About

Efstathios Bakolas is an Associate Professor at The University of Texas at Austin in the Department of Aerospace Engineering (ASE). His research focuses on control systems, optimization, and motion planning for autonomous agents, with applications in complex and dynamic environments. He has contributed to the development of multi-objective path-planning, feedback control of nonlinear systems, and data-driven modeling of high-dimensional systems, including turbulent flows. Dr. Bakolas has supervised numerous graduate students and post-doctoral fellows, many of whom have gone on to prominent positions in industry and academia.

Research topics

• Computer Science
• Artificial Intelligence
• Mathematical optimization
• Machine Learning
• Mathematics
• Distributed computing
• Algorithm
• Operations research
• Applied mathematics

Selected publications

• Game-Theoretic Autonomous Driving: A Graphs of Convex Sets Approach

  ArXiv.org · 2026-01-27

  articleOpen access

  Multi-vehicle autonomous driving couples strategic interaction with hybrid (discrete-continuous) maneuver planning under shared safety constraints. We introduce IBR-GCS, an Iterative Best Response (IBR) planning approach based on the Graphs of Convex Sets (GCS) framework that models highway driving as a generalized noncooperative game. IBR-GCS integrates combinatorial maneuver reasoning, trajectory planning, and game-theoretic interaction within a unified framework. The key novelty is a vehicle-specific, strategy-dependent GCS construction. Specifically, at each best-response update, each vehicle builds its own graph conditioned on the current strategies of the other vehicles, with vertices representing lane-specific, time-varying, convex, collision-free regions and edges encoding dynamically feasible transitions. This yields a shortest-path problem in GCS for each best-response step, which admits an efficient convex relaxation that can be solved using convex optimization tools without exhaustive discrete tree search. We then apply an iterative best-response scheme in which vehicles update their trajectories sequentially and provide conditions under which the resulting inexact updates converge to an approximate generalized Nash equilibrium. Simulation results across multi-lane, multi-vehicle scenarios demonstrate that IBR-GCS produces safe trajectories and strategically consistent interactive behaviors.

  PublisherOA PDF

• Coupled Task Assignment for Hierarchical Multi-Agent Systems in Disaster Response Missions: A Nested Hungarian Approach

  2026-01-08

  article

  This work formulates a novel variant of the classical linear task assignment problem, which we refer to as the coupled linear task assignment (CLTA) problem. This formulation models the task assignment process involving two-echelon agents and tasks, where the goal is to optimally assign tasks to agents within the same echelon to maximize a global utility while complying with the coupling constraints imposed by the problem's hierarchical structure. After discussing the problem's inherent properties that prevent the use of standard relaxation techniques, we propose a variant of the Hungarian algorithm, the nested Hungarian algorithm, that solves the problem exactly in polynomial time. We demonstrate the superior performance of the proposed algorithm by benchmarking it against seven open-source and commercial MILP solvers. Finally, we apply our proposed approach to a fictitious disaster response scenario motivated by the January 2025 Southern California wildfires in the Greater Los Angeles area.

  PublisherDOI

• Distributed Covariance Steering via Non-Convex ADMM for Large-Scale Multi-Agent Systems

  arXiv (Cornell University) · 2026-04-06

  preprintOpen access

  This paper studies the problem of steering large-scale multi-agent stochastic linear systems between Gaussian distributions under probabilistic collision avoidance constraints. We introduce a family of \textit{distributed covariance steering (DCS)} methods based on the Alternating Direction Method of Multipliers (ADMM), each offering different trade-offs between conservatism and computational efficiency. The first method, Full-Covariance-Consensus (FCC)-DCS, enforces consensus over both the means and covariances of neighboring agents, yielding the least conservative safe solutions. The second approach, Partial-Covariance-Consensus (PCC)-DCS, leverages the insight that safety can be maintained by exchanging only partial covariance information, reducing computational demands. The third method, Mean-Consensus (MC)-DCS, provides the most scalable alternative by requiring consensus only on mean states. Furthermore, we establish novel convergence guarantees for distributed ADMM with iteratively linearized non-convex constraints, covering a broad class of consensus optimization problems. This analysis proves convergence to stationary points for PCC-DCS and MC-DCS, while the convergence of FCC-DCS follows from standard ADMM theory. Simulations in 2D and 3D multi-agent environments verify safety, illustrate the trade-offs between methods, and demonstrate scalability to thousands of agents.

  PublisherDOI

• Game-Theoretic Distributed Sensor Tasking in Earth Observation Satellite Constellations

  Journal of Guidance Control and Dynamics · 2026-01-01

  article

  This paper presents a game-theoretic sensor selection for coordinating multiple satellites, where each satellite adjusts its roll angle to observe multiple targets. The main objective is to find a joint sensor schedule for the satellite constellation over a finite time horizon that minimizes both mean square error (MSE) and slew costs, which is a challenging combinatorial optimization problem. Standard MSE-based sensor scheduling problems typically involve optimizing non-submodular functions, which introduces computational complexity in designing algorithms that achieve provable performance guarantees. To address this issue, we propose a submodular surrogate objective function that is monotonic under specific conditions for the weights on MSE and slew cost terms. This reformulation enables the problem to be modeled as a potential game, facilitating the use of a distributed algorithm to find a Nash equilibrium that provides a bounded efficiency. The proposed solution is compared with an alternative game-theoretic solution using a different performance metric, as well as with a centralized greedy solution, to demonstrate the performance of the surrogate approach, particularly in the presence of isolated subgraphs and stochastic communication delays. Additionally, the versatility of the proposed scheme is highlighted, as it is applicable to heterogeneous satellites and sensors with disconnected communication graphs.

  PublisherDOI

• Distributed Covariance Steering via Non-Convex ADMM for Large-Scale Multi-Agent Systems

  arXiv (Cornell University) · 2026-04-06

  articleOpen access

  This paper studies the problem of steering large-scale multi-agent stochastic linear systems between Gaussian distributions under probabilistic collision avoidance constraints. We introduce a family of \textit{distributed covariance steering (DCS)} methods based on the Alternating Direction Method of Multipliers (ADMM), each offering different trade-offs between conservatism and computational efficiency. The first method, Full-Covariance-Consensus (FCC)-DCS, enforces consensus over both the means and covariances of neighboring agents, yielding the least conservative safe solutions. The second approach, Partial-Covariance-Consensus (PCC)-DCS, leverages the insight that safety can be maintained by exchanging only partial covariance information, reducing computational demands. The third method, Mean-Consensus (MC)-DCS, provides the most scalable alternative by requiring consensus only on mean states. Furthermore, we establish novel convergence guarantees for distributed ADMM with iteratively linearized non-convex constraints, covering a broad class of consensus optimization problems. This analysis proves convergence to stationary points for PCC-DCS and MC-DCS, while the convergence of FCC-DCS follows from standard ADMM theory. Simulations in 2D and 3D multi-agent environments verify safety, illustrate the trade-offs between methods, and demonstrate scalability to thousands of agents.

  PublisherOA PDF

• Game-Theoretic Autonomous Driving: A Graphs of Convex Sets Approach

  Open MIND · 2026-01-27

  preprint

  Multi-vehicle autonomous driving couples strategic interaction with hybrid (discrete-continuous) maneuver planning under shared safety constraints. We introduce IBR-GCS, an Iterative Best Response (IBR) planning approach based on the Graphs of Convex Sets (GCS) framework that models highway driving as a generalized noncooperative game. IBR-GCS integrates combinatorial maneuver reasoning, trajectory planning, and game-theoretic interaction within a unified framework. The key novelty is a vehicle-specific, strategy-dependent GCS construction. Specifically, at each best-response update, each vehicle builds its own graph conditioned on the current strategies of the other vehicles, with vertices representing lane-specific, time-varying, convex, collision-free regions and edges encoding dynamically feasible transitions. This yields a shortest-path problem in GCS for each best-response step, which admits an efficient convex relaxation that can be solved using convex optimization tools without exhaustive discrete tree search. We then apply an iterative best-response scheme in which vehicles update their trajectories sequentially and provide conditions under which the resulting inexact updates converge to an approximate generalized Nash equilibrium. Simulation results across multi-lane, multi-vehicle scenarios demonstrate that IBR-GCS produces safe trajectories and strategically consistent interactive behaviors.

  DOI

• Motion prediction of multi-agent systems with multi-view clustering

  Robotics and Autonomous Systems · 2026-04-07 · 1 citations

  preprintOpen accessSenior authorCorresponding
  PublisherOA PDFDOI

• Online Feedback Flow Control for Finite Wings

  2025-01-03

  article

  We conduct numerical flow control studies on a NACA4412 wing. Direct numerical simulation of laminar separated flows is conducted in the Nek5000 spectral element code. We identify the system dynamics in real time and continuously update the state-space model as new measurement data become available using the online dynamic mode decomposition. A linear quadratic tracking controller is designed for the separation location, such that it follows a predefined reference target. The controller gains are then recomputed online based on the new system updates, allowing for an adaptive formulation of real-time feedback control that accounts for changes of the flow due to external disturbances or due to the effects of actuation itself. For the NACA4412 airfoil at $0^\circ$ angle of attack, adaptive online control of the separation location was more effective than steady blowing at moving the separation point downstream for a given actuator strength. At angle of attack of $10^\circ$, an increase of $C_l/C_d$ by $\approx 30\%$ was achieved.

  PublisherDOI

• Constrained Multi-Modal Density Control of Linear Systems via Covariance Steering Theory

  arXiv (Cornell University) · 2025-01-06

  preprintOpen accessSenior author

  In this paper, we investigate finite-horizon optimal density steering problems for discrete-time stochastic linear dynamical systems whose state probability densities can be represented as Gaussian Mixture Models (GMMs). Our goal is to compute optimal controllers that can ensure that the terminal state distribution will match the desired distribution exactly (hard-constrained version) or closely (soft-constrained version) where in the latter case we employ a Wasserstein like metric that can measure the distance between different GMMs. Our approach relies on a class of randomized control policies which allow us to reformulate the proposed density steering problems as finite-dimensional optimization problems, and in particular, linear and bilinear programs. Additionally, we explore more general density steering problems based on the approximation of general distributions by GMMs and characterize bounds for the error between the terminal distribution under our policy and the approximated GMM terminal state distribution. Finally, we demonstrate the effectiveness of our approach through non-trivial numerical experiments.

  PublisherOA PDFDOI

• Distributed and Localized Covariance Control of Coupled Systems: A System Level Approach

  ArXiv.org · 2025-03-03

  preprintOpen accessSenior author

  This work is concerned with the finite-horizon optimal covariance steering of networked systems governed by discrete-time stochastic linear dynamics. In contrast with existing work that has only considered systems with dynamically decoupled agents, we consider a dynamically coupled system composed of interconnected subsystems subject to local communication constraints. In particular, we propose a distributed algorithm to compute the localized optimal feedback control policy for each individual subsystem, which depends only on the local state histories of its neighboring subsystems. Utilizing the system-level synthesis (SLS) framework, we first recast the localized covariance steering problem as a convex SLS problem with locality constraints. Subsequently, exploiting its partially separable structure, we decompose the latter problem into smaller subproblems, introducing a transformation to deal with nonseparable instances. Finally, we employ a variation of the consensus alternating direction method of multipliers (ADMM) to distribute computation across subsystems on account of their local information and communication constraints. We demonstrate the effectiveness of our proposed algorithm on a power system with 36 interconnected subsystems.

  PublisherOA PDFDOI

Recent grants

• Data-Driven Model Reduction and Real-Time Estimation and Control of Coherent Structures in Turbulent Flows

  NSF · $461k · 2021–2025

• EAGER: Microscopic Deployment Algorithms to Achieve Macroscopic Objectives for Spatially Distributed Stochastic Networks of Mobile Agents

  NSF · $150k · 2018–2021

• Optimal Path Planning Among Mobile Sources of Threat in Complex Environments

  NSF · $274k · 2016–2020

• Collaborative Research: Real-Time Trajectory Generation Algorithms for Uncertain Autonomous Systems Based on Gaussian Processes

  NSF · $297k · 2020–2023

• NRI: FND: Efficient algorithms for safety guiding mobile robots through spaces populated by humans and mobile intelligent machines and robots

  NSF · $250k · 2019–2023

Frequent coauthors

• Vrushabh Zinage

  27 shared

• Panagiotis Tsiotras

  21 shared

• Isin M. Balci

  The University of Texas at Austin

  18 shared

• Alexandros Tsolovikos

  The University of Texas at Austin

  17 shared

• Yoonjae Lee

  The University of Texas at Austin

  15 shared

• Jaemin Lee

  California Institute of Technology

  10 shared

• Luis Sentis

  The University of Texas at Austin

  10 shared

• Dimitrios Pylorof

  Idaho National Laboratory

  8 shared

Labs

• Efstathios Bakolas LabPI

Education

• Ph.D., Aerospace Engineering

  Georgia Institute of Technology

  2011

• M.S., Aerospace Engineering

  Georgia Institute of Technology

  2007

• Other, Mechanical Engineering

  National Technical University of Athens

  2004

Awards & honors

• Eli H. and Ramona Thornton Centennial Fellowship in Engineer…
• Elected Associate Fellow of AIAA, 2024
• Elevated to Senior Member of IEEE, 2022