Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
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_ | 1866915331518234624 |
|---|---|
| author | Yang, Jonathan Fu, Chuyuan Kelly Shah, Dhruv Sadigh, Dorsa Xia, Fei Zhang, Tingnan |
| author_facet | Yang, Jonathan Fu, Chuyuan Kelly Shah, Dhruv Sadigh, Dorsa Xia, Fei Zhang, Tingnan |
| contents | In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as inputs to a diffusion policy to solve dexterous bimanual manipulation tasks in the real world. We propose a novel mixture-of-experts policy architecture that combines multiple specialized expert models, each trained on a distinct mid-level representation, to improve policy generalization. This method achieves an average success rate that is 11% higher than a language-grounded baseline and 24 percent higher than a standard diffusion policy baseline on our evaluation tasks. Furthermore, we find that leveraging mid-level representations as supervision signals for policy actions within a weighted imitation learning algorithm improves the precision with which the policy follows these representations, yielding an additional performance increase of 10%. Our findings highlight the importance of grounding robot policies not only with broad perceptual tasks but also with more granular, actionable representations. For further information and videos, please visit https://mid-level-moe.github.io. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_06196 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization Yang, Jonathan Fu, Chuyuan Kelly Shah, Dhruv Sadigh, Dorsa Xia, Fei Zhang, Tingnan Robotics 68T40 In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as inputs to a diffusion policy to solve dexterous bimanual manipulation tasks in the real world. We propose a novel mixture-of-experts policy architecture that combines multiple specialized expert models, each trained on a distinct mid-level representation, to improve policy generalization. This method achieves an average success rate that is 11% higher than a language-grounded baseline and 24 percent higher than a standard diffusion policy baseline on our evaluation tasks. Furthermore, we find that leveraging mid-level representations as supervision signals for policy actions within a weighted imitation learning algorithm improves the precision with which the policy follows these representations, yielding an additional performance increase of 10%. Our findings highlight the importance of grounding robot policies not only with broad perceptual tasks but also with more granular, actionable representations. For further information and videos, please visit https://mid-level-moe.github.io. |
| title | Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization |
| topic | Robotics 68T40 |
| url | https://arxiv.org/abs/2506.06196 |