FEATURE-BASED LEARNING FOR OPTIMAL ABORT GUIDANCE

 The abort mission refers to the mission where the landing vehicle needs to terminate the landing mission when an anomaly happens and be safely guided to the desired orbit. Missions involving crew on board demands for a robust and efficient abort strategy. This thesis focuses on solving the time-optimal abort guidance (TOAG) problem in real-time via the feature-based learning method. First, according to the optimal control theory, the features are identified to represent the optimal solutions of TOAG using a few parameters. After that, a sufficiently large dataset of time-optimal abort trajectories is generated offline by solving the TOAG problems with different initial conditions. Then the features are extracted for all generated cases. To find the implicit relationships between the initial conditions and identified features, neural networks are constructed to map the relationships based on the generated dataset. A successfully trained neural network can generate solution in real time for a reasonable initial condition. Finally, experimental flight tests are conducted to demonstrate the onboard computation capability and effectiveness of the proposed method.