Prof.  Boyuan Chen
Director of General Robotics Lab
Duke University

Abstract

What if a machine could watch a video and write down the equations of motion? I'll discuss our recent work toward this goal - systems that learn to discover the hidden state variables and governing dynamics directly from raw visual data. These discovered Neural State Variables and Neural State Variables and Neural State Vector Fields not only reproduce trajectories but also reveal the structure of these dynamical systems: equilibrium, stability, and chaos. The results suggest a path toward a self-driven AI scientist.