Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.02288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911725925695488 |
|---|---|
| author | Cao, Jianbao Zhao, Zhangrui Feng, Bohan Hu, Zixuan Li, Rui Wan, Haiyuan Li, Chenxi Li, Jingyuan Cai, Wenzhe Bai, Lei Ouyang, Wanli Duan, Lingyu Huang, Di Pan, Minting Zhang, Sha Ma, Xinzhu Tang, Shixiang Zhou, Dongzhan |
| author_facet | Cao, Jianbao Zhao, Zhangrui Feng, Bohan Hu, Zixuan Li, Rui Wan, Haiyuan Li, Chenxi Li, Jingyuan Cai, Wenzhe Bai, Lei Ouyang, Wanli Duan, Lingyu Huang, Di Pan, Minting Zhang, Sha Ma, Xinzhu Tang, Shixiang Zhou, Dongzhan |
| contents | Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the protocol grounding and layout-level safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are realistic and valid under modeled geometric, chemical-safety, and navigation constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02288 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory Cao, Jianbao Zhao, Zhangrui Feng, Bohan Hu, Zixuan Li, Rui Wan, Haiyuan Li, Chenxi Li, Jingyuan Cai, Wenzhe Bai, Lei Ouyang, Wanli Duan, Lingyu Huang, Di Pan, Minting Zhang, Sha Ma, Xinzhu Tang, Shixiang Zhou, Dongzhan Computer Vision and Pattern Recognition Automated laboratories hold the promise of accelerating scientific discovery, yet their deployment is bottlenecked by the difficulty of designing safe and executable environments. While simulator-based design offers scalability, existing 3D scene generation methods are primarily tailored for household settings, optimizing for visual plausibility while neglecting the protocol grounding and layout-level safety constraints essential for scientific experimentation. We present LabBuilder, an end-to-end system that generates and verifies 3D laboratory layouts from concise textual specifications. It operates through three tightly coupled components: LabForge first curates a meta-dataset of annotated assets and chemical knowledge, translating natural language specifications into structured protocols; building on these protocols, LabGen synthesizes laboratory layouts via an iterative, constraint-aware optimization strategy; finally, LabTouchstone evaluates the resulting layouts as a unified benchmark. Extensive experiments demonstrate that LabBuilder significantly outperforms existing state-of-the-art methods, producing laboratory environments that are realistic and valid under modeled geometric, chemical-safety, and navigation constraints. |
| title | LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.02288 |