Trajectory Optimization Using Evolutionary Algorithms for Mars Entry Vehicles

Abstract

This paper explores the application of evolutionary algorithms (EAs) for trajectory optimization of entry vehicles targeted for Mars atmospheric entry. Mars entry missions are constrained by complex aerodynamic and thermodynamic challenges, such as high heat loads, dynamic pressure, and stringent landing accuracy requirements. Conventional optimization techniques often struggle with the non-linearity and high dimensionality of the problem. In this research, we investigate the use of Genetic Algorithms (GA), Particle Swarm Optimization (PSO), and Physics-Informed Neural Networks (PINNs) to identify optimal trajectory profiles that minimize heat load and maximize landing precision while satisfying mission constraints. A supporting simulation and visualization tool has been developed to illustrate the optimization process interactively. The proposed models and algorithms are implemented in Python and validated using simulated Mars atmospheric models.