Research Group

Doruk recieved his B.Sc degree from Bogazici University Department of Mechanical Engineering in Turkey and his MSE degree from University of Michigan Department of Mechanical Engineering. His research interests include design and integration of machine learning tools into modeling and control. His current research is focused on creating an inverse design tool for self oscillating gels using deep learning architectures.

Email Doruk: [doruk] at umich dot edu

LinkedIn: https://www.linkedin.com/in/dorukaks

Brian received his B.S. in mathematics from the University of Chicago. His research interests include reinforcement learning and imitation learning, as well as applications of machine learning to quantum computing. Currently, his work is on imitation learning in games, with the goal of extracting interpretable strategies from gameplay. He is co-advised by Dr. Veerapaneni in the Mathematics department.

Email Brian: [chenbri] at umich dot edu

Thomas received his B.S. in Computational Physics and Mathematics at Francis Marion University. His research interests include using computational methods with machine learning to solve modern aerospace problems.

Email Thomas: [tdixono] at umich dot edu

LinkedIn: https://www.linkedin.com/in/thomas-dixon-855718191/

In-space propulsion research efforts are focused on electric propulsion systems, which are essential for low Earth orbit spacecraft and future long-term space exploration missions. Josh’s research interests in this field are specifically on improving computational and predictive plasma dynamics modeling and increasing performance of high-power Hall-effect thrusters. Josh received his B.S. in Mechanical Engineering from Rose-Hulman Institute of Technology.

Email Joshua: [eckelsjd] at umich dot edu

LinkedIn: https://www.linkedin.com/in/eckelsjd/

Nick’s research is primarily focused on the areas of system identification and Bayesian inference. He is interested in finding ways to integrate our knowledge of physics into system identification approaches to yield more efficient and reliable results. Additionally, the reach of Bayesian inference is in general limited by system complexity and computational demand, and he is interested in overcoming these limits to extend practical methods of Bayesian inference into increasingly complex problems.

Email Nick: [ngalioto] at umich dot edu

LinkedIn: https://www.linkedin.com/in/ngalioto/

Carleen McKenna received her B.S. in Mechanical Engineering from North Carolina State University, and is a National Science Foundation Graduate Fellow. Her research interests include optimal control under uncertainty and the integration of iterative learning control with existing stochastic optimal control methodologies. Currently, her research is focused on the application of these topics to dynamic soaring of unmanned aerial vehicles (UAVs).

Email Carleen: [camckenn] at umich dot edu

LinkedIn: https://www.linkedin.com/in/carleen-mckenna-bb82928a/

Liliang’s research interests include reinforcement learning, stochastic control and computation compression. Currently, her work is focused on incorporation of reinforcement learning and Bayesian inference for optimal control of systems under uncertainties from different sources, for a good balance of controller performance, robustness, without the need of large datasets.