We introduce a new method for the inverse design of nanophotonic devices that guarantees that the resulting designs satisfy strict length scale constraints, including minimum width and spacing constraints required by commercial semiconductor foundries. The method adopts several concepts from machine learning to transform the problem of topology optimization with strict length scale constraints to an unconstrained stochastic gradient optimization problem. Specifically, we introduce a conditional generator for feasible designs and adopt a straight-through estimator for the backpropagation of gradients to a latent design. We demonstrate the performance and reliability of our method by designing several common integrated photonic components.

中文翻译：

---

具有严格铸造制造约束的光子器件逆向设计

我们介绍了一种用于纳米光子器件逆向设计的新方法，该方法可确保最终设计满足严格的长度尺度约束，包括商业半导体代工厂所需的最小宽度和间距约束。该方法采用了机器学习中的几个概念，将具有严格长度尺度约束的拓扑优化问题转化为无约束的随机梯度优化问题。具体来说，我们为可行设计引入了条件生成器，并采用直通估计器将梯度反向传播到潜在设计。我们通过设计几个常见的集成光子组件来展示我们方法的性能和可靠性。