Research Group

Principal Investigator


Alex Gorodetsky is an Assistant Professor of Aerospace Engineering at the University of Michigan. His research interests include using applied mathematics and computational science to enhance autonomous decision making under uncertainty. He is especially interested in controlling systems, like autonomous aircraft, that must act in complex environments that are often represented by expensive computational simulations. Toward this goal, he pursues research in wide-ranging areas including uncertainty quantification, statistical inference, machine learning, numerical analysis, function approximation, control, and optimization.

Prior to coming to the University of Michigan, Alex was the John von Neumann Postdoctoral Research Fellow at Sandia National Laboratories in Albuquerque, New Mexico. At Sandia, Alex worked in the Optimization and Uncertainty Quantification Group on algorithms for propagating uncertainty through physical systems described with computationally expensive simulations.

Alex completed his Ph.D. (2016) and S.M. (2012) in the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology, where he worked on algorithms for stochastic optimal control and estimation in dynamical systems. He received his B.S.E (2010) in Aerospace Engineering from the University of Michigan.

Alex won the Air Force Young Investigator Award in 2018 and the NSF CAREER Award in 2023.

Email Alex: [goroda] at umich dot edu

View Full CV (Updated 7/20/2023)

Research Group

Postdoctoral Fellows

Kamal Abdulraheem


Kamal's research is focused on the design of autonomous control algorithms by enhancing AI/ML capabilities for control theory with applications to complex engineering systems like nuclear power plants (NPPs). The control algorithms will be capable of prognosis, diagnosis, and, importantly, decision-making and adaptivity. He seeks to use AI/ML enhanced control theory to tackle problems where model-based approaches, such as model-predictive control (MPC) and sliding mode control (SMC), are challenging. He is currently developing a novel hybrid controller of MPC-RL with uncertainty quantification (UQ) for micro-reactor applications. This approach learns a model from data, and integration with MPC ensures RL fully respects the physical model constraints.

Email Kamal: [abkamal] at umich dot edu


Google Scholar: link

Thomas Marks


Thomas completed his Ph.D. in Aerospace Engineering at the University of Michigan in the fall of 2023, where he studied data-driven modeling of electron transport in space propulsion devices as part of the Plasmadynamics and Electric Propulsion Laboratory. His research now focuses on integrating models of electric propulsion subsystems into a predictive engineering model of a Hall effect thruster as part of the NASA Joint Advanced Propulsion Institute. He is also interested in developing new methods for accelerating and compressing high-fidelity particle-based simulations of these spacecraft thrusters.

Email Thomas: [marksta] at umich dot edu



PhD Students

Doruk Aksoy


Doruk received 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. Currently, he is also enrolled in the Ph.D. in Scientific Computing joint degree program. His research interests include tensor decompositions, machine learning, and Bayesian inference. He is currently focused on developing efficient incremental algorithms to compute tensor decompositions.

Email Doruk: [doruk] at umich dot edu


Brian Chen


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 Dixon


Thomas received his B.S. in Computational Physics and Mathematics at Francis Marion University. His research interests include multi-fidelity estimation and stochastic optimization for trajectory planning and control. Currently, his research is expanding multi-fidelity sampling strategies to utilize multi-output systems and applying these methods in an Entry, Descent, and Landing (EDL) context.

Email Thomas: [tdixono] at umich dot edu


Joshua Eckels


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


Artem Mustaev


Artem Received his B.S. degree from the Aerospace Engineering Department at the University of Illinois at Urbana Champaign. His research interests include the application of multi-fidelity estimation to joint parameter state estimation problem.

Email Artem: [amustaev] at umich dot edu

Sanjan Muchandimath


Sanjan received his BTech degree in Aerospace Engineering from the Indian Institute of Technology, Madras and his MSE Aerospace degree from the University of Michigan. His research interests include CFD, Aerodynamics and its intersection with Uncertainty quantification and Bayesian Inference. Currently, his work focuses on Uncertainty quantification for CFD and multidisciplinary analysis to aid in reducing costs for certification by analysis . He is co-advised by Dr. Martins in the Aerospace department.

Email Sanjan: [sanjancm] at umich dot edu

Liliang Wang


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.

Master's Students

  • Akshat Dubey, 2024
  • Aditya Deshpande, 2024
  • Sinaendhran Pujali Elilarasan, 2024

Undergraduate Students

  • Jacob Klinger, 2023 - 2024
  • Gabriel Mora, 2024
  • Ritvik Pasham, 2024
  • Elida Sensoy, 2024

Former Members

  • Yaser Afshar, Postdoctoral Fellow 2019
  • Deepika Baskar, Masters 2018 - 2019, now at Collins Aerospace
  • Nicholas Galioto, PhD + Postdoc 2018-2024,
  • Koray Kachar, Masters 2018 — 2020
  • Tejas Kadambi, Undergraduate, 2022
  • Donghak Kim, Masters 2018 - 2019
  • Jiwon Kim, Masters 2022 - 2023
  • Jacob Klinger, Undergraduate, 2023
  • Ian Lasky, Masters 2019
  • Hao Liu, Undergraduate, 2021
  • Carleen McKenna, Masters, 2019-2023
  • Keyshawn Nunely, Undergraduate, 2023
  • Kaijun He, Undergraduate 2018 - 2019,
  • Kazuya Tsuji, Undergraduate 2020-2021
  • Trung Pham, Postdoctoral Fellow 2019-2022
  • Hadi Salehi, Postdoctoral Fellow, 2020, LinkedIn
  • Audelia Szulman, Masters 2020, now at RGBSI LinkedIn
  • Siddhant, Tandon, Masters 2020, LinkedIn, website
  • Sunbochen Tang, Masters 2019 - 2020, now at MIT
  • Jiachen (Lydia) Wang, Masters 2018 - 2019
  • Jose Eduard Castro Villasana (UDEM), SURE 2023
  • Jose Alberto Castro Villasana (UDEM), SURE 2023
  • Sruti Vutukury, Masters 2023-2024, now at SpaceX
  • John Wiegand, Masters 2020, now at Raytheon
  • Alex Xu, Undergraduate 2022-2023,
  • Hang Yang, PhD 2022, now at McKinsey LinkedIn
  • Yulong (Arthur) Yang, Undergraduate 2020
  • Mingfei (Doris) Ye, Masters 2020, LinkedIn
  • Xuhao Zhang, Masters 2022
  • Jingyi Zhou, Masters, 2023

Copyright (c) 2020-2024, Alex Gorodetsky, License: CC BY-SA 4.0