Peter Werner is a fourth-year PhD candidate at MIT CSAIL specializing in robotics, control, and learning, with five years of research experience spanning ETH Zürich, UPenn, Toyota Research Institute, and MIT. His work blends model-based control, deep reinforcement learning, and data-driven residual dynamics to advance mobile manipulation and legged/aerial systems, informed by hands-on projects like teaching ANYmal badminton and swing-up control for tactile cart-pole. Comfortable moving between theory and implementation, he has applied MPC, trajectory optimization, and optimization-based compensation in real robotic platforms. Based in Cambridge, MA, he brings a cross-disciplinary background in mechanical engineering and robotics systems that often uncovers practical failure modes other researchers miss.
5 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD Electrical Engineering and Computer Science, Doctor of Philosophy - PhD Electrical Engineering and Computer Science at Massachusetts Institute of Technology
Robotics Systems and Control MSc, Robotics Systems and Control MSc at ETH Zürich
Exchange Semester Mechatronics Robotics and Automation Engineering, Exchange Semester Mechatronics Robotics and Automation Engineering at University of Pennsylvania
Fast and simple implementation of RL algorithms, designed to run fully on GPU.
Contributions:1 PR, 55 pushes, 7 branches in 1 year 4 months
pytorchcppdeep-learninggpureinforcement-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.