Check this page if you are looking for GTOC club information: GTOC Student Club Initiative

• Astrodynamics
• Attitude Dynamics and Control
• Space Situational Awareness (SSA)
• Machine Learning (ML) and Artificial Intelligence (AI)
  • Supervised Learning
  • Reinforcement Learning

Some detailed topics are included below.

The cislunar region (the space between Earth and the Moon and around them) is the focus of deep space exploration in the next decade. To support a long-duration mission, spacecraft need to have more autonomy than what they currently have. In the near future, a GPS-like positioning system in the cislunar region will be indispensable for all sorts of cislunar activities. The CR3BP model for such a navigation system is under active investigation and many difficulties due to the over-simplification of CR3BP have been noted. Using the rich dynamic characteristics in ER3BP for such a positioning constellation design will bring fresh ideas and options to this challenge. Some preliminary results are:

• Hao Peng, and Xiaoli Bai, “A New Representation for Nominal Orbits of A Cislunar Navigation Satellite Constellation (under review)”, The Journal of the Astronautical Sciences, 2023.
• Hao Peng, and Xiaoli Bai, “Segmented Fitting Representations of Cislunar Navigation Satellite Constellation”, 2023 AAS/AIAA Astrodynamics Specialist Conference, Big Sky, Montana: 2023.

One drawback of reinforcement learning (RL) is that it is risky for practical applications when the transition gap between the simulation environment and the reality cannot be ignored. However, this doesn't render RL useless if a suitable problem can be identified. When any anomaly is detected, the satellite will switch into the safe mode, which will ensure the solar panel and antenna orientations with highest priority to secure the power supply and the communication. Then, the ground control should jump in and rescue the satellite promptly. However, the sudden loss of satellite is not uncommon. For example, India's Mars Orbiter Mission (MOM) possibly due to an automated maneuver. In the case of already losing the satellite, the risk of RL is tolerable and will be used to rescure the satellite. This research makes use of RL and empower the satellite with a self-rescure ability from communication loss. One appealing outcome of this project will be a generic module that can fit to any missions. Some preliminary results are:

• Hao Peng, and Xiaoli Bai, “Reorient Satellite Antenna using Reinforcement Learning under Unknown Attitude Failures”, 33rd AAS/AIAA Space Flight Mechanics Meeting, Austin, TX: 2023.

Mega-constellation is a big trend in satellite communications. Starlink now has more than 3,000 satellites on orbit and more are being launched in a rapid pace. Meanwhile, space situational awareness (SSA) area is highly interested in using space-based optical or radar sensors to track all the resident space objects (RSOs). Due to the close proximity and less atmosphere interference, space-based sensors are expected to improve the overall SSA ability. However, no mega-constellation is built or designed for the SSA purpose. Our research will fill the gap between matured mega-constellations and SSA, including the related orbital dynamical problems, sensor allocations, mission software and hardware requirements, expected outcomes, etc.

In most situations, people discuss mitigating and removing space debris, but our study focus on how to increase the accumulation of space debris to eventually trigger the famous Kessler Syndrome, where cascading collisions occur. To accomplish this goal, we set up a simplified but real-enough environment based on the up-to-date space catalog. The dimension and mass of the debris will also be modeled. Collaborative AI agents will be guided in this virtual reality environment to learn a policy to trigger the catastrophe. Available actions include, for example, blowing up big objects (satellites or rocket bodies), adding new objects, etc. The project goal is, of course, still to prevent the syndrome. We can use this AI to test against other mitigation resorts. Furthermore, this AI will enlighten us what operations should be definitely prevented and what objects should be removed before they break up.

Maneuver detection is a difficult problem for uncooperative resident space objects (RSOs). A common method is to detect the maneuver based on propagating of orbit estimates using a high-fidelity numerical model to a common intermediate epoch, and then analyze the statistics of all the deviations. This process is resource-consuming. My previous work has already established a ML approach to improve orbit prediction accuracy. ML models are trained using historical data to directly improve orbit predictions without modeling additional orbital dynamics or the satellite. For this study, I plan to create a method based on the performance of the trained ML models that are used to improve orbit prediction accuracy.