AeroAgent：面向气动车辆设计的视觉—物理—决策框架
AeroAgent: A Vision-Physics-Decision Framework for Aerodynamic Vehicle Design
把可编辑的三维曲面表示、几何引导的 Transformer 代理模型与预算感知的 propose-evaluate-refine 循环串成闭环，为视觉研究者提供一种「生成结果必须通过物理仿真校验」的 3D 设计范式，其中 AeroFormer 用共享 3D 网格上的多任务头同时回归标量阻力与表面压力、速度场，可直接迁移到其他需要物理场预测的三维生成任务。
原文依据 A physics module, AeroFormer is a geometry-guided Transformer surrogate trained on a large-scale vehicle aerodynamics dataset of roughly 50k CFD simulations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论现代生成模型能够根据文本和图像提出引人注目的三维车辆外形，但要把这些草图转化为气动高效、符合法规的设计，仍需数周的高保真计算流体力学（CFD）计算与人工迭代。因此，缺乏可信物理环节的快速三维生成对缩短端到端设计时间帮助甚微。我们研究在严格的 CFD 预算下，AI 智能体如何闭合这一环路。我们提出 AeroAgent，一个围绕单一三维可编辑曲面表示构建的视觉—物理—决策框架，用于车辆外形设计。视觉模块将文本和二维参考图转化为多样、标准化的三维候选，并支持图像级编辑。物理模块 AeroFormer 是一个几何引导的 Transformer 代理模型，在大约 5 万次 CFD 仿真构成的大规模车辆气动数据集上训练；三个任务专用头在共享三维网格上预测阻力 Cd、表面压力与速度场。决策模块将法规尺寸限制与美学约束编码为可行性检验，利用原型先验与代理模型敏感度引导自由变形编辑，并运行预算感知的 propose-evaluate-refine 循环，其中仅最终排名前 K 的外形由高保真 CFD 确认。在覆盖五类常见车型的大量实验中，每辆车仅运行五次 propose-evaluate-refine 迭代即可将阻力平均降低 2–12%，相比基线工作流将高保真 CFD 调用减少 50–80%，同时保持或改善造型质量。
英文原文摘要 1568 字符
Modern generative models can propose striking 3D vehicle shapes from text and images, but turning these sketches into aerodynamically efficient, regulation compliant designs still requires weeks of high-fidelity computational fluid dynamics (CFD) and manual iteration. As a result, fast 3D generation without trustworthy physics in the loop does little to reduce end-to-end design time. We study how an AI agent can close this loop under a strict CFD budget. We introduce AeroAgent, a vision-physics-decision framework built around a single 3D, editable surface representation for vehicle shapes. A vision module turns text and 2D references into diverse, standardized 3D candidates and supports image-level edits. A physics module, AeroFormer is a geometry-guided Transformer surrogate trained on a large-scale vehicle aerodynamics dataset of roughly 50k CFD simulations; three task-specific heads predict drag Cd, surface pressure, and velocity fields on shared 3D grids. A decision module encodes regulatory size limits and aesthetic constraints as feasibility tests, uses prototype priors and surrogate sensitivities to guide free-form deformation edits, and runs a budget-aware propose evaluate refine loop in which only the final top K shapes are confirmed by high-fidelity CFD. In extensive experiments across five common vehicle classes, running only five propose evaluate refine iterations per vehicle reduces drag by an average of 2-12% and cuts high-fidelity CFD calls by 50-80% compared to baseline workflows, while preserving or improving styling quality.