# Fabrica: Dual-Arm Assembly of General Multi-Part Objects via Integrated Planning and Learning

arXiv: https://arxiv.org/abs/2506.05168 · HTML: https://mlsanity.com/paper/2506.05168/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jun 2025.

## Built on by (most cited first, 8 of 8)

- [A3D: Adaptive Affordance Assembly with Dual-Arm Manipulation](https://mlsanity.com/paper/2601.11076/) (2026)
- [CADKnitter: Compositional CAD Generation from Text and Geometry Guidance](https://mlsanity.com/paper/2512.11199/) (2025)
- [AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects](https://mlsanity.com/paper/2605.12845/) (2026)
- [Sequential Planning via Anchored Robotic Keypoints](https://mlsanity.com/paper/2606.30613/) (2026)
- [Play2Perfect: What Matters in Dexterous Play Pretraining for Precise Assembly?](https://mlsanity.com/paper/2606.26428/) (2026)
- [FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model](https://mlsanity.com/paper/2607.01212/) (2026)
- [CREST: Constraint-Release Execution for Multi-Robot Warehouse Shelf Rearrangement](https://mlsanity.com/paper/2603.28803/) (2026)
- [Generalizable Robotic Insertion with World Models](https://mlsanity.com/paper/2609.28258/) (2026)

## Abstract (arXiv)

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/