Dr. Sai Tej Paruchuri received his Ph.D. in Mechanical Engineering and M.S. in Mathematics from Virginia Tech, USA. Before joining IIT Madras, he was a Research Scientist at the Plasma Control Laboratory in the Department of Mechanical Engineering & Mechanics at Lehigh University, USA, where he had previously served as a Postdoctoral Research Associate.
Dr. Paruchuri pursues theoretical and applied research in control, estimation, and learning for mechanical and other dynamical systems.
His theoretical work lies at the intersection of control theory, approximation theory, and learning theory. He focuses on nonlinear adaptive control and reproducing kernel Hilbert space (RKHS) embedding methods for adaptive estimation, with an emphasis on rigorous theoretical guarantees.
His applied research includes plasma control in tokamaks, devices that use strong magnetic fields to confine hot, ionized gas for nuclear fusion research. He has worked on experiments at international tokamak research facilities such as KSTAR (South Korea), TCV (Switzerland), and DIII-D (USA), and on developing reinforcement learning agents for plasma control. He is also exploring applications of control and learning methods to robotics.
Through collaborations, he has worked on Koopman operator methods and adaptive dynamic programming. His earlier work focused on modeling and estimation of piezoelectric and smart-material structures for vibration attenuation.
Current Courses
ME 4010 - Control Systems (Jan - May 2027)
1. S. T. Paruchuri et al. Density regulation with disruption avoidance in next-generation tokamaks using a safe reinforcement learning-based controller. Fusion Engineering and Design, 216, article 115064, 2025.
2. S. T. Paruchuri, J. Guo, and A. Kurdila. Sufficient Conditions for Parameter Convergence Over Embedded Manifolds Using Kernel Techniques. IEEE Transactions on Automatic Control, 68(2), pp. 753–765, 2023.
1. S. T. Paruchuri and E. Schuster. Distributed Regulation of the Safety Factor Profile in Tokamaks Using Nonlinear Infinite-dimensional Control. 22nd IFAC World Congress, IFAC-PapersOnLine, 56(2), pp. 4466–4471, 2023.
2. S. T. Paruchuri et al. Intrinsic and Extrinsic Approximation of Koopman Operators over Manifolds. 2020 59th IEEE Conference on Decision and Control (CDC), pp. 1608–1613, 2020.
