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.