Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915212657950720 |
|---|---|
| author | Bi, Jianxin Lim, Kelvin Chen, Kaiqi Huang, Yifei Soh, Harold |
| author_facet | Bi, Jianxin Lim, Kelvin Chen, Kaiqi Huang, Yifei Soh, Harold |
| contents | Recent advances in diffusion-based robot policies have demonstrated significant potential in imitating multi-modal behaviors. However, these approaches typically require large quantities of demonstration data paired with corresponding robot action labels, creating a substantial data collection burden. In this work, we propose a plan-then-control framework aimed at improving the action-data efficiency of inverse dynamics controllers by leveraging observational demonstration data. Specifically, we adopt a Deep Koopman Operator framework to model the dynamical system and utilize observation-only trajectories to learn a latent action representation. This latent representation can then be effectively mapped to real high-dimensional continuous actions using a linear action decoder, requiring minimal action-labeled data. Through experiments on simulated robot manipulation tasks and a real robot experiment with multi-modal expert demonstrations, we demonstrate that our approach significantly enhances action-data efficiency and achieves high task success rates with limited action data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07584 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers Bi, Jianxin Lim, Kelvin Chen, Kaiqi Huang, Yifei Soh, Harold Robotics Machine Learning Recent advances in diffusion-based robot policies have demonstrated significant potential in imitating multi-modal behaviors. However, these approaches typically require large quantities of demonstration data paired with corresponding robot action labels, creating a substantial data collection burden. In this work, we propose a plan-then-control framework aimed at improving the action-data efficiency of inverse dynamics controllers by leveraging observational demonstration data. Specifically, we adopt a Deep Koopman Operator framework to model the dynamical system and utilize observation-only trajectories to learn a latent action representation. This latent representation can then be effectively mapped to real high-dimensional continuous actions using a linear action decoder, requiring minimal action-labeled data. Through experiments on simulated robot manipulation tasks and a real robot experiment with multi-modal expert demonstrations, we demonstrate that our approach significantly enhances action-data efficiency and achieves high task success rates with limited action data. |
| title | Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2410.07584 |