The Autonomous Control and Decision Systems (ACDS) Laboratory is part of the Flight Mechanics and Controls (FMC) group at the Daniel Guggenheim School of Aerospace Engineering, Georgia Institute of Technology (GaTech). The ACDS laboratory is also affiliated with the Institute for Robotics and Intelligent Machines (IRIM), the Decision Control Lab (DCL) and the Center for Machine Learning at Georgia Tech.

The research objective of the ACDS lab is to develop computational methods grounded on first principles, for learning and control of engineered, artificial and natural systems characterized by different notions of complexity. These notions include nonlinearities, uncertainty, high dimensionality and the existence of multiple temporal and/or spatial scales. Such characteristics appear in systems in autonomy and robotics, applied physics, artificial intelligence, biology, networked and financial processes.  On the theoretical side, research in ACDS lab spans the areas of stochastic optimal control and dynamical systems theory, information theory, reinforcement learning, dynamic and large-scale distributed optimization.

Lab News and Highlights:

Our paper on Parametric Differential Dynamic Programming was finalist for the best student paper award in RSS 2022.

Another paper from GT on Improving MPPI using Covariance Steering Algorithms was finalist for the best planning paper in ICRA 2022.

Our paper on Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory was accepted in ICLR 2022.

Open PhD Positions for Fall 2023:

We are always interested in prospective students with a strong background in areas of control theory, stochastic processes and probability theory, statistical and/or quantum physics, machine learning, optimization and robotics. In particular there are two positions in the following areas:

Position 1 – Large-Scale Stochastic Optimal Control & Distributed Dynamic Optimization: The ACDS lab has one  open PhD position  in the areas of large scale stochastic optimal control,  distributed optimization,   control and optimization of PDEs.

Position 2  – Deep Learning Theory: An Optimal Control and Dynamical Systems Perspective: The ACDS lab has one open PhD position at the intersection of Deep Learning,  Stochastic and/or Deterministic Optimal Control and Dynamical Systems Theory.