826705489920
author Chen, Xiaoyu
Guo, Junliang
He, Tianyu
Zhang, Chuheng
Zhang, Pushi
Yang, Derek Cathera
Zhao, Li
Bian, Jiang
author_facet Chen, Xiaoyu
Guo, Junliang
He, Tianyu
Zhang, Chuheng
Zhang, Pushi
Yang, Derek Cathera
Zhao, Li
Bian, Jiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00785
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
Chen, Xiaoyu
Guo, Junliang
He, Tianyu
Zhang, Chuheng
Zhang, Pushi
Yang, Derek Cathera
Zhao, Li
Bian, Jiang
Robotics
Artificial Intelligence
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.
title IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2411.00785