This is the home page of Nate Kent. I’m currently a PhD candidate at the University of Rochester and working in the Robotics and Artificial Intelligence Laboratory. My current research focuses on utilizing probabilistic graphical models (PGMs) in order to infer central pattern generator (CPG) parameters that enable locomotion in underactuated robots. These PGMs are trained using reinforcement learning techniques inside of physics simulators, such as RuBullet and nphysics, and then deployed to physical robots via a closed-loop controller.
Most of my current development happens in the Rust programming language with most of my projects being in the domain of simulators, graphics, and distributed computation.