GHIL-Glue: Hierarchical Control with Filtered Subgoal Images
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_ | 1866913565424746496 |
|---|---|
| author | Hatch, Kyle B. Balakrishna, Ashwin Mees, Oier Nair, Suraj Park, Seohong Wulfe, Blake Itkina, Masha Eysenbach, Benjamin Levine, Sergey Kollar, Thomas Burchfiel, Benjamin |
| author_facet | Hatch, Kyle B. Balakrishna, Ashwin Mees, Oier Nair, Suraj Park, Seohong Wulfe, Blake Itkina, Masha Eysenbach, Benjamin Levine, Sergey Kollar, Thomas Burchfiel, Benjamin |
| contents | Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating intermediate subgoals for low-level goal-conditioned policies to reach. However, the performance of these systems can be greatly bottlenecked by the interface between generative models and low-level controllers. For example, generative models may predict photorealistic yet physically infeasible frames that confuse low-level policies. Low-level policies may also be sensitive to subtle visual artifacts in generated goal images. This paper addresses these two facets of generalization, providing an interface to effectively "glue together" language-conditioned image or video prediction models with low-level goal-conditioned policies. Our method, Generative Hierarchical Imitation Learning-Glue (GHIL-Glue), filters out subgoals that do not lead to task progress and improves the robustness of goal-conditioned policies to generated subgoals with harmful visual artifacts. We find in extensive experiments in both simulated and real environments that GHIL-Glue achieves a 25% improvement across several hierarchical models that leverage generative subgoals, achieving a new state-of-the-art on the CALVIN simulation benchmark for policies using observations from a single RGB camera. GHIL-Glue also outperforms other generalist robot policies across 3/4 language-conditioned manipulation tasks testing zero-shot generalization in physical experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20018 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GHIL-Glue: Hierarchical Control with Filtered Subgoal Images Hatch, Kyle B. Balakrishna, Ashwin Mees, Oier Nair, Suraj Park, Seohong Wulfe, Blake Itkina, Masha Eysenbach, Benjamin Levine, Sergey Kollar, Thomas Burchfiel, Benjamin Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating intermediate subgoals for low-level goal-conditioned policies to reach. However, the performance of these systems can be greatly bottlenecked by the interface between generative models and low-level controllers. For example, generative models may predict photorealistic yet physically infeasible frames that confuse low-level policies. Low-level policies may also be sensitive to subtle visual artifacts in generated goal images. This paper addresses these two facets of generalization, providing an interface to effectively "glue together" language-conditioned image or video prediction models with low-level goal-conditioned policies. Our method, Generative Hierarchical Imitation Learning-Glue (GHIL-Glue), filters out subgoals that do not lead to task progress and improves the robustness of goal-conditioned policies to generated subgoals with harmful visual artifacts. We find in extensive experiments in both simulated and real environments that GHIL-Glue achieves a 25% improvement across several hierarchical models that leverage generative subgoals, achieving a new state-of-the-art on the CALVIN simulation benchmark for policies using observations from a single RGB camera. GHIL-Glue also outperforms other generalist robot policies across 3/4 language-conditioned manipulation tasks testing zero-shot generalization in physical experiments. |
| title | GHIL-Glue: Hierarchical Control with Filtered Subgoal Images |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2410.20018 |