Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2506.05168 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915328359923712 |
|---|---|
| author | Tian, Yunsheng Jacob, Joshua Huang, Yijiang Zhao, Jialiang Gu, Edward Ma, Pingchuan Zhang, Annan Javid, Farhad Romero, Branden Chitta, Sachin Sueda, Shinjiro Li, Hui Matusik, Wojciech |
| author_facet | Tian, Yunsheng Jacob, Joshua Huang, Yijiang Zhao, Jialiang Gu, Edward Ma, Pingchuan Zhang, Annan Javid, Farhad Romero, Branden Chitta, Sachin Sueda, Shinjiro Li, Hui Matusik, Wojciech |
| contents | Multi-part assembly poses significant challenges for robots to execute long-horizon, contact-rich manipulation with generalization across complex geometries. We present Fabrica, a dual-arm robotic system capable of end-to-end planning and control for autonomous assembly of general multi-part objects. For planning over long horizons, we develop hierarchies of precedence, sequence, grasp, and motion planning with automated fixture generation, enabling general multi-step assembly on any dual-arm robots. The planner is made efficient through a parallelizable design and is optimized for downstream control stability. For contact-rich assembly steps, we propose a lightweight reinforcement learning framework that trains generalist policies across object geometries, assembly directions, and grasp poses, guided by equivariance and residual actions obtained from the plan. These policies transfer zero-shot to the real world and achieve 80% successful steps. For systematic evaluation, we propose a benchmark suite of multi-part assemblies resembling industrial and daily objects across diverse categories and geometries. By integrating efficient global planning and robust local control, we showcase the first system to achieve complete and generalizable real-world multi-part assembly without domain knowledge or human demonstrations. Project website: http://fabrica.csail.mit.edu/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_05168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning Tian, Yunsheng Jacob, Joshua Huang, Yijiang Zhao, Jialiang Gu, Edward Ma, Pingchuan Zhang, Annan Javid, Farhad Romero, Branden Chitta, Sachin Sueda, Shinjiro Li, Hui Matusik, Wojciech Robotics Multi-part assembly poses significant challenges for robots to execute long-horizon, contact-rich manipulation with generalization across complex geometries. We present Fabrica, a dual-arm robotic system capable of end-to-end planning and control for autonomous assembly of general multi-part objects. For planning over long horizons, we develop hierarchies of precedence, sequence, grasp, and motion planning with automated fixture generation, enabling general multi-step assembly on any dual-arm robots. The planner is made efficient through a parallelizable design and is optimized for downstream control stability. For contact-rich assembly steps, we propose a lightweight reinforcement learning framework that trains generalist policies across object geometries, assembly directions, and grasp poses, guided by equivariance and residual actions obtained from the plan. These policies transfer zero-shot to the real world and achieve 80% successful steps. For systematic evaluation, we propose a benchmark suite of multi-part assemblies resembling industrial and daily objects across diverse categories and geometries. By integrating efficient global planning and robust local control, we showcase the first system to achieve complete and generalizable real-world multi-part assembly without domain knowledge or human demonstrations. Project website: http://fabrica.csail.mit.edu/ |
| title | Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.05168 |