An unsupervised Physics-Informed Neural Network (PINN) for solving optimal control problems with the direct method to design and optimize transfer trajectories is proposed. The network adheres analytically to boundary conditions and includes the objective fitness as regularization in its loss function. A test scenario of a planar Earth-Mars low-thrust optimalfuel transfer and rendezvous is chosen. Comprehensive examination of training strategies reveals that convergence is highly dependent on the initialization of the network and that correctly balancing loss terms is essential for navigating the intricate loss landscape. This balance is achieved by carefully selecting the loss weights and implementing a refined learning rate schedule. Comparative analysis to hodographic shaping solutions demonstrates that the PINN effectively identifies near-optimal solutions across a wide range of initial and final constraints for the Earth-Mars transfer problem, with a maximum improvement of 4.5 km s−1 and median improvement of 0.55 km s−1. The PINN shows promise as a preliminary design tool for trajectory optimization in challenging dynamical conditions. @en

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. @en

In this work, we propose a new method to approximate the cost function of Low-Thrust, Multiple-Gravity-Assist interplanetary trajectories using a Machine Learning surrogate. We identified the computation time required to obtain training data as the main limitation when using Machine Learning methods for this purpose so we present a strategy to build the surrogate with limited training data. We built an Online-Sequential Extreme Learning Machine Multi-Agent System (OS-ELM-MAS) surrogate due to its theoretical good performance when the training data is limited. In addition, we define a method to include the surrogate during the optimization process that can be used with any gradient-free algorithm, and study the effect of several surrogate parameters on the optimization results. Finally, several interplanetary trajectories are optimized with and without the surrogate. Employing the surrogate results in up to 12% lower fuel cost values after a fixed optimization time. The parameters that control the interaction have to be carefully selected to achieve this improvement, and we show that the optimal value of these parameters can be narrowed down based on the characteristics of the transfers. @en

A rapid, grid-based, target-search algorithm is presented to find candidate se-quences of small-body encounters for mission design. The algorithm is especially relevant for cases with large combinatorial spaces. In this paper, the al-gorithm is used to identify candidate flyby sequences of multiple Kuiper-Belt Ob-jects (KBOs). Before reaching the first KBO in the sequence, the trajectories in this paper first use gravity assists at one or more of the giant planets to pump-uptheir orbital energy—reducing launch C3. The target-search algorithm consists offour sequential steps: (1) parameter definition, (2) fine-tuned Lambert-based gridsearch of ballistic trajectories visiting one KBO, (3) rapid, ∆V-based proximitysearch for additional KBOs using the state transition matrices (STMs), and (4) tra-jectory optimization of the most promising KBO sequences using the EvolutionaryMission Trajectory Generator (EMTG). The paper also defines an empirical-basedprocess to characterize the maximum step size for the target arrival dates in theLambert grid search. Lastly, a candidate mission to two KBOs is presented. Theresults indicate that the ∆V computed from the STM propagations is not repre-sentative of the final ∆V computed in EMTG; however, it does serve as a useful‘reachability’ metric to identify nearby KBOs.@en

Low-thrust trajectories can benefit the search for propellant-optimal trajectories, but increases in modeling complexity and computational load remain a challenge for efficient mission design and optimization. In this paper, an approach for developing models utilizing Gaussian Process (GP) regression and classification is proposed to perform computationally efficient optimization while obtaining acceptable accuracies for trajectories based on exponential sinusoid shaping. The goal of this work is to predict a combination of values of input variables which corresponds to a shape-based trajectory with the smallest total velocity increment (ΔV) or propellant mass fraction (J _m). A GP classification model is constructed to assess whether a given combination of values of input variables corresponds to a feasible trajectory. GP regression models are developed to predict the total ΔV and J _m corresponding to a combination of shape parameters, which can replace the required integration along the shape. In addition, advanced regression models are developed to predict the target values while requiring only three input parameters, thereby replacing the entire shape computation. In order to develop a GP model that fits the problem at hand, the underlying functions and parameters should be selected rationally. In this work, a novel model development approach is proposed to ensure that the mean function, covariance function, likelihood function, inference method, and hyperparameters, which dominate the performance of the models, are chosen rationally in terms of mean absolute percentage error (MAPE) and prediction time. Using this approach, GP models are developed and tested on transfer trajectories from Earth to Mars and Ceres, and from Mars to Earth, and their performance, in terms of MAPE and prediction time, is compared to that of more common optimization techniques in combination with the exponential sinusoid and other shape-based methods. The results demonstrate that the computation time can significantly be reduced while achieving promising MAPE’s, especially when the goal is to locate regions of feasible or near-optimal trajectories. The proposed model development procedure is tested for robustness, which provides confidence in the proposed approach. Furthermore, it is found that the models which map three input variables directly to a ΔV or J _m value perform better than the ones trained with shape information, which demonstrates the strength of GP models as applied to low-thrust trajectory optimization.

@en

The ASTER mission under study by the Brazilian National Institute for Space Research would be the first to explore a triple asteroid system. To find orbits stable in such a perturbed environment, an orbit propagation and optimization programme has been written, which makes use of Evolutionary evolution algorithms. The programme written proves sufficient to identify suitable solutions for several use cases based on various mission phases and scenarios. The solar radiation pressure has been identified as a critical perturbation that prevents the existence of solutions in some scenarios, and often drives existing solutions towards terminator orbits. @en

De ontwerpmethode in Ontwerpen van Technische Innovaties bestaat uit een praktisch uitgewerkt stappenplan en legt de nadruk op de vijf essentiële ingrediënten van technisch innoveren: samenwerken, onderzoeken, creatief denken, experimenteren en ondernemen. Dit studieboek is breed inzetbaar. Waarom kiezen voor Ontwerpen van Technische Innovaties? * Breed inzetbaar en praktisch studieboek; * reikt studenten concrete tools aan; * bevat de nieuwste ontwikkelingen en innovaties. Ontwerpen van Technische Innovaties biedt studenten een praktische ontwerpmethode voor het doen van onderzoek en het maken van innovatieve ontwerpen in multidisciplinaire teams. Het volledige ontwerpproces komt aan bod, vanaf de innovatievraag tot en met het ontwikkelen en testen van een effectieve oplossing. Per thema - samenwerken, onderzoeken, creatief denken, experimenteren en ondernemen - worden concrete tools aangereikt, gericht op technologische innovaties. Alle hoofdstukken eindigen met handige samenvattingen en tips voor verdiepende websites en bronnen. Ontwerpen van Technische Innovaties is geschikt voor de propedeusefase van opleidingen als Industrieel Product Ontwerpen, Werktuigbouwkunde, Technische Bedrijfskunde, Civiele Techniek en bijvoorbeeld ook Marketing, Communicatie en Media Design. Het boek is ook beschikbaar als e-book. Wat is nieuw in de tweede editie van Ontwerpen van Technische Innovaties? De tweede editie van Ontwerpen van Technische Innovaties bevat een compleet nieuw hoofdstuk over ondernemen. Ook besteedt het boek aandacht aan de transitie naar een circulaire economie en aan recente innovaties. Online ondersteuning Op de ondersteunende website vinden docenten en studenten extra informatie, afbeeldingen en aanvullende tools. Over de auteurs Inge Oskam is verbonden aan de faculteit Techniek van de Hogeschool van Amsterdam als lector Technisch Innoveren & Ondernemen en is medeverantwoordelijk voor het onderzoeksprogramma Urban Technology. Paul Souren is zelfstandig ontwerper en adviseur en docent aan de Haagse Hogeschool bij de opleidingen IPO en Werktuigbouwkunde. Inge Berg geeft projectmanagement en communicatieve vaardigheden aan de Hanzehogeschool Groningen en begeleidt zowel bachelor- als master-studenten bij het schrijven van afstudeerscripties. Lukien Hoiting werkt als docent bij de Hogeschool van Amsterdam en heeft vele jaren ervaring met het geven van diverse technische vakken en het begeleiden van ontwerpprojecten uitgevoerd door studenten. Kevin Cowan is werkzaam bij de Hogeschool van Amsterdam, waar hij lesgeeft in Aviation Studies met bijzondere aandacht voor dynamische systemen in vakken als meet- en regeltechniek.@en

Driven by wide interest among TU Delft (Delft University of Technology) students to acquire focussed knowledge on space engineering, missions and planetary exploration, a new spaceflight minor was developed for the minor program of the university. With its minor program, TU Delft affords its students an opportunity to dedicate the first semester of their 3rd BSc year to a set of courses chosen among the numerous options offered specifically by the TU Delft or another university. Students are not only allowed but encouraged to explore topics and study fields outside their main BSc track. The spaceflight minor is designed as a multidisciplinary, thematic program, in which the students gain insight in the demand for space applications, mission analysis, system requirements and sizing. This multidisciplinary setup is facilitated by the recently established TU Delft Space Institute (DSI), of which all the faculties involved in the minor are members. The minor and the DSI provide a unique opportunity to strengthen space education and research across TU Delft. The minor covers two quarters of the academic year, spanning twenty weeks, and includes six courses. Offered in the first quarter are: Introduction to Spaceflight (for students without Aerospace Engineering background) or Electronic Circuits (for the other students); Space Exploration, with basics and examples of planetary and astronomical exploration and an introduction to space law; Earth Observation, covering basics of remote sensing of the Earth. The second quarter includes: Spacecraft Technology, providing an overview of the technology of spacecraft subsystems with emphasis on small satellites; Satellite Tracking & Communication, on telecommunications, ground station operations and telemetry analysis from a theoretical and practical point of view; Spaceflight Assignment, the final project in which students produce real, small-scale space deliverables, and reflect on the process and results of development and analysis in the complex space engineering and scientific environment. In total, 15 lecturers from three TU Delft faculties and one from Leiden University contributed to the minor. Many of the courses employ innovative education techniques, such as flipped classrooms and videos produced by the lecturers. Some courses are simultaneously offered to campus students and external participants in a full online format. The first edition of the minor, delivered from September 2015 to January 2016 to 44 students from various TU Delft faculties, can be considered a success with excellent feedback from participants. The paper elaborates on the minor design and learning objectives, showing how multidisciplinary, innovative education can be effectively implemented for students with different academic backgrounds. @en