Vigor improves industrial layout programs by fixing geometry errors
VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs
Artificial Intelligence
Summary
Industrial layouts made by computers can sometimes look right but break important rules like spacing or safety. The authors found that making sure a program runs doesn’t mean the layout is actually possible or safe. They created a special dataset to test these problems and built VIGOR, a system that checks and fixes layout mistakes by carefully adjusting parts so everything fits together properly. Their approach works much better than previous methods at making sure layouts are both runnable and follow engineering rules.
What this means in practice
- •For industrial designers: Automatically generate and verify factory layouts that meet complex engineering spacing and safety constraints.
- •For robotics teams: Create executable but also physically feasible robot workspace arrangements ensuring no collisions or clearance violations.
Authors
Fuqiang Wang, Zheng Guo, Xiaoming Wu, Hanlin Kong, Nayu Liu, Chuanting Zhang, Daojun Liang, Jingxuan Wei
Abstract
Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, clearance, aisle, or structural constraints. We identify this mismatch as the executability-engineering-feasibility gap, where locally plausible placements can remain globally infeasible because corrections to one device may introduce violations elsewhere. To make this gap measurable in a controlled setting, we construct an execution-grounded industrial scene-program dataset with 1,749 constructible scenarios, complete executable programs, and 94 final-state geometric checks per scenario. We further propose VIGOR, which combines supervised scene-program generation with execution-grounded verification and staged geometric refinement. Supervised fine-tuning establishes complete program generation, local projection resolves independently correctable violations, and joint conflict-graph repair coordinates residual multi-object conflicts while preserving structural relations. Experiments show that VIGOR achieves 96.86% Complete Feasibility and an Overall score of 91.20, outperforming the strongest evaluated baseline by 10.42 points in Overall. These results show that, under controlled industrial layout conditions, reliable scene-program generation requires not only executable programs, but also explicit verification and coordinated resolution of coupled engineering constraints.