LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory

2026-05-04

AI Summary

Existing 3D scene generation methods struggle to meet the stringent requirements of automated laboratories regarding functional semantics and safety constraints. To address this gap, this work proposes the first end-to-end, three-stage system: it begins by constructing a metadata repository enriched with chemical knowledge and parsing it into structured experimental protocols; next, it generates compliant laboratory layouts through constraint-aware iterative optimization guided by these protocols; and finally, it validates layout feasibility and safety using a multidimensional benchmark. By unifying experimental protocols, functional semantics, and safety constraints within a single generative framework, the method significantly outperforms existing approaches, delivering layouts that support complex scientific workflows with high visual realism, functional validity, and experimental safety.

Abstract

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 rigorous functional semantics and 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 not only realistic but also functionally valid and safe for complex experimental workflows.

Problem

• 3D layout generation
• laboratory design
• functional semantics
• safety constraints
• scientific experimentation

Innovation

• protocol-grounded generation
• constraint-aware optimization
• functional 3D layout
• laboratory safety
• automated lab design