ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915219190579200 |
|---|---|
| author | Shi, Junyao Zhao, Zhuolun Wang, Tianyou Pedroza, Ian Luo, Amy Wang, Jie Ma, Jason Jayaraman, Dinesh |
| author_facet | Shi, Junyao Zhao, Zhuolun Wang, Tianyou Pedroza, Ian Luo, Amy Wang, Jie Ma, Jason Jayaraman, Dinesh |
| contents | Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same objects as the trained policy must handle at test time. In contrast, large pre-recorded human video datasets demonstrating manipulation skills in-the-wild already exist, which contain valuable information for robots. Is it possible to distill a repository of useful robotic skill policies out of such data without any additional requirements on robot-specific demonstrations or exploration? We present the first such system ZeroMimic, that generates immediately deployable image goal-conditioned skill policies for several common categories of manipulation tasks (opening, closing, pouring, pick&place, cutting, and stirring) each capable of acting upon diverse objects and across diverse unseen task setups. ZeroMimic is carefully designed to exploit recent advances in semantic and geometric visual understanding of human videos, together with modern grasp affordance detectors and imitation policy classes. After training ZeroMimic on the popular EpicKitchens dataset of ego-centric human videos, we evaluate its out-of-the-box performance in varied real-world and simulated kitchen settings with two different robot embodiments, demonstrating its impressive abilities to handle these varied tasks. To enable plug-and-play reuse of ZeroMimic policies on other task setups and robots, we release software and policy checkpoints of our skill policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23877 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos Shi, Junyao Zhao, Zhuolun Wang, Tianyou Pedroza, Ian Luo, Amy Wang, Jie Ma, Jason Jayaraman, Dinesh Robotics Computer Vision and Pattern Recognition Machine Learning Many recent advances in robotic manipulation have come through imitation learning, yet these rely largely on mimicking a particularly hard-to-acquire form of demonstrations: those collected on the same robot in the same room with the same objects as the trained policy must handle at test time. In contrast, large pre-recorded human video datasets demonstrating manipulation skills in-the-wild already exist, which contain valuable information for robots. Is it possible to distill a repository of useful robotic skill policies out of such data without any additional requirements on robot-specific demonstrations or exploration? We present the first such system ZeroMimic, that generates immediately deployable image goal-conditioned skill policies for several common categories of manipulation tasks (opening, closing, pouring, pick&place, cutting, and stirring) each capable of acting upon diverse objects and across diverse unseen task setups. ZeroMimic is carefully designed to exploit recent advances in semantic and geometric visual understanding of human videos, together with modern grasp affordance detectors and imitation policy classes. After training ZeroMimic on the popular EpicKitchens dataset of ego-centric human videos, we evaluate its out-of-the-box performance in varied real-world and simulated kitchen settings with two different robot embodiments, demonstrating its impressive abilities to handle these varied tasks. To enable plug-and-play reuse of ZeroMimic policies on other task setups and robots, we release software and policy checkpoints of our skill policies. |
| title | ZeroMimic: Distilling Robotic Manipulation Skills from Web Videos |
| topic | Robotics Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2503.23877 |