Printed Circuit Boards (PCBs) are used in nearly all modern electronics; yet, circuit design is highly complex and costly. The aim of my project is to develop a differentiable, physics-based model of the PCB placement process and devise methods to efficiently find optimal placements of circuit components. Sampling-based approaches broadly explore the solution space but are computationally expensive, whereas gradient-based approaches converge quickly but are prone to local optima. To achieve both robust exploration and efficient convergence while satisfying physical constraints such as wire length, heat dissipation, and electromagnetic interference, we will explore algorithms that combine evolutionary search with gradient-based optimization guided by a differentiable physics simulator.

I hope to apply the skills I’ve developed through prior classes and internships during this SuperUROP project and strengthen my abilities as a researcher. I’m particularly excited to continue my work in the Algorithmic Design Group and deepen my understanding of how optimization techniques can be leveraged to tangible problems in the design domain!