Seminars

Uncertainty propagation and mitigation is at the core of all robotic and control systems. The standard approach so far has followed the spirit of controlling a system “with uncertainties,” as opposed to the direct control “of uncertainties.” Borrowing ideas from the classical Optimal Mass Transport (OMT) and Schrödinger Bridge problems, distributional control has recently emerged as a principled approach to characterize and mitigate uncertainty in stochastic systems with strict performance guarantees. In this talk, I will review some recent results on covariance and distribution control for stochastic systems subject to chance constraints, including data-driven and distributionally robust implementations; I will demonstrate the application of the theory to a variety of problems ranging from model predictive control, robot motion planning under uncertainty, multi-agent mean-field control, and generative AI.

Bio: Dr. Panagiotis Tsiotras is the David and Andrew Lewis Endowed Chair Professor at the School of Aerospace Engineering at Georgia Tech. He is a former Associate Director for the Institute for Robotics and Intelligent Machines (IRIM). His current research interests are in nonlinear and stochastic optimal control and their connections with AI, emphasizing application to aerial, space, and ground vehicle autonomy. He holds degrees in Mechanical Engineering, Aerospace Engineering, and Mathematics. He is the recipient of the NSF Career Award, the IEEE Excellence Award in Aerospace Control, and the Outstanding Aerospace Engineer award from Purdue. He is a Fellow of AIAA, IEEE, and AAS.