{"title":"Reinforced Lyapunov controllers for low-thrust lunar transfers","authors":"Harry Holt, Nicola Baresi, Roberto Armellin","doi":"10.1007/s42064-024-0212-x","DOIUrl":null,"url":null,"abstract":"<div><p>Future missions to the Moon and beyond are likely to involve low-thrust propulsion technologies due to their propellant efficiency. However, these still present a difficult trajectory design problem, owing to the near continuous thrust, lack of control authority and chaotic dynamics. Lyapunov control laws can generate sub-optimal trajectories for such missions with minimal computational cost and are suitable for feasibility studies and as initial guesses for optimisation methods. In this work a Reinforced Lyapunov Controller is used to design optimal low-thrust transfers from geostationary transfer orbit towards lunar polar orbit. Within the reinforcement learning (RL) framework, a dual-actor network setup is used, one in each of the Earth- and Moon-centred inertial frames respectively. A key contribution of this paper is the demonstration of a forwards propagated trajectory, removing the need to define a patch point <i>a priori</i>. This is enabled by an adaptive patch distance and extensive initial geometry exploration during the RL training. Results for both time- and fuel-optimal transfers are presented, along with a Monte Carlo analysis of the robustness to disturbances for such transfers. Phasing is introduced where necessary to aid rendezvous with the Moon. The results demonstrate the potential for such techniques to provide a basis for the design and guidance of low-thrust lunar transfers.</p><div><figure><div><div><picture><source><img></source></picture></div></div></figure></div></div>","PeriodicalId":52291,"journal":{"name":"Astrodynamics","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s42064-024-0212-x.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Astrodynamics","FirstCategoryId":"1087","ListUrlMain":"https://link.springer.com/article/10.1007/s42064-024-0212-x","RegionNum":1,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ASTRONOMY & ASTROPHYSICS","Score":null,"Total":0}
引用次数: 0
Abstract
Future missions to the Moon and beyond are likely to involve low-thrust propulsion technologies due to their propellant efficiency. However, these still present a difficult trajectory design problem, owing to the near continuous thrust, lack of control authority and chaotic dynamics. Lyapunov control laws can generate sub-optimal trajectories for such missions with minimal computational cost and are suitable for feasibility studies and as initial guesses for optimisation methods. In this work a Reinforced Lyapunov Controller is used to design optimal low-thrust transfers from geostationary transfer orbit towards lunar polar orbit. Within the reinforcement learning (RL) framework, a dual-actor network setup is used, one in each of the Earth- and Moon-centred inertial frames respectively. A key contribution of this paper is the demonstration of a forwards propagated trajectory, removing the need to define a patch point a priori. This is enabled by an adaptive patch distance and extensive initial geometry exploration during the RL training. Results for both time- and fuel-optimal transfers are presented, along with a Monte Carlo analysis of the robustness to disturbances for such transfers. Phasing is introduced where necessary to aid rendezvous with the Moon. The results demonstrate the potential for such techniques to provide a basis for the design and guidance of low-thrust lunar transfers.
期刊介绍:
Astrodynamics is a peer-reviewed international journal that is co-published by Tsinghua University Press and Springer. The high-quality peer-reviewed articles of original research, comprehensive review, mission accomplishments, and technical comments in all fields of astrodynamics will be given priorities for publication. In addition, related research in astronomy and astrophysics that takes advantages of the analytical and computational methods of astrodynamics is also welcome. Astrodynamics would like to invite all of the astrodynamics specialists to submit their research articles to this new journal. Currently, the scope of the journal includes, but is not limited to:Fundamental orbital dynamicsSpacecraft trajectory optimization and space mission designOrbit determination and prediction, autonomous orbital navigationSpacecraft attitude determination, control, and dynamicsGuidance and control of spacecraft and space robotsSpacecraft constellation design and formation flyingModelling, analysis, and optimization of innovative space systemsNovel concepts for space engineering and interdisciplinary applicationsThe effort of the Editorial Board will be ensuring the journal to publish novel researches that advance the field, and will provide authors with a productive, fair, and timely review experience. It is our sincere hope that all researchers in the field of astrodynamics will eagerly access this journal, Astrodynamics, as either authors or readers, making it an illustrious journal that will shape our future space explorations and discoveries.