Automated Creation of Digital Cousins for Robust Policy Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916445423665152 |
|---|---|
| author | Dai, Tianyuan Wong, Josiah Jiang, Yunfan Wang, Chen Gokmen, Cem Zhang, Ruohan Wu, Jiajun Fei-Fei, Li |
| author_facet | Dai, Tianyuan Wong, Josiah Jiang, Yunfan Wang, Chen Gokmen, Cem Zhang, Ruohan Wu, Jiajun Fei-Fei, Li |
| contents | Training robot policies in the real world can be unsafe, costly, and difficult to scale. Simulation serves as an inexpensive and potentially limitless source of training data, but suffers from the semantics and physics disparity between simulated and real-world environments. These discrepancies can be minimized by training in digital twins, which serve as virtual replicas of a real scene but are expensive to generate and cannot produce cross-domain generalization. To address these limitations, we propose the concept of digital cousins, a virtual asset or scene that, unlike a digital twin, does not explicitly model a real-world counterpart but still exhibits similar geometric and semantic affordances. As a result, digital cousins simultaneously reduce the cost of generating an analogous virtual environment while also facilitating better robustness during sim-to-real domain transfer by providing a distribution of similar training scenes. Leveraging digital cousins, we introduce a novel method for their automated creation, and propose a fully automated real-to-sim-to-real pipeline for generating fully interactive scenes and training robot policies that can be deployed zero-shot in the original scene. We find that digital cousin scenes that preserve geometric and semantic affordances can be produced automatically, and can be used to train policies that outperform policies trained on digital twins, achieving 90% vs. 25% success rates under zero-shot sim-to-real transfer. Additional details are available at https://digital-cousins.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07408 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Automated Creation of Digital Cousins for Robust Policy Learning Dai, Tianyuan Wong, Josiah Jiang, Yunfan Wang, Chen Gokmen, Cem Zhang, Ruohan Wu, Jiajun Fei-Fei, Li Robotics Training robot policies in the real world can be unsafe, costly, and difficult to scale. Simulation serves as an inexpensive and potentially limitless source of training data, but suffers from the semantics and physics disparity between simulated and real-world environments. These discrepancies can be minimized by training in digital twins, which serve as virtual replicas of a real scene but are expensive to generate and cannot produce cross-domain generalization. To address these limitations, we propose the concept of digital cousins, a virtual asset or scene that, unlike a digital twin, does not explicitly model a real-world counterpart but still exhibits similar geometric and semantic affordances. As a result, digital cousins simultaneously reduce the cost of generating an analogous virtual environment while also facilitating better robustness during sim-to-real domain transfer by providing a distribution of similar training scenes. Leveraging digital cousins, we introduce a novel method for their automated creation, and propose a fully automated real-to-sim-to-real pipeline for generating fully interactive scenes and training robot policies that can be deployed zero-shot in the original scene. We find that digital cousin scenes that preserve geometric and semantic affordances can be produced automatically, and can be used to train policies that outperform policies trained on digital twins, achieving 90% vs. 25% success rates under zero-shot sim-to-real transfer. Additional details are available at https://digital-cousins.github.io/. |
| title | Automated Creation of Digital Cousins for Robust Policy Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2410.07408 |