# Prompt-to-Product: Generative Assembly via Bimanual Manipulation

**Authors:** Ruixuan Liu, Philip Huang, Ava Pun, Kangle Deng, Shobhit Aggarwal, Kevin Tang, Michelle Liu, Deva Ramanan, Jun-Yan Zhu, Jiaoyang Li, Changliu Liu

arXiv: 2508.21063 · 2025-08-29

## TL;DR

Prompt-to-Product is an automated pipeline that transforms natural language prompts into physical LEGO assemblies using robotic manipulation, significantly reducing manual effort and expertise needed for product creation.

## Contribution

It introduces a novel system that automatically generates and constructs LEGO assembly structures from natural language descriptions, integrating design and robotic construction.

## Key findings

- Reduces manual effort in assembly creation
- Enables real-world construction from natural language prompts
- Demonstrates effectiveness through user study

## Abstract

Creating assembly products demands significant manual effort and expert knowledge in 1) designing the assembly and 2) constructing the product. This paper introduces Prompt-to-Product, an automated pipeline that generates real-world assembly products from natural language prompts. Specifically, we leverage LEGO bricks as the assembly platform and automate the process of creating brick assembly structures. Given the user design requirements, Prompt-to-Product generates physically buildable brick designs, and then leverages a bimanual robotic system to construct the real assembly products, bringing user imaginations into the real world. We conduct a comprehensive user study, and the results demonstrate that Prompt-to-Product significantly lowers the barrier and reduces manual effort in creating assembly products from imaginative ideas.

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/2508.21063/full.md

## Figures

20 figures with captions in the complete paper: https://tomesphere.com/paper/2508.21063/full.md

## References

30 references — full list in the complete paper: https://tomesphere.com/paper/2508.21063/full.md

---
Source: https://tomesphere.com/paper/2508.21063