Join the Research Group
Join my research group at Oklahoma State University–Tulsa advancing
trustworthy autonomy through control, optimization, and machine learning,
with a focus on planning and control under uncertainty.
Students with strengths in control, optimization, probability, applied mathematics, machine learning, or experimental systems are welcome. Prior AI or machine learning experience is not required.
If you would like to be considered for current or future opportunities, please use the form below rather than sending a general PhD inquiry by email.
Explore the Group
Research Opportunities
I welcome expressions of interest from prospective PhD students who would like to conduct research in the School of Mechanical and Aerospace Engineering at Oklahoma State University. My group is based at the OSU-Tulsa campus and focuses on trustworthy autonomy for aerospace systems.
PhD research in the group is shaped around the student’s background, interests, and the projects that are active when they join. I therefore encourage strong prospective students to introduce themselves even when I am not advertising a specific position.
Our central research question is:
How can autonomous aerospace and robotic systems make safe and efficient decisions under uncertainty, constraints, and limited computation?
My group develops model-based, learning-enabled, and hybrid methods, choosing an approach according to the research question, available information, computational resources, and safety and performance requirements. Stochastic optimal control and convex optimization are central research directions, alongside machine-learning-based methods and their integration with control. A PhD project may focus on any of these approaches, depending on the student’s interests and the projects active in the group.
As a PhD student in my group, you will have opportunities to work across the full research pipeline:
Research Areas
Research in the group is intentionally not limited to a single predetermined project. A PhD student may work across one or more of the following interconnected themes, depending on their background, interests, and the projects active in the group.
1. Optimization-Based Planning and Control
We develop computationally efficient methods for planning and control under nonlinear dynamics and mission constraints. Research includes optimal control, trajectory optimization, lossless and successive convexification, and model predictive control (MPC).
Projects may focus on new mathematical formulations, numerical algorithms, and real-time guidance for spacecraft, UAVs, and robotic systems. A central goal is to make optimization reliable and practical for autonomous decision-making.
2. Stochastic Optimal Control and Covariance Control
We investigate how to jointly design trajectories and feedback policies while explicitly accounting for uncertainty. Topics include covariance control, chance-constrained planning, uncertainty propagation, and risk-aware guidance.
These projects offer opportunities for students interested in probability, control theory, convex optimization, and numerical methods. Applications include UAV obstacle avoidance, spacecraft rendezvous and docking, low-thrust transfers, and stationkeeping.
3. Learning-Enabled and Hybrid Autonomy
We develop learning-enabled methods and investigate how machine learning can improve models, control policies, and optimization algorithms. Topics include data-driven dynamical models, system identification, reinforcement-learning-enhanced MPC, physics-informed neural networks, imitation learning, and learned warm starts for optimization.
Research examines when learning improves prediction, performance, adaptation, or computational efficiency, and how to evaluate the resulting system's reliability and constraint satisfaction. Students with machine learning experience can contribute to both learning-based methods and their integration with control and optimization.
4. Safety, Verification, and Experimental Autonomous Systems
We aim to connect mathematical analysis and simulation with systematic testing and experiments across model-based, learning-enabled, and hybrid methods. Directions include uncertainty analysis, stress testing, runtime assurance, and hardware-in-the-loop validation.
The laboratory is being established at OSU-Tulsa. Planned capabilities include a spacecraft maneuver platform operating over an almost frictionless surface and autonomous UAVs with onboard computing and sensing. These platforms will support studies of rendezvous, docking, navigation, and multi-vehicle coordination.
Students will have opportunities to help develop these platforms and carry theoretical and computational ideas into experimental validation.
Selected work related to these directions
The following papers illustrate complementary research directions that I plan to expand in the group:
- Convex Approach to Covariance Control with Application to Stochastic Low-Thrust Trajectory Optimization — stochastic optimal control and joint trajectory and feedback-policy design (2022).
- Stochastic Path Planning with Obstacle Avoidance for UAVs Using Covariance Control — chance-constrained planning and uncertainty control (2025).
- Convex Approach to Optimal Spacecraft Attitude Reorientation with Keep-Out Constraints — constrained maneuver design through convex optimization (2026).
- Reinforcement Learning Enhanced Model Predictive Control with Application to Autonomous Planetary Landing — hybrid learning and model-based control (2026).
- Physics-Informed Pontryagin Neural Networks for Path-Constrained Optimal Control Problems — learning with embedded dynamics and optimality conditions (2025).
More information about my broader research program is available on the Research and Publications pages.
From Theory to Experimental Validation
The laboratory is currently being established at OSU-Tulsa. Its planned capabilities will support research from computational development and simulation to experiments on real autonomous systems:
Computing & Simulation
High-performance computing for numerical optimization, stochastic control, machine learning, Monte Carlo analysis, and high-fidelity simulation of autonomous aerospace systems.
Autonomous UAVs & Flight Testing
UAV platforms with onboard computing and sensing for autonomous flight, planning and control under uncertainty, navigation, and multi-vehicle coordination, supported by indoor motion-capture experiments and outdoor flight testing.
Spacecraft Maneuver Simulation
Laboratory platforms designed to recreate key aspects of spacecraft motion and operations on Earth, enabling experimental research in autonomous rendezvous, proximity operations, docking, formation flight, on-orbit servicing, and spacecraft guidance and control.
Because these capabilities are being developed as the group grows, students will have opportunities to help design, build, and test the platforms that support their research, under my supervision. This gives students the chance to shape the experimental infrastructure around their own theoretical and computational work and to carry new ideas from simulation to real-world validation.
Why OSU-Tulsa?
The positions are located at Oklahoma State University–Tulsa, not the Stillwater campus. The group is based in the Helmerich Research Center, near downtown Tulsa.
A major advantage of being based in Tulsa is the opportunity to connect the group’s research with OSU’s broader aerospace and advanced-air-mobility ecosystem. Through the Oklahoma Aerospace Institute for Research and Education (OAIRE), OSU brings together university researchers, government organizations, and industry partners across Oklahoma’s aerospace sector. Within this ecosystem, the LaunchPad Center supports advanced air mobility research, technology development, and entrepreneurship in the Tulsa region, while the Skyway Range provides infrastructure and expertise for research and testing of uncrewed systems.
For students working in autonomous aerospace systems, this creates opportunities to connect fundamental research with real platforms, flight testing, and industry-relevant problems.
Who Is a Good Fit?
I am interested in students who are curious, mathematically and technically strong, motivated to do research, and interested in developing into independent researchers.
There is no single ideal academic background. Relevant preparation may come from:
- Aerospace Engineering
- Mechanical Engineering
- Electrical or Computer Engineering
- Robotics and Autonomous Systems
- Computer Science
- Applied Mathematics
- Controls, Optimization, or related quantitative fields
An M.S. degree is preferred but not required. I also encourage strong bachelor’s-level students to get in touch if they have developed relevant experience through research, industry, internships, independent projects, or other technical work. A student who already brings a strong combination of skills in areas such as controls, optimization, machine learning, robotics, or autonomous systems may be an excellent fit even without a master’s degree.
You are not expected to have experience in every research area listed above. Strong preparation in control, optimization, probability, or applied mathematics can be an excellent foundation for a project centered on model-based methods. Students with machine learning or experimental experience bring complementary strengths to the group. If your background is outside traditional aerospace engineering, I am especially interested in understanding how your expertise could contribute to autonomous aerospace systems. Strong candidates should not hesitate to express interest based solely on differences between their academic background and the traditional aerospace engineering path.
Particularly useful preparation
Any subset of the following can be valuable:
- dynamics and control;
- optimal control and numerical optimization;
- probability, estimation, stochastic systems, or covariance control;
- machine learning and reinforcement learning;
- robotics or autonomous systems;
- numerical methods and scientific computing;
- programming in Python, MATLAB, C/C++, or related languages;
- simulation, embedded systems, sensors, or experimental hardware.
What matters most is not checking every box, but demonstrating strong fundamentals, research potential, intellectual curiosity, and the ability to learn independently.
Funding & Availability
Funding for PhD students in the group is typically provided through graduate research assistantships (GRAs) and/or graduate teaching assistantships (GTAs) when appointments are available. Assistantship packages and university benefits are determined by the specific appointment and may change from year to year.
Because this is a standing expression-of-interest page, submitting the form does not imply that a funded position is currently open or guarantee an assistantship. Availability depends on research funding, teaching needs, project timing, and the semester of entry.
If I see a strong potential match and there is a realistic opportunity to move forward, we will discuss the expected funding arrangement before you proceed with the formal OSU application.
Mentoring & Group Culture
Choosing a PhD advisor is about more than choosing a research topic. I want to build a group where students can pursue ambitious research while feeling supported, comfortable asking questions, and progressively confident in developing ideas of their own.
My mentoring philosophy emphasizes guided independence, freedom to explore, and work-life balance. I care about strong research and meaningful progress, but I also want students to enjoy this stage of their lives and develop into independent researchers without feeling that they have to navigate difficult problems alone.
Learn More About Mentoring & Group Culture
Express Interest in Joining the Group
If you are interested in joining the group in a future semester, I would be happy to learn more about you. The form below is my preferred way for prospective PhD students to contact me about research opportunities, because it allows me to keep expressions of interest organized and review them consistently.
This form is simply a way to introduce yourself, tell me about your background and research interests, and share your CV or other relevant material. It is not a formal application to Oklahoma State University, and it is not an application to a guaranteed open position.
I review submissions on a rolling basis. If your background and interests appear to align well with the group and there is a realistic current or upcoming opportunity, I may contact you to schedule an informal research conversation. Because the form remains open throughout the year, I may not be able to respond individually to every submission.
If we both feel that moving forward makes sense, I will then guide you toward the formal OSU PhD application and discuss the anticipated research direction, timing, and funding arrangement.
What to share
To help me get to know you, please include:
- CV or résumé — required.
- A short research-interest statement — entered directly in the form below. Introduce yourself, explain what interests you about the group, and describe how your background connects to one or more of the research directions above.
- Anything else you think may be helpful — optional. This could include an unofficial transcript, publications or preprints, a thesis or thesis abstract, project documentation, a portfolio, or other material that gives me a better sense of your experience.
There is no need to provide recommendation letters at this stage. Please do not include sensitive personal information that is not relevant to evaluating your academic and research background.
Tell Me About Yourself
Next Step: Formal OSU Application
If, after our research conversations, we both feel that the group could be a good fit and there is an appropriate opportunity, the next step will be the formal PhD application to Oklahoma State University through the Graduate College and the School of Mechanical and Aerospace Engineering.
The OSU application is separate from the expression-of-interest form above. The university’s requirements, deadlines, and admission policies may change, so the official pages below should be treated as the current source of information when you are ready to apply.