Learning-based optimal control for end-to-end human-mars entry, powered-descent, and landing mission

This paper investigates the end-to-end human-Mars entry, powered-descent, and landing (EDL) guidance problem by developing a learning-based real-time optimal control method to achieve the goal of precise and fuel-efficient planetary landing. First, the end-to-end EDL guidance problem is formulated as a multi-phase optimal control problem with different dynamics and constraints at each phase. Then the customized alternating direction method of multipliers (ADMM) is applied to solve the end-to-end EDL guidance problem with different initial states off-line. After that, based on the optimized off-line solutions, the learning-based real-time optimal control method is developed. To be specific, supported by the optimal control theory, the necessary conditions of optimality for the entry phase and powered-descent phase guidance are derived, respectively, which leads to two-point-boundary-value-problems (TPBVPs). We then identify critical parameters that can determine the complete solutions of the TPBVPs. To find the implicit relationship between the initial states and these critical parameters, deep neural networks are constructed to learn the values of these critical parameters in real-time with sufficient training data. Finally, the learning-based optimal control method is implemented in simulation cases to verify the effectiveness of the proposed method. © 2021 by the American Institute of Aeronautics and Astronautics, Inc. All rights reserved.