09/02/2026
U-M Associate Professor of Aerospace Engineering, Ricardo Vinuesa, and international co-authors were recently published in Nature for their work on "The HydroGym reinforcement learning platform for fluid dynamics."
Together, the team's work showcases a platform for training and comparing machine learning models for actively reducing drag, improving lift, cutting noise, and managing heat in relation to fluid dynamics.
Read the full article from the University of Michigan College of Engineering here: https://news.engin.umich.edu/2026/08/hydrogym-trains-assesses-ai-for-actively-controlling-fluid-dynamics/
With more than 60 environments, the simulated proving ground aims to speed the development of AI controllers that optimize drag, lift, noise and heat management.