Belén Carro

Mario Villaizán-Vallelado, Matteo Salvatori, Belén Carro Martinez et al.

All industries are trying to leverage Artificial Intelligence (AI) based on their existing big data which is available in so called tabular form, where each record is composed of a number of heterogeneous continuous and categorical columns also known as features. Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing, but its applicability to tabular data has been more challenging. More classical Machine Learning (ML) models like tree-based ensemble ones usually perform better. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN), for contextual embedding and modelling interactions among tabular features. Its results outperform those of a recently published survey with DL benchmark based on five public datasets, also achieving competitive results when compared to boosted-tree solutions.

Carlos M. Casas, Belen Carro, Antonio Sanchez-Esguevillas

Low-thrust trajectory design and in-flight control remain two of the most challenging topics for new-generation satellite operations. Most of the solutions currently implemented are based on reference trajectories and lead to sub-optimal fuel usage. Other solutions are based on simple guidance laws that need to be updated periodically, increasing the cost of operations. Whereas some optimization strategies leverage Artificial Intelligence methods, all of the approaches studied so far need either previously generated data or a strong a priori knowledge of the satellite dynamics. This study uses model-free Reinforcement Learning to train an agent on a constrained pericenter raising scenario for a low-thrust medium-Earth-orbit satellite. The agent does not have any prior knowledge of the environment dynamics, which makes it unbiased from classical trajectory optimization patterns. The trained agent is then used to design a trajectory and to autonomously control the satellite during the cruise. Simulations show that a dynamics-agnostic agent is able to learn a quasi-optimal guidance law and responds well to uncertainties in the environment dynamics. The results obtained open the door to the usage of Reinforcement Learning on more complex scenarios, multi-satellite problems, or to explore trajectories in environments where a reference solution is not known