A survey on artificial intelligence trends in spacecraft guidance dynamics and control

The rapid developments of artificial intelligence in the last decade are influencing aerospace engineering to a great extent and research in this context is proliferating.We share our observations on the recent developments in the area of spacecraft guidance dynamics and control,giving selected examples on success stories that have been motivated by mission designs.Our focus is on evolutionary optimisation,tree searches and machine learning,including deep learning and reinforcement learning as the key technologies and drivers for current and future research in the field.From a high-level perspective,we survey various scenarios for which these approaches have been successfully applied or are under strong scientific investigation.Whenever possible,we highlight the relations and synergies that can be obtained by combining different techniques and projects towards future domains for which newly emerging artificial intelligence techniques are expected to become game changers.

Spacecraft collision avoidance challenge:Design and results of a machine learning competition

Spacecraft collision avoidance procedures have become an essential part of satellite operations.Complex and constantly updated estimates of the collision risk between orbiting objects inform various operators who can then plan risk mitigation measures.Such measures can be aided by the development of suitable machine learning(ML)models that predict,for example,the evolution of the collision risk over time.In October 2019,in an attempt to study this opportunity,the European Space Agency released a large curated dataset containing information about close approach events in the form of conjunction data messages(CDMs),which was collected from 2015 to 2019.This dataset was used in the Spacecraft Collision Avoidance Challenge,which was an ML competition where participants had to build models to predict the final collision risk between orbiting objects.This paper describes the design and results of the competition and discusses the challenges and lessons learned when applying ML methods to this problem domain.

Learning the optimal state-feedback via supervised imitation learning

Imitation learning is a control design paradigm that seeks to learn a control policy reproducing demonstrations from expert agents.By substituting expert demonstrations for optimal behaviours,the same paradigm leads to the design of control policies closely approximating the optimal state-feedback.This approach requires training a machine learning algorithm(in our case deep neural networks)directly on state-control pairs originating from optimal trajectories.We have shown in previous work that,when restricted to low-dimensional state and control spaces,this approach is very successful in several deterministic,non-linear problems in continuous-time.In this work,we refine our previous studies using as a test case a simple quadcopter model with quadratic and time-optimal objective functions.We describe in detail the best learning pipeline we have developed,that is able to approximate via deep neural networks the state-feedback map to a very high accuracy.We introduce the use of the softplus activation function in the hidden units of neural networks showing that it results in a smoother control profile whilst retaining the benefits of rectifiers.We show how to evaluate the optimality of the trained state-feedback,and find that already with two layers the objective function reached and its optimal value differ by less than one percent.We later consider also an additional metric linked to the system asymptotic behaviour-time taken to converge to the policy’s fixed point.With respect to these metrics,we show that improvements in the mean absolute error do not necessarily correspond to better policies.

Message from the Guest Editors of the Special Issue on Applications of Artificial Intelligence in Aerospace Engineering

Dear authors and readers,Artificial intelligence(AI)has recently found many new applications in aerospace engineering,which range from long-term scheduling of space telescope observations to science planning for the Rosetta mission,from AI-based“astronaut assistant”in International Space Station to AI instrument equipped in the Mars rover Curiosity.The current perception is that methods and techniques developed within the AI research field have the potential to revolutionize almost every aspect of space exploration.It is thus very important for aerospace engineers to monitor the advances on the state-of-the-art methods available in the AI field and be aware of their proposed applications,owing to which,this special issue is organized.

Target selection for a small low-thrust mission to near-Earth asteroids

The preliminary mission design of spacecraft missions to asteroids often involves,in the early phases,the selection of candidate target asteroids.The final result of such an analysis is a list of asteroids,ranked with respect to the necessary propellant to be used,that the spacecraft could potentially reach.In this paper we investigate the sensitivity of the produced asteroids rank to the employed trajectory model in the specific case of a small low-thrust propelled spacecraft beginning its journey from the Sun–Earth L2 Lagrangian point and heading to a rendezvous with some near-Earth asteroid.We consider five increasingly complex trajectory models:impulsive,Lambert,nuclear electric propulsion,nuclear electric propulsion including the Earth’s gravity,solar electric propulsion including the Earth’s gravity and we study the final correlation between the obtained target rankings.We find that the use of a lowthrust trajectory model is of great importance for target selection,since the use of chemical propulsion surrogates leads to favouring less attractive options 19%of times,a percentage that drops to 8%already using a simple nuclear electric propulsion model that neglects the Earth’s gravity effects and thrust dependence on the solar distance.We also find that for the study case considered,a small interplanetary CubeSat named M-ARGO,the inclusion of the Earth’s gravity in the considered dynamics does not affect the target selection significantly.