In a group of 31 poster submissions and 3 winners, Hao Wang walked away with Second Place, and an approved $300 travel reward for her Submission
Poster Title: NEURAL NETWORK TRAINED CONTROLLER FOR ATMOSPHERIC ENTRY IN MARS MISSIONS
Abstract: We present a new method to design the controller of Mars capsule atmospheric entry using neural networks. Compared to Apollo controller as a baseline, the simulation of neural network controller reproduces the classical Apollo results over a variation of initial conditions, e.g. initial position. This leads to the potential of achieving landing accuracy requirements of future manned Mars missions. The data from Apollo re-entry simulation in Earth model is used for neural networks training. The neural network controller for Earth reentry is evaluated with Apollo real data. It is then adapted for the Mars environment and achieves the desired landing accuracy for a Mars capsule. The results show significant promise in using that approach for future Mars missions.