Nathan obtained a Bachelor's degree from the Massachusetts Institute of Technology in 2015 and a Master's degree from Stanford in 2017, majoring in Mechanical Engineering. During his work at MIT, he focused on 3D printing at multiple scales, including micro-scale 3D printing of single biological cells, and large-scale 3D printing of buildings. Nathan is currently pursuing a PhD degree at Stanford University, focusing on integrating machine learning and vehicle control at the limits of friction.
Professional drivers are not only able to safely maneuver vehicles at the limits of road-tire friction, but also able to do so in conditions ranging from snowy to dry roads. Drawing inspiration from how skilled drivers learn and harnessing the abundance of data that automated vehicles generate, I aim to design automated driving techniques that learn from data to improve performance. Whether this constitutes learning neural network models for improved predictive control or lap-to-lap improvement for racing by using policy gradients, I am interested in the intersection of learning and control. By fully leveraging the available data and taking inspiration from how professional drivers learn, road safety can be vastly improved.