Inverse design of photonic devices with strict foundry fabrication constraints
This addresses the challenge of creating manufacturable photonic devices for semiconductor foundries, though it appears incremental as it builds on existing topology optimization with new constraints.
The paper tackles the problem of inverse design for nanophotonic devices by ensuring designs meet strict fabrication constraints, such as minimum width and spacing, using a method that transforms topology optimization into an unconstrained stochastic gradient problem, and demonstrates its performance by designing integrated photonic components.
We introduce a new method for inverse design of nanophotonic devices which guarantees that 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 backpropagation of gradients to a latent design. We demonstrate the performance and reliability of our method by designing several common integrated photonic components.