Mark Brudnak

Clemson University, United States Department of the Army

Papers

Total Citations

H-Index

About

Mark Brudnak is a leading researcher at the intersection of autonomous vehicle control, robotics, and nonlinear dynamics, with a focus on safe and optimal motion planning. His work has pioneered the application of hybrid reinforcement learning and Koopman operator theory to real-world autonomous navigation, particularly for Ackermann-steered vehicles operating in close proximity to humans. Brudnak’s 2022 paper on hybrid reinforcement learning controllers (13 citations) addresses the critical challenge of low tracking error trajectory control, combining linear optimal techniques like LQR and MPC with adaptive learning for enhanced safety. In 2023, he advanced the field with an analytical construction of Koopman EDMD candidate functions (8 citations), enabling more accurate system identification and path-tracking performance for autonomous vehicles. Earlier, his foundational work on real-time, distributed UGV dynamics simulation (2002, 8 citations) contributed to the U.S. Army’s Vehicle Dynamics and Mobility Server, a high-fidelity platform for conceptual unmanned ground vehicle testing. Brudnak’s contributions bridge theoretical control methods and practical deployment, making him a key figure in the development of safer, more capable autonomous systems.