Max Robotics — Global Service Robot Directory + US Certification

About

Tyler Westenbroek is a robotics and control systems researcher whose work sits at the intersection of nonlinear control theory and modern machine learning, with a particular focus on reinforcement learning as a tool for solving classical control problems. His most recognized contribution is a novel framework that uses model-free policy optimization to learn feedback linearizing controllers for systems with unknown dynamics — work that has garnered over 50 citations across two closely related publications from 2019 and 2020. This research elegantly bridges decades-old nonlinear control techniques with contemporary data-driven methods, offering practical solutions where precise system models are unavailable. Westenbroek has extended these ideas to bipedal robotics, addressing real-world challenges such as model uncertainty and actuator constraints in locomotion systems. His 2022 work on Lyapunov-guided reinforcement learning demonstrates a growing interest in making RL methods safer and more sample-efficient for physical robot deployment — a critical challenge in the field. Additionally, his research on hybrid optimal control for robotic walking tackles the mathematical difficulties introduced by event-driven discontinuities in locomotion dynamics. Taken together, Westenbroek's body of work reflects a principled effort to make advanced control and learning methods more robust, efficient, and deployable on real robotic platforms.