Improving the Evolutionary Optimization of Interplanetary Low-Thrust Trajectories Using a Neural Network Surrogate Model

Building on recent advances in the fields of low-thrust trajectory optimization based on shaping methods, Artificial Neural Networks, and surrogate models in Evolutionary Algorithms, an investigation into a novel optimization routine is conducted. A flexible Python tool to evaluate linked trajectories in a two-body model based on hodographic shaping is implemented and used to develop a novel evolutionary optimization approach where a Genetic Algorithm is assisted in finding new candidate solutions by an online surrogate. The algorithm and different surrogate designs are experimentally investigated on two example problems based on the Dawn trajectory and the GTOC2 problem. Employing the surrogate yields new candidate solutions that improve the population’s fitness especially when the surrogate is used to approximate the shaping computation. Additionally, the use of a surrogate pretrained on a general data set of low-thrust transfers is tested and found to considerably improve the initial quality of the model, meaning that more good candidate solutions are found early on, accelerating the algorithm’s convergence.