Corina Barbalata

Associate Professor Louisiana State University

  • Baton Rouge LA

Dr. Barbalata and her group are working on proposing solutions for real-world robotics applications.

Contact

Louisiana State University

View more experts managed by Louisiana State University

Biography

Corina Barbalata is an Assistant Professor in the Department of Mechanical and Industrial Engineering, at Louisiana State University, United States. She is the co-director of the iCORE Laboratory and a fellow in the Coastal Studies Institute at LSU. She received a BS degree from Transilvania University of Brasov, Romania, in 2011. In 2013 through the VIsion and RoBOTics (VIBOT) program, she got her double MS degree in Computer Vision and Robotics from Heriot-Watt University (Scotland, UK) and University of Burgundy (France). She received her PhD from the School of Engineering and Physical Sciences, Heriot-Watt University (Edinburgh, UK) in 2017, and between 2017 and 2019 she was a postdoctoral researcher in the Naval Architecture and Marine Engineering department at University of Michigan, United States. Dr. Barbalata and her group are working on proposing solutions for real-world robotics applications with social and environmental merits, through the combination of theoretical, computational, and experimental methods for the design new reactive capabilities for autonomous robotic systems working in complex and dynamic environments. Her research interests are in physics- and data-driven modeling of vehicle-manipulator systems, development of model-based control structures for autonomous robotic systems, and scene understanding and interpretation for robotic navigation. Her application domains are marine robotics and industrial automation.

Areas of Expertise

Marine Robotics
Autonomous Systems
Model-based Control Systems
Physics and Data-driven Dynamic Modeling
Underwater Perception and Algorithms

Research Focus

Marine Robotics and Autonomous Systems

Dr. Barbalata is proposing solutions for real-world robotics applications with social and environmental merits, through the combination of theoretical, computational, and experimental methods for the design new reactive capabilities for autonomous robotic systems working in complex and dynamic environments.

Education

Heriot-Watt University

Ph.D.

2017

Media Appearances

Chance Maritime Technologies and LSU Join Forces on Uncrewed Underwater Research

Ocean News  online

2024-11-14

Led by LSU Mechanical Engineering Assistant Professor Corina Barbalata and her students—Donovan Gegg, Mikhalib Green, and Edward Morgan—the project is a collaboration between the LSU College of Engineering and Chance Maritime Technologies, headquartered in Lafayette. The two parties were brought together by Integer Technologies, which is involved in another of Barbalata’s current research projects.

View More

Research team uses robots to search for shipwrecks

The Alpena News  online

2022-06-06

“We have two remotely-operated vehicles, Dory and Nemo,” said Corina Barbalata of Louisiana State University in the Department of Mechanical and Industrial Engineering. “So, with Dory, what we are trying to do is making autonomous by adding some sensors, but still keeping it low-cost.”

View More

LSU Engineering Faculty Design Sensor to Improve Vision of Underwater Robots

Science X  online

2022-03-31

Barbalata, an assistant professor in the LSU Department of Mechanical & Industrial Engineering, is helping with the testing of the imaging system that will be deployed in an underwater vehicle and used to help the vehicle navigate the environment.

"We are going to look at tracking various aspects in the underwater environment and design a control structure based on this computational imaging system," she said.

View More

Articles

On the Stabilization of Directed Formation Using Geometric Algebra Approach

IEEE Control Systems Letters

2025

Distance-based formation control on minimally rigid graphs often encounters ambiguous shapes, where agents form incorrect shape formations due to multiple equilibrium points in the error dynamics. Recent studies on distance-based controllers, even those that introduce extra control variables, struggle to resolve this fundamental issue fully, typically requiring specific conditions or failing to manage reflections effectively. In this paper, we address both flip and reflection ambiguities in formation control by reexamining core geometric constraints and integrating them with traditional bearing-based formation control methods. We propose a novel controller that guarantees convergence to the correct formation without imposing any additional conditions. Numerical simulations demonstrate the controller’s effectiveness in avoiding formation ambiguities.

View more

RecGS: Removing Water Caustic with Recurrent Gaussian Splatting

RecGS: Removing Water Caustic with Recurrent Gaussian Splatting

2024

Water caustics are commonly observed in seafloor imaging data from shallow-water areas. Traditional methods that remove caustic patterns from images often rely on 2D filtering or pre-training on an annotated dataset, hindering the performance when generalizing to real-world seafloor data with 3D structures. In this letter, we present a novel method Recurrent Gaussian Splatting (RecGS), which takes advantage of today's photorealistic 3D reconstruction technology, 3D Gaussian Splatting (3DGS), to separate caustics from seafloor imagery. With a sequence of images taken by an underwater robot, we build 3DGS recurrently and decompose the caustic with low-pass filtering in each iteration. In the experiments, we analyze and compare with different methods, including joint optimization, 2D filtering, and deep learning approaches.

View more

Dynamic event-triggered control of linear continuous-time systems using a positive systems approach

Nonlinear Analysis: Hybrid Systems

2024

We provide new dynamic event-triggered controls for continuous-time linear systems that contain additive uncertainties. We prove input-to-state stability properties that imply uniform global exponential stability when the additive uncertainties are zero. Significant novel features include (a) new dynamic extensions and new trigger rules that provide a new positive systems analog of significant prior dynamic event-triggered work of A. Girard and (b) our application to a BlueROV2 underwater vehicle model, where we provide significantly larger lower bounds on the inter-execution times, and usefully fewer trigger times, compared with standard dynamic event-triggered approaches that used the usual Euclidean norm, and as compared with static event-triggered controls that instead used positive systems approaches.

View more

Show All +

Affiliations

  • Marine Technology Society (MTS)
  • Institute of Electrical and Electronics Engineers (IEEE)
  • Coastal Studies Institute, Louisiana State University : Fellow

Media

Social