Will Sharpless

Email: wsharpless (at) ucsd.edu

Will is a Ph.D. student in Mechanical and Aerospace Engineering at UCSD. His interests revolve around control and optimization in nonlinear, stochastic systems for autonomous devices in robotics, medicine and economics. He is particularly captivated by the graphs underlying differential systems and how their topology influences stability.

He also generally enjoys employing learning methods in these spaces. As an undergraduate, Will studied applied math and biology at UC Berkeley, during which he discovered a fascination for the theory of nonlinear systems and control that arose in the metabolic networks and cellular ecology.

When away from work, Will is likely running, reading, or listening to music.

Selected Projects

High-Dimensional Physics-Informed Machine Learning: Advancing methods for semi-supervised learning the solution to differential games using physics-informed neural networks (PINNs). On the left is a 50D nonlinear problem (top row is the baseline, bottom rows are our method). On the right is a quadrotor experiment with 99.9% probabilistic safety guarantees.

Efficient Linear Reachability with Guarantees for Nonlinear Dynamics: A method to linearize a nonlinear control system wherein the linearization error is treated as an adversarial disturbance in Hopf reachability analysis to provide guaranteed conservative (green) sets to reach a goal or avoid an obstacle

Related Papers