Joint Trajectory Replanning for Mars Ascent Vehicle under Propulsion System Faults: A Suboptimal Learning-Based Warm-Start Approach

Abstract

During the Mars ascent vehicle (MAV) launch missions, when encountering a thrust drop type of propulsion system fault problem, the general trajectory replanning methods relying on step-by-step judgments may fail to make timely decisions, potentially leading to mission failure. This paper proposes a suboptimal joint trajectory replanning (SJTR) method, which formulates the joint optimization problem of target orbit and flight trajectory after a fault within a convex optimization framework. By incorporating penalty coefficients for terminal constraints, the optimization solution adheres to the orbit redecision principle, thereby avoiding complex decision-making processes and resulting in a concise and rapid solution to the replanning problem. A learning-based warm-start scheme is proposed in conjunction with the designed SJTR method. Offline, a deep neural network (DNN) is trained using a dataset generated by the SJTR method. Online, the DNN provides initial guesses for the time optimization variables based on the current fault situation, enhancing the solving efficiency and reliability of the algorithm. Numerical simulations of the MAV flight scenario under the thrust drop faults are performed, and Monte Carlo experiments and case studies across all orbit types demonstrate the effectiveness of the proposed method.