Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2502.18015 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908352208961536 |
|---|---|
| author | Jung, Haewon Lee, Donguk Park, Haecheol Kim, JunHyeop Kim, Beomjoon |
| author_facet | Jung, Haewon Lee, Donguk Park, Haecheol Kim, JunHyeop Kim, Beomjoon |
| contents | Current robots struggle with long-horizon manipulation tasks requiring sequences of prehensile and non-prehensile skills, contact-rich interactions, and long-term reasoning. We present $\texttt{SPIN}$ ($\textbf{S}$kill $\textbf{P}$lanning to $\textbf{IN}$ference), a framework that distills a computationally intensive planning algorithm into a policy via imitation learning. We propose $\texttt{Skill-RRT}$, an extension of RRT that incorporates skill applicability checks and intermediate object pose sampling for solving such long-horizon problems. To chain independently trained skills, we introduce $\textit{connectors}$, goal-conditioned policies trained to minimize object disturbance during transitions. High-quality demonstrations are generated with $\texttt{Skill-RRT}$ and distilled through noise-based replay in order to reduce online computation time. The resulting policy, trained entirely in simulation, transfers zero-shot to the real world and achieves over 80% success across three challenging long-horizon manipulation tasks and outperforms state-of-the-art hierarchical RL and planning methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_18015 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | $\texttt{SPIN}$: distilling $\texttt{Skill-RRT}$ for long-horizon prehensile and non-prehensile manipulation Jung, Haewon Lee, Donguk Park, Haecheol Kim, JunHyeop Kim, Beomjoon Robotics Current robots struggle with long-horizon manipulation tasks requiring sequences of prehensile and non-prehensile skills, contact-rich interactions, and long-term reasoning. We present $\texttt{SPIN}$ ($\textbf{S}$kill $\textbf{P}$lanning to $\textbf{IN}$ference), a framework that distills a computationally intensive planning algorithm into a policy via imitation learning. We propose $\texttt{Skill-RRT}$, an extension of RRT that incorporates skill applicability checks and intermediate object pose sampling for solving such long-horizon problems. To chain independently trained skills, we introduce $\textit{connectors}$, goal-conditioned policies trained to minimize object disturbance during transitions. High-quality demonstrations are generated with $\texttt{Skill-RRT}$ and distilled through noise-based replay in order to reduce online computation time. The resulting policy, trained entirely in simulation, transfers zero-shot to the real world and achieves over 80% success across three challenging long-horizon manipulation tasks and outperforms state-of-the-art hierarchical RL and planning methods. |
| title | $\texttt{SPIN}$: distilling $\texttt{Skill-RRT}$ for long-horizon prehensile and non-prehensile manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2502.18015 |