Computing low-thrust transfers in the asteroid belt, a comparison between astrodynamical manipulations and a machine learning approach

TL;DR

This paper compares analytical and machine learning methods for estimating low-thrust asteroid belt transfer trajectories, demonstrating the superior accuracy of machine learning, especially for longer transfers, based on a large dataset of optimized trajectories.

Contribution

It introduces new analytical approximations and provides a comprehensive comparison with neural network-based machine learning methods for low-thrust trajectory prediction.

Findings

Machine learning outperforms analytical methods for longer transfers.

Both methods achieve final mass errors within a few percent.

A dataset of 3 million optimized transfers is released open-source.

Abstract

Low-thrust trajectories play a crucial role in optimizing scientific output and cost efficiency in asteroid belt missions. Unlike high-thrust transfers, low-thrust trajectories require solving complex optimal control problems. This complexity grows exponentially with the number of asteroids visited due to orbital mechanics intricacies. In the literature, methods for approximating low-thrust transfers without full optimization have been proposed, including analytical and machine learning techniques. In this work, we propose new analytical approximations and compare their accuracy and performance to machine learning methods. While analytical approximations leverage orbit theory to estimate trajectory costs, machine learning employs a more black-box approach, utilizing neural networks to predict optimal transfers based on various attributes. We build a dataset of about 3 million transfers, found by solving the time and fuel optimal control problems, for different time of flights, which we also release open-source. Comparison between the two methods on this database reveals the superiority of machine learning, especially for longer transfers. Despite challenges such as multi revolution transfers, both approaches maintain accuracy within a few percent in the final mass errors, on a database of trajectories involving numerous asteroids. This work contributes to the efficient exploration of mission opportunities in the asteroid belt, providing insights into the strengths and limitations of different approximation strategies.